Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning

TL;DR

This paper presents a deep autoencoder-based method for unsupervised clustering of 1.39 million bioactive molecules in 3D chemical space, revealing meaningful sub-structural features and bioactivity patterns.

Contribution

It introduces a novel deep learning approach for large-scale bioactive molecule clustering that uncovers structural and activity-based subgroups beyond traditional similarity methods.

Findings

Successfully clustered 1.39 million molecules into meaningful band-clusters

Revealed sub-structural features associated with bioactivity classes

Demonstrated applicability to big data clustering tasks

Abstract

Unsupervised clustering has broad applications in data stratification, pattern investigation and new discovery beyond existing knowledge. In particular, clustering of bioactive molecules facilitates chemical space mapping, structure-activity studies, and drug discovery. These tasks, conventionally conducted by similarity-based methods, are complicated by data complexity and diversity. We ex-plored the superior learning capability of deep autoencoders for unsupervised clustering of 1.39 mil-lion bioactive molecules into band-clusters in a 3-dimensional latent chemical space. These band-clusters, displayed by a space-navigation simulation software, band molecules of selected bioactivity classes into individual band-clusters possessing unique sets of common sub-structural features beyond structural similarity. These sub-structural features form the frameworks of the literature-reported pharmacophores and privileged fragments. Within each band-cluster, molecules are further banded into selected sub-regions with respect to their bioactivity target, sub-structural features and molecular scaffolds. Our method is potentially applicable for big data clustering tasks of different fields.