Supervised machine learning in drug discovery and development - Algorithms, applications, challenges, and prospects

Aug 5, 2026

Upload by Maeve

Drug discovery and development is a time-consuming pipeline requiring identification, design, and rigorous testing of new compounds to meet unmet medical needs. Machine learning has emerged as a key enabler across multiple stages, and it can be grouped into supervised, unsupervised, semi-supervised, and reinforcement learning. This survey focuses on supervised learning algorithms for drug design and development, highlighting their learning process, clear mathematical formulations, and common practical challenges with potential solutions for adoption by researchers and industry practitioners.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Drug discovery pipeline and challenges

Role of machine learning and automation

Supervised learning in drug design and development

Survey scope and algorithm learning process

Mathematical formulations and real-world usage

Challenges and prospects

Practical application barriers

Potential solutions and future directions

Machine Learning with Applications 17 (2024) 100576 | Supervised machine learning in drug discovery and development: Algorithms, applications, challenges, and prospects
George Obaido a,∗, Ibomoiye Domor Mienyeb, Oluwaseun F. Egbelowo c,
Ikiomoye Douglas Emmanuel d, Adeola Ogunleyeb, Blessing Ogbuokiri e, Pere Mienye f, Kehinde Aruleba g
a Center for Human-Compatible Artificial Intelligence (CHAI), Berkeley Institute for Data Science (BIDS), University of California, Berkeley, CA, 94720, USA b Institute of Intelligent Systems, University of Johannesburg, Johannesburg, 2006, South Africa
c Department of Integrative Biology, The University of Texas at Austin, Austin, TX, 78712, USA
d School of Science, Engineering and Environment, University of Salford, Salford, United Kingdome Department of Computer Science, Brock University, Niagara Region, St. Catharines, ON, L2S 3A1, Canada f Health Plus, Lekki, Lagos, Nigeria
g School of Computing and Mathematical Sciences, University of Leicester, Leicester, LE1 7RH, United Kingdom | | | | | --- | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Artificial intelligence Deep learning Machine learning Neural network Supervised learning | | Drug discovery and development is a time-consuming process that involves identifying, designing, and testing new drugs to address critical medical needs. In recent years, machine learning (ML) has played a vital role in technological advancements and has shown promising results in various drug discovery and development stages. ML can be categorized into supervised, unsupervised, semi-supervised, and reinforcement learning. Supervised learning is the most used category, helping organizations solve several real-world problems. This study presents a comprehensive survey of supervised learning algorithms in drug design and development, focusing on their learning process and succinct mathematical formulations, which are lacking in the literature. Additionally, the study discusses widely encountered challenges in applying supervised learning for drug discovery and potential solutions. This study will be beneficial to researchers and practitioners in the pharmaceutical industry as it provides a simplified yet comprehensive review of the main concepts, algorithms, challenges, and prospects in supervised learning. | | 1. Introduction Drug discovery and development is a time-consuming process that involves identifying, designing, and testing new drugs to address critical medical needs (Aly & Alotaibi, 2023; Athreya et al., 2019; Ekinset al., 2019; Sarkar et al., 2023; Vamathevan et al., 2019). Once a promising compound is identified, it undergoes rigorous testing in preclinical and clinical trials to assess its safety, efficacy, and potential side effects (Jantan, Ahmad, & Bukhari, 2015; Koivisto, Belvisi, Gaudet, & Szallasi, 2022; Zhou et al., 2016). This process can take years, involving collaboration between scientists, physicians, regulatory agencies, and pharmaceutical companies. Despite these challenges, successful drug discovery can lead to groundbreaking treatments that improve patients’lives and advance medical science. In recent years, technological advancements have revolutionized various aspects of the drug discovery process, streamlining and accelerating certain stages (Mak, Wong, & Pichika, 2023; Rubin, Tummala, Both, Wang, & Delaney, 2006; Selekman et al., 2017). High-throughput screening techniques allow researchers to rapidly test thousands of compounds for potential therapeutic effects, significantly speeding up the initial identification phase. Additionally, computational methods, such as artificial intelligence are increasingly utilized to predict the properties and behavior of drug candidates, reducing the reliance on traditional trial-and-error approaches (Fu et al., 2024; Janakiraman, Khanna, & Ramkanth, 2023; Marchetti, Moroni, Pandini, & Colombo, 2021; Tayyebi et al., 2023; Walla

FAQs

What stages of drug discovery and development can supervised machine learning support?

Supervised learning is discussed as assisting multiple stages involved in identifying, designing, and testing drug candidates, leveraging data-driven prediction to streamline workflows.

How does this survey characterize supervised learning compared with other ML types?

The document notes that ML includes supervised, unsupervised, semi-supervised, and reinforcement learning, with supervised learning highlighted as the most widely used category for real-world problem solving.

What challenges arise when applying supervised learning to drug discovery?

The survey explains widely encountered challenges in applying supervised learning for drug discovery and provides potential solutions to address these issues for researchers and practitioners.

Aug 5, 2026

Upload by Maeve