Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio

Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (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];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Confirmatory Results Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio View ORCID Profile Pravin Badhe doi: https://doi.org/10.1101/2025.08.31.673331 Pravin Badhe 1 Swalife Biotech Ltd North Point House , North Point Business Park, New Mallow Road, Cork ( Republic of Ireland ) Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Pravin Badhe For correspondence: drpravinbadhe{at}swalifebiotech.com Abstract Full Text Info/History Metrics Preview PDF Abstract Artificial intelligence–assisted scientific prompting is reshaping how biological targets can be rapidly identified and contextualized. In this work, we present the Swalife PromptStudio – Target Identification workflow and illustrate its application to poly(ADP-ribose) polymerase-1 (PARP1), a central regulator of DNA repair and genome integrity. Using structured prompts, we systematically explored literature, pathway databases, and genetic repositories to compile a multi-dimensional profile of PARP1. Prompt-guided mining revealed strong associations with base-excision repair, single-strand break repair, and homologous recombination pathways, positioning PARP1 as a hub in genome stability networks. Disease-mapping identified links to cancer, neurodegeneration, and ischemic injury, while variant-focused prompts highlighted replicated associations such as rs1136410 (Val762Ala) and the pharmacogenomic marker rs1805414. Together, these findings demonstrate the effectiveness of prompt-driven target identification in rapidly assembling actionable biological insights. The framework is scalable and adaptable, offering a reproducible strategy for prioritizing targets across therapeutic areas. Introduction Scientific prompting in target identification refers to the strategic use of advanced AI models—especially large language models (LLMs)—and domain-specific prompts to accelerate the discovery and validation of biological targets relevant to disease, such as potential molecular targets for new drugs 1 . Scientific prompting, when combined with large language models (LLMs), is emerging as a transformative approach for drug discovery and target validation. By tailoring queries, prompts guide LLMs to mine literature, integrate multi-omics datasets, and predict gene and protein functions with context-aware precision, even in low-data settings. 2 Prompt-driven strategies accelerate target identification by extracting disease associations and mechanistic insights from biomedical corpora, while also enabling the integration of genomics, transcriptomics, and proteomics data for pathway mapping. 3 In biological sequence analysis, prompting supports predictions of protein function, structural features, and drug–target binding affinities. 2 Moreover, end-to-end frameworks such as multi-agent systems demonstrate how LLMs can span the full discovery pipeline, from hypothesis generation to molecular design and screening. 4 Although challenges remain in interpretability, computational resources, and data integration, combining prompt-engineered outputs with experimental or computational validation strengthens the reliability and impact of LLM-driven drug discovery. Scientific prompting enables rapid, multi-dimensional target discovery by leveraging LLMs and precise, context-tailored instructions, representing a transformative advance in modern drug discovery and computational biology. Swalife PromptStudio — Target Identification & Validation Swalife PromptStudio is a web-based application designed for researchers, students, and biotech innovators to generate structured prompts for protein target identification and validation. Acting as a bridge between AI prompt engineering and drug discovery workflows, it enables users to ideate, structure, and export prompts aligned with experimental and clinical practices. PromptStudio also serves as the foundation for a more advanced Scientific Prompting Studio an AI-powered ecosystem integrating prompt engineering, workflow orchestration, and data harmonization to accelerate drug discovery and validation. 4 , 5 , 6 Extended Vision — Scientific Prompting Studio To evolve into a fully-fledged AI-driven studio, several core modules are envisioned: Prompt Engineering Interface intuitive tools for scientists to design, test, and refine zero-shot, few-shot, and multimodal prompts. 7 Workflow Orchestration Engine automates literature mining, target scoring, and druggability assessment using LLM-powered agents. 5 Data Integration Hub links omics datasets, pathway databases, and bioassays for real-time grounding. 4 , 6 Validation & Evaluation Modules suggest experimental strategies, safety checks, and prioritization pipelines integrated with LIMS. 6 Example Workflow A researcher inputs a query (e.g., “Prioritize druggable kinases in HER2+ breast cancer”), designs a guided prompt, invokes LLM agents for annotation, integrates omics datasets, and ranks candidates by novelty and safety before planning in vitro/in vivo validation. 5 , 8 Key Features, Best Practices & Emerging Trends Libraries & Templates for literature mining, pathway analysis, and biomarker discovery. 7 , 9 Collaboration Tools to support multi-disciplinary teams. 5 Transparency via annotated outputs, prompt history, and evaluation metrics. 7 API Integration with PubMed, STRING, and KEGG for evidence-based contextualization. 4 , 6 Emerging Trends Multi-agent ecosystems like DrugAgent and Receptor.AI Orchestrator dynamically adapt prompts and automate workflows. 5 , 8 Continuous learning loops, combining AI with lab feedback, improve reliability over time. 6 , 8 Pros Intuitive, Customizable, Educational, Bridges AI and science, Export-ready. Limitations: not a database/analysis engine, dependent on user expertise, currently static, and at early development stage. Poly(ADP-ribose) polymerase-1 (PARP1) is a pivotal regulator of DNA repair and an essential guardian of genome integrity. As one of the most abundant nuclear proteins, PARP1 acts as a molecular sensor of DNA strand breaks and orchestrates multiple repair processes to ensure genomic stability 10 , 11 , 12 . When DNA damage occurs, PARP1 rapidly binds to sites of single- and double-strand breaks and catalyzes the addition of poly(ADP-ribose) (PAR) chains to itself and other chromatin-associated proteins, a process termed PARylation . This modification, driven by NAD + as a substrate, generates a molecular scaffold that recruits base excision repair (BER) factors such as XRCC1, DNA ligase III, and DNA polymerase β, thereby accelerating the repair of damaged DNA templates 11 . Beyond protein recruitment, PARP1 modifies histones and remodels chromatin structure, enabling access for repair enzymes while preserving the integrity of the replication machinery. Excessive activation of PARP1, however, can deplete NAD + and ATP pools, triggering a caspase-independent cell death pathway known as parthanatos 12 .This dual role highlights its importance not only in promoting cell survival after genotoxic stress but also in eliminating irreparably damaged cells to prevent malignant transformation. Mechanistically, PARP1 stabilizes replication forks and prevents chromosomal rearrangements, thereby reducing mutagenesis during cell division. Its ability to regulate chromatin relaxation ensures timely access of repair complexes to DNA lesions, reinforcing its function as a genomic caretaker. Dysregulation or loss of PARP1 activity compromises repair fidelity, resulting in genomic instability, a hallmark of cancer development 12 . Clinically, this has been exploited in oncology through the use of PARP inhibitors. In tumors deficient in homologous recombination repair (e.g., BRCA1/2 mutations), pharmacological inhibition of PARP1 induces synthetic lethality, selectively killing cancer cells while sparing normal cells. Such inhibitors have become integral in the management of breast, ovarian, and prostate cancers, demonstrating how fundamental DNA repair mechanisms can be translated into targeted therapies. 10 , 11 . PARP1 functions as both a sentinel and executor of DNA repair, balancing genome protection with controlled cell death when damage is beyond repair. Its central role in DNA repair pathways, chromatin remodeling, replication fork stabilization, and cell fate determination underscores its indispensable contribution to genome integrity. The therapeutic success of PARP inhibitors further emphasizes PARP1’s relevance as a drug target, making it a cornerstone of precision oncology 10 , 11 , 12 . Material and Method We employed the Swalife PromptStudio – Target Identification framework (available at https://promptstudio1.swalifebiotech.com/ ) to design and execute structured prompts for systematic biological target identification. All analyses were performed using ChatGPT-5 (Plus account), integrated with PromptStudio to ensure reproducibility and modularity of prompt design. Download figure Open in new tab Figure 1 User Interface of Swalife PromptStudio The methodology followed these steps: Prompt Design: Target-focused prompts were created within Swalife PromptStudio, structured around key evidence categories—basic biology, pathways, protein interactions, genetic evidence, and disease associations. Target Selection: PARP1 (poly[ADP-ribose] polymerase-1) was chosen as the case study gene, given its established role in DNA damage response and therapeutic targeting. Information Mining: Prompts guided ChatGPT-5 to systematically mine publicly available knowledge from literature, curated pathway repositories (GO, KEGG, Reactome), and genetic evidence resources (GWAS, ClinVar, variant databases). Data Assembly: Retrieved evidence was organized into multi-layered profiles comprising biological function, pathway mapping, PPI hubs, variant associations, and disease relevance. This methodology demonstrates how Scientiffic prompting can standardize and accelerate early-stage target identification without requiring manual multi-database scripting, offering a reproducible AI-assisted workflow. Result and Discussion PARP1 is a DNA damage sensor and repair coordinator. It facilitates single-strand break repair, replication fork stabilization, and chromatin remodeling, thereby preserving genomic stability. However, when overactivated, it can drive cell death through NAD + /ATP depletion. Base on the PARP1 search following prompt were generated in PromptStudio Literature & database mining : Identify PARP1-related pathways, diseases, and co-factors using PubMed, GeneCards, and UniProt. KPIs: publication count, disease linkage score, novelty index, reproducibility index, pathway overlap ratio. Download figure Open in new tab Figure-1 Literature & database mining The integrative analysis of PARP1 across pathways, diseases, and co-factors underscores its multifaceted role in genome stability and disease etiology. Pathway overlap analyses consistently highlight base excision repair (BER), single-strand break (SSB) repair, and homologous recombination (HR) as the most reproducible modules, confirming PARP1’s canonical function in DNA repair fidelity. Disease linkage is strongest in BRCA1/2-related cancers and neurodegeneration, with ischemic injury and inflammatory syndromes also showing strong associations, reflecting PARP1’s involvement in both nuclear repair and stress signaling. Co-factors such as XRCC1 and HPF1 emerge as high-reproducibility anchors in multiple datasets, whereas TSG101, FUS, and TIMELESS are identified as promising but less validated interactors, suggesting potential novel regulatory axes. The publication burden demonstrates a skewed research emphasis, with repair pathways dominating, diseases receiving secondary attention, and protein co-factors remaining underexplored. Heatmap analyses reinforce these findings: DNA repair modules (BER, HR, replication fork protection) are heavily represented in oncology, parthanatos strongly maps to ischemia and neurodegeneration, and NF-κB signaling connects PARP1 to immune and inflammatory pathways. Complementing these data, multi-omics profiling (transcriptomics, proteomics, metabolomics) provides quantitative support, with key performance indicators such as fold-change consistency, cross-platform correlation, and biomarker strength reinforcing PARP1’s role as a robust, translationally relevant target. This integrated framework highlights PARP1 as a nexus between DNA repair and disease phenotypes. Its well-established role in BER/SSB repair and HR is critical to the development and clinical use of PARP inhibitors in BRCA-mutant cancers, while its regulation of NF-κB and parthanatos extends its impact to immune and neurodegenerative disorders 13 . Multi-omics approaches have begun to reveal biomarker strength and cross-platform reproducibility of PARP1 and its partners, supporting therapeutic expansion beyond oncology 14 . However, emerging interactors such as TIMELESS and TSG101 remain underexplored, warranting further validation to expand the scope of PARP1-targeted interventions. Multi-omics profiling Integrate transcriptomics, proteomics, and metabolomics to assess PARP1’s disease role. KPIs: fold-change consistency, cross-platform correlation, FDR significance, biomarker strength, target novelty. Download figure Open in new tab Figure 2 Multi-omics profiling This multi-omics analysis provides a layered perspective on PARP1 biology and its interactors. Panel A demonstrates that PARP1 exhibits the highest fold-change consistency across omics layers, confirming its reliability as a cross-platform biomarker. Panel B shows PARP1 and its metabolite PAR as dominant in composite biomarker strength, while XRCC1 and HPF1 emerge as secondary yet strong markers. Panel C reveals that most features cluster at moderate integrated significance, with only a small subset showing strong multi-omics support, underscoring the selective reproducibility of certain targets. Panel D highlights limited overlap of significant hits across transcriptomics, proteomics, and metabolomics, reflecting omics-specific sensitivities rather than universal signatures. Panel E places PARP1 at the high-strength but low-novelty quadrant, while TIMELESS and TSG101 appear as promising, less-characterized candidates. Panel F extends fold-change consistency to BRCA1/2 and TSG101, indicating broader network robustness. Panels G–I dissect layer-specific profiles: metabolomics reveals strong PAR accumulation and NAD + depletion (PARP1 activation footprint), proteomics shows pronounced upregulation of PARP1 itself, and transcriptomics identifies elevated PARP1, XRCC1, HPF1, and NMNAT1 expression, driving repair responses. Finally, Panel J integrates these data with a moderate cross-platform correlation (r = 0.40), with PARP1, XRCC1, and HPF1 remaining coherent across transcript and protein levels. These findings confirm PARP1 as a robust, multi-omics-supported biomarker in DNA repair and stress responses. Its reproducibility across omics layers validates the clinical relevance of PARP inhibitors, now approved for BRCA1/2-mutant cancers and under evaluation for broader indications 15 . Metabolomic signatures, such as PAR accumulation and NAD + depletion, capture functional consequences of PARP1 hyperactivation and have been linked to therapeutic responses and toxicity profiles 16 . The emergence of secondary players such as XRCC1 and HPF1 reinforces their roles in base excision repair and PARylation regulation, while less-studied interactors like TIMELESS and TSG101 suggest novel regulatory axes requiring further exploration. Collectively, this framework highlights PARP1’s centrality but also identifies potential co-targets for biomarker development and mechanistic research. Gene ontology & pathway mapping Map PARP1 to GO terms, KEGG/Reactome pathways. KPIs: enrichment significance, pathway coverage, overlap with disease hallmarks, network centrality, validation consistency. Download figure Open in new tab Figure 3 Gene ontology & pathway mapping The analysis highlights PARP1 as a central regulator of DNA repair and genome stability. Panel A demonstrates that PARP1 has the highest network centrality, establishing it as the key hub gene within repair modules. Panel B shows strong overlap of PARP1-associated pathways with cancer-related hallmarks, especially genome instability and DNA damage response. In Panel C, Reactome mapping places PARP1-mediated PARylation and DNA repair pathways among the top for pathway coverage with moderate centrality, underscoring their biological breadth. Panel D further validates these findings, with KEGG enrichment showing strong signals for base-excision repair and homologous recombination, two core PARP1-driven mechanisms. Finally, Panel E confirms through GO enrichment that PARP1 is predominantly linked with DNA repair, replication fork stabilization, and chromatin organization, consolidating its role as a critical mediator of genome integrity. Together, these findings affirm PARP1’s dual importance as both a molecular sensor of DNA breaks and a signaling hub that orchestrates multiple repair pathways. Its central role explains why PARP inhibitors have shown such success in targeting homologous recombination–deficient cancers, particularly those with BRCA1/2 mutations 15 . Moreover, PARP1’s involvement in replication fork protection and chromatin remodeling extends its influence beyond DNA repair to broader aspects of genome architecture and stress responses, making it a versatile therapeutic target 17 . The enrichment patterns observed across pathway databases therefore not only validate known mechanisms but also underscore opportunities for expanding PARP1-targeted strategies into cancer types and stress-related diseases beyond those currently addressed. Protein interaction mapping Use STRING/Cytoscape to identify PARP1’s partners and hubs. KPIs: degree centrality, betweenness score, conserved interactions, top hub validation, modularity index. Download figure Open in new tab Figure 4 Protein interaction mapping This five-panel PPI analysis highlights the centrality and robustness of PARP1 within the DNA repair interactome. Panel A shows that the PARP1 community forms a single cohesive module, indicating tightly connected partners. Panel B identifies nodes such as H2AX, RPA1, LIG3, and BRCA1 with high conserved-edge ratios, underscoring their evolutionary stability in interaction with PARP1. Panel C maps degree versus betweenness, confirming PARP1 as a topological bottleneck with both high connectivity and strong control over information flow. Panel D lists the top hubs by degree, where PARP1 outpaces all others, reinforcing its role as the most connected protein. Finally, Panel E visualizes the synthetic PARP1-centric PPI network, showing dense and diverse interaction edges that bridge multiple repair pathways. Together, these results emphasize PARP1’s pivotal role as a highly connected and conserved hub in genome maintenance networks. The centrality of PARP1 within repair networks is consistent with experimental evidence showing its rapid recruitment to DNA breaks and its role in scaffolding key repair factors such as XRCC1, BRCA1, and histone H2AX 18 . Its dual role as a sensor and signaling hub explains why PARP1 inhibition not only affects single repair events but also disrupts wider genomic maintenance, making it a critical target in BRCA-deficient cancers 19 . The conserved nature of its interactome suggests evolutionary pressure to maintain PARP1-centered modules, highlighting its importance in genome stability across species. These findings justify ongoing clinical interest in PARP1 inhibitors and point to underexplored interactors like LIG3 and RPA1 as potential co-targets in synthetic lethality strategies. Genetic evidence Use GWAS, ClinVar, and variant databases for PARP1. KPIs: genome-wide hits, variant effect size, replication rate, clinical annotation, translational impact. Download figure Open in new tab Figure 5 Genetic evidence This infographic integrates GWAS evidence for PARP1 variants. Panel A compares two key variants (rs1805414 and rs1136410), showing distinct profiles where rs1805414 has stronger translational impact while rs1136410 demonstrates higher replication support. Panel B highlights replication intensity, with an average of over two associations per trait, reflecting robust reproducibility across studies. Panel C summarizes GWAS catalog data, revealing 58 associations across 55 studies and 27 traits, underscoring the broad relevance of PARP1 in diverse phenotypes. Collectively, these findings support PARP1 variants as impactful and consistently validated contributors to human disease traits. These results align with earlier studies showing that PARP1 polymorphisms, particularly rs1136410, are associated with altered enzymatic activity and increased cancer risk in multiple populations 20 . The broad catalog of associations highlights PARP1 as a pleiotropic locus, reflecting its roles in DNA repair, apoptosis, and immune signaling. Replication across independent GWAS adds confidence to the clinical utility of PARP1 variants, both as biomarkers and as potential modulators of therapeutic response to PARP inhibitors 21 . The reproducibility of findings across diverse traits indicates that PARP1 serves as a genetic hub bridging oncology, neurology, and immunology. Conclusion Through the Swalife PromptStudio – Target Identification workflow, we demonstrate that AI-assisted prompt engineering can rapidly integrate literature, pathway, omics, and genetic evidence to prioritize therapeutic targets. Application to PARP1 confirms its central role in DNA repair and genome stability, with consistent support from multi-omics profiling, pathway enrichment, PPI networks, and replicated variants such as rs1136410 and rs1805414. Beyond oncology, disease associations extend to neurodegeneration, ischemia, and inflammation, underscoring its broad translational relevance. This framework offers a scalable, reproducible strategy for accelerating target discovery and validation across therapeutic areas. References 1. ↵ Jiang J , Wang Z , Shan Y , Chai H , Li J , Ma Z , et al. Biological sequence with language model prompting: A survey [preprint] . arxiv: 2503.04135 v1 [cs.CL]. 2025 Mar 6. 2. ↵ Liu X , Zhang J , Wang X , Teng M , Wang G , Zhou X. Application of artificial intelligence large language models in drug target discovery . Front Pharmacol . 2025 ; 16 : 1597351 . doi: 10.3389/fphar.2025.1597351 . OpenUrl CrossRef PubMed 3. ↵ Zhao T , et al. Multi-agent systems in drug discovery [preprint] . arxiv: 2411.15692 v1 [cs]. 2024 Nov . 4. ↵ Liu X , Zhang J , Wang X , Teng M , Wang G , Zhou X. Application of artificial intelligence large language models in drug target discovery . Front Pharmacol . 2025 ; 16 : 1597351 . doi: 10.3389/fphar.2025.1597351 . OpenUrl CrossRef PubMed 5. ↵ Zhao T , et al. Multi-agent systems in drug discovery [preprint] . arxiv: 2411.15692 v1 [cs]. 2024 Nov . 6. ↵ Receptor.AI . LLM-Driven Workflow Orchestrator for Drug Discovery [Internet] . 2024 [cited 2025 Aug 30]. Available from: https://www.receptor.ai/news/presenting-the-llm-driven-workflow-orchestrator 7. ↵ White R , et al. Prompt engineering: A guide for effective LLM use [preprint] . arxiv: 2402.17721 v2 [cs]. 2024 Feb . 8. ↵ Jiang J , Wang Z , Shan Y , Chai H , Li J , Ma Z , et al. Biological sequence with language model prompting: A survey [preprint] . arxiv: 2503.04135 v1 [cs.CL]. 2025 Mar 6. 9. ↵ Klu.ai. Prompt engineering guide [Internet] . [cited 2025 Aug 30]. Available from: https://klu.ai/blog/prompt-engineering-guide 10. ↵ Ray Chaudhuri A , Nussenzweig A. The multifaceted roles of PARP1 in DNA repair and chromatin remodeling . Nat Rev Mol Cell Biol . 2017 ; 18 ( 10 ): 610 – 21 . PMID: 31302005. OpenUrl CrossRef PubMed 11. ↵ Lord CJ , Ashworth A. PARP inhibitors: Synthetic lethality in the clinic . Science . 2017 ; 355 ( 6330 ): 1152 – 8 . PMID: 37627260. OpenUrl Abstract / FREE Full Text 12. ↵ Morales J , Li L , Fattah FJ , Dong Y , Bey EA , Patel M , Gao J , Boothman DA . Review of poly(ADP-ribose) polymerase (PARP) mechanisms of action and rationale for targeting in cancer and other diseases . Crit Rev Eukaryot Gene Expr . 2014 ; 24 ( 1 ): 15 – 28 . PMC6591728. OpenUrl CrossRef PubMed 13. ↵ Curtin NJ , Szabo C. Therapeutic applications of PARP inhibitors: anticancer therapy and beyond . Nat Rev Drug Discov . 2013 Jul ; 12 ( 7 ): 502 – 520 . OpenUrl 14. ↵ Mateo J , Lord CJ , Serra V , Tutt A , Balmana J , Castroviejo-Bermejo M , Cruz C , Oaknin A , Kaye SB , de Bono JS . A decade of clinical development of PARP inhibitors in perspective . Ann Oncol . 2019 Sep ; 30 ( 9 ): 1437 – 1447 . OpenUrl CrossRef PubMed 15. ↵ Lord CJ , Ashworth A. PARP inhibitors: Synthetic lethality in the clinic . Science . 2017 Mar 24; 355 ( 6330 ): 1152 – 1158 . OpenUrl Abstract / FREE Full Text 16. ↵ Luo X , Kraus WL . On PAR with PARP: cellular stress signaling through poly(ADP-ribose) and PARP-1 . Genes Dev . 2012 Jan 15; 26 ( 2 ): 417 – 432 . OpenUrl Abstract / FREE Full Text 17. ↵ Ray Chaudhuri A , Nussenzweig A. The multifaceted roles of PARP1 in DNA repair and chromatin remodeling . Nat Rev Mol Cell Biol . 2017 Oct ; 18 ( 10 ): 610 – 621 . OpenUrl CrossRef PubMed 18. ↵ Caldecott KW . XRCC1 and DNA strand break repair . DNA Repair (Amst) . 2008 Jul ; 7 ( 7 ): 858 – 866 . OpenUrl CrossRef PubMed 19. ↵ Ray Chaudhuri A , Nussenzweig A. The multifaceted roles of PARP1 in DNA repair and chromatin remodeling . Nat Rev Mol Cell Biol . 2017 Oct ; 18 ( 10 ): 610 – 621 OpenUrl CrossRef PubMed 20. ↵ Wang X , Luo Y , Wang L , Chen S , Li J , Guo H , et al. PARP-1 polymorphisms increase cancer risk: a meta-analysis . Crit Rev Eukaryot Gene Expr . 2016 ; 26 ( 4 ): 291 – 300 . OpenUrl 21. ↵ Curtin NJ , Szabo C. Therapeutic applications of PARP inhibitors: anticancer therapy and beyond . Nat Rev Drug Discov . 2013 Jul ; 12 ( 7 ): 502 – 520 . OpenUrl View the discussion thread. Back to top Previous Next Posted September 01, 2025. Download PDF Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio Pravin Badhe bioRxiv 2025.08.31.673331; doi: https://doi.org/10.1101/2025.08.31.673331 Share This Article: Copy Citation Tools Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio Pravin Badhe bioRxiv 2025.08.31.673331; doi: https://doi.org/10.1101/2025.08.31.673331 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Pharmacology and Toxicology Subject Areas All Articles Animal Behavior and Cognition (7637) Biochemistry (17705) Bioengineering (13899) Bioinformatics (41970) Biophysics (21463) Cancer Biology (18605) Cell Biology (25526) Clinical Trials (138) Developmental Biology (13385) Ecology (19911) Epidemiology (2067) Evolutionary Biology (24329) Genetics (15615) Genomics (22514) Immunology (17743) Microbiology (40424) Molecular Biology (17194) Neuroscience (88650) Paleontology (667) Pathology (2835) Pharmacology and Toxicology (4827) Physiology (7648) Plant Biology (15160) Scientific Communication and Education (2046) Synthetic Biology (4302) Systems Biology (9825) Zoology (2271)