{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:53:09Z","timestamp":1791175989817,"version":"4.1.0"},"posted":{"date-parts":[[2026,9,29]]},"group-title":"Bioinformatics","reference-count":46,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"id":[{"id":"https:\/\/ror.org\/02qwkrw10","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/05xj56w78","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Identifying which target-indication (T-I) hypotheses can translate into clinical success remains a central challenge in drug discovery. We present PRIORITI (Prospective Rationale-Informed Outcome Reasoning for Integrated Target-indication Intelligence), a leakage-resistant framework that separates upstream biological evidence synthesis from outcome prediction. Given only a target gene and disease indication, a domain-instructed large language model (LLM) synthesizes drug-agnostic human genetics across prespecified channels. These evidence were embedded and combined with static entity context derived from gene summaries and disease definitions. The resulting representation is used to fit a supervised model trained on 6,784 temporally curated historical T-I outcomes, which is one of the largest cohorts assembled for this task. On a held-out historical test set of 1,696 T-I pairs, PRIORITI achieved a ROC-AUC of 0.883 and an expected calibration error (ECE) of 0.023, outperforming both a static target and indication context baseline and a human-curated genetic-evidence reference. On a strictly post-cutoff out-of-time benchmark of 765 T-I pairs, the largest such evaluation cohort reported to date, performance remained robust, with ROC-AUC 0.817, PR-AUC 0.357 and ECE 0.044, exceeding static target and indication context baseline and direct zero-shot LLM forecasting. A label-blinded LLM-based explainer further converted locked predictions into auditable prioritization rationales. Together, PRIORITI provides a calibrated, biology-first probability together with decision-oriented rationales for T-I prioritization before downstream translational investment.<\/jats:p>","DOI":"10.64898\/2026.09.24.754137","type":"posted-content","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:35:23Z","timestamp":1790750123000},"source":"Crossref","is-referenced-by-count":0,"title":["Biological rationales from language models enable leakage-resistant forecasts of target-indication success"],"prefix":"10.64898","author":[{"given":"Wanheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Molecular Oncology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bissan","family":"Al-lazikani","sequence":"additional","affiliation":[{"name":"Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiling","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Gastrointestinal Medical Oncology, Division of Cancer Medicine, MD Anderson Cancer Center, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Kopetz","sequence":"additional","affiliation":[{"name":"Department of Gastrointestinal Medical Oncology, Division of Cancer Medicine, MD Anderson Cancer Center, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lang","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Interdisciplinary Oncology and Department of Genetics, LSU-LCMC Health Cancer Center, School of Medicine, Louisiana State University Health Sciences Center, New Orleans, Louisiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingxin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, PA 19104, USA"},{"name":"Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8400-1785","authenticated-orcid":false,"given":"Chong","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA"},{"name":"Institute for Data Science in Oncology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026100421400958000_2026.09.24.754137v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/nrd3078"},{"key":"2026100421400958000_2026.09.24.754137v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.2786"},{"key":"2026100421400958000_2026.09.24.754137v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhealeco.2016.01.012"},{"key":"2026100421400958000_2026.09.24.754137v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1120"},{"key":"2026100421400958000_2026.09.24.754137v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/nrd.2018.14"},{"key":"2026100421400958000_2026.09.24.754137v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAA1027"},{"key":"2026100421400958000_2026.09.24.754137v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3314"},{"key":"2026100421400958000_2026.09.24.754137v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07316-0"},{"key":"2026100421400958000_2026.09.24.754137v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/nrd4051"},{"key":"2026100421400958000_2026.09.24.754137v1.10","doi-asserted-by":"crossref","unstructured":"Pi\u00f1ero, J. et al. DisGeNET: a comprehensive platform integrating information on human disease-associated genes and variants. Nucleic Acids Res. gkw943 (2016).","DOI":"10.1093\/nar\/gkw943"},{"key":"2026100421400958000_2026.09.24.754137v1.11","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw1072"},{"key":"2026100421400958000_2026.09.24.754137v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-05116-5"},{"key":"2026100421400958000_2026.09.24.754137v1.13","doi-asserted-by":"crossref","unstructured":"Guney, E. , Menche, J. , Vidal, M. & Bar\u00e1basi, A.-L . Network-based in silico drug efficacy screening. Nat. Commun. 7, 10331 (2016).","DOI":"10.1038\/ncomms10331"},{"key":"2026100421400958000_2026.09.24.754137v1.14","doi-asserted-by":"crossref","unstructured":"Fu, T. , Huang, K. , Xiao, C. , Glass, L. M. & Sun, J . Hint: Hierarchical interaction network for clinical-trial-outcome predictions. Patterns 3, (2022).","DOI":"10.1016\/j.patter.2022.100445"},{"key":"2026100421400958000_2026.09.24.754137v1.15","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1016\/j.chembiol.2016.07.023","article-title":"A data-driven approach to predicting successes and failures of clinical trials","volume":"23","year":"2016","journal-title":"Cell Chem. Biol"},{"key":"2026100421400958000_2026.09.24.754137v1.16","doi-asserted-by":"crossref","unstructured":"Lo, A. W. , Siah, K. W. & Wong, C. H . Machine Learning with Statistical Imputation for Predicting Drug Approvals. vol. 60 (SSRN, 2019).","DOI":"10.1162\/99608f92.5c5f0525\/2a3160be"},{"key":"2026100421400958000_2026.09.24.754137v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"2026100421400958000_2026.09.24.754137v1.18","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2026100421400958000_2026.09.24.754137v1.19","unstructured":"Carlini, N. et al. Extracting training data from large language models. in 30th USENIX security symposium (USENIX Security 21) 2633\u20132650 (2021)."},{"key":"2026100421400958000_2026.09.24.754137v1.20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.14425"},{"key":"2026100421400958000_2026.09.24.754137v1.21","unstructured":"Carlini, N. , et al. Quantifying memorization across neural language models. In The Eleventh International Conference on Learning Representations (2022)."},{"key":"2026100421400958000_2026.09.24.754137v1.22","doi-asserted-by":"crossref","unstructured":"Geng, J. et al. A survey of confidence estimation and calibration in large language models. in Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) 6577\u20136595 (2024).","DOI":"10.18653\/v1\/2024.naacl-long.366"},{"key":"2026100421400958000_2026.09.24.754137v1.23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.06505"},{"key":"2026100421400958000_2026.09.24.754137v1.24","unstructured":"Ke, G. et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, (2017)."},{"key":"2026100421400958000_2026.09.24.754137v1.25","unstructured":"Prokhorenkova, L. , Gusev, G. , Vorobev, A. , Dorogush, A. V. & Gulin, A . CatBoost: unbiased boosting with categorical features. Adv. Neural Inf. Process. Syst. 31, (2018)."},{"key":"2026100421400958000_2026.09.24.754137v1.26","first-page":"26577","article-title":"Better by default: Strong pre-tuned mlps and boosted trees on tabular data","volume":"37","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2026100421400958000_2026.09.24.754137v1.27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.18164"},{"key":"2026100421400958000_2026.09.24.754137v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08328-6"},{"key":"2026100421400958000_2026.09.24.754137v1.29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.08667"},{"key":"2026100421400958000_2026.09.24.754137v1.30","doi-asserted-by":"crossref","unstructured":"Yao, J. , Hurle, M. R. , Nelson, M. R. & Agarwal, P . Predicting clinically promising therapeutic hypotheses using tensor factorization. BMC Bioinformatics 20, 69 (2019).","DOI":"10.1186\/s12859-019-2664-1"},{"key":"2026100421400958000_2026.09.24.754137v1.31","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3008"},{"key":"2026100421400958000_2026.09.24.754137v1.32","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.0000077913.60364.D2"},{"key":"2026100421400958000_2026.09.24.754137v1.33","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.0000124490.27666.B2"},{"key":"2026100421400958000_2026.09.24.754137v1.34","doi-asserted-by":"crossref","unstructured":"Anderer, S. FDA approves tirzepatide as first drug for obstructive sleep apnea. (2025).","DOI":"10.1001\/jama.2024.28055"},{"key":"2026100421400958000_2026.09.24.754137v1.35","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2404881"},{"key":"2026100421400958000_2026.09.24.754137v1.36","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201807-1326ST"},{"key":"2026100421400958000_2026.09.24.754137v1.37","doi-asserted-by":"crossref","unstructured":"Lo, A. W. , Siah, K. W. & Wong, C. H . Machine Learning with Statistical Imputation for Predicting Drug Approvals. vol. 60 (SSRN, 2019).","DOI":"10.1162\/99608f92.5c5f0525\/2a3160be"},{"key":"2026100421400958000_2026.09.24.754137v1.38","doi-asserted-by":"crossref","first-page":"e0253614","DOI":"10.1371\/journal.pone.0253614","article-title":"An integrative network-based approach for drug target indication expansion","volume":"16","year":"2021","journal-title":"PloS One"},{"key":"2026100421400958000_2026.09.24.754137v1.39","doi-asserted-by":"crossref","unstructured":"Bieske, L. , Zinner, M. , Dahlhausen, F. & Tr\u00fcbel, H . Trends, challenges, and success factors in pharmaceutical portfolio management: cognitive biases in decision-making and their mitigating measures. Drug Discov. Today 28, 103734 (2023).","DOI":"10.1016\/j.drudis.2023.103734"},{"key":"2026100421400958000_2026.09.24.754137v1.40","unstructured":"Bedi, S. et al. Holistic evaluation of large language models for medical tasks with MedHELM. Nat. Med. 1\u20139 (2026)."},{"key":"2026100421400958000_2026.09.24.754137v1.41","unstructured":"Packer, C. , et al. MemGPT: towards LLMs as operating systems. https:\/\/par.nsf.gov\/servlets\/purl\/10524107 (2023)."},{"key":"2026100421400958000_2026.09.24.754137v1.42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"2026100421400958000_2026.09.24.754137v1.43","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume":"36","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2026100421400958000_2026.09.24.754137v1.44","unstructured":"Lipscomb, C. E . Medical subject headings (MeSH). Bull. Med. Libr. Assoc. 88, 265 (2000)."},{"key":"2026100421400958000_2026.09.24.754137v1.45","doi-asserted-by":"crossref","unstructured":"Xin, J. et al. High-performance web services for querying gene and variant annotation. Genome Biol. 17, 91 (2016).","DOI":"10.1186\/s13059-016-0953-9"},{"key":"2026100421400958000_2026.09.24.754137v1.46","doi-asserted-by":"crossref","unstructured":"Chicco, D. & Jurman, G . The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21, 6 (2020).","DOI":"10.1186\/s12864-019-6413-7"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.24.754137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:40:22Z","timestamp":1791175222000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.24.754137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":46,"URL":"https:\/\/doi.org\/10.64898\/2026.09.24.754137","relation":{},"subject":[],"published":{"date-parts":[[2026,9,29]]},"subtype":"preprint"}}