Polypharmacology prediction: the long road toward comprehensively anticipating small-molecule selectivity to de-risk drug discovery

ABSTRACT

Introduction

Small molecules often bind to multiple targets, a behavior termed polypharmacology. Anticipating polypharmacology is essential for drug discovery since unknown off-targets can modulate safety and efficacy – profoundly affecting drug discovery success. Unfortunately, experimental methods to assess selectivity present significant limitations and drugs still fail in the clinic due to unanticipated off-targets. Computational methods are a cost-effective, complementary approach to predict polypharmacology.

Areas covered

This review aims to provide a comprehensive overview of the state of polypharmacology prediction and discuss its strengths and limitations, covering both classical cheminformatics methods and bioinformatic approaches. The authors review available data sources, paying close attention to their different coverage. The authors then discuss major algorithms grouped by the types of data that they exploit using selected examples.

Expert opinion

Polypharmacology prediction has made impressive progress over the last decades and contributed to identify many off-targets. However, data incompleteness currently limits most approaches to comprehensively predict selectivity. Moreover, our limited agreement on model assessment challenges the identification of the best algorithms – which at present show modest performance in prospective real-world applications. Despite these limitations, the exponential increase of multidisciplinary Big Data and AI hold much potential to better polypharmacology prediction and de-risk drug discovery.

KEYWORDS:

• Polypharmacology
• target prediction
• chemical similarity
• machine learning
• deep learning
• AI
• Big data
• drug discovery

Article highlights

• Identifying all the on- and off-targets of small molecule drugs remains key to reduce attrition in drug discovery and development.

• Many computational methods to predict polypharmacology have been developed and successfully used to identify new targets of drugs but their real-world performance is modest.

• The major limitation to comprehensively predict drug selectivity is the lack of comprehensive data.

• Improving how we assess new methods is paramount to ensure they outperform simpler approaches.

• Advances in AI and Big Data hold much potential to improve polypharmacology prediction in the near future.

Declaration of interest

AA Antolin was an employee of The Institute of Cancer Research (ICR), which has a commercial interest in a range of drug targets, including PARP and protein kinases. The ICR operates a Rewards to Inventors scheme whereby employees of the ICR may receive financial benefit following commercial licensing of a project. AA Antolin has been instrumental in the creation/development of canSAR, the Chemical Probes Portal and Probe Miner. AA Antolin is/was a consultant of DarwinHealth and has received funds from VIVAN Therapeutics. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

Reviewer disclosures

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Additional information

Funding

The authors are funded by the Miguel de Servet Fellowship from the Instituto de Salud Carlos III, Spain (award no. CP23/00115) the Bellvitge Biomedical Research Institute and the Catalan Institute of Oncology. In the past, AA Antolin has received support in the way of a fellowship from “la Caixa” Foundation (LCF/BQ/PI22/11910016), and a Fellowship from The Institute of Cancer Research. This work was also supported by the Spanish Ministry of Science and Innovation (MCIN/AEI) (PID2022-136344OA-I00), the CERCA Program/Generalitat de Catalunya, and FEDER funds/European Regional Development Fund (ERDF) – a way to Build Europe.