{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T18:29:21Z","timestamp":1786645761067,"version":"build-2736575974"},"reference-count":63,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Learning to Rank (LeToR) methods have gained increasing attention in drug response prediction, offering a direct way to prioritize effective treatments for cancer cell lines. In this study, we systematically benchmark six ranking loss functions, including state-of-the-art listwise methods, and five types of molecular representations across two large-scale drug screening datasets, CTRP and PRISM. Using high-dimensional gene expression profiles and various drug fingerprints and descriptors, we evaluated models under multiple validation setups and ranking metrics. Our results demonstrate that listwise loss functions such as LambdaLoss and LambdaRank consistently excel in both early and overall ranking quality. Additionally, combining molecular fingerprints with physicochemical descriptors yielded improved performance. A novel attention-based mechanism and a modified version of RankingSHAP were integrated to enhance interpretability, uncovering key genes and substructures aligned with known biological insights. The explainability pipeline successfully distinguished estrogen receptor-positive (ER\u207a) and estrogen receptor-negative (ER\n                    <jats:sup>\u2212<\/jats:sup>\n                    ) breast cancer subtypes. The model successfully identified critical substructures in docetaxel, an FDA-approved therapy, and triptolide, which is currently undergoing clinical evaluation for breast cancer. These findings are consistent with established structure-activity relationship (SAR) data. Overall, this study presents a comprehensive evaluation framework and underscores the importance of carefully selecting loss functions and feature representations when developing robust and interpretable drug-ranking systems.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0345854","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:35:26Z","timestamp":1786642526000},"page":"e0345854","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Shedding light on neural learning to rank models for anticancer drug prioritization"],"prefix":"10.1371","volume":"21","author":[{"given":"Faraz","family":"Sarmeili","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benyamin","family":"Ghahremani-Nezhad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Khalilpour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2135-8864","authenticated-orcid":true,"given":"Karim","family":"Abbasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rassoul","family":"Dinarvand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9835-4493","authenticated-orcid":true,"given":"Hamid R.","family":"Rabiee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"issue":"7","key":"pone.0345854.ref001","doi-asserted-by":"crossref","first-page":"1336","DOI":"10.1002\/ijc.35278","article-title":"The GLOBOCAN 2022 cancer estimates: Data sources, methods, and a snapshot of the cancer burden worldwide","volume":"156","author":"AM Filho","year":"2025","journal-title":"Int J Cancer"},{"key":"pone.0345854.ref002","first-page":"119","article-title":"The role of artificial intelligence in enhancing small molecule-based cancer treatments","volume-title":"Small molecules for cancer treatment","author":"S Babu","year":"2025"},{"issue":"3","key":"pone.0345854.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0317240","article-title":"Advances in analytical approaches for background parenchymal enhancement in predicting breast tumor response to neoadjuvant chemotherapy: A systematic review","volume":"20","author":"J Thomas","year":"2025","journal-title":"PLoS One"},{"issue":"1","key":"pone.0345854.ref004","first-page":"5837235","article-title":"The adaptive complexity of cancer","volume":"2018","author":"Y Derbal","year":"2018","journal-title":"BioMed Research International"},{"issue":"1","key":"pone.0345854.ref005","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/s41568-024-00763-x","article-title":"The present and future of the Cancer Dependency Map","volume":"25","author":"R Arafeh","year":"2025","journal-title":"Nat Rev Cancer"},{"issue":"1","key":"pone.0345854.ref006","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/s41392-021-00572-w","article-title":"Small molecules in targeted cancer therapy: advances, challenges, and future perspectives","volume":"6","author":"L Zhong","year":"2021","journal-title":"Signal Transduct Target Ther"},{"issue":"4","key":"pone.0345854.ref007","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1097\/PAI.0000000000000891","article-title":"What to Expect From the New ASCO\/CAP Guideline Recommendations for Hormone Receptor Testing in Breast Cancer: A National Reference Laboratory Experience","volume":"29","author":"J Mahlow","year":"2021","journal-title":"Appl Immunohistochem Mol Morphol"},{"issue":"1","key":"pone.0345854.ref008","doi-asserted-by":"crossref","first-page":"34","DOI":"10.4132\/jptm.2019.11.03","article-title":"HER2 status in breast cancer: changes in guidelines and complicating factors for interpretation","volume":"54","author":"S Ahn","year":"2020","journal-title":"J Pathol Transl Med"},{"issue":"6","key":"pone.0345854.ref009","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.15445","article-title":"Costs of drug development and research and development intensity in the US, 2000-2018","volume":"7","author":"A Sertkaya","year":"2024","journal-title":"JAMA Network Open"},{"issue":"11","key":"pone.0345854.ref010","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1038\/d41573-021-00190-9","article-title":"Clinical development times for innovative drugs","volume":"21","author":"DG Brown","year":"2022","journal-title":"Nat Rev Drug Discov"},{"issue":"1","key":"pone.0345854.ref011","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/nrd.2018.168","article-title":"Drug repurposing: progress, challenges and recommendations","volume":"18","author":"S Pushpakom","year":"2019","journal-title":"Nat Rev Drug Discov"},{"key":"pone.0345854.ref012","doi-asserted-by":"crossref","first-page":"100121","DOI":"10.1016\/j.metop.2021.100121","article-title":"Drug repurposing in COVID-19: A review with past, present and future","volume":"12","author":"K Srivastava","year":"2021","journal-title":"Metabol Open"},{"key":"pone.0345854.ref013","doi-asserted-by":"crossref","first-page":"1086097","DOI":"10.3389\/fmed.2023.1086097","article-title":"Deep learning methods for drug response prediction in cancer: Predominant and emerging trends","volume":"10","author":"A Partin","year":"2023","journal-title":"Front Med (Lausanne)"},{"issue":"1","key":"pone.0345854.ref014","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1093\/bib\/bbz171","article-title":"Deep learning for drug response prediction in cancer","volume":"22","author":"D Baptista","year":"2021","journal-title":"Brief Bioinform"},{"issue":"6","key":"pone.0345854.ref015","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab294","article-title":"Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models","volume":"22","author":"H Sharifi-Noghabi","year":"2021","journal-title":"Brief Bioinform"},{"issue":"1","key":"pone.0345854.ref016","article-title":"A cross-study analysis of drug response prediction in cancer cell lines","volume":"23","author":"F Xia","year":"2022","journal-title":"Brief Bioinform"},{"issue":"20","key":"pone.0345854.ref017","doi-asserted-by":"crossref","first-page":"4034","DOI":"10.1002\/sim.9491","article-title":"Deep reinforcement learning for personalized treatment recommendation","volume":"41","author":"M Liu","year":"2022","journal-title":"Stat Med"},{"issue":"11","key":"pone.0345854.ref018","doi-asserted-by":"crossref","first-page":"3154","DOI":"10.1109\/JBHI.2020.3004663","article-title":"Q-Rank: Reinforcement Learning for Recommending Algorithms to Predict Drug Sensitivity to Cancer Therapy","volume":"24","author":"S Daoud","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"issue":"2","key":"pone.0345854.ref019","article-title":"SRDFM: Siamese Response Deep Factorization Machine to improve anti-cancer drug recommendation","volume":"23","author":"R Su","year":"2022","journal-title":"Brief Bioinform"},{"issue":"22","key":"pone.0345854.ref020","doi-asserted-by":"crossref","first-page":"3907","DOI":"10.1093\/bioinformatics\/bty452","article-title":"Predicting Cancer Drug Response using a Recommender System","volume":"34","author":"C Suphavilai","year":"2018","journal-title":"Bioinformatics"},{"issue":"16","key":"pone.0345854.ref021","doi-asserted-by":"crossref","first-page":"2808","DOI":"10.1093\/bioinformatics\/bty132","article-title":"Kernelized rank learning for personalized drug recommendation","volume":"34","author":"X He","year":"2018","journal-title":"Bioinformatics"},{"issue":"1","key":"pone.0345854.ref022","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/TCBB.2018.2848908","article-title":"Drug Selection via Joint Push and Learning to Rank","volume":"17","author":"Y He","year":"2020","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"pone.0345854.ref023","doi-asserted-by":"crossref","unstructured":"Cao Z, Qin T, Liu T-Y, Tsai M-F, Li H. Learning to rank: from pairwise approach to listwise approach. In: Proceedings of the 24th International Conference on Machine Learning, 2007.","DOI":"10.1145\/1273496.1273513"},{"key":"pone.0345854.ref024","doi-asserted-by":"crossref","first-page":"108312","DOI":"10.1016\/j.compbiomed.2024.108312","article-title":"ITNR: Inversion Transformer-based Neural Ranking for cancer drug recommendations","volume":"172","author":"S Sotudian","year":"2024","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0345854.ref025","article-title":"Matching anticancer compounds and tumor cell lines by neural networks with ranking loss","volume":"4","author":"P Prasse","year":"2022","journal-title":"NAR Genom Bioinform"},{"issue":"12","key":"pone.0345854.ref026","doi-asserted-by":"crossref","first-page":"4797","DOI":"10.1021\/acs.molpharmaceut.9b00520","article-title":"Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders","volume":"16","author":"M Manica","year":"2019","journal-title":"Mol Pharm"},{"issue":"10","key":"pone.0345854.ref027","doi-asserted-by":"crossref","first-page":"4071","DOI":"10.1021\/acs.jcim.3c01060","article-title":"Improving Anticancer Drug Selection and Prioritization via Neural Learning to Rank","volume":"64","author":"V Dey","year":"2024","journal-title":"J Chem Inf Model"},{"key":"pone.0345854.ref028","article-title":"Neuralndcg: Direct optimisation of a ranking metric via differentiable relaxation of sorting","author":"P Pobrotyn","year":"2021","journal-title":"arXiv preprint"},{"key":"pone.0345854.ref029","first-page":"193","article-title":"Learning to Rank with Nonsmooth Cost Functions","author":"CJC Burges","year":"2007","journal-title":"Advances in Neural Information Processing Systems 19"},{"key":"pone.0345854.ref030","doi-asserted-by":"crossref","unstructured":"Wang X, Li C, Golbandi N, Bendersky M, Najork M. The LambdaLoss Framework for Ranking Metric Optimization. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018. 1313\u201322. https:\/\/doi.org\/10.1145\/3269206.3271784","DOI":"10.1145\/3269206.3271784"},{"key":"pone.0345854.ref031","doi-asserted-by":"crossref","unstructured":"Heuss M, de Rijke M, Anand A. RankingSHAP--Listwise Feature Attribution Explanations for Ranking Models. In: 2024. https:\/\/doi.org\/arXiv:2403.16085","DOI":"10.1145\/3726302.3729971"},{"key":"pone.0345854.ref032","article-title":"RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank","author":"T Chowdhury","year":"2024","journal-title":"arXiv preprint"},{"issue":"7","key":"pone.0345854.ref033","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1021\/ci500232g","article-title":"Atom pair 2D-fingerprints perceive 3D-molecular shape and pharmacophores for very fast virtual screening of ZINC and GDB-17","volume":"54","author":"M Awale","year":"2014","journal-title":"J Chem Inf Model"},{"key":"pone.0345854.ref034","article-title":"A Python library for efficient computation of molecular fingerprints","author":"M Szafarczyk","year":"2024","journal-title":"arXiv preprint"},{"issue":"1","key":"pone.0345854.ref035","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s13321-024-00830-3","article-title":"Effectiveness of molecular fingerprints for exploring the chemical space of natural products","volume":"16","author":"D Boldini","year":"2024","journal-title":"J Cheminform"},{"key":"pone.0345854.ref036","first-page":"4","article-title":"Rdkit documentation","volume":"1","author":"G Landrum","year":"2013","journal-title":"Release"},{"key":"pone.0345854.ref037","doi-asserted-by":"crossref","first-page":"606668","DOI":"10.3389\/fphar.2020.606668","article-title":"Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning","volume":"11","author":"L Xie","year":"2020","journal-title":"Front Pharmacol"},{"issue":"6","key":"pone.0345854.ref038","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab312","article-title":"A gentle introduction to understanding preclinical data for cancer pharmaco-omic modeling","volume":"22","author":"C Piyawajanusorn","year":"2021","journal-title":"Brief Bioinform"},{"key":"pone.0345854.ref039","doi-asserted-by":"crossref","unstructured":"Burges C, Shaked T, Renshaw E, Lazier A, Deeds M, Hamilton N, et al. Learning to rank using gradient descent. In: Proceedings of the 22nd international conference on Machine learning - ICML \u201905, 2005. 89\u201396. https:\/\/doi.org\/10.1145\/1102351.1102363","DOI":"10.1145\/1102351.1102363"},{"key":"pone.0345854.ref040","first-page":"324","article-title":"Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons","volume":"39","author":"RA Bradley","year":"1952","journal-title":"Biometrika"},{"key":"pone.0345854.ref041","unstructured":"Grover A, Wang E, Zweig A, Ermon S. Stochastic optimization of sorting networks via continuous relaxations. In: 2019. https:\/\/arxiv.org\/abs\/1903.08850"},{"issue":"2","key":"pone.0345854.ref042","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1214\/aoms\/1177703591","article-title":"A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices","volume":"35","author":"R Sinkhorn","year":"1964","journal-title":"Ann Math Statist"},{"key":"pone.0345854.ref043","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0345854.ref044","doi-asserted-by":"crossref","unstructured":"Rozemberczki B, Watson L, Bayer P, Yang H-T, Kiss O, Nilsson S, et al. The Shapley Value in Machine Learning. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022. 5572\u20139. https:\/\/doi.org\/10.24963\/ijcai.2022\/778","DOI":"10.24963\/ijcai.2022\/778"},{"key":"pone.0345854.ref045","unstructured":"Singh J, Wang Z, Kohsla M, Anand A. Valid explanations for learning to rank models. In: 2020. https:\/\/arxiv.org\/abs\/2004.13972"},{"key":"pone.0345854.ref046","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gku1003","article-title":"STRING v10: protein-protein interaction networks, integrated over the tree of life","volume":"43","author":"D Szklarczyk","year":"2015","journal-title":"Nucleic Acids Res"},{"issue":"11","key":"pone.0345854.ref047","doi-asserted-by":"crossref","first-page":"1210","DOI":"10.1158\/2159-8290.CD-15-0235","article-title":"Harnessing Connectivity in a Large-Scale Small-Molecule Sensitivity Dataset","volume":"5","author":"B Seashore-Ludlow","year":"2015","journal-title":"Cancer Discov"},{"issue":"2","key":"pone.0345854.ref048","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1038\/nchembio.1986","article-title":"Correlating chemical sensitivity and basal gene expression reveals mechanism of action","volume":"12","author":"MG Rees","year":"2016","journal-title":"Nat Chem Biol"},{"issue":"2","key":"pone.0345854.ref049","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1038\/s43018-019-0018-6","article-title":"Discovering the anti-cancer potential of non-oncology drugs by systematic viability profiling","volume":"1","author":"SM Corsello","year":"2020","journal-title":"Nat Cancer"},{"issue":"12","key":"pone.0345854.ref050","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1038\/nbt.2877","article-title":"A community effort to assess and improve drug sensitivity prediction algorithms","volume":"32","author":"JC Costello","year":"2014","journal-title":"Nat Biotechnol"},{"key":"pone.0345854.ref051","doi-asserted-by":"crossref","first-page":"11","DOI":"10.2165\/1163018-S0-000000000-00000","article-title":"Role of erlotinib in the treatment of non-small cell lung cancer: clinical outcomes in wild-type epidermal growth factor receptor patients","author":"B Piperdi","year":"2012","journal-title":"Drugs"},{"issue":"6","key":"pone.0345854.ref052","doi-asserted-by":"crossref","first-page":"1307","DOI":"10.1158\/1078-0432.CCR-15-2266","article-title":"FDA Approval of Gefitinib for the Treatment of Patients with Metastatic EGFR Mutation-Positive Non-Small Cell Lung Cancer","volume":"22","author":"D Kazandjian","year":"2016","journal-title":"Clin Cancer Res"},{"issue":"5","key":"pone.0345854.ref053","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1016\/j.jtho.2019.12.126","article-title":"Afatinib for the Treatment of NSCLC Harboring Uncommon EGFR Mutations: A Database of 693 Cases","volume":"15","author":"JC-H Yang","year":"2020","journal-title":"J Thorac Oncol"},{"issue":"1","key":"pone.0345854.ref054","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1056\/NEJMoa1412690","article-title":"Improved overall survival in melanoma with combined dabrafenib and trametinib","volume":"372","author":"C Robert","year":"2015","journal-title":"N Engl J Med"},{"key":"pone.0345854.ref055","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1146\/annurev-biochem-061516-044916","article-title":"Mechanisms of Deubiquitinase Specificity and Regulation","volume":"86","author":"TET Mevissen","year":"2017","journal-title":"Annu Rev Biochem"},{"issue":"3","key":"pone.0345854.ref056","doi-asserted-by":"crossref","first-page":"2107","DOI":"10.3390\/ijms24032107","article-title":"The Critical Impact of Sphingolipid Metabolism in Breast Cancer Progression and Drug Response","volume":"24","author":"PA Corsetto","year":"2023","journal-title":"Int J Mol Sci"},{"key":"pone.0345854.ref057","doi-asserted-by":"crossref","first-page":"1361351","DOI":"10.3389\/fimmu.2024.1361351","article-title":"CLEC7A regulates M2 macrophages to suppress the immune microenvironment and implies poorer prognosis of glioma","volume":"15","author":"J Wang","year":"2024","journal-title":"Front Immunol"},{"key":"pone.0345854.ref058","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkac963","article-title":"KEGG for taxonomy-based analysis of pathways and genomes","volume":"51","author":"M Kanehisa","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"11","key":"pone.0345854.ref059","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.1038\/s41592-023-02014-7","article-title":"Extending support for mouse data in the Molecular Signatures Database (MSigDB)","volume":"20","author":"AS Castanza","year":"2023","journal-title":"Nat Methods"},{"key":"pone.0345854.ref060","doi-asserted-by":"crossref","first-page":"102760","DOI":"10.1016\/j.ceca.2023.102760","article-title":"Calcium signal modulation in breast cancer aggressiveness","volume":"113","author":"C Bantsimba-Malanda","year":"2023","journal-title":"Cell Calcium"},{"issue":"5","key":"pone.0345854.ref061","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1007\/s13402-022-00694-5","article-title":"Cholesterol homeostasis and cancer: a new perspective on the low-density lipoprotein receptor","volume":"45","author":"J Gu","year":"2022","journal-title":"Cell Oncol (Dordr)"},{"issue":"1","key":"pone.0345854.ref062","doi-asserted-by":"crossref","first-page":"47","DOI":"10.20883\/medical.e43","article-title":"A brief history of taxol","volume":"83","author":"J \u017bwawiak","year":"2014","journal-title":"Journal of Medical Science"},{"issue":"1","key":"pone.0345854.ref063","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1186\/s13020-021-00525-z","article-title":"Therapeutic potential of triptolide in autoimmune diseases and strategies to reduce its toxicity","volume":"16","author":"Y Cheng","year":"2021","journal-title":"Chin Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:35:35Z","timestamp":1786642535000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0345854"}},"subtitle":[],"editor":[{"given":"Khalid","family":"Raza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":63,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0345854","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}