The Commoditization of AI for Molecule Design

Abstract

Anyone involved in designing or finding molecules in the life sciences over the past few years has witnessed a dramatic change in how we now work due to the COVID-19 pandemic. Computational technologies like artificial intelligence (AI) seemed to become ubiquitous in 2020 and have been increasingly applied as scientists worked from home and were separated from the laboratory and their colleagues. This shift may be more permanent as the future of molecule design across different industries will increasingly require machine learning models for design and optimization of molecules as they become "designed by AI". AI and machine learning has essentially become a commodity within the pharmaceutical industry. This perspective will briefly describe our personal opinions of how machine learning has evolved and is being applied to model different molecule properties that crosses industries in their utility and ultimately suggests the potential for tight integration of AI into equipment and automated experimental pipelines. It will also describe how many groups have implemented generative models covering different architectures, for de novo design of molecules. We also highlight some of the companies at the forefront of using AI to demonstrate how machine learning has impacted and influenced our work. Finally, we will peer into the future and suggest some of the areas that represent the most interesting technologies that may shape the future of molecule design, highlighting how we can help increase the efficiency of the design-make-test cycle which is currently a major focus across industries.

Keywords: Artificial intelligence; design-make-test; machine learning; molecule design; recurrent neural networks.

Figure 1.

A. The design-make-test cycle. B. A hypothetical example of how a Recurrent Neural Network can be combined with the machine learning models and feedback from scientists to optimize the kinase inhibitor lapatinib.

Figure 2.

A case study of generative peptide design for GLP-1. A. An RNN-LSTM was trained on a dataset of 1554 antimicrobial peptides and generated peptides were scored with a GLP-1 agonist model generated from data in ChEMBL. B. dimensionality reduction using a t-SNE plot and nearest neighbor distance of generated proposed GLP-1 agonists. C. visualizing de novo generated GLP-1 agonists alongside commercial GLP-1 drugs to illustrate they are close in chemical property space.

Figure 2.

A case study of generative peptide design for GLP-1. A. An RNN-LSTM was trained on a dataset of 1554 antimicrobial peptides and generated peptides were scored with a GLP-1 agonist model generated from data in ChEMBL. B. dimensionality reduction using a t-SNE plot and nearest neighbor distance of generated proposed GLP-1 agonists. C. visualizing de novo generated GLP-1 agonists alongside commercial GLP-1 drugs to illustrate they are close in chemical property space.