Disease-level drug approval forecasting from trial-agnostic public data

Abstract

Drug development is an expensive and lengthy process requiring developers to select drugs for human trials and diseases to target. Computational tools that can estimate before testing which drug-disease candidates are most likely to reach FDA approval could reduce development time and costs through early program advancement and disease prioritization. Yet existing approaches predict outcomes at a single level or stage or do not distinguish between disease outcomes for the same drug. We ask (1) whether FDA approval can be forecast for a drug-disease pair using only pre-clinical trial information, and (2) whether these forecasts can help prioritize diseases for the same drug. We built a cohort of 14,134 drug-disease pairs by reconstructing programs from ClinicalTrials.gov, extracting disease-level approvals from FDA label documentation, and enriching each pair with molecular, disease, ADMET, target, and pathway features. We divided the cohort into pre- and post-2019 programs and trained a classifier on pre-2019 data to predict FDA approval. On the post-2019 cohort (2,637 programs), the model would have prioritized a program that ultimately gained approval over one that did not approximately three out of four times. For drugs tested across multiple diseases, selecting the model's highest-ranked disease would have identified an ultimately approved disease 61.3% of the time, compared with 40.7% under random selection. These results show that public pre-trial information contains signal for forecasting FDA approval at the drug-disease level and can help prioritize diseases for the same drug. We provide a public web tool for SMILES- and ICD-10-based drug-disease approval forecasting.

Phylogeny-agnostic strain-level prediction of phage–host interactions from genomes using machine learning
Avery J. C. Noonan, Lucas Moriniere, Edwin O. Rivera-López +8
Nature Microbiology29 Sep 2026Peer-reviewedCC BY-NC-ND 4.0Full text1 citedEcologyPMC
MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models
Robert Moore, Frank Agayie-Ntim, Lindsey B. Crawford +5
arXiv2 Sep 2026PreprintCC BY-SA 4.0Full textGeneral biologyarXiv
Stock-level volatility forecasting using machine learning: A comparative study of GARCH, Random Forest, LSTM, and GRU on US Equities
R V Pragadeeshwaran, R Tarun Narayanan, R M Bhavadharini
PLOS One29 Oct 2026Peer-reviewedCC BYFull textNeuroscience StatisticsPLOSEurope PMCPMC
Public Health Pharmacology: a framework for population-level immunologic monitoring (PLIM) to optimize vaccine performance in Africa
Ahmed Adebowale Adedeji, Aminah Adeola Adedeji, Einas Mohammed ElHabibi Adam +7
Frontiers in public health2 Oct 2026Peer-reviewedCC BYFull textImmunologyEurope PMCCrossref
Survey of public health education combined with intelligent prescription intervention system on antibiotic use in the county-level hospitals
Xiaoyan Xie, Lei Yang, Xiaohui Yue +2
Frontiers in public health30 Sep 2026Peer-reviewedCC BYFull textMicrobiologyEurope PMCCrossref

Cite

BibTeX RIS

BibTeX

@misc{townsley2026diseaselevel,
  title = {{Disease-level drug approval forecasting from trial-agnostic public data}},
  author = {Samir Townsley and Pagkratios Tagkopoulos and Ilias Tagkopoulos},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.14013},
  eprint = {2610.14013},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.14013},
  note = {CC BY-NC-ND 4.0},
}

RIS

TY  - UNPB
TI  - Disease-level drug approval forecasting from trial-agnostic public data
AU  - Samir Townsley
AU  - Pagkratios Tagkopoulos
AU  - Ilias Tagkopoulos
PY  - 2026
DA  - 2026/10/01
PB  - arXiv
DO  - 10.48550/arxiv.2610.14013
UR  - https://arxiv.org/abs/2610.14013
AB  - Drug development is an expensive and lengthy process requiring developers to select drugs for human trials and diseases to target. Computational tools that can estimate before testing which drug-disease candidates are most likely to reach FDA approval could reduce development time and costs through early program advancement and disease prioritization. Yet existing approaches predict outcomes at a single level or stage or do not distinguish between disease outcomes for the same drug. We ask (1) whether FDA approval can be forecast for a drug-disease pair using only pre-clinical trial information, and (2) whether these forecasts can help prioritize diseases for the same drug. We built a cohort of 14,134 drug-disease pairs by reconstructing programs from ClinicalTrials.gov, extracting disease-level approvals from FDA label documentation, and enriching each pair with molecular, disease, ADMET, target, and pathway features. We divided the cohort into pre- and post-2019 programs and trained a classifier on pre-2019 data to predict FDA approval. On the post-2019 cohort (2,637 programs), the model would have prioritized a program that ultimately gained approval over one that did not approximately three out of four times. For drugs tested across multiple diseases, selecting the model's highest-ranked disease would have identified an ultimately approved disease 61.3% of the time, compared with 40.7% under random selection. These results show that public pre-trial information contains signal for forecasting FDA approval at the drug-disease level and can help prioritize diseases for the same drug. We provide a public web tool for SMILES- and ICD-10-based drug-disease approval forecasting.
ER  -

Abstract

Related

Cite