Bioactivity descriptors for uncharacterized chemical compounds

Abstract

Chemical descriptors encode the physicochemical and structural properties of small molecules, and they are at the core of chemoinformatics. The broad release of bioactivity data has prompted enriched representations of compounds, reaching beyond chemical structures and capturing their known biological properties. Unfortunately, bioactivity descriptors are not available for most small molecules, which limits their applicability to a few thousand well characterized compounds. Here we present a collection of deep neural networks able to infer bioactivity signatures for any compound of interest, even when little or no experimental information is available for them. Our signaturizers relate to bioactivities of 25 different types (including target profiles, cellular response and clinical outcomes) and can be used as drop-in replacements for chemical descriptors in day-to-day chemoinformatics tasks. Indeed, we illustrate how inferred bioactivity signatures are useful to navigate the chemical space in a biologically relevant manner, unveiling higher-order organization in natural product collections, and to enrich mostly uncharacterized chemical libraries for activity against the drug-orphan target Snail1. Moreover, we implement a battery of signature-activity relationship (SigAR) models and show a substantial improvement in performance, with respect to chemistry-based classifiers, across a series of biophysics and physiology activity prediction benchmarks.

Artificial Intelligence uncovers carcinogenic human metabolites

“…To obtain the best performing models, we tried three different feature extraction methods i.e. bioactivity-based descriptors (Signaturizer library) 46 , chemistry-based molecular descriptors (Mordred software) 47 , and graph-based features (DeepChem library) 48 . In addition to these diversified features, we also tried multiple machine learning/deep learning-based classification algorithms for model building such as Random Forest (RF), Multilayer Perceptron (MLP), k-Nearest Neighbor (KNN), Support Vector Machine (SVM), Stochastic Gradient Descent (SGD), Logistic Regression (LR), GraphConvModel (GCM), Attentive FP (AFP), Graph Convolution Network (GCN), and Graph Attention Network (GAT) (Supplementary Figure 1b) .…”

“…To obtain the best performing models, we tried three different feature extraction methods i.e. bioactivity-based descriptors (Signaturizer library) 46 , chemistry-based molecular descriptors (Mordred software) 47 , and graph-based features (DeepChem library) 48 . In addition to these diversified features, we also tried 50 , implementation of an array of classifiers for model building, and testing of all models on the same unseen testing dataset.…”

Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning

“…The RDMD contained 200 molecular descriptors, including physicochemical properties and structure characteristics, which have been used in many studies and have achieved satisfactory results [ 23 , 24 , 25 , 26 , 27 ]. The CCMD is a novel type of biological descriptor containing 25 various bioactive spaces [ 28 ]. Moreover, the simple representation of CCMD is compatible with different types of computational tools in a multi-dimensional form.…”

Deep Machine Learning for Computer-Aided Drug Design

“…Accordingly, graph-based DNNs including message passing networks have increasingly been investigated for learning model-internal representations from molecular structure (Chuang et al, 2020). In addition to graph-based representation learning, DL has recently also been applied to predict biological signatures of test compounds (Bertoni et al, 2021), which might be combined with standard structural descriptors in virtual screening (vide supra). However, on the basis of currently available data, it remains to be determined whether alternative molecular representations-be they learned from graphs or predicted-might yield higher performance in ML and other applications than long-used standards such as molecular fingerprints or numerical descriptors.…”