Research work · 2026

e-Resources Relevant to Machine Learning Tools for Medicinal Chemistry

Sushmita Barua, B. Balaji, S. Balaji

Machine Learning and Deep Learning in Drug Design

Abstract

The integration of machine learning (ML) into medicinal chemistry has revolutionized the drug discovery process by enabling data-driven predictions and decision-making. This chapter provides a detailed overview of key e-resources that support the effective application of ML in medicinal chemistry. It covers essential chemical and drug databases that serve as primary sources of structured chemical and biological data, along with cheminformatics tools that facilitate molecular encoding and analysis. The chapter also discusses visualization tools for interpreting complex datasets, molecular descriptors used to quantify chemical features, and ADMET tools that predict absorption, distribution, metabolism, excretion, and toxicity profiles. Additionally, the chapter highlights quantitative structure–activity relationship (QSAR) tools for activity prediction and explores various ML models and large language models (LLMs) that have become integral to modern drug discovery workflows. These e-resources collectively equip medicinal chemists with the computational infrastructure necessary to accelerate and optimize the design and development of new therapeutic compounds.

DOI: 10.1039/9781837070206-00583