Prediction of Clinical Trials Outcomes Based on Target Choice and Clinical Trial Design with Multi‐Modal Artificial Intelligence
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Drug discovery and development is a notoriously risky process with high failure rates at every stage, including disease modeling, target discovery, hit discovery, lead optimization, preclinical development, human safety, and efficacy studies. Accurate prediction of clinical trial outcomes may help significantly improve the efficiency of this process by prioritizing therapeutic programs that are more likely to succeed in clinical trials and ultimately benefit patients. Here, we describe inClinico, a transformer‐based artificial intelligence software platform designed to predict the outcome of phase II clinical trials. The platform combines an ensemble of clinical trial outcome prediction engines that leverage generative artificial intelligence and multimodal data, including omics, text, clinical trial design, and small molecule properties. inClinico was validated in retrospective, quasi‐prospective, and prospective validation studies internally and with pharmaceutical companies and financial institutions. The platform achieved 0.88 receiver operating characteristic area under the curve in predicting the phase II to phase III transition on a quasi‐prospective validation dataset. The first prospective predictions were made and placed on date‐stamped preprint servers in 2016. To validate our model in a real‐world setting, we published forecasted outcomes for several phase II clinical trials achieving 79% accuracy for the trials that have read out. We also present an investment application of inClinico using date stamped virtual trading portfolio demonstrating 35% 9‐month return on investment.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
From local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551 · cited 2×
“Figure 2 The features that impacted the probability of phase II clinical trial success the most as per SHAP values.(31,32) Full list of features and the descriptions are summarized in Table S2.”
BackgroundMethodLarian Studios Dev Team (2024) · doi:10.1145/3292500.3330701 · Cited by 8,618
ChEMBL: a large-scale bioactivity database for drug discovery
Gaulton, A., Bellis, L. J., Bento, A. P., Chambers, J., Davies, M., Hersey, A., Light, Y., McGlinchey, S., Michalovich, D., Al-Lazikani, B., et al. (2012) · Nucleic Acids Research · doi:10.1093/nar/gkr777 · Cited by 4,382
Can the pharmaceutical industry reduce attrition rates?
Kola, I., & Landis, J. (2004) · Nature Reviews Drug Discovery · doi:10.1038/nrd1470 · Cited by 4,167
Clinical development success rates for investigational drugs
Hay, M., Thomas, D. W., Craighead, J. L., Economides, C., & Rosenthal, J. (2014) · Nature Biotechnology · doi:10.1038/nbt.2786 · Cited by 2,536
Diagnosing the decline in pharmaceutical R&D efficiency
Scannell, J. W., Blanckley, A., Boldon, H., & Warrington, B. (2012) · Nature Reviews Drug Discovery · doi:10.1038/nrd3681 · Cited by 1,981
Artificial intelligence in drug discovery and development
Paul, D., Sanap, G., Shenoy, S., Kalyane, D., Kalia, K., & Tekade, R. K. (2021) · Drug Discovery Today · doi:10.1016/j.drudis.2020.10.010 · Cited by 1,695
Heterogeneous Graph Transformer
Hu, Z., Dong, Y., Wang, K., & Sun, Y. (2020) · Proceedings of The Web Conference 2020 · doi:10.1145/3366423.3380027 · Cited by 1,646
The ClinicalTrials.gov Results Database — Update and Key Issues
Zarin, D. A., Tse, T., Williams, R. J., Califf, R. M., & Ide, N. C. (2011) · New England Journal of Medicine · doi:10.1056/nejmsa1012065 · Cited by 838
Applications of Deep Learning in Biomedicine
Mamoshina, P., Vieira, A., Lane, E., & Zhavoronkov, A. (2016) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.5b00982 · Cited by 701
Self-citationAliper, A., Plis, S., Artemov, A., Ulloa, A., Mamoshina, P., & Zhavoronkov, A. (2016) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.6b00248 · Cited by 610
Self-citationRavi, R., Noonan, K. A., Pham, V., Bedi, R., Zhavoronkov, A., Ozerov, I. V., Makarev, E., V. Artemov, A., Wysocki, P. T., Mehra, R., et al. (2018) · Nature Communications · doi:10.1038/s41467-017-02696-6 · Cited by 325
Self-citationA Data-Driven Approach to Predicting Successes and Failures of Clinical Trials
Gayvert, K. M., Madhukar, N. S., & Elemento, O. (2016) · Cell chemical biology · doi:10.1016/j.chembiol.2016.07.023 · Cited by 310 · cited 1×
“,(11) do not utilize clinical trial timestamps and do not account for information leaks that come from the results of future trials.(9,12,13) In order to extinguish this bias during retrospective validation, we trained the models and optimized model hyperparameters on the trials that started before 2018 and validated…”
Design of efficient computational workflows for in silico drug repurposing
Vanhaelen, Q., Mamoshina, P., Aliper, A. M., Artemov, A., Lezhnina, K., Ozerov, I., Labat, I., & Zhavoronkov, A. (2017) · Drug Discovery Today · doi:10.1016/j.drudis.2016.09.019 · Cited by 150
Self-citation
Cited by
Artificial intelligence in drug development
Zhang, K., Yang, X., Wang, Y., Yu, Y., Huang, N., Li, G., Li, X., Wu, J. C., & Yang, S. (2025) · Nature Medicine · doi:10.1038/s41591-024-03434-4 · Cited by 498
A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models
Ren, F., Aliper, A., Chen, J., Zhao, H., Rao, S., Kuppe, C., Ozerov, I. V., Zhang, M., Witte, K., Kruse, C., et al. (2025) · Nature Biotechnology · doi:10.1038/s41587-024-02143-0 · Cited by 348
“Given the scarcity of anti-fibrotic therapies for IPF or CKD, we used our published generative AI pipeline 14,15,40–42 to address this clinical need.”
Self-citationXu, Z., Ren, F., Wang, P., Cao, J., Tan, C., Ma, D., Zhao, L., Dai, J., Ding, Y., Fang, H., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03743-2 · Cited by 180
“…have demonstrated proof-of-concept innovation and potential to accelerate and decrease costs across all stages of pharmaceutical research and development by facilitating disease-associated target prioritization 3–5 , compound design and optimization 6–10 , and clinical trial performance 11–15 .”
Self-citationEmerging pharmacological options in the treatment of idiopathic pulmonary fibrosis (IPF)
Aribindi, K., Liu, G. Y., & Albertson, T. E. (2024) · Expert Review of Clinical Pharmacology · doi:10.1080/17512433.2024.2396121 · Cited by 17
Saady, M., Eissa, M., Yacoub, A. S., Hamed, A. B., & Azzazy, H. M. E.-S. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103066 · Cited by 15
Metadata
- Authors
- Aliper, A., Kudrin, R., Polykovskiy, D., Kamya, P., Tutubalina, E., Chen, S., Ren, F., & Zhavoronkov, A.
- Venue
- Clinical Pharmacology & Therapeutics
- Publisher
- Wiley
- Published
- 2023-08-10
- Volume
- 114
- Issue
- 5
- Pages
- 972-980
- ISSN
- 0009-9236 (ISSN-L)
- 1532-6535
- OpenAlex
- W4385072800
- Cited by
- 89
- References
- 14
- FWCI
- 11.71
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.