{"paper_id":"2a95dd1d-e901-405c-8067-1234924d6d40","body_text":"PepPharmaHub: A Cloud-Based Platform Integrating Multimodel Language Architectures with Curated Data Resources for Therapeutic Peptide Discovery | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Method Article PepPharmaHub: A Cloud-Based Platform Integrating Multimodel Language Architectures with Curated Data Resources for Therapeutic Peptide Discovery Dongya Qin, Hai Fang, Zheng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7645806/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Background Therapeutic peptides represent a rapidly expanding class of drug candidates due to their diverse biological activities and high specificity. However, accurately predicting peptide functions directly from sequence information remains a major challenge in computational peptidomics. Current tools, typically standalone applications or functionally constrained web servers, lack the flexibility and scalability essential for modern peptide discovery workflows. Therefore, it is necessary to develop a cloud-based, no-code platform that enables customizable modeling and high-throughput functional screening of therapeutic peptides. Results PepPharmaHub ( http://bioinmed.jflab.ac.cn:18090/peppharmahub/ ) provides a cloud-based, end-to-end platform that integrates advanced sequence-based language modeling with curated benchmark datasets and interactive visualization modules. The platform features a high-throughput screening module powered by a diverse set of 24 models targeting 20 therapeutic properties, alongside a customizable model training pipeline for user-defined screening tasks. Comprehensive benchmarking on 24 public datasets demonstrates that PepPharmaHub matches or surpasses state-of-the-art predictors, significantly improving the efficiency of large-scale peptide screening. Compared with existing public web servers, PepPharmaHub attains a higher, more tightly distributed accuracy on 3,475 newly reported bioactive peptides from 2023–2025 (20 independent tasks), indicating stronger generalization and practical utility. Conclusions PepPharmaHub enables accurate, high-throughput prediction of peptide functions through customizable deep learning models and a no-code interface. By outperforming existing tools across multiple benchmarks and supporting interpretable sequence analysis, the platform offers a practical solution for accelerating peptide-based drug discovery. Therapeutic peptide discovery Web server Deep learning BERT Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Background Therapeutic peptides have emerged as a promising class of drug candidates owing to their high specificity and favorable safety profiles. These peptides exert therapeutic effects by mimicking or modulating the biological activities of endogenous peptides, proteins, or hormones[ 1 ], targeting pathways such as receptor agonism or antagonism, enzyme modulation, signal transduction regulation, and immune system modulation [ 2 ]. Over 40 types of functional peptides have been identified, including antihypertensive, antioxidant, immunomodulatory, anticancer, antibacterial, opioid-like, cholesterol-lowering, antithrombotic, or antidiabetic activities [ 3 , 4 ]. These peptides have attracted significant attention due to their high target specificity, functional diversity, good biocompatibility, and low immunogenicity [ 5 ]. Consequently, peptide drugs are increasingly recognized as a pivotal direction for future drug development [ 6 , 7 ]. Despite their therapeutic potential, the discovery and development of these molecules are hindered by the complexity of predicting functional activities from peptide sequences. The vast diversity of peptide sequences in biological systems complicates the functional annotation, and traditional experimental methods are often too resource-intensive to capture this complexity [ 8 ]. Advances in bioinformatics and artificial intelligence have enabled data-driven approaches, such as machine learning and deep learning to analyze the relationships between sequence features and experimentally determined activities, thereby improving functional prediction [ 9 , 10 ]. Numerous computational predictors have been developed for specific therapeutic properties, including anticancer activity [ 11 ], angiotensin-converting enzyme (ACE) inhibition [ 12 ], antimicrobial properties [ 13 ], antioxidant [ 14 ], cell penetration [ 15 ], toxicity [ 16 ], dipeptidyl peptidase IV inhibition [ 17 ], and anti-coronavirus activity [ 18 ]. These predictors utilize a variety of modeling approaches, ranging from Simple Recurrent Neural Networks (SimpleRNN), Long Short-Term Memory Networks (LSTM), Bidirectional Long Short-Term Memory Networks (BiLSTM), Gated Recurrent Unit (GRU), and transformer-based pretrained models like BERT, as well as hybrid variants. Sequence characterization methods can be categorized into five main types: (i) encoding methods leveraging physicochemical descriptors of amino acid residues (e.g., hydrophobicity, polarity, volume) and one-hot sparse matrices [ 19 ]; (ii) deep feature extraction using attention mechanisms from pretrained models [ 20 ]; (iii) computation of physicochemical properties such as molecular weight, volume, and isoelectric point [ 21 ]; (iv) k-mer segmentation for fixed-length fragment representation [ 22 ]; (v) molecular fingerprint encoding based on chemical structures or simplified molecular input line entry system (SMILES) representations, generating molecular fingerprints like extended connectivity fingerprints (ECFP) to describe structural features of molecules [ 23 ]. However, this field faces three critical challenges. First, the absence of a unified modeling platform undermines reproducibility and limits the diversity, and timeliness of data analysis. Second, the insufficient computational resources, standard data integration, and pre-selected peptide libraries hinder the development of integrated algorithms and high-throughput screening capabilities. Third, poor model interpretability, with inadequate visualization of key residues and motifs, impedes mechanistic insights into peptide functionality. To address these issues, we have developed PepPharmaHub, a comprehensive web-based platform that integrates modules for model training, model deployment, virtual screening, and sequence characterization. PepPharmaHub features a user-friendly interface that eliminates the need for specialized programming skills, allowing researchers to visually monitor model training, filtering, and functional motif analysis. Additionally, the platform includes small-sample standard datasets and pre-selected peptide libraries. In summary, PepPharmaHub addresses critical challenges in therapeutic peptide discovery by improving the accuracy, efficiency, and interpretability of functional prediction. It provides a powerful, user-friendly tool for biomedical researchers and drug developers, accelerating the discovery and development of peptide-based therapeutics. Results PepPharmaHub facilitates one-stop screening for therapeutic peptides To streamline the development of therapeutic peptides, we developed PepPharmaHub, a unified web platform that integrates curated peptide databases, customizable modeling frameworks, high-throughput virtual screening, and result visualization into a cohesive, end-to-end workflow. The system is organized into five core functional modules, each contributing to a one-stop pipeline comprising data access, model training, virtual screening, visualization, and analysis (Fig. 1 ). (1) Built-in centralized and structured peptide data resources This database module provides foundational data support for model development and benchmarking. It integrates 24 public peptide datasets and two in-house sequence libraries encompassing over 2.3 million peptides with unknown activity. Additionally, it hosts 24 prediction datasets and characteristic sequence profiles for 20 classes of bioactive peptides (Supplementary Fig. 1), offering a rich and standardized resource for both model training and screening tasks. (2) Deep Learning and Dual-Mode Screening PepPharmaHub provide a flexible and extensible framework for constructing and deploying deep learning-based peptide prediction models. The training module supports the online development of task-specific models through two components: the RNN-Trainer, which offers four types of recurrent neural networks with customizable configurations, including 24 residue encoding schemes, 19 activation functions, adjustable network depth, early stopping, and checkpointing; and the BERT-Trainer, which enables fine-tuning of transformer-based architectures using both standard parameters such as batch size, epochs, and learning rate, and advanced parameters such as attention heads, dropout, and activation layers (Fig. 1 b). These tools allow users to build biologically tailored models without requiring programming expertise. For downstream deployment, the Virtual Screening module (Fig. 1 c) provides two complementary options: the Peptide-Predictor, which includes 24 optimized pre-trained models for functional classification across 20 peptide attributes; and the Model-Caller, which supports high-throughput batch predictions using user-defined models trained within the platform. This dual-mode screening framework distinguishes PepPharmaHub from conventional predictors by enabling both rapid inference using standardized models and customizable prediction via user-trained models. (3) Web-based implementation for interactive visualization PepPharmaHub features a web-based architecture that enables seamless user interaction and real-time task monitoring. The Visual Analysis module (Fig. 1 d) allows users to interactively inspect modeling and screening workflows by associating each task with a unique identifier, through which dynamic logs, intermediate outputs, final results, and performance metrics can be accessed and downloaded. Visualization capabilities include sequence feature comparisons, classification overviews, and model evaluation statistics, supporting transparent and reproducible analysis. The platform is organized into six functional interfaces including: Home, Database, RNN-Trainer, BERT-Trainer, Peptide-Predictor, and Model-Caller (Supplementary Fig. 2 and Fig. 1 e), which together support end-to-end task execution. Users can initiate analyses by uploading FASTA files and selecting relevant parameters, while monitoring progress and retrieving results for up to 15 days. The modular design allows individual components to be used independently or combined into integrated pipelines, thereby enhancing flexibility and usability for both expert and non-expert users in therapeutic peptide research. PepPharmaHub demonstrates robust generalization and adaptability across open benchmark datasets To evaluate the generalization performance and adaptability of PepPharmaHub across diverse peptide prediction tasks, we conducted systematic cross-validation and independent testing on 24 publicly available benchmark datasets (Table 1 ). Using the BiLSTM model with SDPZ27 encoding and the BERT model with k-mer = 1, cross-validation demonstrated robust performance: 17 BiLSTM-based models achieved average accuracies exceeding 0.8015, with Sensitivity, Specificity, MCC, and AUC ranging from 0.3000 to 1.0000, 0.8514 to 1.0000, 0.3191 to 0.9729, and 0.8000 to 0.9975, respectively (Supplementary Table 2). Similarly, 22 BERT-based models yielded average accuracies above 0.8242, with respective performance metrics spanning 0.6800-1.0000 (Sensitivity), 0.8438-1.0000 (Specificity), 0.6401-1.0000 (MCC), and 0.8741-1.0000 (AUC) (Supplementary Table 3). On independent test sets (Fig. 2 a-x), PepPharmaHub-BiLSTM achieved superior predictive performance on two antioxidant, interleukin-6-inducing, and ACE-inhibitory datasets, showed comparable performance on 7 datasets, and relatively lower performance on the remaining 13 datasets. In contrast, PepPharmaHub-BERT outperformed on 11 datasets, was comparable to state-of-the-art models on 7 datasets, and underperformed on 6 tasks. Notably, BERT exhibited stronger feature extraction capabilities than BiLSTM on 17 datasets, though its performance was slightly inferior on antioxidant, ACE-inhibitory, anti-coronavirus, antiparasitic, and antibacterial tasks. Overall, the PepPharmaHub models matched or exceeded the performance of existing methods on 19 out of 24 datasets. These findings underscore the platform’s capacity to deliver competitive and generalizable predictive models across a wide range of peptide functional categories. Importantly, users can complete the entire evaluation pipeline by simply uploading datasets, selecting model architectures, and defining training parameters, demonstrating the platform’s accessibility and suitability for broad peptide screening applications without the need for complex modeling workflows. PepPharmaHub outperforms greater generalization capabilities than existing web servers To assess the real-world generalization capability of PepPharmaHub relative to existing peptide prediction servers, we deployed 24 optimal models comprising 18 BERT-based and 6 RNN-based architectures into the Peptide-Predictor module ( http://bioinmed.jflab.ac.cn:18090/peppharmahub/PeptidePredictor/input.jsp ) and evaluated their performance on a dataset of 3,475 newly reported bioactive peptide sequences collected between 2023 and 2025 (Table 1 ). Across 20 independent test tasks, Peptide-Predictor demonstrated a more concentrated and robust prediction accuracy distribution (ranging from 44.35% to 92.37%) compared to the broader and sparser accuracy range observed in existing web predictors (0% to 93.37%) (Fig. 3 ). Notably, the predictor achieved superior performance in 14 tasks (Fig. 3 a-n), with prediction accuracies ranging from 52.38% to 88.89%, surpassing the best existing predictors by a margin of 0.38% to 75%. In particular, it attained accuracies of 81.3% for antimicrobial prediction (Fig. 3 d), 85.71% for quorum sensing (Fig. 3 f), and 88.89% for antiparasitic prediction (Fig. 3 i). In neuropeptide and blood-brain barrier datasets (Fig. 3 o–p), the Predictor showed comparable performance, with accuracies of 70.37% and 91.67%. While Matthews correlation coefficient (MCC) values for all 54 models varied broadly (− 0.3068 to 0.6064), 13 PepPharmaHub-based models exhibited relatively high MCCs in the range of 0.0085 to 0.5774, indicating meaningful discriminative power in many cases. The system performed relatively slightly lower in a subset of tasks, including antibacterial, antiviral, bitter and anticancer peptide prediction (Fig. 3 q-t). Overall, these results suggest that Peptide-Predictor delivers enhanced functional prediction accuracy for novel peptide sequences compared to current publicly available web servers, highlighting its strong generalization capability and practical utility in peptide discovery workflow. Rapid screening pipeline and feature mapping for bioactive peptides To evaluate the interpretability and functional relevance of model predictions, we implemented a rapid screening and feature mapping pipeline using PepPharmaHub. A total of 2,321,342 unlabeled peptide sequences (length 2–20) were retrieved from Sequence Library-1 and screened using the 24 packaged predictive models in the Peptide-Predictor module (task ID: PRE20250616113524). The resulting predictions, visualized through the platform’s analysis interface, included workflow logs, data preprocessing, classification summaries, sequence profiles, and downloadable result packages (Fig. 4 a). These outputs were stored in the Pre-selected Library ( http://bioinmed.jflab.ac.cn:18090/peppharmahub/Database/SeqLogoPrediction.jsp?PreID=PRE20250616113524 ) for further inspection. Visualization of sequence feature distributions revealed substantial variation in the predicted abundance of different bioactive peptides—e.g., tumor T cell antigens (1,927,539), antioxidants ( 1,794,986), and quorum sensing peptides (1,674,051) were highly represented, while anti-coronavirus (7,837), anti-MRSA (89,058), and anticancer peptides (341,509) were comparatively rare (Fig. 4 b). Amino acid composition analysis indicated both shared and unique residue preferences across peptide types; for instance, Leu was commonly enriched in 21 peptide classes but underrepresented in toxicity and antiparasitic peptides. Antioxidants featured residues such as Leu, Pro, Gly, and Ala, whereas anticancer peptides were enriched in Lys, Leu, Ala, Gly, and Ile. Notably, sequence composition analyses revealed that screened and experimental peptides exhibited concordant N-/C-terminal and key residue profiles (Fig. 4 c), suggesting that the models effectively captured discriminative sequence features. To our knowledge, this constitutes one of the most extensive feature maps for bioactive peptide sequences, demonstrating that PepPharmaHub not only enables high-throughput screening but also enhances model transparency and interpretability through comprehensive feature analysis. Self-trained framework for efficient screening of ACE-inhibitory peptides To improve predictive accuracy for ACE-inhibitory peptides, we constructed a new benchmark dataset (ACEiPs) and employed the PepPharmaHub platform to develop 27 self-trained models using BiLSTM and fine-tuned BERT architectures via the RNN-Trainer and BERT-Trainer modules. Figure 5 a demonstrates the whole screening workflow. Cross-validation on the ACEiPs benchmark dataset showed that 20 models achieved over 80% accuracy, with precision, specificity, sensitivity, MCC, and AUC ranging from 0.7902 to 0.9241, 0.7821 to 0.9250, 0.7904 to 0.9126, 0.6068 to 0.8384, and 0.8490 to 0.9538, respectively. Independent testing on ACEiPs-test confirmed consistent high performance across the same 20 models (Supplementary Table 4). Among all models, the RNN model (RNN20250624111715) encoded with VVSFZL37 demonstrated the best generalization performance, achieving accuracy, precision, specificity, sensitivity, and MCC scores of 0.9169, 0.9088, 0.9070, 0.9268, and 0.8340, respectively (Fig. 5 b). When benchmarked against three established ACE prediction servers (mAHTPred[ 24 ], ACEiPP [ 12 ], and pLM4ACE[ 25 ], which includes Logistic Regression, SVM, and Multilayer Perceptron models), the RNN20250624111715 model consistently outperformed across all evaluation metrics, with improvements ranging from 0.0366 to 0.4479 in accuracy and up to 0.896 in MCC (Fig. 5 c). Notably, while mAHTPred and ACEiPP showed moderate performance, pLM4ACE performed poorly with accuracies below 0.4845 and negative MCCs. To demonstrate scalability, the best-performing self-trained model was deployed via the Model-Caller module to screen 3,740,614 peptides from Sequence-Library 2. As shown in Fig. 5 c, the predicted ACEiPs have similar residue composition and two-terminal features to experimental ACEiPs, i.e., they are all mainly composed of hydrophobic amino acids (Pro, Leu, Val, Gly, and Ala), the C-terminus tending to hydrophobic (Pro, Phe, and Leu), positively charged (Arg and Lys), and bulky aromatic (Tyr) amino acids, and the N-terminus favoring hydrophobic amino acids (Leu, Val, Ala, Gly, Ile, and Pro). Taken together, these findings validate the self-training framework implemented in PepPharmaHub as a robust and efficient approach for the identification of ACE-inhibitory peptides, demonstrating superior predictive performance, enhanced scalability, and greater biological relevance compared to existing web-based prediction tools. Discussion In this study, we present PepPharmaHub, a comprehensive and scalable web platform that enables end-to-end modeling, screening, sequence feature interpretation, and data sharing for bioactive peptides. By integrating multiple natural language processing (NLP) architectures into a unified, user-friendly web framework including SimpleRNN, LSTM, GRU, BiLSTM, and BERT, the platform supports both platform-provided and self-trained prediction models, covering a wide range of peptide classification tasks without requiring programming expertise or local computational resources. Across 24 benchmark datasets, PepPharmaHub demonstrates superior or comparable performance to existing state-of-the-art models in terms of accuracy, generalization, and throughput. Compared to conventional web servers (such as ACEiPP[ 12 ], AnOxPP [ 14 ], TransImbAMP [ 26 ], BERT4Bitter[ 27 ], and SCMRSA[ 28 ]) PepPharmaHub overcomes limitations associated with fixed model architectures and static data, enabling continuous model retraining and task-specific customization through its RNN-Trainer, BERT-Trainer, and Model-Caller modules. Beyond predictive performance, the platform facilitates sequence-level interpretability through feature mapping and comparative analysis between theoretical predictions and experimental peptide profiles. While strong concordance was observed for many peptide classes, notable inconsistencies were detected in specific sequence regions (e.g., N-termini of bitter, blood-brain barrier, and antifungal peptides; C-termini of DPP IV inhibitors), likely reflecting the limited size and diversity of current training datasets. These findings underscore the need for continued dataset expansion and iterative model refinement to improve sequence-level resolution. Despite its strengths, the current version of PepPharmaHub has two primary limitations. First, computational throughput is constrained by limited GPU availability, which may affect real-time usability during peak demand. Second, the platform currently supports only RNN and BERT based models. While effective, other emerging architectures such as CNN BiLSTM attention hybrids [ 29 ], CNN BiLSTM SVM classifiers [ 30 ], and BiLSTM multi scale CNNs [ 31 ] may offer complementary benefits and warrant integration in future versions. In future, PepPharmaHub will expand computational resources, integrate broader peptide data sources, and support additional modeling paradigms. The platform's low-code interface and modular design aim to democratize access to deep learning-driven peptide discovery, empowering researchers across disciplines to deploy, refine, and interpret advanced models with minimal technical barriers. Ultimately, PepPharmaHub offers a sustainable and extensible solution to accelerate therapeutic peptide research and improve prediction-driven biological discovery. Conclusions PepPharmaHub is a comprehensive, user-friendly, and scalable platform that streamlines therapeutic peptide discovery by integrating curated datasets, advanced language modeling, and real-time visualization into a unified workflow. Through its dual-mode high-throughput screening and self-training capabilities, the platform supports both rapid prediction with platform-provided models and flexible customization using user-defined architectures. Benchmarking across 24 public datasets and 20 external test sets demonstrates that PepPharmaHub consistently achieves state-of-the-art or superior performance, while also enhancing interpretability through sequence feature mapping. By lowering technical barriers and enabling reproducible, interpretable, and high-throughput predictions, PepPharmaHub offers a powerful tool for accelerating data-driven peptide drug discovery. Methods Data collection This study utilizes 20 types of open-source peptide sequence datasets, comprising a total of 24 datasets, including anti-hypertensive, antioxidant, dipeptidyl peptidase IV inhibition, bitter, umami, antimicrobial, antimalarial, quorum sensing, anticancer, anti-MRSA strains, tumor T cell antigens, blood-brain barrier, antiparasitic, neuropeptide, antibacterial, antifungal, antiviral, toxicity, anti-coronavirus and interleukin-6 inducing activity, to train and evaluate RNN and BERT modeling methods. Table 1 provides an overview of these open-source datasets. The data volume distribution is as follows: >2000 (11 datasets), 1000–2000 (5 datasets), < 1000 (8 datasets), including 15 balanced datasets with an equal number of positive and negative samples, and 9 imbalanced datasets. To ensure a fair comparison with existing methods, the training set, validation set, and independent test set used are consistent with those in the original paper, and the same number of cross-validation folds are applied. Specifically, 20 fair external independent tests were constructed by collecting data on 20 types of bioactive peptides, newly identified in 2023–2025 and not included in the aforementioned 24 datasets (Table 1 ), to assess the model's generalization ability. The ACEiPs dataset was constructed by deduplicating and balancing the ACEiPP dataset [ 12 ], AHTpin dataset [ 32 ], and newly reported ACE inhibitory peptides (104 positive samples and 98 negative samples), resulting in a total of 1181 positive and negative samples (Table 1 ). The ACEiPs dataset was randomly split into a benchmark dataset (ACEiPs_benchmark) and an independent test set (ACEiPs_test) in a 7:3 ratio. Additionally, two large peptide sequence datasets with unknown activities were constructed to assess the model’s ability to pre-screen features. The first dataset, named Sequence-Library 1, contains a total of 3,768,340 peptide sequences retrieved from the UniProt database using the search term ‘(length:[2 TO 50])’. The second dataset, named Sequence-Library 2, consists of 2,321,342 non-redundant peptide sequences of length 2–20 from 21,249 food-derived proteins, downloaded from the ACEiPP database [ 12 ]. Recurrent neural network modelling module The peptide sequence, based on the single-letter codes of the 20 natural amino acids (R, K, N, D, Q, E, H, P, Y, W, S, T, G, A, M, C, F, L, V, I), can be represented as: Peptide = [A 1 , A 2 , ..., A i ] (1) where A i​ is the i-th amino acid in the peptide sequence, i.e., the positional index of the amino acid residue. And then, peptide sequences were transformed into feature vectors using One-hot coding and 23 sets of amino acid descriptors (AADs) to represent the types and physicochemical properties of sequence residues (Table S1 ). By referencing these AADs, peptide sequences can be transformed from non-numeric sequence data into numeric feature vectors, which are then input into recurrent neural networks for model training. The AADs coding is defined as follows: $$\\:\\text{A}\\text{A}\\text{D}\\text{s}=\\left[\\begin{array}{cccc}{\\text{V}}_{1}^{1}&\\:{\\text{V}}_{2}^{1}&\\:\\cdots\\:&\\:{\\text{V}}_{n}^{1}\\\\\\:{\\text{V}}_{1}^{2}&\\:{\\text{V}}_{2}^{2}&\\:\\cdots\\:&\\:{\\text{V}}_{\\text{n}}^{2}\\\\\\:⋮&\\:⋮&\\:⋮&\\:⋮\\\\\\:{\\text{V}}_{1}^{20}&\\:{\\text{V}}_{2}^{20}&\\:\\cdots\\:&\\:{\\text{V}}_{\\text{n}}^{20}\\end{array}\\right]$$ 2 where V represents the feature variables of the 20 natural amino acids, n is the number of variables per residue, and the AADs coding matrix has dimensions of 20×n. The RNN-Trainer module was developed based on the TensorFlow framework and incorporates four recurrent neural networks: SimpleRNN, LSTM, GRU, and BiLSTM. For each of these networks, 24 amino acid encoding schemes (Table S1 ), 19 activation functions, N-fold cross-validation (N = 5, 10, 15, 20), and other training parameters (network layers, neurons, learning rate, dropout, nEpochs, early stopping and checkpoint) are provided. Table 1 Open-source benchmark and test datasets collected from various sources in the literature and platform Bioactivity Dataset reference Training dataset Test dataset Newly reported peptides Positive Negative Positive Negative Positive Negative Antihypertensive activity mAHTPred [ 24 ] 913 913 386 386 102 93 ACEiPP[ 12 ] 730 730 313 313 ACEiPs (this study) 826 826 355 355 Antioxidant activity AnOxPP [ 14 ] 848 848 212 212 112 42 AnOxPePred-FRS [ 33 ] 530 593 146 135 DPP IV inhibitory activity iDPPIV-SCM [ 34 ] 532 532 133 133 109 75 Bitter BERT4Bitter [ 27 ] 256 256 64 64 179 184 Umami iUMAMI-SCM [ 35 ] 112 241 28 61 244 19 Antimicrobial activity TransImbAMP [ 26 ] 3876 9552 2584 6369 376 9 Antimalarial activity iAMAP-SCM (Main dataset) [ 36 ] 111 1708 28 427 17 4 iAMAP-SCM (Alternative dataset) [ 36 ] 111 542 28 135 Quorum sensing activity QSPred-FL [ 37 ] 200 200 20 20 7 0 Anticancer activity AntiCP 2.0 (Main dataset) [ 38 ] 689 689 172 172 570 71 AntiCP 2.0 (Alternative dataset) [ 38 ] 776 776 194 194 Anti-MRSA strains activity SCMRSA [ 28 ] 118 678 30 169 12 1 Tumor T cell antigens iTTCA-Hybrid [ 39 ] 470 318 122 75 122 75 Blood-Brain Barrier BBPpred [ 40 ] 100 100 19 19 45 3 Antiparasitic activity PredAPP [ 41 ] 255 1863 46 46 23 4 Neuropeptide NeuroPred-CLQ [ 42 ] 1940 1940 485 485 9 18 Antibacterial activity starPep_AB [ 43 ] 6583 6583 1695 1695 226 27 Antifungal activity starPep_AF [ 43 ] 778 778 215 215 117 21 Antiviral activity starPep_AV [ 43 ] 2321 2321 623 623 31 467 Toxicity ATSE [ 44 ] 1663 1621 290 290 22 6 Anti-coronavirus activity FEOpti-ACVP [ 18 ] 125 1587 32 397 63 38 Interleukin-6 inducing activity StackIL6[ 47 ] 292 2393 73 597 2 1 BERT pre-training fine-tuning module A total of 556,603 protein sequences were downloaded from UniProt as the peptide-related pre-training corpus. UniProt, which integrates data from SWISS-PROT, TrEMBL, and UniParc, is the largest and most comprehensive protein database, providing ample data for model pre-training. Based on the extensive discussion in the literature regarding the relationship between peptide sequences and activity, amino acid residues and specific motifs (dipeptides and tripeptides) are key determinants of the activity of therapeutic peptides [ 45 , 46 ]. We divide proteins into motifs, where every k (k = 1, 2, 3) residues in the sequence are grouped into k-mers. When fewer than k amino acids remain at the end of the sequence, the remaining amino acids are grouped together [ 13 ]. The computational formula of the BERT model is as follows: MultiHead (Q, K, V) = Concat (head 1 , …, head h ) (3) Head i = Attention ( \\(\\:{\\text{Q}\\text{W}}_{\\text{i}}^{\\text{Q}}\\) , \\(\\:{\\text{K}\\text{W}}_{\\text{i}}^{\\text{K}}\\) , \\(\\:{\\text{V}\\text{W}}_{\\text{i}}^{\\text{V}}\\) ) (4) Attention (Q, K, V) = softmax( \\(\\:\\frac{{QK}^{T}}{\\sqrt{{d}_{k}}}\\) )V (5) where d k ​ is the dimension of the Key, \\(\\:{\\text{W}}_{\\text{i}}^{\\text{Q}}\\) , \\(\\:{\\text{W}}_{\\text{i}}^{\\text{K}}\\) , \\(\\:{\\text{W}}_{\\text{i}}^{\\text{V}}\\) and \\(\\:{\\text{W}}^{\\text{O}}\\) are the parameter matrices. Three pre-trained k-mer models were trained based on the TensorFlow framework for model fine-tuning. The developed BERT-Trainer module provides 7 standard configuration parameters: Batch size, Evaluate, Train epochs, Warmup proportion, Learning rate, Classification, and Cross-validation (supporting 5-, 10-, 15-, and 20-fold), along with 11 advanced configuration parameters: Attention probability, Dropout probability, 5 Hidden layer activation functions, Hidden layer dropout probability, Hidden layer size, Initializer range, Intermediate layer size, Maximum position embeddings, Number of attention heads, Number of hidden layers, Type vocabulary size, and 3 Vocabulary sizes (k-mers). Furthermore, Early stopping and Checkpoint parameters are designed to monitor the model's performance and systematically save its state during training. Evaluation criteria The prediction ability of the models in n-fold cross-validation and external testing is evaluated using six evaluation parameters: Precision, Sensitivity, Specificity, Accuracy, Matthew’s correlation coefficient (MCC), and the area under the receiver operating characteristics curves (AUC). Their definitions are as follows: $$\\:Precision=\\frac{TP}{TP+FP}$$ 6 $$\\:Sensitivity=\\frac{TP}{TP+FN}$$ 7 $$\\:Specificity=\\frac{TN}{TN+FP}$$ 8 $$\\:Accuracy=\\frac{TP+TN}{TP+TN+FP+FN}$$ 9 $$\\:MCC=\\frac{TP\\times\\:TN-FP\\times\\:FN}{\\sqrt{(TP+FP)(TP+FN)(TN+FP)(TN+FN)}}$$ 10 where TP, FP, TN, and FN represent the number of true positive samples, false positive samples, true negative samples, and false negative samples, respectively. Declarations Author contributions DY.Q. and Z.W. conceptualized and supervised the project. DY.Q. constructed PepPharmaHub web server, built the project website, and created online tutorial. DY.Q., Z.W., K.S. and H.F. wrote the manuscript and curated all figures. All authors reviewed and approved the final manuscript. Funding This work was supported by the Science and Technology Innovation Key R&D Program of Chongqing [CSTB2023TIAD-STX0001], National Natural Science Foundation of China [82470220, 32470681], National Key R&D Program of China [2022YFA1103300], Chongqing Municipal Science and Health Joint Medical Research Project [2025ZDXM004], Chongqing Municipal PhD Fast-Track Program [CSTB2024NSCQ-BSX0019], Youth Talent Development Program from Second Affiliated Hospital, Army Medical University [2022YQB014]. Data availability The 25 benchmark datasets (Table 1), and 19 independent test sets are available in the Dataset Library of PepPharmaHub (http://bioinmed.jflab.ac.cn:18090/peppharmahub/ Database/datasetLibrary.jsp). Sequence Library-1 and Sequence Library-2 can be downloaded at http://bioinmed.jflab.ac.cn:18090/peppharmahub/Database/seqLibrary .jsp. Screening results for 23 peptide types are accessible via the Pre-selected Library, with data downloads and sequence profile visualization at http://bioinmed. jflab.ac.cn:18090/peppharmahub/Database/SeqLogoPrediction.jsp?PreID=PRE20241227191128. All model and task IDs mentioned in this study can be retrieved via the Home page search function (http://bioinmed.jflab.ac.cn:18090/pepnlp/index.jsp). Source data are provided with this paper. Code availability The developed PepPharmaHub platform is now available and can be accessed at: http://bioinmed.jflab.ac.cn:18090/pepnlp/index.jsp. Future updates and new versions will also be released through this link. Competing interests The authors declare no competing interests. References Rossino, G., et al., Peptides as Therapeutic Agents: Challenges and Opportunities in the Green Transition Era. Molecules, 2023. 28 (20). Li, C.M., et al., Novel Peptide Therapeutic Approaches for Cancer Treatment. Cells, 2021. 10 (11). D’Aloisio, V., et al., PepTherDia: database and structural composition analysis of approved peptide therapeutics and diagnostics. Drug Discovery Today, 2021. 26 (6): p. 1409-1419. Qin, D., et al., DFBP: a comprehensive database of food-derived bioactive peptides for peptidomics research. Bioinformatics, 2022. 38 (12): p. 3275-3280. Drucker, D.J., Advances in oral peptide therapeutics. Nature Reviews Drug Discovery, 2019. 19 (4): p. 277-289. Muttenthaler, M., et al., Trends in peptide drug discovery. Nature Reviews Drug Discovery, 2021. 20 (4): p. 309-325. Sharma, K., et al., Peptide-based drug discovery: Current status and recent advances. Drug Discovery Today, 2023. 28 (2). Mann, M., et al., Artificial intelligence for proteomics and biomarker discovery. Cell Systems, 2021. 12 (8): p. 759-770. Jia, W., et al., Exploring novel ANGICon-EIPs through ameliorated peptidomics techniques: Can deep learning strategies as a core breakthrough in peptide structure and function prediction? Food Research International, 2023. 174 . Wu, X., et al., Deep learning for advancing peptide drug development: Tools and methods in structure prediction and design. European Journal of Medicinal Chemistry, 2024. 268 . Ghafoor, H., et al., CAPTURE: Comprehensive anti-cancer peptide predictor with a unique amino acid sequence encoder. Computers in Biology and Medicine, 2024. 176 . Qin, D., et al., Sequence–Activity Relationship of Angiotensin-Converting Enzyme Inhibitory Peptides Derived from Food Proteins, Based on a New Deep Learning Model. Foods, 2024. 13 (22). Zhang, Y., et al., A novel antibacterial peptide recognition algorithm based on BERT. Briefings in Bioinformatics, 2021. 22 (6). Qin, D., et al., Prediction of antioxidant peptides using a quantitative structure−activity relationship predictor (AnOxPP) based on bidirectional long short-term memory neural network and interpretable amino acid descriptors. Computers in Biology and Medicine, 2023. 154 . Naseem, A., et al., BBB-PEP-prediction: improved computational model for identification of blood–brain barrier peptides using blending position relative composition specific features and ensemble modeling. Journal of Cheminformatics, 2023. 15 (1). Wang, J.-H. and T.-Y. Sung, ToxTeller: Predicting Peptide Toxicity Using Four Different Machine Learning Approaches. ACS Omega, 2024. 9 (29): p. 32116-32123. Wang, D., et al., StructuralDPPIV: a novel deep learning model based on atom structure for predicting dipeptidyl peptidase-IV inhibitory peptides. Bioinformatics, 2024. 40 (2). Jiang, J., et al., FEOpti-ACVP: identification of novel anti-coronavirus peptide sequences based on feature engineering and optimization. Briefings in Bioinformatics, 2024. 25 (2). Zhou, P., et al., Systematic Comparison and Comprehensive Evaluation of 80 Amino Acid Descriptors in Peptide QSAR Modeling. Journal of Chemical Information and Modeling, 2021. 61 (4): p. 1718-1731. Zhang, J., et al., Umami-BERT: An interpretable BERT-based model for umami peptides prediction. Food Research International, 2023. 172 . Klepach, A., et al., Characterization and impact of peptide physicochemical properties on oral and subcutaneous delivery. Advanced Drug Delivery Reviews, 2022. 186 . Kurata, H., S. Tsukiyama, and B. Manavalan, iACVP: markedly enhanced identification of anti-coronavirus peptides using a dataset-specific word2vec model. Briefings in Bioinformatics, 2022. 23 (4). Minkiewicz, P., A. Iwaniak, and M. Darewicz, Annotation of Peptide Structures Using SMILES and Other Chemical Codes–Practical Solutions. Molecules, 2017. 22 (12). Manavalan, B., et al., mAHTPred: a sequence-based meta-predictor for improving the prediction of anti-hypertensive peptides using effective feature representation. Bioinformatics, 2019. 35 (16): p. 2757-2765. Du, Z., et al., pLM4ACE: A protein language model based predictor for antihypertensive peptide screening. Food Chemistry, 2024. 431 . Pang, Y., et al., Integrating transformer and imbalanced multi-label learning to identify antimicrobial peptides and their functional activities. Bioinformatics, 2022. 38 (24): p. 5368-5374. Charoenkwan, P., et al., BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides. Bioinformatics, 2021. 37 (17): p. 2556-2562. Charoenkwan, P., et al., SCMRSA: a New Approach for Identifying and Analyzing Anti-MRSA Peptides Using Estimated Propensity Scores of Dipeptides. ACS Omega, 2022. 7 (36): p. 32653-32664. Xing, W., et al., iAMP-Attenpred: a novel antimicrobial peptide predictor based on BERT feature extraction method and CNN-BiLSTM-Attention combination model. Briefings in Bioinformatics, 2024. 25 (1). Xiao, X., et al., iAMP-CA2L: a new CNN-BiLSTM-SVM classifier based on cellular automata image for identifying antimicrobial peptides and their functional types. Briefings in Bioinformatics, 2021. 22 (6). Qi, Y., P. Zheng, and G. Huang, DeepLBCEPred: A Bi-LSTM and multi-scale CNN-based deep learning method for predicting linear B-cell epitopes. Frontiers in Microbiology, 2023. 14 . Kumar, R., et al., An in silico platform for predicting, screening and designing of antihypertensive peptides. Scientific Reports, 2015. 5 (1). Olsen, T.H., et al., AnOxPePred: using deep learning for the prediction of antioxidative properties of peptides. Scientific Reports, 2020. 10 (1). Charoenkwan, P., et al., iDPPIV-SCM: A Sequence-Based Predictor for Identifying and Analyzing Dipeptidyl Peptidase IV (DPP-IV) Inhibitory Peptides Using a Scoring Card Method. Journal of Proteome Research, 2020. 19 (10): p. 4125-4136. Charoenkwan, P., et al., iUmami-SCM: A Novel Sequence-Based Predictor for Prediction and Analysis of Umami Peptides Using a Scoring Card Method with Propensity Scores of Dipeptides. Journal of Chemical Information and Modeling, 2020. 60 (12): p. 6666-6678. Charoenkwan, P., et al., iAMAP-SCM: A Novel Computational Tool for Large-Scale Identification of Antimalarial Peptides Using Estimated Propensity Scores of Dipeptides. ACS Omega, 2022. 7 (45): p. 41082-41095. Wei, L., et al., Comparative analysis and prediction of quorum-sensing peptides using feature representation learning and machine learning algorithms. Briefings in Bioinformatics, 2018. Agrawal, P., et al., AntiCP 2.0: an updated model for predicting anticancer peptides. Briefings in Bioinformatics, 2021. 22 (3). Charoenkwan, P., et al., iTTCA-Hybrid: Improved and robust identification of tumor T cell antigens by utilizing hybrid feature representation. Analytical Biochemistry, 2020. 599 . Dai, R., et al., BBPpred: Sequence-Based Prediction of Blood-Brain Barrier Peptides with Feature Representation Learning and Logistic Regression. Journal of Chemical Information and Modeling, 2021. 61 (1): p. 525-534. Zhang, W., et al., PredAPP: Predicting Anti-Parasitic Peptides with Undersampling and Ensemble Approaches. Interdisciplinary Sciences: Computational Life Sciences, 2021. 14 (1): p. 258-268. Bin, Y., et al., Prediction of Neuropeptides from Sequence Information Using Ensemble Classifier and Hybrid Features. Journal of Proteome Research, 2020. 19 (9): p. 3732-3740. Pinacho-Castellanos, S.A., et al., Alignment-Free Antimicrobial Peptide Predictors: Improving Performance by a Thorough Analysis of the Largest Available Data Set. Journal of Chemical Information and Modeling, 2021. 61 (6): p. 3141-3157. Wei, L., et al., ATSE: a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural network and attention mechanism. Briefings in Bioinformatics, 2021. 22 (5). Wu, J., R.E. Aluko, and S. Nakai, Structural Requirements of Angiotensin I-Converting Enzyme Inhibitory Peptides: Quantitative Structure−Activity Relationship Study of Di- and Tripeptides. Journal of Agricultural and Food Chemistry, 2006. 54 (3): p. 732-738. Du, A. and W. Jia, New insights into the bioaccessibility and metabolic fates of short-chain bioactive peptides in goat milk using the INFOGEST static digestion model and an improved data acquisition strategy. Food Research International, 2023. 169 . Charoenkwan P, Chiangjong W, Nantasenamat C, Hasan MM, Manavalan B, Shoombuatong W. StackIL6: a stacking ensemble model for improving the prediction of IL-6 inducing peptides . Brief Bioinform. 2021; 22 (6):bbab172. Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterial.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Nov, 2025 Reviews received at journal 02 Nov, 2025 Reviews received at journal 17 Oct, 2025 Reviews received at journal 16 Oct, 2025 Reviews received at journal 06 Oct, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers agreed at journal 26 Sep, 2025 Reviewers invited by journal 26 Sep, 2025 Editor assigned by journal 19 Sep, 2025 Submission checks completed at journal 18 Sep, 2025 First submitted to journal 18 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {\"props\":{\"pageProps\":{\"initialData\":{\"identity\":\"rs-7645806\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Method Article\",\"associatedPublications\":[],\"authors\":[{\"id\":525678797,\"identity\":\"2b2ec0c3-32a6-4478-872e-81edb018f57f\",\"order_by\":0,\"name\":\"Dongya Qin\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Jinfeng Laboratory\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Dongya\",\"middleName\":\"\",\"lastName\":\"Qin\",\"suffix\":\"\"},{\"id\":525678798,\"identity\":\"fbeb036a-b022-487a-aeeb-d42f65470c28\",\"order_by\":1,\"name\":\"Hai Fang\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"National Research Center for Translational Medicine at Shanghai, Shanghai Jiao Tong University School of Medicine\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Hai\",\"middleName\":\"\",\"lastName\":\"Fang\",\"suffix\":\"\"},{\"id\":525678799,\"identity\":\"a2c5c9e4-b20e-4660-bcf6-8f954bec147d\",\"order_by\":2,\"name\":\"Zheng Wang\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYBACA2YQWcHAwMYOF0sgRssZoBZmuGpCWkAEYxuQIFqLOTvzMcmf87bJ8zEzsEn+/GHHwM+eY8DwcwduLZbNbGkSkttuG7YBtUjzJCQzSPa8MWDsPYPHYYd5zG4YbrvNCNbCkHCAweBGjgEz2Kn4tCTOuW0P0iL5A6jFnigtBxtuJ4K0SPCAbJEgoAXol/SfDcduJ7cxMzZb86Ql80iceVZwsBePFnP+w4cNf9Tctp3f3nzw5g8bOzn+9uSND37i0YIEGBtAJA+IOECUhlEwCkbBKBgFOAEAPbZGm1KZ0CUAAAAASUVORK5CYII=\",\"orcid\":\"\",\"institution\":\"Jinfeng Laboratory\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Zheng\",\"middleName\":\"\",\"lastName\":\"Wang\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-09-18 06:23:18\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-7645806/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7645806/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":93027872,\"identity\":\"bbf6208b-494b-4794-8633-e34105b2dfda\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"docx\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":2490424,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Manuscript.docx\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/1f3e53041d8e911045800ff6.docx\"},{\"id\":93027868,\"identity\":\"e73ed6e8-668e-4c14-bfe2-3c7f5e5cd176\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"json\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":6187,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"188bc369f1934f14a28b974b5de771c5.json\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/e4369ff55ab1717f594ba681.json\"},{\"id\":93027878,\"identity\":\"eddc0206-dfc4-40a3-b48e-8e86917c3d88\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"docx\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":1071735,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"SupplementaryMaterial.docx\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/c81b360ad90808ebc49a186f.docx\"},{\"id\":93028356,\"identity\":\"82609486-cf4c-4173-9462-483dc3872a98\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:52:33\",\"extension\":\"xml\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":123079,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"188bc369f1934f14a28b974b5de771c51enriched.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/f1988d78a3e31e6e35cf505b.xml\"},{\"id\":93027887,\"identity\":\"f7e46848-6cd0-414a-a57c-f9b547aacf8e\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:34\",\"extension\":\"png\",\"order_by\":4,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":399601,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/4d4fd43abe850885e0fb7c6e.png\"},{\"id\":93027873,\"identity\":\"8e3f1127-48be-4a27-983e-2af8de9503b3\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"png\",\"order_by\":5,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":536230,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/78769dd3dfb20100fc7817eb.png\"},{\"id\":93028358,\"identity\":\"874e0484-a664-4db8-bca3-4d9320fc72b8\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:52:33\",\"extension\":\"png\",\"order_by\":6,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":340568,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/72dff89fb2d2e391ba97dd65.png\"},{\"id\":93027876,\"identity\":\"8bd98c0d-6472-4a5e-a3d0-8e66b6969e96\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"png\",\"order_by\":7,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":754305,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage4.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/3d691f6f92388e75734cf5d7.png\"},{\"id\":93029818,\"identity\":\"71e8844a-453a-4bb9-b60a-faecb2659a85\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 10:00:34\",\"extension\":\"png\",\"order_by\":8,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":360659,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/29262176881a2ec083767b75.png\"},{\"id\":93027879,\"identity\":\"6d909bdd-53f8-462e-918d-b742ffeb3e37\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"png\",\"order_by\":9,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":97466,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/55b9ff3656a201bb0b4551e5.png\"},{\"id\":93027880,\"identity\":\"9501a393-f33f-4b7b-b201-c2db3fc69c43\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:34\",\"extension\":\"png\",\"order_by\":10,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":99988,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/4be357bd1cf1fa0b25a5bdf3.png\"},{\"id\":93028361,\"identity\":\"8024a3f5-6b99-4cf0-b0cd-9179c39aefa5\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:52:34\",\"extension\":\"png\",\"order_by\":11,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":57937,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/2d4adaad8394fb5c8feb344d.png\"},{\"id\":93027883,\"identity\":\"da374c45-2904-469c-ad2a-9bf4b0ab4f2e\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:34\",\"extension\":\"png\",\"order_by\":12,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":180228,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage4.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/d2fa9627770d916f6dd6da01.png\"},{\"id\":93028362,\"identity\":\"b1847d7a-37d0-4b62-8811-0c652fc696c2\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:52:34\",\"extension\":\"png\",\"order_by\":13,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":83969,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/426d722a2149ac912d516815.png\"},{\"id\":93027885,\"identity\":\"c18d071d-5d66-4a03-a44a-9d4fbf8ecd04\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:34\",\"extension\":\"xml\",\"order_by\":14,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":123590,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"188bc369f1934f14a28b974b5de771c51structuring.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/295b1dbf230b506a08d6ff1d.xml\"},{\"id\":93028359,\"identity\":\"2f6a303b-880d-459a-a13a-ee76468a38ff\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:52:34\",\"extension\":\"html\",\"order_by\":15,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":132584,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"earlyproof.html\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/2d5b5e8c88980f39cede85ff.html\"},{\"id\":93027866,\"identity\":\"89be37f2-d8ec-44a7-bf61-7bd56ad5dc2d\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"png\",\"order_by\":1,\"title\":\"Figure 1\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":473662,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003e\\u003cstrong\\u003eThe bioinformatic architecture of the PepPharmaHub platform. a \\u003c/strong\\u003eDatabase module, including 25 benchmark datasets, two unlabeled sequence libraries, 24 preselected peptide libraries, and sequence profiles. \\u003cstrong\\u003eb \\u003c/strong\\u003eModel training module, including four types of RNN models (SimpleRNN, LSTM, GRU and BiLSTM) and a BERT pretraining fine-tuning model based on three sets of motifs (k-mer = 1, 2, 3). \\u003cstrong\\u003ec \\u003c/strong\\u003eVirtual screening module, including 24 pre-configured fast model screening protocols and user-defined model methods. \\u003cstrong\\u003ed \\u003c/strong\\u003eVisual analysis module, including task workflows, therapeutic peptide classification statistics, and comparisons of experimental and screening sequence profiles.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/10459b8861e173b81374cef4.png\"},{\"id\":93027867,\"identity\":\"dfc99e3f-229f-40b9-a721-1c3f5475311d\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"png\",\"order_by\":2,\"title\":\"Figure 2\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":424370,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003e\\u003cstrong\\u003ePerformance comparison between PepPharmaHub and state-of-the-art models on the 24 test datasets. a\\u003c/strong\\u003e Antioxidant (AnOxPP), \\u003cstrong\\u003eb\\u003c/strong\\u003e Antioxidant (AnOxPePred-FRS), \\u003cstrong\\u003ec\\u003c/strong\\u003e Antiviral, \\u003cstrong\\u003ed\\u003c/strong\\u003e ACE-inhibitory, \\u003cstrong\\u003ee\\u003c/strong\\u003e DPP IV inhibitory,\\u003cstrong\\u003e f\\u003c/strong\\u003e Bitter, \\u003cstrong\\u003eg\\u003c/strong\\u003e Antimalarial (main dataset), \\u003cstrong\\u003eh \\u003c/strong\\u003eAnti-MRSA strains, \\u003cstrong\\u003ei\\u003c/strong\\u003e Antifungal, \\u003cstrong\\u003ej\\u003c/strong\\u003e Anticancer (alternative dataset), \\u003cstrong\\u003ek\\u003c/strong\\u003e Umami, \\u003cstrong\\u003el \\u003c/strong\\u003eTumor T cell antigens, \\u003cstrong\\u003em\\u003c/strong\\u003eBlood-brain barrier, \\u003cstrong\\u003en \\u003c/strong\\u003eInterleukin-6-inducing, \\u003cstrong\\u003eo\\u003c/strong\\u003e Antimalarial (alternative dataset), \\u003cstrong\\u003ep\\u003c/strong\\u003e Antimicrobial, \\u003cstrong\\u003eq\\u003c/strong\\u003e Quorum sensing, \\u003cstrong\\u003er\\u003c/strong\\u003eToxicity, \\u003cstrong\\u003es\\u003c/strong\\u003e Anti-coronavirus, \\u003cstrong\\u003et\\u003c/strong\\u003e Anticancer (main dataset), \\u003cstrong\\u003eu\\u003c/strong\\u003eNeuropeptide, \\u003cstrong\\u003ev\\u003c/strong\\u003e Antiparasitic, \\u003cstrong\\u003ew\\u003c/strong\\u003e Antibacterial, \\u003cstrong\\u003ex\\u003c/strong\\u003eAntihypertensive (mAHTPred).\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/5a50b394d4bd3b7837e160df.png\"},{\"id\":93027869,\"identity\":\"f3498290-ade8-4ba0-9672-9408411a22dd\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"png\",\"order_by\":3,\"title\":\"Figure 3\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":838054,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003e\\u003cstrong\\u003eComparison of the generalization performance of the Peptide-Predictor module with existing web servers for newly reported active peptides in 2023-2025. a\\u003c/strong\\u003e Antihypertensive, \\u003cstrong\\u003eb\\u003c/strong\\u003e Antioxidant, \\u003cstrong\\u003ec\\u003c/strong\\u003e DPP IV inhibitory, \\u003cstrong\\u003ed \\u003c/strong\\u003eAntimicrobial, \\u003cstrong\\u003ee \\u003c/strong\\u003eAntimalarial, \\u003cstrong\\u003ef \\u003c/strong\\u003eQuorum sensing, \\u003cstrong\\u003eg \\u003c/strong\\u003eAnti-MRSA strains, \\u003cstrong\\u003eh \\u003c/strong\\u003eTumor T cell antigens, \\u003cstrong\\u003ei\\u003c/strong\\u003e, Antiparasitic,\\u003cstrong\\u003e j \\u003c/strong\\u003eAntifungal, \\u003cstrong\\u003ek \\u003c/strong\\u003eToxicity, \\u003cstrong\\u003el\\u003c/strong\\u003e Anti-coronavirus, \\u003cstrong\\u003em\\u003c/strong\\u003e Umami, \\u003cstrong\\u003en \\u003c/strong\\u003eInterleukin-6 inducing, \\u003cstrong\\u003eo\\u003c/strong\\u003e Blood-brain barrier, \\u003cstrong\\u003ep\\u003c/strong\\u003e Neuropeptide, \\u003cstrong\\u003eq \\u003c/strong\\u003eAntibacterial, \\u003cstrong\\u003er\\u003c/strong\\u003e Antiviral, \\u003cstrong\\u003es\\u003c/strong\\u003e Bitter, \\u003cstrong\\u003et\\u003c/strong\\u003e Anticancer.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/1994b5e4599d9a600c43f269.png\"},{\"id\":93029817,\"identity\":\"eb2dbf86-18fd-4402-8144-e728a43dec2a\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 10:00:33\",\"extension\":\"png\",\"order_by\":4,\"title\":\"Figure 4\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":1114853,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003e\\u003cstrong\\u003eRapid screening pipeline for 24 sets of bioactive peptides and feature map comparison between experimental and predicted samples. a\\u003c/strong\\u003e The rapid screening process for the 24 groups of bioactive peptides designed based on the PepPharmaHub platform data and tools. \\u003cstrong\\u003eb\\u003c/strong\\u003e Statistical view of the number of positive and negative samples theoretically screened from Sequence Library-1. \\u003cstrong\\u003ec\\u003c/strong\\u003e Sequence feature importance plots of the experimental dataset compared to the screening dataset, where the X-axis represents the classification of bioactive peptides, and the Y-axis represents the feature importance scoring of the 20 amino acid residues. For each group of active peptides, the eigenvalues are arranged in a columnar order from left to right, representing the N-terminal, C-terminal, and residue composition. Feature importance scores for both experimental and predicted samples are ranked in descending order based on their distance from the X-axis. The closer the distance to the X-axis, the higher the importance score and the more prominent the feature; conversely, the farther the distance, the lower the score and the weaker the feature.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"4.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/91827e872313d5551190fa36.png\"},{\"id\":93028355,\"identity\":\"c1ea892d-159e-4eae-b4c1-189603798a53\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:52:33\",\"extension\":\"png\",\"order_by\":5,\"title\":\"Figure 5\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":553459,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003e\\u003cstrong\\u003ePerformance comparison between the custom ACE-inhibitory peptide screening pipeline and current methods.\\u003c/strong\\u003e \\u003cstrong\\u003ea\\u003c/strong\\u003e The custom screening process for ACE-inhibitory peptides, developed utilizing the data and tools provided by the PepPharmaHub platform, including Database, RNN-Trainer, BERT-Trainer and Model-Caller modules. \\u003cstrong\\u003eb\\u003c/strong\\u003eVisualization of training progress for the best model (RNN20250624111715), along with validation evaluation, independent test performance, and ROC analysis. \\u003cstrong\\u003ec \\u003c/strong\\u003ePerformance comparison of the best model (RNN20250624111715) and three antihypertensive peptide web servers (mAHTPred, pLM4ACE, and ACEiPP) on the independent test set (ACEiPs_test). pLM4ACE includes three models: Logistic regression, SVM, and Multilayer perceptron. \\u003cstrong\\u003ed\\u003c/strong\\u003e Hydrolyzed peptide prediction (1,605,115 unique sequences with probability ≥ 0.5) and comparison of their sequence features with experimental ACEiPs, including N-terminal residues, C-terminal residues, and sequence composition.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/6597009fe8eef29cb961ba75.png\"},{\"id\":93030694,\"identity\":\"f1257a8c-406c-4641-806e-58bced8d6fbf\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 10:08:48\",\"extension\":\"pdf\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":4663830,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"manuscript.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/4aead0c1-d939-406d-a81b-32f96df9ba92.pdf\"},{\"id\":93027870,\"identity\":\"07cfc281-029e-46d3-bda1-86e97b550ee7\",\"added_by\":\"auto\",\"created_at\":\"2025-10-08 09:44:33\",\"extension\":\"docx\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"supplement\",\"size\":1071735,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"SupplementaryMaterial.docx\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7645806/v1/5ba8933f1024aa286f80fcd7.docx\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"PepPharmaHub: A Cloud-Based Platform Integrating Multimodel Language Architectures with Curated Data Resources for Therapeutic Peptide Discovery\",\"fulltext\":[{\"header\":\"Background\",\"content\":\"\\u003cp\\u003eTherapeutic peptides have emerged as a promising class of drug candidates owing to their high specificity and favorable safety profiles. These peptides exert therapeutic effects by mimicking or modulating the biological activities of endogenous peptides, proteins, or hormones[\\u003cspan citationid=\\\"CR1\\\" class=\\\"CitationRef\\\"\\u003e1\\u003c/span\\u003e], targeting pathways such as receptor agonism or antagonism, enzyme modulation, signal transduction regulation, and immune system modulation [\\u003cspan citationid=\\\"CR2\\\" class=\\\"CitationRef\\\"\\u003e2\\u003c/span\\u003e]. Over 40 types of functional peptides have been identified, including antihypertensive, antioxidant, immunomodulatory, anticancer, antibacterial, opioid-like, cholesterol-lowering, antithrombotic, or antidiabetic activities [\\u003cspan citationid=\\\"CR3\\\" class=\\\"CitationRef\\\"\\u003e3\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR4\\\" class=\\\"CitationRef\\\"\\u003e4\\u003c/span\\u003e]. These peptides have attracted significant attention due to their high target specificity, functional diversity, good biocompatibility, and low immunogenicity [\\u003cspan citationid=\\\"CR5\\\" class=\\\"CitationRef\\\"\\u003e5\\u003c/span\\u003e]. Consequently, peptide drugs are increasingly recognized as a pivotal direction for future drug development [\\u003cspan citationid=\\\"CR6\\\" class=\\\"CitationRef\\\"\\u003e6\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR7\\\" class=\\\"CitationRef\\\"\\u003e7\\u003c/span\\u003e].\\u003c/p\\u003e\\u003cp\\u003eDespite their therapeutic potential, the discovery and development of these molecules are hindered by the complexity of predicting functional activities from peptide sequences. The vast diversity of peptide sequences in biological systems complicates the functional annotation, and traditional experimental methods are often too resource-intensive to capture this complexity [\\u003cspan citationid=\\\"CR8\\\" class=\\\"CitationRef\\\"\\u003e8\\u003c/span\\u003e]. Advances in bioinformatics and artificial intelligence have enabled data-driven approaches, such as machine learning and deep learning to analyze the relationships between sequence features and experimentally determined activities, thereby improving functional prediction [\\u003cspan citationid=\\\"CR9\\\" class=\\\"CitationRef\\\"\\u003e9\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR10\\\" class=\\\"CitationRef\\\"\\u003e10\\u003c/span\\u003e].\\u003c/p\\u003e\\u003cp\\u003eNumerous computational predictors have been developed for specific therapeutic properties, including anticancer activity [\\u003cspan citationid=\\\"CR11\\\" class=\\\"CitationRef\\\"\\u003e11\\u003c/span\\u003e], angiotensin-converting enzyme (ACE) inhibition [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e], antimicrobial properties [\\u003cspan citationid=\\\"CR13\\\" class=\\\"CitationRef\\\"\\u003e13\\u003c/span\\u003e], antioxidant [\\u003cspan citationid=\\\"CR14\\\" class=\\\"CitationRef\\\"\\u003e14\\u003c/span\\u003e], cell penetration [\\u003cspan citationid=\\\"CR15\\\" class=\\\"CitationRef\\\"\\u003e15\\u003c/span\\u003e], toxicity [\\u003cspan citationid=\\\"CR16\\\" class=\\\"CitationRef\\\"\\u003e16\\u003c/span\\u003e], dipeptidyl peptidase IV inhibition [\\u003cspan citationid=\\\"CR17\\\" class=\\\"CitationRef\\\"\\u003e17\\u003c/span\\u003e], and anti-coronavirus activity [\\u003cspan citationid=\\\"CR18\\\" class=\\\"CitationRef\\\"\\u003e18\\u003c/span\\u003e]. These predictors utilize a variety of modeling approaches, ranging from Simple Recurrent Neural Networks (SimpleRNN), Long Short-Term Memory Networks (LSTM), Bidirectional Long Short-Term Memory Networks (BiLSTM), Gated Recurrent Unit (GRU), and transformer-based pretrained models like BERT, as well as hybrid variants. Sequence characterization methods can be categorized into five main types: (i) encoding methods leveraging physicochemical descriptors of amino acid residues (e.g., hydrophobicity, polarity, volume) and one-hot sparse matrices [\\u003cspan citationid=\\\"CR19\\\" class=\\\"CitationRef\\\"\\u003e19\\u003c/span\\u003e]; (ii) deep feature extraction using attention mechanisms from pretrained models [\\u003cspan citationid=\\\"CR20\\\" class=\\\"CitationRef\\\"\\u003e20\\u003c/span\\u003e]; (iii) computation of physicochemical properties such as molecular weight, volume, and isoelectric point [\\u003cspan citationid=\\\"CR21\\\" class=\\\"CitationRef\\\"\\u003e21\\u003c/span\\u003e]; (iv) k-mer segmentation for fixed-length fragment representation [\\u003cspan citationid=\\\"CR22\\\" class=\\\"CitationRef\\\"\\u003e22\\u003c/span\\u003e]; (v) molecular fingerprint encoding based on chemical structures or simplified molecular input line entry system (SMILES) representations, generating molecular fingerprints like extended connectivity fingerprints (ECFP) to describe structural features of molecules [\\u003cspan citationid=\\\"CR23\\\" class=\\\"CitationRef\\\"\\u003e23\\u003c/span\\u003e].\\u003c/p\\u003e\\u003cp\\u003eHowever, this field faces three critical challenges. First, the absence of a unified modeling platform undermines reproducibility and limits the diversity, and timeliness of data analysis. Second, the insufficient computational resources, standard data integration, and pre-selected peptide libraries hinder the development of integrated algorithms and high-throughput screening capabilities. Third, poor model interpretability, with inadequate visualization of key residues and motifs, impedes mechanistic insights into peptide functionality.\\u003c/p\\u003e\\u003cp\\u003eTo address these issues, we have developed PepPharmaHub, a comprehensive web-based platform that integrates modules for model training, model deployment, virtual screening, and sequence characterization. PepPharmaHub features a user-friendly interface that eliminates the need for specialized programming skills, allowing researchers to visually monitor model training, filtering, and functional motif analysis. Additionally, the platform includes small-sample standard datasets and pre-selected peptide libraries. In summary, PepPharmaHub addresses critical challenges in therapeutic peptide discovery by improving the accuracy, efficiency, and interpretability of functional prediction. It provides a powerful, user-friendly tool for biomedical researchers and drug developers, accelerating the discovery and development of peptide-based therapeutics.\\u003c/p\\u003e\"},{\"header\":\"Results\",\"content\":\"\\u003cdiv id=\\\"Sec3\\\" class=\\\"Section2\\\"\\u003e\\u003ch2\\u003ePepPharmaHub facilitates one-stop screening for therapeutic peptides\\u003c/h2\\u003e\\u003cp\\u003eTo streamline the development of therapeutic peptides, we developed PepPharmaHub, a unified web platform that integrates curated peptide databases, customizable modeling frameworks, high-throughput virtual screening, and result visualization into a cohesive, end-to-end workflow. The system is organized into five core functional modules, each contributing to a one-stop pipeline comprising data access, model training, virtual screening, visualization, and analysis (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e).\\u003c/p\\u003e\\u003c/div\\u003e\\n\\u003ch3\\u003e(1) Built-in centralized and structured peptide data resources\\u003c/h3\\u003e\\n\\u003cp\\u003eThis database module provides foundational data support for model development and benchmarking. It integrates 24 public peptide datasets and two in-house sequence libraries encompassing over 2.3\\u0026nbsp;million peptides with unknown activity. Additionally, it hosts 24 prediction datasets and characteristic sequence profiles for 20 classes of bioactive peptides (Supplementary Fig.\\u0026nbsp;1), offering a rich and standardized resource for both model training and screening tasks.\\u003c/p\\u003e\\n\\u003ch3\\u003e(2) Deep Learning and Dual-Mode Screening\\u003c/h3\\u003e\\n\\u003cp\\u003ePepPharmaHub provide a flexible and extensible framework for constructing and deploying deep learning-based peptide prediction models. The training module supports the online development of task-specific models through two components: the RNN-Trainer, which offers four types of recurrent neural networks with customizable configurations, including 24 residue encoding schemes, 19 activation functions, adjustable network depth, early stopping, and checkpointing; and the BERT-Trainer, which enables fine-tuning of transformer-based architectures using both standard parameters such as batch size, epochs, and learning rate, and advanced parameters such as attention heads, dropout, and activation layers (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003eb). These tools allow users to build biologically tailored models without requiring programming expertise. For downstream deployment, the Virtual Screening module (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003ec) provides two complementary options: the Peptide-Predictor, which includes 24 optimized pre-trained models for functional classification across 20 peptide attributes; and the Model-Caller, which supports high-throughput batch predictions using user-defined models trained within the platform. This dual-mode screening framework distinguishes PepPharmaHub from conventional predictors by enabling both rapid inference using standardized models and customizable prediction via user-trained models.\\u003c/p\\u003e\\n\\u003ch3\\u003e(3) Web-based implementation for interactive visualization\\u003c/h3\\u003e\\n\\u003cp\\u003ePepPharmaHub features a web-based architecture that enables seamless user interaction and real-time task monitoring. The Visual Analysis module (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003ed) allows users to interactively inspect modeling and screening workflows by associating each task with a unique identifier, through which dynamic logs, intermediate outputs, final results, and performance metrics can be accessed and downloaded. Visualization capabilities include sequence feature comparisons, classification overviews, and model evaluation statistics, supporting transparent and reproducible analysis. The platform is organized into six functional interfaces including: Home, Database, RNN-Trainer, BERT-Trainer, Peptide-Predictor, and Model-Caller (Supplementary Fig.\\u0026nbsp;2 and Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003ee), which together support end-to-end task execution. Users can initiate analyses by uploading FASTA files and selecting relevant parameters, while monitoring progress and retrieving results for up to 15 days. The modular design allows individual components to be used independently or combined into integrated pipelines, thereby enhancing flexibility and usability for both expert and non-expert users in therapeutic peptide research.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\n\\u003ch3\\u003ePepPharmaHub demonstrates robust generalization and adaptability across open benchmark datasets\\u003c/h3\\u003e\\n\\u003cp\\u003eTo evaluate the generalization performance and adaptability of PepPharmaHub across diverse peptide prediction tasks, we conducted systematic cross-validation and independent testing on 24 publicly available benchmark datasets (Table\\u0026nbsp;\\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e). Using the BiLSTM model with SDPZ27 encoding and the BERT model with k-mer\\u0026thinsp;=\\u0026thinsp;1, cross-validation demonstrated robust performance: 17 BiLSTM-based models achieved average accuracies exceeding 0.8015, with Sensitivity, Specificity, MCC, and AUC ranging from 0.3000 to 1.0000, 0.8514 to 1.0000, 0.3191 to 0.9729, and 0.8000 to 0.9975, respectively (Supplementary Table\\u0026nbsp;2). Similarly, 22 BERT-based models yielded average accuracies above 0.8242, with respective performance metrics spanning 0.6800-1.0000 (Sensitivity), 0.8438-1.0000 (Specificity), 0.6401-1.0000 (MCC), and 0.8741-1.0000 (AUC) (Supplementary Table\\u0026nbsp;3). On independent test sets (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig2\\\" class=\\\"InternalRef\\\"\\u003e2\\u003c/span\\u003ea-x), PepPharmaHub-BiLSTM achieved superior predictive performance on two antioxidant, interleukin-6-inducing, and ACE-inhibitory datasets, showed comparable performance on 7 datasets, and relatively lower performance on the remaining 13 datasets. In contrast, PepPharmaHub-BERT outperformed on 11 datasets, was comparable to state-of-the-art models on 7 datasets, and underperformed on 6 tasks. Notably, BERT exhibited stronger feature extraction capabilities than BiLSTM on 17 datasets, though its performance was slightly inferior on antioxidant, ACE-inhibitory, anti-coronavirus, antiparasitic, and antibacterial tasks. Overall, the PepPharmaHub models matched or exceeded the performance of existing methods on 19 out of 24 datasets. These findings underscore the platform\\u0026rsquo;s capacity to deliver competitive and generalizable predictive models across a wide range of peptide functional categories. Importantly, users can complete the entire evaluation pipeline by simply uploading datasets, selecting model architectures, and defining training parameters, demonstrating the platform\\u0026rsquo;s accessibility and suitability for broad peptide screening applications without the need for complex modeling workflows.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\u003cdiv id=\\\"Sec8\\\" class=\\\"Section2\\\"\\u003e\\u003ch2\\u003ePepPharmaHub outperforms greater generalization capabilities than existing web servers\\u003c/h2\\u003e\\u003cp\\u003eTo assess the real-world generalization capability of PepPharmaHub relative to existing peptide prediction servers, we deployed 24 optimal models comprising 18 BERT-based and 6 RNN-based architectures into the Peptide-Predictor module (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttp://bioinmed.jflab.ac.cn:18090/peppharmahub/PeptidePredictor/input.jsp\\u003c/span\\u003e\\u003cspan address=\\\"http://bioinmed.jflab.ac.cn:18090/peppharmahub/PeptidePredictor/input.jsp\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e) and evaluated their performance on a dataset of 3,475 newly reported bioactive peptide sequences collected between 2023 and 2025 (Table\\u0026nbsp;\\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e). Across 20 independent test tasks, Peptide-Predictor demonstrated a more concentrated and robust prediction accuracy distribution (ranging from 44.35% to 92.37%) compared to the broader and sparser accuracy range observed in existing web predictors (0% to 93.37%) (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003e). Notably, the predictor achieved superior performance in 14 tasks (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003ea-n), with prediction accuracies ranging from 52.38% to 88.89%, surpassing the best existing predictors by a margin of 0.38% to 75%. In particular, it attained accuracies of 81.3% for antimicrobial prediction (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003ed), 85.71% for quorum sensing (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003ef), and 88.89% for antiparasitic prediction (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003ei). In neuropeptide and blood-brain barrier datasets (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003eo\\u0026ndash;p), the Predictor showed comparable performance, with accuracies of 70.37% and 91.67%. While Matthews correlation coefficient (MCC) values for all 54 models varied broadly (\\u0026minus;\\u0026thinsp;0.3068 to 0.6064), 13 PepPharmaHub-based models exhibited relatively high MCCs in the range of 0.0085 to 0.5774, indicating meaningful discriminative power in many cases. The system performed relatively slightly lower in a subset of tasks, including antibacterial, antiviral, bitter and anticancer peptide prediction (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003eq-t). Overall, these results suggest that Peptide-Predictor delivers enhanced functional prediction accuracy for novel peptide sequences compared to current publicly available web servers, highlighting its strong generalization capability and practical utility in peptide discovery workflow.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\u003c/div\\u003e\\n\\u003ch3\\u003eRapid screening pipeline and feature mapping for bioactive peptides\\u003c/h3\\u003e\\n\\u003cp\\u003eTo evaluate the interpretability and functional relevance of model predictions, we implemented a rapid screening and feature mapping pipeline using PepPharmaHub. A total of 2,321,342 unlabeled peptide sequences (length 2\\u0026ndash;20) were retrieved from Sequence Library-1 and screened using the 24 packaged predictive models in the Peptide-Predictor module (task ID: PRE20250616113524). The resulting predictions, visualized through the platform\\u0026rsquo;s analysis interface, included workflow logs, data preprocessing, classification summaries, sequence profiles, and downloadable result packages (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig4\\\" class=\\\"InternalRef\\\"\\u003e4\\u003c/span\\u003ea). These outputs were stored in the Pre-selected Library (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttp://bioinmed.jflab.ac.cn:18090/peppharmahub/Database/SeqLogoPrediction.jsp?PreID=PRE20250616113524\\u003c/span\\u003e\\u003cspan address=\\\"http://bioinmed.jflab.ac.cn:18090/peppharmahub/Database/SeqLogoPrediction.jsp?PreID=PRE20250616113524\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e) for further inspection. Visualization of sequence feature distributions revealed substantial variation in the predicted abundance of different bioactive peptides\\u0026mdash;e.g., tumor T cell antigens (1,927,539), antioxidants ( 1,794,986), and quorum sensing peptides (1,674,051) were highly represented, while anti-coronavirus (7,837), anti-MRSA (89,058), and anticancer peptides (341,509) were comparatively rare (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig4\\\" class=\\\"InternalRef\\\"\\u003e4\\u003c/span\\u003eb). Amino acid composition analysis indicated both shared and unique residue preferences across peptide types; for instance, Leu was commonly enriched in 21 peptide classes but underrepresented in toxicity and antiparasitic peptides. Antioxidants featured residues such as Leu, Pro, Gly, and Ala, whereas anticancer peptides were enriched in Lys, Leu, Ala, Gly, and Ile. Notably, sequence composition analyses revealed that screened and experimental peptides exhibited concordant N-/C-terminal and key residue profiles (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig4\\\" class=\\\"InternalRef\\\"\\u003e4\\u003c/span\\u003ec), suggesting that the models effectively captured discriminative sequence features. To our knowledge, this constitutes one of the most extensive feature maps for bioactive peptide sequences, demonstrating that PepPharmaHub not only enables high-throughput screening but also enhances model transparency and interpretability through comprehensive feature analysis.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\n\\u003ch3\\u003eSelf-trained framework for efficient screening of ACE-inhibitory peptides\\u003c/h3\\u003e\\n\\u003cp\\u003eTo improve predictive accuracy for ACE-inhibitory peptides, we constructed a new benchmark dataset (ACEiPs) and employed the PepPharmaHub platform to develop 27 self-trained models using BiLSTM and fine-tuned BERT architectures via the RNN-Trainer and BERT-Trainer modules. Figure\\u0026nbsp;\\u003cspan refid=\\\"Fig5\\\" class=\\\"InternalRef\\\"\\u003e5\\u003c/span\\u003ea demonstrates the whole screening workflow. Cross-validation on the ACEiPs benchmark dataset showed that 20 models achieved over 80% accuracy, with precision, specificity, sensitivity, MCC, and AUC ranging from 0.7902 to 0.9241, 0.7821 to 0.9250, 0.7904 to 0.9126, 0.6068 to 0.8384, and 0.8490 to 0.9538, respectively. Independent testing on ACEiPs-test confirmed consistent high performance across the same 20 models (Supplementary Table\\u0026nbsp;4). Among all models, the RNN model (RNN20250624111715) encoded with VVSFZL37 demonstrated the best generalization performance, achieving accuracy, precision, specificity, sensitivity, and MCC scores of 0.9169, 0.9088, 0.9070, 0.9268, and 0.8340, respectively (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig5\\\" class=\\\"InternalRef\\\"\\u003e5\\u003c/span\\u003eb). When benchmarked against three established ACE prediction servers (mAHTPred[\\u003cspan citationid=\\\"CR24\\\" class=\\\"CitationRef\\\"\\u003e24\\u003c/span\\u003e], ACEiPP [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e], and pLM4ACE[\\u003cspan citationid=\\\"CR25\\\" class=\\\"CitationRef\\\"\\u003e25\\u003c/span\\u003e], which includes Logistic Regression, SVM, and Multilayer Perceptron models), the RNN20250624111715 model consistently outperformed across all evaluation metrics, with improvements ranging from 0.0366 to 0.4479 in accuracy and up to 0.896 in MCC (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig5\\\" class=\\\"InternalRef\\\"\\u003e5\\u003c/span\\u003ec). Notably, while mAHTPred and ACEiPP showed moderate performance, pLM4ACE performed poorly with accuracies below 0.4845 and negative MCCs.\\u003c/p\\u003e\\u003cp\\u003eTo demonstrate scalability, the best-performing self-trained model was deployed via the Model-Caller module to screen 3,740,614 peptides from Sequence-Library 2. As shown in Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig5\\\" class=\\\"InternalRef\\\"\\u003e5\\u003c/span\\u003ec, the predicted ACEiPs have similar residue composition and two-terminal features to experimental ACEiPs, i.e., they are all mainly composed of hydrophobic amino acids (Pro, Leu, Val, Gly, and Ala), the C-terminus tending to hydrophobic (Pro, Phe, and Leu), positively charged (Arg and Lys), and bulky aromatic (Tyr) amino acids, and the N-terminus favoring hydrophobic amino acids (Leu, Val, Ala, Gly, Ile, and Pro). Taken together, these findings validate the self-training framework implemented in PepPharmaHub as a robust and efficient approach for the identification of ACE-inhibitory peptides, demonstrating superior predictive performance, enhanced scalability, and greater biological relevance compared to existing web-based prediction tools.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\"},{\"header\":\"Discussion\",\"content\":\"\\u003cp\\u003eIn this study, we present PepPharmaHub, a comprehensive and scalable web platform that enables end-to-end modeling, screening, sequence feature interpretation, and data sharing for bioactive peptides. By integrating multiple natural language processing (NLP) architectures into a unified, user-friendly web framework including SimpleRNN, LSTM, GRU, BiLSTM, and BERT, the platform supports both platform-provided and self-trained prediction models, covering a wide range of peptide classification tasks without requiring programming expertise or local computational resources. Across 24 benchmark datasets, PepPharmaHub demonstrates superior or comparable performance to existing state-of-the-art models in terms of accuracy, generalization, and throughput. Compared to conventional web servers (such as ACEiPP[\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e], AnOxPP [\\u003cspan citationid=\\\"CR14\\\" class=\\\"CitationRef\\\"\\u003e14\\u003c/span\\u003e], TransImbAMP [\\u003cspan citationid=\\\"CR26\\\" class=\\\"CitationRef\\\"\\u003e26\\u003c/span\\u003e], BERT4Bitter[\\u003cspan citationid=\\\"CR27\\\" class=\\\"CitationRef\\\"\\u003e27\\u003c/span\\u003e], and SCMRSA[\\u003cspan citationid=\\\"CR28\\\" class=\\\"CitationRef\\\"\\u003e28\\u003c/span\\u003e]) PepPharmaHub overcomes limitations associated with fixed model architectures and static data, enabling continuous model retraining and task-specific customization through its RNN-Trainer, BERT-Trainer, and Model-Caller modules.\\u003c/p\\u003e\\u003cp\\u003eBeyond predictive performance, the platform facilitates sequence-level interpretability through feature mapping and comparative analysis between theoretical predictions and experimental peptide profiles. While strong concordance was observed for many peptide classes, notable inconsistencies were detected in specific sequence regions (e.g., N-termini of bitter, blood-brain barrier, and antifungal peptides; C-termini of DPP IV inhibitors), likely reflecting the limited size and diversity of current training datasets. These findings underscore the need for continued dataset expansion and iterative model refinement to improve sequence-level resolution.\\u003c/p\\u003e\\u003cp\\u003eDespite its strengths, the current version of PepPharmaHub has two primary limitations. First, computational throughput is constrained by limited GPU availability, which may affect real-time usability during peak demand. Second, the platform currently supports only RNN and BERT based models. While effective, other emerging architectures such as CNN BiLSTM attention hybrids [\\u003cspan citationid=\\\"CR29\\\" class=\\\"CitationRef\\\"\\u003e29\\u003c/span\\u003e], CNN BiLSTM SVM classifiers [\\u003cspan citationid=\\\"CR30\\\" class=\\\"CitationRef\\\"\\u003e30\\u003c/span\\u003e], and BiLSTM multi scale CNNs [\\u003cspan citationid=\\\"CR31\\\" class=\\\"CitationRef\\\"\\u003e31\\u003c/span\\u003e] may offer complementary benefits and warrant integration in future versions. In future, PepPharmaHub will expand computational resources, integrate broader peptide data sources, and support additional modeling paradigms. The platform's low-code interface and modular design aim to democratize access to deep learning-driven peptide discovery, empowering researchers across disciplines to deploy, refine, and interpret advanced models with minimal technical barriers. Ultimately, PepPharmaHub offers a sustainable and extensible solution to accelerate therapeutic peptide research and improve prediction-driven biological discovery.\\u003c/p\\u003e\"},{\"header\":\"Conclusions\",\"content\":\"\\u003cp\\u003ePepPharmaHub is a comprehensive, user-friendly, and scalable platform that streamlines therapeutic peptide discovery by integrating curated datasets, advanced language modeling, and real-time visualization into a unified workflow. Through its dual-mode high-throughput screening and self-training capabilities, the platform supports both rapid prediction with platform-provided models and flexible customization using user-defined architectures. Benchmarking across 24 public datasets and 20 external test sets demonstrates that PepPharmaHub consistently achieves state-of-the-art or superior performance, while also enhancing interpretability through sequence feature mapping. By lowering technical barriers and enabling reproducible, interpretable, and high-throughput predictions, PepPharmaHub offers a powerful tool for accelerating data-driven peptide drug discovery.\\u003c/p\\u003e\"},{\"header\":\"Methods\",\"content\":\"\\u003ch2\\u003eData collection\\u003c/h2\\u003e\\u003cp\\u003eThis study utilizes 20 types of open-source peptide sequence datasets, comprising a total of 24 datasets, including anti-hypertensive, antioxidant, dipeptidyl peptidase IV inhibition, bitter, umami, antimicrobial, antimalarial, quorum sensing, anticancer, anti-MRSA strains, tumor T cell antigens, blood-brain barrier, antiparasitic, neuropeptide, antibacterial, antifungal, antiviral, toxicity, anti-coronavirus and interleukin-6 inducing activity, to train and evaluate RNN and BERT modeling methods. Table\\u0026nbsp;\\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e provides an overview of these open-source datasets. The data volume distribution is as follows: \\u0026gt;2000 (11 datasets), 1000–2000 (5 datasets), \\u0026lt; 1000 (8 datasets), including 15 balanced datasets with an equal number of positive and negative samples, and 9 imbalanced datasets. To ensure a fair comparison with existing methods, the training set, validation set, and independent test set used are consistent with those in the original paper, and the same number of cross-validation folds are applied. Specifically, 20 fair external independent tests were constructed by collecting data on 20 types of bioactive peptides, newly identified in 2023–2025 and not included in the aforementioned 24 datasets (Table\\u0026nbsp;\\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e), to assess the model's generalization ability. The ACEiPs dataset was constructed by deduplicating and balancing the ACEiPP dataset [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e], AHTpin dataset [\\u003cspan citationid=\\\"CR32\\\" class=\\\"CitationRef\\\"\\u003e32\\u003c/span\\u003e], and newly reported ACE inhibitory peptides (104 positive samples and 98 negative samples), resulting in a total of 1181 positive and negative samples (Table\\u0026nbsp;\\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e). The ACEiPs dataset was randomly split into a benchmark dataset (ACEiPs_benchmark) and an independent test set (ACEiPs_test) in a 7:3 ratio.\\u003c/p\\u003e\\u003cp\\u003eAdditionally, two large peptide sequence datasets with unknown activities were constructed to assess the model’s ability to pre-screen features. The first dataset, named Sequence-Library 1, contains a total of 3,768,340 peptide sequences retrieved from the UniProt database using the search term ‘(length:[2 TO 50])’. The second dataset, named Sequence-Library 2, consists of 2,321,342 non-redundant peptide sequences of length 2–20 from 21,249 food-derived proteins, downloaded from the ACEiPP database [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e].\\u003c/p\\u003e\\u003ch2\\u003eRecurrent neural network modelling module\\u003c/h2\\u003e\\u003cp\\u003eThe peptide sequence, based on the single-letter codes of the 20 natural amino acids (R, K, N, D, Q, E, H, P, Y, W, S, T, G, A, M, C, F, L, V, I), can be represented as:\\u003c/p\\u003e\\u003cp\\u003ePeptide = [A\\u003csub\\u003e1\\u003c/sub\\u003e, A\\u003csub\\u003e2\\u003c/sub\\u003e, ..., A\\u003csub\\u003ei\\u003c/sub\\u003e] (1)\\u003c/p\\u003e\\u003cp\\u003ewhere A\\u003csub\\u003ei​\\u003c/sub\\u003e is the i-th amino acid in the peptide sequence, i.e., the positional index of the amino acid residue. And then, peptide sequences were transformed into feature vectors using One-hot coding and 23 sets of amino acid descriptors (AADs) to represent the types and physicochemical properties of sequence residues (Table \\u003cspan refid=\\\"MOESM1\\\" class=\\\"InternalRef\\\"\\u003eS1\\u003c/span\\u003e). By referencing these AADs, peptide sequences can be transformed from non-numeric sequence data into numeric feature vectors, which are then input into recurrent neural networks for model training. The AADs coding is defined as follows:\\u003c/p\\u003e\\u003cdiv id=\\\"Equ1\\\" class=\\\"Equation\\\"\\u003e\\u003cdiv format=\\\"TEX\\\" class=\\\"mathdisplay\\\" id=\\\"FileID_Equ1\\\" name=\\\"EquationSource\\\"\\u003e\\n$$\\\\:\\\\text{A}\\\\text{A}\\\\text{D}\\\\text{s}=\\\\left[\\\\begin{array}{cccc}{\\\\text{V}}_{1}^{1}\\u0026amp;\\\\:{\\\\text{V}}_{2}^{1}\\u0026amp;\\\\:\\\\cdots\\\\:\\u0026amp;\\\\:{\\\\text{V}}_{n}^{1}\\\\\\\\\\\\:{\\\\text{V}}_{1}^{2}\\u0026amp;\\\\:{\\\\text{V}}_{2}^{2}\\u0026amp;\\\\:\\\\cdots\\\\:\\u0026amp;\\\\:{\\\\text{V}}_{\\\\text{n}}^{2}\\\\\\\\\\\\:⋮\\u0026amp;\\\\:⋮\\u0026amp;\\\\:⋮\\u0026amp;\\\\:⋮\\\\\\\\\\\\:{\\\\text{V}}_{1}^{20}\\u0026amp;\\\\:{\\\\text{V}}_{2}^{20}\\u0026amp;\\\\:\\\\cdots\\\\:\\u0026amp;\\\\:{\\\\text{V}}_{\\\\text{n}}^{20}\\\\end{array}\\\\right]$$\\u003c/div\\u003e\\u003cdiv class=\\\"EquationNumber\\\"\\u003e2\\u003c/div\\u003e\\u003c/div\\u003e\\u003cp\\u003ewhere V represents the feature variables of the 20 natural amino acids, n is the number of variables per residue, and the AADs coding matrix has dimensions of 20×n.\\u003c/p\\u003e\\u003cp\\u003eThe RNN-Trainer module was developed based on the TensorFlow framework and incorporates four recurrent neural networks: SimpleRNN, LSTM, GRU, and BiLSTM. For each of these networks, 24 amino acid encoding schemes (Table \\u003cspan refid=\\\"MOESM1\\\" class=\\\"InternalRef\\\"\\u003eS1\\u003c/span\\u003e), 19 activation functions, N-fold cross-validation (N = 5, 10, 15, 20), and other training parameters (network layers, neurons, learning rate, dropout, nEpochs, early stopping and checkpoint) are provided.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\u003cdiv class=\\\"gridtable\\\"\\u003e\\u003cdiv align=\\\"left\\\" class=\\\"colspec\\\" colname=\\\"c1\\\" colnum=\\\"1\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"left\\\" class=\\\"colspec\\\" colname=\\\"c2\\\" colnum=\\\"2\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c3\\\" colnum=\\\"3\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c4\\\" colnum=\\\"4\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c5\\\" colnum=\\\"5\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c6\\\" colnum=\\\"6\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c7\\\" colnum=\\\"7\\\"\\u003e\\u003c/div\\u003e\\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c8\\\" colnum=\\\"8\\\"\\u003e\\u003c/div\\u003e\\u003ctable float=\\\"Yes\\\" id=\\\"Tab1\\\" border=\\\"1\\\"\\u003e\\u003ccaption language=\\\"En\\\"\\u003e\\u003cdiv class=\\\"CaptionNumber\\\"\\u003eTable 1\\u003c/div\\u003e\\u003cdiv class=\\\"CaptionContent\\\"\\u003e\\u003cp\\u003eOpen-source benchmark and test datasets collected from various sources in the literature and platform\\u003c/p\\u003e\\u003c/div\\u003e\\u003c/caption\\u003e\\u003ccolgroup cols=\\\"8\\\"\\u003e\\u003c/colgroup\\u003e\\u003cthead\\u003e\\u003ctr\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c1\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003eBioactivity\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c2\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003eDataset reference\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colspan=\\\"2\\\" nameend=\\\"c4\\\" namest=\\\"c3\\\"\\u003e\\u003cp\\u003eTraining dataset\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colspan=\\\"2\\\" nameend=\\\"c6\\\" namest=\\\"c5\\\"\\u003e\\u003cp\\u003eTest dataset\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colspan=\\\"2\\\" nameend=\\\"c8\\\" namest=\\\"c7\\\"\\u003e\\u003cp\\u003eNewly reported peptides\\u003c/p\\u003e\\u003c/th\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003ePositive\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003eNegative\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003ePositive\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003eNegative\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003ePositive\\u003c/p\\u003e\\u003c/th\\u003e\\u003cth align=\\\"left\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003eNegative\\u003c/p\\u003e\\u003c/th\\u003e\\u003c/tr\\u003e\\u003c/thead\\u003e\\u003ctbody\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\" morerows=\\\"2\\\" rowspan=\\\"3\\\"\\u003e\\u003cp\\u003eAntihypertensive activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003emAHTPred [\\u003cspan citationid=\\\"CR24\\\" class=\\\"CitationRef\\\"\\u003e24\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e913\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e913\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e386\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e386\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\" morerows=\\\"2\\\" rowspan=\\\"3\\\"\\u003e\\u003cp\\u003e102\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\" morerows=\\\"2\\\" rowspan=\\\"3\\\"\\u003e\\u003cp\\u003e93\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eACEiPP[\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e730\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e730\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e313\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e313\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eACEiPs (this study)\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e826\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e826\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e355\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e355\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003eAntioxidant activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eAnOxPP [\\u003cspan citationid=\\\"CR14\\\" class=\\\"CitationRef\\\"\\u003e14\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e848\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e848\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e212\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e212\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003e112\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003e42\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eAnOxPePred-FRS [\\u003cspan citationid=\\\"CR33\\\" class=\\\"CitationRef\\\"\\u003e33\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e530\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e593\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e146\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e135\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eDPP IV inhibitory activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eiDPPIV-SCM [\\u003cspan citationid=\\\"CR34\\\" class=\\\"CitationRef\\\"\\u003e34\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e532\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e532\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e133\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e133\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e109\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e75\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eBitter\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eBERT4Bitter [\\u003cspan citationid=\\\"CR27\\\" class=\\\"CitationRef\\\"\\u003e27\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e256\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e256\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e64\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e64\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e179\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e184\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eUmami\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eiUMAMI-SCM [\\u003cspan citationid=\\\"CR35\\\" class=\\\"CitationRef\\\"\\u003e35\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e112\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e241\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e28\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e61\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e244\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e19\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAntimicrobial activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eTransImbAMP [\\u003cspan citationid=\\\"CR26\\\" class=\\\"CitationRef\\\"\\u003e26\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e3876\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e9552\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e2584\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e6369\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e376\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e9\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003eAntimalarial activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eiAMAP-SCM (Main dataset) [\\u003cspan citationid=\\\"CR36\\\" class=\\\"CitationRef\\\"\\u003e36\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e111\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e1708\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e28\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e427\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003e17\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003e4\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eiAMAP-SCM (Alternative dataset) [\\u003cspan citationid=\\\"CR36\\\" class=\\\"CitationRef\\\"\\u003e36\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e111\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e542\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e28\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e135\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eQuorum sensing activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eQSPred-FL [\\u003cspan citationid=\\\"CR37\\\" class=\\\"CitationRef\\\"\\u003e37\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e200\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e200\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e20\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e20\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e7\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e0\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003eAnticancer activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eAntiCP 2.0 (Main dataset) [\\u003cspan citationid=\\\"CR38\\\" class=\\\"CitationRef\\\"\\u003e38\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e689\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e689\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e172\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e172\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003e570\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\" morerows=\\\"1\\\" rowspan=\\\"2\\\"\\u003e\\u003cp\\u003e71\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eAntiCP 2.0 (Alternative dataset) [\\u003cspan citationid=\\\"CR38\\\" class=\\\"CitationRef\\\"\\u003e38\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e776\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e776\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e194\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e194\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAnti-MRSA strains activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eSCMRSA [\\u003cspan citationid=\\\"CR28\\\" class=\\\"CitationRef\\\"\\u003e28\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e118\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e678\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e30\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e169\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e12\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e1\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eTumor T cell antigens\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eiTTCA-Hybrid [\\u003cspan citationid=\\\"CR39\\\" class=\\\"CitationRef\\\"\\u003e39\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e470\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e318\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e122\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e75\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e122\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e75\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eBlood-Brain Barrier\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eBBPpred [\\u003cspan citationid=\\\"CR40\\\" class=\\\"CitationRef\\\"\\u003e40\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e100\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e100\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e19\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e19\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e45\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e3\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAntiparasitic activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003ePredAPP [\\u003cspan citationid=\\\"CR41\\\" class=\\\"CitationRef\\\"\\u003e41\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e255\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e1863\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e46\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e46\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e23\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e4\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eNeuropeptide\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eNeuroPred-CLQ [\\u003cspan citationid=\\\"CR42\\\" class=\\\"CitationRef\\\"\\u003e42\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e1940\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e1940\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e485\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e485\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e9\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e18\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAntibacterial activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003estarPep_AB [\\u003cspan citationid=\\\"CR43\\\" class=\\\"CitationRef\\\"\\u003e43\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e6583\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e6583\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e1695\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e1695\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e226\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e27\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAntifungal activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003estarPep_AF [\\u003cspan citationid=\\\"CR43\\\" class=\\\"CitationRef\\\"\\u003e43\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e778\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e778\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e215\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e215\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e117\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e21\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAntiviral activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003estarPep_AV [\\u003cspan citationid=\\\"CR43\\\" class=\\\"CitationRef\\\"\\u003e43\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e2321\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e2321\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e623\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e623\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e31\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e467\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eToxicity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eATSE [\\u003cspan citationid=\\\"CR44\\\" class=\\\"CitationRef\\\"\\u003e44\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e1663\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e1621\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e290\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e290\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e22\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e6\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eAnti-coronavirus activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eFEOpti-ACVP [\\u003cspan citationid=\\\"CR18\\\" class=\\\"CitationRef\\\"\\u003e18\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e125\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e1587\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e32\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e397\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e63\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e38\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003ctr\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e\\u003cp\\u003eInterleukin-6 inducing activity\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"left\\\" colname=\\\"c2\\\"\\u003e\\u003cp\\u003eStackIL6[\\u003cspan citationid=\\\"CR47\\\" class=\\\"CitationRef\\\"\\u003e47\\u003c/span\\u003e]\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e\\u003cp\\u003e292\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e\\u003cp\\u003e2393\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e\\u003cp\\u003e73\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e\\u003cp\\u003e597\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e\\u003cp\\u003e2\\u003c/p\\u003e\\u003c/td\\u003e\\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e\\u003cp\\u003e1\\u003c/p\\u003e\\u003c/td\\u003e\\u003c/tr\\u003e\\u003c/tbody\\u003e\\u003c/table\\u003e\\u003c/div\\u003e\\u003ch2\\u003eBERT pre-training fine-tuning module\\u003c/h2\\u003e\\u003cp\\u003eA total of 556,603 protein sequences were downloaded from UniProt as the peptide-related pre-training corpus. UniProt, which integrates data from SWISS-PROT, TrEMBL, and UniParc, is the largest and most comprehensive protein database, providing ample data for model pre-training. Based on the extensive discussion in the literature regarding the relationship between peptide sequences and activity, amino acid residues and specific motifs (dipeptides and tripeptides) are key determinants of the activity of therapeutic peptides [\\u003cspan citationid=\\\"CR45\\\" class=\\\"CitationRef\\\"\\u003e45\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR46\\\" class=\\\"CitationRef\\\"\\u003e46\\u003c/span\\u003e]. We divide proteins into motifs, where every k (k = 1, 2, 3) residues in the sequence are grouped into k-mers. When fewer than k amino acids remain at the end of the sequence, the remaining amino acids are grouped together [\\u003cspan citationid=\\\"CR13\\\" class=\\\"CitationRef\\\"\\u003e13\\u003c/span\\u003e]. The computational formula of the BERT model is as follows:\\u003c/p\\u003e\\u003cp\\u003eMultiHead (Q, K, V) = Concat (head\\u003csub\\u003e1\\u003c/sub\\u003e, …, head\\u003csub\\u003eh\\u003c/sub\\u003e) (3)\\u003c/p\\u003e\\u003cp\\u003eHead\\u003csub\\u003ei\\u003c/sub\\u003e = Attention (\\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{Q}\\\\text{W}}_{\\\\text{i}}^{\\\\text{Q}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e, \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{K}\\\\text{W}}_{\\\\text{i}}^{\\\\text{K}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e, \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{V}\\\\text{W}}_{\\\\text{i}}^{\\\\text{V}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e) (4)\\u003c/p\\u003e\\u003cp\\u003eAttention (Q, K, V) = softmax(\\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:\\\\frac{{QK}^{T}}{\\\\sqrt{{d}_{k}}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e)V (5)\\u003c/p\\u003e\\u003cp\\u003ewhere d\\u003csub\\u003ek\\u003c/sub\\u003e​ is the dimension of the Key, \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{W}}_{\\\\text{i}}^{\\\\text{Q}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e, \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{W}}_{\\\\text{i}}^{\\\\text{K}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e, \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{W}}_{\\\\text{i}}^{\\\\text{V}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e and \\u003cspan class=\\\"InlineEquation\\\"\\u003e\\u003cspan class=\\\"mathinline\\\"\\u003e\\\\(\\\\:{\\\\text{W}}^{\\\\text{O}}\\\\)\\u003c/span\\u003e\\u003c/span\\u003e are the parameter matrices.\\u003c/p\\u003e\\u003cp\\u003eThree pre-trained k-mer models were trained based on the TensorFlow framework for model fine-tuning. The developed BERT-Trainer module provides 7 standard configuration parameters: Batch size, Evaluate, Train epochs, Warmup proportion, Learning rate, Classification, and Cross-validation (supporting 5-, 10-, 15-, and 20-fold), along with 11 advanced configuration parameters: Attention probability, Dropout probability, 5 Hidden layer activation functions, Hidden layer dropout probability, Hidden layer size, Initializer range, Intermediate layer size, Maximum position embeddings, Number of attention heads, Number of hidden layers, Type vocabulary size, and 3 Vocabulary sizes (k-mers). Furthermore, Early stopping and Checkpoint parameters are designed to monitor the model's performance and systematically save its state during training.\\u003c/p\\u003e\\u003ch2\\u003eEvaluation criteria\\u003c/h2\\u003e\\u003cp\\u003eThe prediction ability of the models in n-fold cross-validation and external testing is evaluated using six evaluation parameters: Precision, Sensitivity, Specificity, Accuracy, Matthew’s correlation coefficient (MCC), and the area under the receiver operating characteristics curves (AUC). Their definitions are as follows:\\u003c/p\\u003e\\u003cdiv id=\\\"Equ2\\\" class=\\\"Equation\\\"\\u003e\\u003cdiv format=\\\"TEX\\\" class=\\\"mathdisplay\\\" id=\\\"FileID_Equ2\\\" name=\\\"EquationSource\\\"\\u003e\\n$$\\\\:Precision=\\\\frac{TP}{TP+FP}$$\\u003c/div\\u003e\\u003cdiv class=\\\"EquationNumber\\\"\\u003e6\\u003c/div\\u003e\\u003c/div\\u003e\\u003cdiv id=\\\"Equ3\\\" class=\\\"Equation\\\"\\u003e\\u003cdiv format=\\\"TEX\\\" class=\\\"mathdisplay\\\" id=\\\"FileID_Equ3\\\" name=\\\"EquationSource\\\"\\u003e\\n$$\\\\:Sensitivity=\\\\frac{TP}{TP+FN}$$\\u003c/div\\u003e\\u003cdiv class=\\\"EquationNumber\\\"\\u003e7\\u003c/div\\u003e\\u003c/div\\u003e\\u003cdiv id=\\\"Equ4\\\" class=\\\"Equation\\\"\\u003e\\u003cdiv format=\\\"TEX\\\" class=\\\"mathdisplay\\\" id=\\\"FileID_Equ4\\\" name=\\\"EquationSource\\\"\\u003e\\n$$\\\\:Specificity=\\\\frac{TN}{TN+FP}$$\\u003c/div\\u003e\\u003cdiv class=\\\"EquationNumber\\\"\\u003e8\\u003c/div\\u003e\\u003c/div\\u003e\\u003cdiv id=\\\"Equ5\\\" class=\\\"Equation\\\"\\u003e\\u003cdiv format=\\\"TEX\\\" class=\\\"mathdisplay\\\" id=\\\"FileID_Equ5\\\" name=\\\"EquationSource\\\"\\u003e\\n$$\\\\:Accuracy=\\\\frac{TP+TN}{TP+TN+FP+FN}$$\\u003c/div\\u003e\\u003cdiv class=\\\"EquationNumber\\\"\\u003e9\\u003c/div\\u003e\\u003c/div\\u003e\\u003cdiv id=\\\"Equ6\\\" class=\\\"Equation\\\"\\u003e\\u003cdiv format=\\\"TEX\\\" class=\\\"mathdisplay\\\" id=\\\"FileID_Equ6\\\" name=\\\"EquationSource\\\"\\u003e\\n$$\\\\:MCC=\\\\frac{TP\\\\times\\\\:TN-FP\\\\times\\\\:FN}{\\\\sqrt{(TP+FP)(TP+FN)(TN+FP)(TN+FN)}}$$\\u003c/div\\u003e\\u003cdiv class=\\\"EquationNumber\\\"\\u003e10\\u003c/div\\u003e\\u003c/div\\u003e\\u003cp\\u003ewhere TP, FP, TN, and FN represent the number of true positive samples, false positive samples, true negative samples, and false negative samples, respectively.\\u003c/p\\u003e\"},{\"header\":\"Declarations\",\"content\":\"\\u003cp\\u003e\\u003cstrong\\u003eAuthor contributions\\u0026nbsp;\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eDY.Q. and Z.W. conceptualized and supervised the project. DY.Q. constructed PepPharmaHub web server, built the project website, and created online tutorial. DY.Q., Z.W., K.S. and H.F. wrote the manuscript and curated all figures. All authors reviewed and approved the final manuscript.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eFunding\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eThis work was supported by the Science and Technology Innovation Key R\\u0026amp;D Program of Chongqing [CSTB2023TIAD-STX0001], National Natural Science Foundation of China [82470220, 32470681], National Key R\\u0026amp;D Program of China [2022YFA1103300], Chongqing Municipal Science and Health Joint Medical Research Project [2025ZDXM004], Chongqing Municipal PhD Fast-Track Program [CSTB2024NSCQ-BSX0019], Youth Talent Development Program from Second Affiliated Hospital, Army Medical University [2022YQB014].\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eData availability\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eThe 25 benchmark datasets (Table 1), and 19 independent test sets are available in the Dataset Library of PepPharmaHub (http://bioinmed.jflab.ac.cn:18090/peppharmahub/\\u003cbr\\u003e\\u0026nbsp;Database/datasetLibrary.jsp). Sequence Library-1 and Sequence Library-2 can be downloaded at http://bioinmed.jflab.ac.cn:18090/peppharmahub/Database/seqLibrary\\u003cbr\\u003e\\u0026nbsp;.jsp. Screening results for 23 peptide types are accessible via the Pre-selected Library, with data downloads and sequence profile visualization at http://bioinmed.\\u003cbr\\u003e\\u0026nbsp;jflab.ac.cn:18090/peppharmahub/Database/SeqLogoPrediction.jsp?PreID=PRE20241227191128. All model and task IDs mentioned in this study can be retrieved via the Home page search function (http://bioinmed.jflab.ac.cn:18090/pepnlp/index.jsp). Source data are provided with this paper.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eCode availability\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eThe developed PepPharmaHub platform is now available and can be accessed at: http://bioinmed.jflab.ac.cn:18090/pepnlp/index.jsp. Future updates and new versions will also be released through this link.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eCompeting interests\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eThe authors declare no competing interests.\\u003c/p\\u003e\"},{\"header\":\"References\",\"content\":\"\\u003col\\u003e\\n\\u003cli\\u003eRossino, G., et al., \\u003cem\\u003ePeptides as Therapeutic Agents: Challenges and Opportunities in the Green Transition Era.\\u003c/em\\u003e Molecules, 2023. \\u003cstrong\\u003e28\\u003c/strong\\u003e(20).\\u003c/li\\u003e\\n\\u003cli\\u003eLi, C.M., et al., \\u003cem\\u003eNovel Peptide Therapeutic Approaches for Cancer Treatment.\\u003c/em\\u003e Cells, 2021. \\u003cstrong\\u003e10\\u003c/strong\\u003e(11).\\u003c/li\\u003e\\n\\u003cli\\u003eD\\u0026rsquo;Aloisio, V., et al., \\u003cem\\u003ePepTherDia: database and structural composition analysis of approved peptide therapeutics and diagnostics.\\u003c/em\\u003e Drug Discovery Today, 2021. \\u003cstrong\\u003e26\\u003c/strong\\u003e(6): p. 1409-1419.\\u003c/li\\u003e\\n\\u003cli\\u003eQin, D., et al., \\u003cem\\u003eDFBP: a comprehensive database of food-derived bioactive peptides for peptidomics research.\\u003c/em\\u003e Bioinformatics, 2022. \\u003cstrong\\u003e38\\u003c/strong\\u003e(12): p. 3275-3280.\\u003c/li\\u003e\\n\\u003cli\\u003eDrucker, D.J., \\u003cem\\u003eAdvances in oral peptide therapeutics.\\u003c/em\\u003e Nature Reviews Drug Discovery, 2019. \\u003cstrong\\u003e19\\u003c/strong\\u003e(4): p. 277-289.\\u003c/li\\u003e\\n\\u003cli\\u003eMuttenthaler, M., et al., \\u003cem\\u003eTrends in peptide drug discovery.\\u003c/em\\u003e Nature Reviews Drug Discovery, 2021. \\u003cstrong\\u003e20\\u003c/strong\\u003e(4): p. 309-325.\\u003c/li\\u003e\\n\\u003cli\\u003eSharma, K., et al., \\u003cem\\u003ePeptide-based drug discovery: Current status and recent advances.\\u003c/em\\u003e Drug Discovery Today, 2023. \\u003cstrong\\u003e28\\u003c/strong\\u003e(2).\\u003c/li\\u003e\\n\\u003cli\\u003eMann, M., et al., \\u003cem\\u003eArtificial intelligence for proteomics and biomarker discovery.\\u003c/em\\u003e Cell Systems, 2021. \\u003cstrong\\u003e12\\u003c/strong\\u003e(8): p. 759-770.\\u003c/li\\u003e\\n\\u003cli\\u003eJia, W., et al., \\u003cem\\u003eExploring novel ANGICon-EIPs through ameliorated peptidomics techniques: Can deep learning strategies as a core breakthrough in peptide structure and function prediction?\\u003c/em\\u003e Food Research International, 2023. \\u003cstrong\\u003e174\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eWu, X., et al., \\u003cem\\u003eDeep learning for advancing peptide drug development: Tools and methods in structure prediction and design.\\u003c/em\\u003e European Journal of Medicinal Chemistry, 2024. \\u003cstrong\\u003e268\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eGhafoor, H., et al., \\u003cem\\u003eCAPTURE: Comprehensive anti-cancer peptide predictor with a unique amino acid sequence encoder.\\u003c/em\\u003e Computers in Biology and Medicine, 2024. \\u003cstrong\\u003e176\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eQin, D., et al., \\u003cem\\u003eSequence\\u0026ndash;Activity Relationship of Angiotensin-Converting Enzyme Inhibitory Peptides Derived from Food Proteins, Based on a New Deep Learning Model.\\u003c/em\\u003e Foods, 2024. \\u003cstrong\\u003e13\\u003c/strong\\u003e(22).\\u003c/li\\u003e\\n\\u003cli\\u003eZhang, Y., et al., \\u003cem\\u003eA novel antibacterial peptide recognition algorithm based on BERT.\\u003c/em\\u003e Briefings in Bioinformatics, 2021. \\u003cstrong\\u003e22\\u003c/strong\\u003e(6).\\u003c/li\\u003e\\n\\u003cli\\u003eQin, D., et al., \\u003cem\\u003ePrediction of antioxidant peptides using a quantitative structure\\u0026minus;activity relationship predictor (AnOxPP) based on bidirectional long short-term memory neural network and interpretable amino acid descriptors.\\u003c/em\\u003e Computers in Biology and Medicine, 2023. \\u003cstrong\\u003e154\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eNaseem, A., et al., \\u003cem\\u003eBBB-PEP-prediction: improved computational model for identification of blood\\u0026ndash;brain barrier peptides using blending position relative composition specific features and ensemble modeling.\\u003c/em\\u003e Journal of Cheminformatics, 2023. \\u003cstrong\\u003e15\\u003c/strong\\u003e(1).\\u003c/li\\u003e\\n\\u003cli\\u003eWang, J.-H. and T.-Y. Sung, \\u003cem\\u003eToxTeller: Predicting Peptide Toxicity Using Four Different Machine Learning Approaches.\\u003c/em\\u003e ACS Omega, 2024. \\u003cstrong\\u003e9\\u003c/strong\\u003e(29): p. 32116-32123.\\u003c/li\\u003e\\n\\u003cli\\u003eWang, D., et al., \\u003cem\\u003eStructuralDPPIV: a novel deep learning model based on atom structure for predicting dipeptidyl peptidase-IV inhibitory peptides.\\u003c/em\\u003e Bioinformatics, 2024. \\u003cstrong\\u003e40\\u003c/strong\\u003e(2).\\u003c/li\\u003e\\n\\u003cli\\u003eJiang, J., et al., \\u003cem\\u003eFEOpti-ACVP: identification of novel anti-coronavirus peptide sequences based on feature engineering and optimization.\\u003c/em\\u003e Briefings in Bioinformatics, 2024. \\u003cstrong\\u003e25\\u003c/strong\\u003e(2).\\u003c/li\\u003e\\n\\u003cli\\u003eZhou, P., et al., \\u003cem\\u003eSystematic Comparison and Comprehensive Evaluation of 80 Amino Acid Descriptors in Peptide QSAR Modeling.\\u003c/em\\u003e Journal of Chemical Information and Modeling, 2021. \\u003cstrong\\u003e61\\u003c/strong\\u003e(4): p. 1718-1731.\\u003c/li\\u003e\\n\\u003cli\\u003eZhang, J., et al., \\u003cem\\u003eUmami-BERT: An interpretable BERT-based model for umami peptides prediction.\\u003c/em\\u003e Food Research International, 2023. \\u003cstrong\\u003e172\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eKlepach, A., et al., \\u003cem\\u003eCharacterization and impact of peptide physicochemical properties on oral and subcutaneous delivery.\\u003c/em\\u003e Advanced Drug Delivery Reviews, 2022. \\u003cstrong\\u003e186\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eKurata, H., S. Tsukiyama, and B. Manavalan, \\u003cem\\u003eiACVP: markedly enhanced identification of anti-coronavirus peptides using a dataset-specific word2vec model.\\u003c/em\\u003e Briefings in Bioinformatics, 2022. \\u003cstrong\\u003e23\\u003c/strong\\u003e(4).\\u003c/li\\u003e\\n\\u003cli\\u003eMinkiewicz, P., A. Iwaniak, and M. Darewicz, \\u003cem\\u003eAnnotation of Peptide Structures Using SMILES and Other Chemical Codes\\u0026ndash;Practical Solutions.\\u003c/em\\u003e Molecules, 2017. \\u003cstrong\\u003e22\\u003c/strong\\u003e(12).\\u003c/li\\u003e\\n\\u003cli\\u003eManavalan, B., et al., \\u003cem\\u003emAHTPred: a sequence-based meta-predictor for improving the prediction of anti-hypertensive peptides using effective feature representation.\\u003c/em\\u003e Bioinformatics, 2019. \\u003cstrong\\u003e35\\u003c/strong\\u003e(16): p. 2757-2765.\\u003c/li\\u003e\\n\\u003cli\\u003eDu, Z., et al., \\u003cem\\u003epLM4ACE: A protein language model based predictor for antihypertensive peptide screening.\\u003c/em\\u003e Food Chemistry, 2024. \\u003cstrong\\u003e431\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003ePang, Y., et al., \\u003cem\\u003eIntegrating transformer and imbalanced multi-label learning to identify antimicrobial peptides and their functional activities.\\u003c/em\\u003e Bioinformatics, 2022. \\u003cstrong\\u003e38\\u003c/strong\\u003e(24): p. 5368-5374.\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan, P., et al., \\u003cem\\u003eBERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides.\\u003c/em\\u003e Bioinformatics, 2021. \\u003cstrong\\u003e37\\u003c/strong\\u003e(17): p. 2556-2562.\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan, P., et al., \\u003cem\\u003eSCMRSA: a New Approach for Identifying and Analyzing Anti-MRSA Peptides Using Estimated Propensity Scores of Dipeptides.\\u003c/em\\u003e ACS Omega, 2022. \\u003cstrong\\u003e7\\u003c/strong\\u003e(36): p. 32653-32664.\\u003c/li\\u003e\\n\\u003cli\\u003eXing, W., et al., \\u003cem\\u003eiAMP-Attenpred: a novel antimicrobial peptide predictor based on BERT feature extraction method and CNN-BiLSTM-Attention combination model.\\u003c/em\\u003e Briefings in Bioinformatics, 2024. \\u003cstrong\\u003e25\\u003c/strong\\u003e(1).\\u003c/li\\u003e\\n\\u003cli\\u003eXiao, X., et al., \\u003cem\\u003eiAMP-CA2L: a new CNN-BiLSTM-SVM classifier based on cellular automata image for identifying antimicrobial peptides and their functional types.\\u003c/em\\u003e Briefings in Bioinformatics, 2021. \\u003cstrong\\u003e22\\u003c/strong\\u003e(6).\\u003c/li\\u003e\\n\\u003cli\\u003eQi, Y., P. Zheng, and G. Huang, \\u003cem\\u003eDeepLBCEPred: A Bi-LSTM and multi-scale CNN-based deep learning method for predicting linear B-cell epitopes.\\u003c/em\\u003e Frontiers in Microbiology, 2023. \\u003cstrong\\u003e14\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eKumar, R., et al., \\u003cem\\u003eAn in silico platform for predicting, screening and designing of antihypertensive peptides.\\u003c/em\\u003e Scientific Reports, 2015. \\u003cstrong\\u003e5\\u003c/strong\\u003e(1).\\u003c/li\\u003e\\n\\u003cli\\u003eOlsen, T.H., et al., \\u003cem\\u003eAnOxPePred: using deep learning for the prediction of antioxidative properties of peptides.\\u003c/em\\u003e Scientific Reports, 2020. \\u003cstrong\\u003e10\\u003c/strong\\u003e(1).\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan, P., et al., \\u003cem\\u003eiDPPIV-SCM: A Sequence-Based Predictor for Identifying and Analyzing Dipeptidyl Peptidase IV (DPP-IV) Inhibitory Peptides Using a Scoring Card Method.\\u003c/em\\u003e Journal of Proteome Research, 2020. \\u003cstrong\\u003e19\\u003c/strong\\u003e(10): p. 4125-4136.\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan, P., et al., \\u003cem\\u003eiUmami-SCM: A Novel Sequence-Based Predictor for Prediction and Analysis of Umami Peptides Using a Scoring Card Method with Propensity Scores of Dipeptides.\\u003c/em\\u003e Journal of Chemical Information and Modeling, 2020. \\u003cstrong\\u003e60\\u003c/strong\\u003e(12): p. 6666-6678.\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan, P., et al., \\u003cem\\u003eiAMAP-SCM: A Novel Computational Tool for Large-Scale Identification of Antimalarial Peptides Using Estimated Propensity Scores of Dipeptides.\\u003c/em\\u003e ACS Omega, 2022. \\u003cstrong\\u003e7\\u003c/strong\\u003e(45): p. 41082-41095.\\u003c/li\\u003e\\n\\u003cli\\u003eWei, L., et al., \\u003cem\\u003eComparative analysis and prediction of quorum-sensing peptides using feature representation learning and machine learning algorithms.\\u003c/em\\u003e Briefings in Bioinformatics, 2018.\\u003c/li\\u003e\\n\\u003cli\\u003eAgrawal, P., et al., \\u003cem\\u003eAntiCP 2.0: an updated model for predicting anticancer peptides.\\u003c/em\\u003e Briefings in Bioinformatics, 2021. \\u003cstrong\\u003e22\\u003c/strong\\u003e(3).\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan, P., et al., \\u003cem\\u003eiTTCA-Hybrid: Improved and robust identification of tumor T cell antigens by utilizing hybrid feature representation.\\u003c/em\\u003e Analytical Biochemistry, 2020. \\u003cstrong\\u003e599\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eDai, R., et al., \\u003cem\\u003eBBPpred: Sequence-Based Prediction of Blood-Brain Barrier Peptides with Feature Representation Learning and Logistic Regression.\\u003c/em\\u003e Journal of Chemical Information and Modeling, 2021. \\u003cstrong\\u003e61\\u003c/strong\\u003e(1): p. 525-534.\\u003c/li\\u003e\\n\\u003cli\\u003eZhang, W., et al., \\u003cem\\u003ePredAPP: Predicting Anti-Parasitic Peptides with Undersampling and Ensemble Approaches.\\u003c/em\\u003e Interdisciplinary Sciences: Computational Life Sciences, 2021. \\u003cstrong\\u003e14\\u003c/strong\\u003e(1): p. 258-268.\\u003c/li\\u003e\\n\\u003cli\\u003eBin, Y., et al., \\u003cem\\u003ePrediction of Neuropeptides from Sequence Information Using Ensemble Classifier and Hybrid Features.\\u003c/em\\u003e Journal of Proteome Research, 2020. \\u003cstrong\\u003e19\\u003c/strong\\u003e(9): p. 3732-3740.\\u003c/li\\u003e\\n\\u003cli\\u003ePinacho-Castellanos, S.A., et al., \\u003cem\\u003eAlignment-Free Antimicrobial Peptide Predictors: Improving Performance by a Thorough Analysis of the Largest Available Data Set.\\u003c/em\\u003e Journal of Chemical Information and Modeling, 2021. \\u003cstrong\\u003e61\\u003c/strong\\u003e(6): p. 3141-3157.\\u003c/li\\u003e\\n\\u003cli\\u003eWei, L., et al., \\u003cem\\u003eATSE: a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural network and attention mechanism.\\u003c/em\\u003e Briefings in Bioinformatics, 2021. \\u003cstrong\\u003e22\\u003c/strong\\u003e(5).\\u003c/li\\u003e\\n\\u003cli\\u003eWu, J., R.E. Aluko, and S. Nakai, \\u003cem\\u003eStructural Requirements of Angiotensin I-Converting Enzyme Inhibitory Peptides:\\u0026thinsp; Quantitative Structure\\u0026minus;Activity Relationship Study of Di- and Tripeptides.\\u003c/em\\u003e Journal of Agricultural and Food Chemistry, 2006. \\u003cstrong\\u003e54\\u003c/strong\\u003e(3): p. 732-738.\\u003c/li\\u003e\\n\\u003cli\\u003eDu, A. and W. Jia, \\u003cem\\u003eNew insights into the bioaccessibility and metabolic fates of short-chain bioactive peptides in goat milk using the INFOGEST static digestion model and an improved data acquisition strategy.\\u003c/em\\u003e Food Research International, 2023. \\u003cstrong\\u003e169\\u003c/strong\\u003e.\\u003c/li\\u003e\\n\\u003cli\\u003eCharoenkwan P, Chiangjong W, Nantasenamat C, Hasan MM, Manavalan B, Shoombuatong W. \\u003cem\\u003eStackIL6: a stacking ensemble model for improving the prediction of IL-6 inducing peptides\\u003c/em\\u003e. Brief Bioinform. 2021;\\u003cstrong\\u003e22\\u003c/strong\\u003e(6):bbab172.\\u003c/li\\u003e\\n\\u003c/ol\\u003e\"}],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":true,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":true,\"isAuthorSuppliedPdf\":false,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":false,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"bmc-biology\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"\",\"sideBox\":\"Learn more about [BMC Biology](https://bmcbiol.biomedcentral.com/)\",\"snPcode\":\"12915\",\"submissionUrl\":\"https://submission.springernature.com/new-submission/12915/3\",\"title\":\"BMC Biology\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"stoa\",\"reportingPortfolio\":\"BMC Series\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":true},\"keywords\":\"Therapeutic peptide discovery, Web server, Deep learning, BERT\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7645806/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7645806/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003ch2\\u003eBackground\\u003c/h2\\u003e\\u003cp\\u003eTherapeutic peptides represent a rapidly expanding class of drug candidates due to their diverse biological activities and high specificity. However, accurately predicting peptide functions directly from sequence information remains a major challenge in computational peptidomics. Current tools, typically standalone applications or functionally constrained web servers, lack the flexibility and scalability essential for modern peptide discovery workflows. Therefore, it is necessary to develop a cloud-based, no-code platform that enables customizable modeling and high-throughput functional screening of therapeutic peptides.\\u003c/p\\u003e\\u003ch2\\u003eResults\\u003c/h2\\u003e\\u003cp\\u003ePepPharmaHub (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttp://bioinmed.jflab.ac.cn:18090/peppharmahub/\\u003c/span\\u003e\\u003cspan address=\\\"http://bioinmed.jflab.ac.cn:18090/peppharmahub/\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e) provides a cloud-based, end-to-end platform that integrates advanced sequence-based language modeling with curated benchmark datasets and interactive visualization modules. The platform features a high-throughput screening module powered by a diverse set of 24 models targeting 20 therapeutic properties, alongside a customizable model training pipeline for user-defined screening tasks. Comprehensive benchmarking on 24 public datasets demonstrates that PepPharmaHub matches or surpasses state-of-the-art predictors, significantly improving the efficiency of large-scale peptide screening. Compared with existing public web servers, PepPharmaHub attains a higher, more tightly distributed accuracy on 3,475 newly reported bioactive peptides from 2023\\u0026ndash;2025 (20 independent tasks), indicating stronger generalization and practical utility.\\u003c/p\\u003e\\u003ch2\\u003eConclusions\\u003c/h2\\u003e\\u003cp\\u003ePepPharmaHub enables accurate, high-throughput prediction of peptide functions through customizable deep learning models and a no-code interface. By outperforming existing tools across multiple benchmarks and supporting interpretable sequence analysis, the platform offers a practical solution for accelerating peptide-based drug discovery.\\u003c/p\\u003e\",\"manuscriptTitle\":\"PepPharmaHub: A Cloud-Based Platform Integrating Multimodel Language Architectures with Curated Data Resources for Therapeutic Peptide Discovery\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-10-08 09:44:28\",\"doi\":\"10.21203/rs.3.rs-7645806/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2025-11-27T13:22:01+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-11-03T03:54:34+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-10-17T04:48:37+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-10-16T10:27:18+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-10-07T02:18:09+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"319744150879692805599693806695749416168\",\"date\":\"2025-09-26T06:55:51+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"171202971071403392406571402432060899714\",\"date\":\"2025-09-26T05:46:45+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"238935843587915979237861930800236682120\",\"date\":\"2025-09-26T05:24:11+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"17153069103583765351002392473008263385\",\"date\":\"2025-09-26T05:23:17+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2025-09-26T05:13:50+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2025-09-19T12:48:53+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2025-09-18T07:20:53+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"BMC Biology\",\"date\":\"2025-09-18T06:17:30+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"bmc-biology\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"\",\"sideBox\":\"Learn more about [BMC Biology](https://bmcbiol.biomedcentral.com/)\",\"snPcode\":\"12915\",\"submissionUrl\":\"https://submission.springernature.com/new-submission/12915/3\",\"title\":\"BMC Biology\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"stoa\",\"reportingPortfolio\":\"BMC Series\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":true}}],\"origin\":\"\",\"ownerIdentity\":\"bcb5b859-227d-45d5-9274-d19c0451d8d7\",\"owner\":[],\"postedDate\":\"October 8th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-05-07T11:25:27+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-10-08 09:44:28\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7645806\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7645806\",\"identity\":\"rs-7645806\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}