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
  • Publicly accessible chemical data repositories to consider for your own projects

This is a book about medicine, disease, and the process of discovering new drugs for the benefit of humanity. This is also a book about the computational tools that make these discoveries possible. 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].

Computational approaches continue to be an important tool for rapid prototyping and screening of drug candidates. 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. In this chapter, we’ll cover the value proposition of breakthroughs in artificial intelligence (AI) as they propagate from theory to application in computational drug design.

1.1 Deep Learning’s Value Proposition

1.1.1 Needle in a Haystack

1.1.2 Virtual Screening & Property Prediction

1.1.3 Generative Chemistry

1.1.4 Chemical Reaction Prediction & Retrosynthesis

1.1.5 Protein Folding & Simulations

1.2 What is ML? What is a Molecule?

1.2.1 What is ML?

1.2.2 What is a Molecule? The Joy of SMILES

1.2.3 An Example Application with USAN Stems & RDKit

1.3 Introducing Drug Discovery

1.3.1 Target Identification & Hit Discovery

1.3.2 Lead Identification & Lead Optimization

1.3.3 Drug Development

1.4 Summary

1.5 References