A Data-Driven Approach to Predicting Successes and Failures of Clinical Trials

Overview

Journal Cell Chem Biol

Publisher Cell Press

Specialty Biochemistry

Date 2016 Sep 20

PMID 27642066

Citations 65

Authors

Kaitlyn M Gayvert

Neel S Madhukar

Olivier Elemento

Affiliations

Soon will be listed here.

Abstract

Over the past decade, the rate of drug attrition due to clinical trial failures has risen substantially. Unfortunately it is difficult to identify compounds that have unfavorable toxicity properties before conducting clinical trials. Inspired by the effective use of sabermetrics in predicting successful baseball players, we sought to use a similar "moneyball" approach that analyzes overlooked features to predict clinical toxicity. We introduce a new data-driven approach (PrOCTOR) that directly predicts the likelihood of toxicity in clinical trials. PrOCTOR integrates the properties of a compound's targets and its structure to provide a new measure, the PrOCTOR score. Drug target network connectivity and expression levels, along with molecular weight, were identified as important indicators of adverse clinical events. Our method provides a data-driven, broadly applicable strategy to identify drugs likely to possess manageable toxicity in clinical trials and will help drive the design of therapeutic agents with less toxicity.

Citing Articles

Integrating convolutional layers and biformer network with forward-forward and backpropagation training.

Kianfar A, Razzaghi P, Asgari Z Sci Rep. 2025; 15(1):7230.

PMID: 40021838 PMC: 11871031. DOI: 10.1038/s41598-025-92218-y.

Role of Artificial Intelligence in Drug Discovery to Revolutionize the Pharmaceutical Industry: Resources, Methods and Applications.

Singh P, Sachan K, Khandelwal V, Singh S, Singh S Recent Pat Biotechnol. 2025; 19(1):35-52.

PMID: 39840410 DOI: 10.2174/0118722083297406240313090140.

Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow.

Jung S, Jung G, Cole J J Chem Inf Model. 2024; 65(1):133-152.

PMID: 39714952 PMC: 11733926. DOI: 10.1021/acs.jcim.4c01862.

Flourishing and job satisfaction in employees working in UK clinical trial units: a national cross-sectional survey.

Hall S, Riga E, Sprange K, Hagan P, Carr L, Taylor J BMC Health Serv Res. 2024; 24(1):1522.

PMID: 39623423 PMC: 11610179. DOI: 10.1186/s12913-024-11986-x.

Predicting clinical trial success for infections based on preclinical data.

Li F, Youn J, Millsop C, Tagkopoulos I Front Artif Intell. 2024; 7:1487335.

PMID: 39444663 PMC: 11496251. DOI: 10.3389/frai.2024.1487335.

References

Jeliazkova N, Jeliazkov V . AMBIT RESTful web services: an implementation of the OpenTox application programming interface. J Cheminform. 2011; 3:18. PMC: 3120779. DOI: 10.1186/1758-2946-3-18. View

Anders S, Pyl P, Huber W . HTSeq--a Python framework to work with high-throughput sequencing data. Bioinformatics. 2014; 31(2):166-9. PMC: 4287950. DOI: 10.1093/bioinformatics/btu638. View

Kuhn M, Campillos M, Letunic I, Jensen L, Bork P . A side effect resource to capture phenotypic effects of drugs. Mol Syst Biol. 2010; 6:343. PMC: 2824526. DOI: 10.1038/msb.2009.98. View

Lipinski C . Lead- and drug-like compounds: the rule-of-five revolution. Drug Discov Today Technol. 2014; 1(4):337-41. DOI: 10.1016/j.ddtec.2004.11.007. View

Aksoy B, Gao J, Dresdner G, Wang W, Root A, Jing X . PiHelper: an open source framework for drug-target and antibody-target data. Bioinformatics. 2013; 29(16):2071-2. PMC: 3722529. DOI: 10.1093/bioinformatics/btt345. View

Knox C, Law V, Jewison T, Liu P, Ly S, Frolkis A . DrugBank 3.0: a comprehensive resource for 'omics' research on drugs. Nucleic Acids Res. 2010; 39(Database issue):D1035-41. PMC: 3013709. DOI: 10.1093/nar/gkq1126. View

Leeson P, Springthorpe B . The influence of drug-like concepts on decision-making in medicinal chemistry. Nat Rev Drug Discov. 2007; 6(11):881-90. DOI: 10.1038/nrd2445. View

Hay M, Thomas D, Craighead J, Economides C, Rosenthal J . Clinical development success rates for investigational drugs. Nat Biotechnol. 2014; 32(1):40-51. DOI: 10.1038/nbt.2786. View

Bickerton G, Paolini G, Besnard J, Muresan S, Hopkins A . Quantifying the chemical beauty of drugs. Nat Chem. 2012; 4(2):90-8. PMC: 3524573. DOI: 10.1038/nchem.1243. View

10.

Sahota T, Danhof M, Della Pasqua O . Pharmacology-based toxicity assessment: towards quantitative risk prediction in humans. Mutagenesis. 2016; 31(3):359-74. DOI: 10.1093/mutage/gev081. View

11.

Blind E, Dunder K, de Graeff P, Abadie E . Rosiglitazone: a European regulatory perspective. Diabetologia. 2010; 54(2):213-8. DOI: 10.1007/s00125-010-1992-5. View

12.

Ghose A, Viswanadhan V, Wendoloski J . A knowledge-based approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases. J Comb Chem. 2000; 1(1):55-68. DOI: 10.1021/cc9800071. View

13.

Veber D, Johnson S, Cheng H, Smith B, Ward K, Kopple K . Molecular properties that influence the oral bioavailability of drug candidates. J Med Chem. 2002; 45(12):2615-23. DOI: 10.1021/jm020017n. View

14.

Arastu-Kapur S, Anderl J, Kraus M, Parlati F, Shenk K, Lee S . Nonproteasomal targets of the proteasome inhibitors bortezomib and carfilzomib: a link to clinical adverse events. Clin Cancer Res. 2011; 17(9):2734-43. DOI: 10.1158/1078-0432.CCR-10-1950. View

15.

Scannell J, Blanckley A, Boldon H, Warrington B . Diagnosing the decline in pharmaceutical R&D efficiency. Nat Rev Drug Discov. 2012; 11(3):191-200. DOI: 10.1038/nrd3681. View

16.

Patlewicz G, Fitzpatrick J . Current and Future Perspectives on the Development, Evaluation, and Application of in Silico Approaches for Predicting Toxicity. Chem Res Toxicol. 2015; 29(4):438-51. DOI: 10.1021/acs.chemrestox.5b00388. View

17.

Das J, Yu H . HINT: High-quality protein interactomes and their applications in understanding human disease. BMC Syst Biol. 2012; 6:92. PMC: 3483187. DOI: 10.1186/1752-0509-6-92. View

18.

Khurana E, Fu Y, Chen J, Gerstein M . Interpretation of genomic variants using a unified biological network approach. PLoS Comput Biol. 2013; 9(3):e1002886. PMC: 3591262. DOI: 10.1371/journal.pcbi.1002886. View

19.

Massacesi C, Marcucci F, Rocchi M, Mazzanti P, Pilone A, Bonsignori M . Factors predicting docetaxel-related toxicity: experience at a single institution. J Chemother. 2004; 16(1):86-93. View

20.

Lipinski C, Lombardo F, Dominy B, Feeney P . Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv Drug Deliv Rev. 2001; 46(1-3):3-26. DOI: 10.1016/s0169-409x(00)00129-0. View