chapter one

1 The Drug Discovery Process

 

This chapter covers

  • What is drug discovery and how it relates to drug development
  • What does it mean to discover a drug
  • How machine learning and deep learning aid in drug discovery
  • A foundation of drug discovery and machine learning terminology
  • Where to find chemical and biological data for your own projects

Developing therapeutics entails a long, arduous process. Progressing from ideation to market can cost estimates of $1 to $3 billion over a time span of 10-15 years. Failure rates abound at a rate of 90% for drug candidates that reach clinical trial and the estimated funds and labor to explore experimental avenues that end up as unreported dead ends account for $1.1 billion per approved drug [3].

These figures reflect a fundamental challenge: the space of possible drug-like molecules is vast, the biological systems they must interact with are complex, and the safety standards they must meet are rigorous. Computational approaches continue to be an important tool for rapid prototyping and screening of drug candidates, and machine learning is increasingly at the center of these efforts. For example, better methods for assessing drug candidate safety prevent unsafe or ineffective drugs from reaching the market, which mitigates withdrawal announcements that tarnish brand image and incur notable costs.

1.1 The Challenge of Drug Discovery

1.1.1 Needle in a Haystack

1.1.2 Eroom’s Law

1.1.3 The Regulatory Landscape

1.2 The Language of Molecules

1.2.1 What is a Molecule? The Joy of SMILES

1.2.2 What is Machine Learning?

1.2.3 An Example Application with USAN Stems & RDKit

1.3 Deep Learning’s Value Proposition

1.3.1 Virtual Screening & Property Prediction

1.3.2 Generative Chemistry

1.3.3 Chemical Reaction Prediction & Retrosynthesis

1.3.4 Protein Folding & Simulations

1.4 Introducing Drug Discovery

1.4.1 Target Identification & Hit Discovery

1.4.2 Lead Identification & Lead Optimization

1.4.3 Drug Development

1.5 Summary