macpie: scalable workflow for high-throughput transcriptomic profiling

macpie: scalable workflow for high-throughput transcriptomic profiling | 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 New Results macpie: scalable workflow for high-throughput transcriptomic profiling View ORCID Profile Nenad Bartonicek , Xin Liu , View ORCID Profile Laura Twomey , View ORCID Profile Michelle Meier , View ORCID Profile Richard Lupat , Stuart Craig , View ORCID Profile David Yoannidis , Jason Li , Tim Semple , View ORCID Profile Kaylene J Simpson , View ORCID Profile Mark X Li , View ORCID Profile Susanne Ramm doi: https://doi.org/10.1101/2025.08.06.669002 Nenad Bartonicek 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nenad Bartonicek For correspondence: nbartonicek{at}gmail.com Xin Liu 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 3 Victorian Centre for Functional Genomics, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 5 Bioinformatics Core Facility, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site Laura Twomey 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Laura Twomey Michelle Meier 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia 5 Bioinformatics Core Facility, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Michelle Meier Richard Lupat 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 5 Bioinformatics Core Facility, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Richard Lupat Stuart Craig 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site David Yoannidis 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for David Yoannidis Jason Li 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia 5 Bioinformatics Core Facility, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site Tim Semple 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site Kaylene J Simpson 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia 3 Victorian Centre for Functional Genomics, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 4 Department of Biochemistry and Pharmacology, The University of Melbourne , Victoria 3010, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Kaylene J Simpson Mark X Li 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia 3 Victorian Centre for Functional Genomics, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Mark X Li Susanne Ramm 1 Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia 2 Sir Peter MacCallum Department of Oncology, The University of Melbourne , Victoria 3010, Australia 3 Victorian Centre for Functional Genomics, Peter MacCallum Cancer Centre , Melbourne, Victoria 3000, Australia Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Susanne Ramm Abstract Full Text Info/History Metrics Data/Code Preview PDF Abstract High-throughput transcriptomic profiling (HTTr) enables scalable characterisation of transcriptional responses to chemical and genetic perturbations. While plate-based technologies such as MAC-Seq, TempO-seq and PLATE-seq have made HTTr more accessible, they pose unique computational challenges in modelling data and integration across modalities. We present macpie , an R package designed to streamline the analysis of HTTr data from plate-based screens. Built on the tidySeurat framework, macpie streamlines the entire analytical pipeline from preprocessing and quality control to pathway enrichment, chemical feature extraction, and multimodal data integration. The package incorporates multiple statistical frameworks and leverages parallelisation for scalability. By leveraging Docker and Nextflow, macpie ensures reproducibility and ease of use for transcriptome-wide screening. Availability The R package macpie is freely available at https://github.com/PMCC-BioinformaticsCore/macpie , with images of the working environment hosted at Docker Hub: xliu81/macpie. A companion Nextflow pipeline for preprocessing from FASTQ files is available at https://github.com/PMCC-BioinformaticsCore/dinoflow . Contact nenad.bartonicek{at}petermac.org Supplementary information Package vignettes with the full analytical workflow available at https://pmcc-bioinformaticscore.github.io/macpie/articles/macpie.html Introduction High-throughput screening (HTS) platforms are widely used in modern biomedical research, supporting a broad range of applications from functional genomics (e.g., CRISPR or RNAi screens), biomarker identification, drug discovery, to toxicology 1 - 4 . Early HTS approaches commonly reduced complex cellular phenotypes to a limited set of features such as proliferation rates, morphological changes or biomarker abundance, and were gradually replaced with multi-feature, high-content screening (HCS) 5 . More recently, high-throughput transcriptomic (HTTr) profiling has emerged as an increasingly accessible and scalable extension to HCS, capturing dynamic cellular states in response to chemical or genetic perturbations 6 - 8 . Several technologies support HTTr, including DRUG-seq 9 , TempO-seq 10 , L1000 6 , PLATE-seq 11 , and commercial platforms such as Insphero’s Organoid DRUG-seq 12 . MAC-Seq (Multiplexed Analysis of Cells) was introduced as a cost-effective HTTr method that eliminates RNA extraction steps and supports integration with suspension cells, flow cytometry read outs and high-content imaging for adherent, 3D matrix embedded cell models, as well as complex co-culture systems 13 . Even though these platforms overcome considerable technical barriers related to plate-based workflows, they also present unique analytical challenges. High-throughput transcriptomic platforms generate datasets that fall outside the scope of existing computational workflows. Compared to conventional RNA-seq, HTTr datasets often involve complex experimental designs with larger number of perturbations and higher potential for latent batch effects. The limited input material and small cell numbers frequently result in zero-inflated count distributions, resembling those seen in single-cell RNA-seq (scRNA-seq) 14 . However, HTTr datasets generally lack the number of samples needed to support statistical models developed for scRNA-seq, presenting unique analytical challenges. Current HTTr analytical frameworks were mostly built to address toxicology analyses and are available as standalone applications ( BMDExpress-2 15 ) or partial workflows in R for quality control (e.g. httrpl 8 ), analysis and visualisation (e.g. DRUG-seq 16 ) or modelling of compound concentration-response curves (e.g. tcplfit2 17 , and bmd 18 ). A complete, modular, and scalable R-based framework integrating both bioinformatics and cheminformatics components remains absent. To address this gap, we introduce macpie , an R package for the comprehensive analysis of HTTr data from plate-based sequencing technologies. Implementation The macpie package was developed for analysis and visualisation of HTTr data, particularly for large, 384 well plate-based screens. The workflow is based on the tidySeurat framework that combines properties of Seurat and tidyverse objects, benefitting from their respective functionalities. Seurat is a widely used R package for complete analysis of transcriptomic data from single cell experiments 19 , including QC, dimensionality reduction, clustering, marker selection and data integration. The tidyverse collection of R packages is the standard in R-based data analytics 20 for preprocessing, modelling and visualisation of complex data structures. macpie is compatible with R version >4.3.3 and is available as a Docker container to ensure reproducibility and ease of installation. Key steps of the analytical workflow are outlined in the package vignettes. Data preprocessing macpie requires gene expression matrices and corresponding sample metadata sheet as inputs. Matrices can be imported from the standard sparse matrix format, as generated by Cell Ranger 22 or STARsolo 23 from raw FASTQ files. The sample metadata sheet must contain a minimal set of standard columns as outlined in the documentation, ensuring accurate mapping of expression values to sample annotation via sample barcodes, and can be further populated by descriptors of samples or perturbations. To simplify and standardise data preprocessing from FASTQ files, we provide a companion Nextflow pipeline, available at https://github.com/PMCC-BioinformaticsCore/dinoflow . macpie currently supports data from Homo sapiens and Mus musculus . Quality control Given the large-scale nature of HTTr transcription-based screens, quality controls are important to ensure data integrity and minimise technical artefacts ( Fig 1A ). The QC workflow begins with metadata validation, as screens involve complex, often manually entered combinations of treatments. To streamline this step, we simplified inspection of large numbers of experimental variables for potential errors or inconsistencies, including automated checks for missing values and special characters. Next, macpie provides a set of QC tools that assess various properties of read distribution across genes and experimental conditions: read depth, variability, variance decomposition, outlier detection and normalisation. Relative log expression (RLE) plots are especially effective at visualising impacts of filtering cutoffs and various normalisations methods, while quantifying differences with the average coefficient of covariation ( Fig 1A ). Download figure Open in new tab Figure 1. Overview of macpie key functionalities. A. Relative log expression (RLE) plots to estimate sources of variability during quality control and normalization. B. Volcano plot showing differential gene expression (DE) following Staurosporine 10 µM treatment vs DMSO vehicle control. C. Pathway enrichment heatmap derived from DE analysis. D. Aggregated pathway visualisation, combining pathway enrichment results across replicates. E. UMAP dimensionality reduction based on DE of treatments compared to DMSO. F. Point plot for signature detection, based on the enrichment of top 500 genes from an existing perturbation profile, as measured by Normalised Enrichment Score (NES). G. Dose-response curves at the gene level (top) and pathway level (bottom), with EC50 values indicated by dashed red lines. H. Multimodal analysis using MOFA 21 . Upper panels describe latent factors of a model that combines cell viability, gene expression, pathway enrichment and chemical properties of compounds. Lower panel shows low-dimensional representation of samples coloured by molecular descriptor MDEC.33, with data point size defined by expression of by PSMD2 gene, a cancer growth promoter. Transcriptomic workflow Following QC, macpie supports two principal analytical modes: single-treatment and multi-treatment analysis. At the single-treatment level, macpie simplifies characterization of transcriptional responses to individual perturbations. Differential expression analysis is implemented with support for multiple statistical frameworks, including Seurat 19 , DESeq2 24 , edgeR 25 , RUVSeq 26 and ZINB-WaVE 27 , allowing users to choose between models based on their dataset characteristics. Differentially expressed genes (DEGs) can be visualised on volcano plots ( Fig. 1B ), placed in biological context with gene set enrichment and pathway analysis tools ( Fig. 1C ), and samples visualised on multidimensional scaling (MDS) and Uniform Manifold Approximation and Projection (UMAP) plots. In addition, macpie offers a multi-treatment analysis framework, enabling users to compare transcriptional profiles across numerous perturbations in parallel. This mode automates the computation of DEGs and the enrichment analysis via standardized pipelines, producing summaries of results on gene and pathway levels (Fig D-F). All multi-treatment analyses are parallelized to optimize runtime and computational efficiency. Screen-level analyses To explore higher-order effects across perturbations and integrate them with user-provided external annotations such as cell counts of surface markers, the macpie workflow streamlines several visualisations and analyses. First, macpie simplifies UMAP dimensionality reduction, enabling users to cluster experimental factors by the similarity of their transcriptional responses ( Fig 1E ). In addition, macpie supports cheminformatics workflows by extracting SMILES strings from compound names, computing and filtering molecular descriptors (e.g. physicochemical properties and fingerprints) or calculating half maximal effective concentrations for genes or pathways ( Fig 1G ). Finally, macpie allows data integration with Multi-Omics Factor Analysis (MOFA) 21 , facilitating unsupervised decomposition of variance across different data modalities, revealing latent factors driving biological or technical variation ( Fig 1H ). Conclusion macpie offers a robust, well-structured and flexible R-based framework for the analysis of high-throughput transcriptomics screens. By standardizing preprocessing and integrating diverse statistical methods, it enables consistent and interpretable analysis of complex datasets. A complementary Nextflow pipeline for raw data preprocessing and containerized environment support were developed to provide scalability and reproducibility required for large-scale screening efforts. The modular architecture and emphasis on portability were designed to encourage community contributions to macpie in the future. We successfully applied macpie to other external HTTr datasets (vignette “cross_platform_compatibility”), confirming its robustness across different platforms, cell types, and perturbations. As multi-modal profiling becomes standard for characterizing cellular responses, macpie provides a foundation for integrating transcriptomic and phenotypic data with chemical or biological properties of treatments. Future developments will incorporate additional omics layers, such as surface proteomics, secretomes, long-read sequencing and cellular barcoding 28 , facilitating more comprehensive systems-level analyses. Acknowledgements We thank Ricky Johnstone, Magdalena Nakova and Hasan Quraishi for helpful discussions during the preparation of this manuscript, and Jenni Luu, Robert Vary, Kavya Pamulapati, and Karla Cowley from Victorian Centre for Functional Genomics (Peter Mac) for data generation. We acknowledge the Computational Biology Program at Peter MacCallum Cancer Centre and the Data Sprint initiative, including Miriam Yeung for her work on the Nextflow workflow. This work was supported by a Peter Mac Foundation Grant awarded to SR. Funder Information Declared Peter MacCallum Cancer Centre Foundation , awarded to Susanne Ramm Footnotes ↵ * co-first ↵ $ co-last https://github.com/PMCC-BioinformaticsCore/macpie https://zenodo.org/records/15778812 References 1. ↵ Tsherniak A , Vazquez F , Montgomery PG , Weir BA , Kryukov G , Cowley GS , Gill S , Harrington WF , Pantel S , Krill-Burger JM , Meyers RM , Ali L , Goodale A , Lee Y , Jiang G , Hsiao J , Gerath WFJ , Howell S , Merkel E , Ghandi M , Garraway LA , Root DE , Golub TR , Boehm JS , Hahn WC . Defining a Cancer Dependency Map . Cell . 2017 ; 170 ( 3 ): 564 – 76 e16 . OpenUrl CrossRef PubMed 2. Janvilisri T , Suzuki H , Scaria J , Chen JW , Charoensawan V. High-Throughput Screening for Biomarker Discovery . Dis Markers . 2015 ; 2015 : 108064 . OpenUrl PubMed 3. Macarron R , Banks MN , Bojanic D , Burns DJ , Cirovic DA , Garyantes T , Green DV , Hertzberg RP , Janzen WP , Paslay JW , Schopfer U , Sittampalam GS . Impact of high-throughput screening in biomedical research . Nat Rev Drug Discov . 2011 ; 10 ( 3 ): 188 – 95 . OpenUrl CrossRef PubMed 4. ↵ Lynch C , Sakamuru S , Ooka M , Huang R , Klumpp-Thomas C , Shinn P , Gerhold D , Rossoshek A , Michael S , Casey W , Santillo MF , Fitzpatrick S , Thomas RS , Simeonov A , Xia M. High-Throughput Screening to Advance In Vitro Toxicology: Accomplishments, Challenges, and Future Directions . Annu Rev Pharmacol Toxicol . 2024 ; 64 : 191 – 209 . OpenUrl CrossRef PubMed 5. ↵ Fox S , Farr-Jones S , Sopchak L , Boggs A , Nicely HW , Khoury R , Biros M. High-throughput screening: update on practices and success . J Biomol Screen . 2006 ; 11 ( 7 ): 864 – 9 . OpenUrl CrossRef PubMed Web of Science 6. ↵ Subramanian A , Narayan R , Corsello SM , Peck DD , Natoli TE , Lu X , Gould J , Davis JF , Tubelli AA , Asiedu JK , Lahr DL , Hirschman JE , Liu Z , Donahue M , Julian B , Khan M , Wadden D , Smith IC , Lam D , Liberzon A , Toder C , Bagul M , Orzechowski M , Enache OM , Piccioni F , Johnson SA , Lyons NJ , Berger AH , Shamji AF , Brooks AN , Vrcic A , Flynn C , Rosains J , Takeda DY , Hu R , Davison D , Lamb J , Ardlie K , Hogstrom L , Greenside P , Gray NS , Clemons PA , Silver S , Wu X , Zhao WN , Read-Button W , Wu X , Haggarty SJ , Ronco LV , Boehm JS , Schreiber SL , Doench JG , Bittker JA , Root DE , Wong B , Golub TR . A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 Profiles . Cell . 2017 ; 171 ( 6 ): 1437 – 52 e17 . OpenUrl CrossRef PubMed 7. Iorio F , Rittman T , Ge H , Menden M , Saez-Rodriguez J. Transcriptional data: a new gateway to drug repositioning? Drug Discov Today . 2013 ; 18 ( 7-8 ): 350 - 7 . OpenUrl CrossRef PubMed Web of Science 8. ↵ Harrill JA , Everett LJ , Haggard DE , Word LJ , Bundy JL , Chambers B , Harris F , Willis C , Thomas RS , Shah I , Judson R. Signature analysis of high-throughput transcriptomics screening data for mechanistic inference and chemical grouping . Toxicol Sci . 2024 ; 202 ( 1 ): 103 – 22 . OpenUrl CrossRef PubMed 9. ↵ Ye C , Ho DJ , Neri M , Yang C , Kulkarni T , Randhawa R , Henault M , Mostacci N , Farmer P , Renner S , Ihry R , Mansur L , Keller CG , McAllister G , Hild M , Jenkins J , Kaykas A. DRUG-seq for miniaturized high-throughput transcriptome profiling in drug discovery . Nat Commun . 2018 ; 9 ( 1 ): 4307 . OpenUrl CrossRef PubMed 10. ↵ Yeakley JM , Shepard PJ , Goyena DE , VanSteenhouse HC , McComb JD , Seligmann BE . A trichostatin A expression signature identified by TempO-Seq targeted whole transcriptome profiling . PLoS One . 2017 ; 12 ( 5 ): e0178302 . OpenUrl CrossRef PubMed 11. ↵ Bush EC , Ray F , Alvarez MJ , Realubit R , Li H , Karan C , Califano A , Sims PA . PLATE-Seq for genome-wide regulatory network analysis of high-throughput screens . Nat Commun . 2017 ; 8 ( 1 ): 105 . OpenUrl CrossRef PubMed 12. ↵ Fas L , Chen M , Tong W , Wenz F , Hewitt NJ , Tu M , Sanchez K , Zapiorkowska-Blumer N , Varga H , Kaczmarska K , Colombo MV , Filippi BGH . Physiological liver microtissue 384-well microplate system for preclinical hepatotoxicity assessment of therapeutic small molecule drugs . Toxicol Sci . 2025 ; 203 ( 1 ): 79 – 87 . OpenUrl PubMed 13. ↵ Li XM , Yoannidis D , Ramm S , Luu J , Arnau GM , Semple T , Simpson KJ . MAC-Seq: Coupling Low-Cost, High-Throughput RNA-Seq with Image-Based Phenotypic Screening in 2D and 3D Cell Models . Methods Mol Biol . 2023 ; 2691 : 279 – 325 . OpenUrl CrossRef PubMed 14. ↵ Jiang R , Sun T , Song D , Li JJ . Statistics or biology: the zero-inflation controversy about scRNA-seq data . Genome Biol . 2022 ; 23 ( 1 ): 31 . OpenUrl CrossRef PubMed 15. ↵ Phillips JR , Svoboda DL , Tandon A , Patel S , Sedykh A , Mav D , Kuo B , Yauk CL , Yang L , Thomas RS , Gift JS , Davis JA , Olszyk L , Merrick BA , Paules RS , Parham F , Saddler T , Shah RR , Auerbach SS . BMDExpress 2: enhanced transcriptomic dose-response analysis workflow . Bioinformatics . 2019 ; 35 ( 10 ): 1780 – 2 . OpenUrl CrossRef PubMed 16. ↵ Li J , Ho DJ , Henault M , Yang C , Neri M , Ge R , Renner S , Mansur L , Lindeman A , Kelly B , Tumkaya T , Ke X , Soler-Llavina G , Shanker G , Russ C , Hild M , Gubser Keller C , Jenkins JL , Worringer KA , Sigoillot FD , Ihry RJ . DRUG-seq Provides Unbiased Biological Activity Readouts for Neuroscience Drug Discovery . ACS Chem Biol . 2022 ; 17 ( 6 ): 1401 – 14 . OpenUrl CrossRef PubMed 17. ↵ Sheffield T , Brown J , Davidson S , Friedman KP , Judson R. tcplfit2: an R-language general purpose concentration-response modeling package . Bioinformatics . 2022 ; 38 ( 4 ): 1157 – 8 . OpenUrl CrossRef PubMed 18. ↵ Jensen SM , Kluxen FM , Streibig JC , Cedergreen N , Ritz C. bmd: an R package for benchmark dose estimation . PeerJ . 2020 ; 8 : e10557 . OpenUrl PubMed 19. ↵ Satija R , Farrell JA , Gennert D , Schier AF , Regev A. Spatial reconstruction of single-cell gene expression data . Nat Biotechnol . 2015 ; 33 ( 5 ): 495 – 502 . OpenUrl CrossRef PubMed 20. ↵ Wickham H , Averick M , Bryan J , Chang W , McGowan LDa , François R , Grolemund G , Hayes A , Henry L , Hester J , Kuhn M , Pedersen TL , Miller E , Bache SM , Müller K , Ooms J , Robinson D , Seidel DP , Spinu V , Takahashi K , Vaughan D , Wilke C , Woo K , Yutani H. Welcome to the Tidyverse . Journal of Open Source Software . 2019 ; 4 ( 43 ): 1686 . OpenUrl CrossRef 21. ↵ Argelaguet R , Velten B , Arnol D , Dietrich S , Zenz T , Marioni JC , Buettner F , Huber W , Stegle O. Multi-Omics Factor Analysis-a framework for unsupervised integration of multi-omics data sets . Mol Syst Biol . 2018 ; 14 ( 6 ): e8124 . OpenUrl Abstract / FREE Full Text 22. ↵ Zheng GX , Terry JM , Belgrader P , Ryvkin P , Bent ZW , Wilson R , Ziraldo SB , Wheeler TD , McDermott GP , Zhu J , Gregory MT , Shuga J , Montesclaros L , Underwood JG , Masquelier DA , Nishimura SY , Schnall-Levin M , Wyatt PW , Hindson CM , Bharadwaj R , Wong A , Ness KD , Beppu LW , Deeg HJ , McFarland C , Loeb KR , Valente WJ , Ericson NG , Stevens EA , Radich JP , Mikkelsen TS , Hindson BJ , Bielas JH . Massively parallel digital transcriptional profiling of single cells . Nat Commun . 2017 ; 8 : 14049 . OpenUrl CrossRef PubMed 23. ↵ Kaminow B , Yunusov D , Dobin A. STARsolo: accurate, fast and versatile mapping/quantification of single-cell and single-nucleus RNA-seq data . bioRxiv . 2021 :2021.05.05.442755. 24. ↵ Love MI , Huber W , Anders S. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2 . Genome Biol . 2014 ; 15 ( 12 ): 550 . OpenUrl CrossRef PubMed 25. ↵ Chen Y , Chen L , Lun ATL , Baldoni PL , Smyth GK . edgeR v4: powerful differential analysis of sequencing data with expanded functionality and improved support for small counts and larger datasets . Nucleic Acids Res . 2025 ; 53 ( 2 ). 26. ↵ Risso D , Ngai J , Speed TP , Dudoit S. Normalization of RNA-seq data using factor analysis of control genes or samples . Nat Biotechnol . 2014 ; 32 ( 9 ): 896 – 902 . OpenUrl CrossRef PubMed 27. ↵ Risso D , Perraudeau F , Gribkova S , Dudoit S , Vert JP . A general and flexible method for signal extraction from single-cell RNA-seq data . Nat Commun . 2018 ; 9 ( 1 ): 284 . OpenUrl CrossRef PubMed 28. ↵ Fennell KA , Vassiliadis D , Lam EYN , Martelotto LG , Balic JJ , Hollizeck S , Weber TS , Semple T , Wang Q , Miles DC , MacPherson L , Chan YC , Guirguis AA , Kats LM , Wong ES , Dawson SJ , Naik SH , Dawson MA . Non-genetic determinants of malignant clonal fitness at single-cell resolution . Nature . 2022 ; 601 ( 7891 ): 125 – 31 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted August 09, 2025. Download PDF Data/Code 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 macpie: scalable workflow for high-throughput transcriptomic profiling 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 macpie: scalable workflow for high-throughput transcriptomic profiling Nenad Bartonicek , Xin Liu , Laura Twomey , Michelle Meier , Richard Lupat , Stuart Craig , David Yoannidis , Jason Li , Tim Semple , Kaylene J Simpson , Mark X Li , Susanne Ramm bioRxiv 2025.08.06.669002; doi: https://doi.org/10.1101/2025.08.06.669002 Share This Article: Copy Citation Tools macpie: scalable workflow for high-throughput transcriptomic profiling Nenad Bartonicek , Xin Liu , Laura Twomey , Michelle Meier , Richard Lupat , Stuart Craig , David Yoannidis , Jason Li , Tim Semple , Kaylene J Simpson , Mark X Li , Susanne Ramm bioRxiv 2025.08.06.669002; doi: https://doi.org/10.1101/2025.08.06.669002 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 Bioinformatics Subject Areas All Articles Animal Behavior and Cognition (7642) Biochemistry (17708) Bioengineering (13904) Bioinformatics (41992) Biophysics (21466) Cancer Biology (18618) Cell Biology (25531) Clinical Trials (138) Developmental Biology (13387) Ecology (19924) Epidemiology (2067) Evolutionary Biology (24337) Genetics (15615) Genomics (22521) Immunology (17749) Microbiology (40424) Molecular Biology (17194) Neuroscience (88673) Paleontology (667) Pathology (2839) Pharmacology and Toxicology (4827) Physiology (7650) Plant Biology (15160) Scientific Communication and Education (2046) Synthetic Biology (4302) Systems Biology (9826) Zoology (2271)