Acute toxicity is one of the most challenging properties to predict purely with computational methods due to its direct relationship to biological interactions. Moreover, toxicity can be represented by different endpoints: it can be measured for different species using different types of administration, etc., and it is questionable if the knowledge transfer between endpoints is possible. We performed a comparative study of prediction multi-task toxicity for a broad chemical space using different descriptors and modeling algorithms and applied multi-task learning for a large toxicity dataset extracted from the Registry of Toxic Effects of Chemical Substances (RTECS). We demonstrated that multi-task modeling provides significant improvement over singleoutput models and other machine learning methods. Our research reveals that multi-task learning can be very useful to improve the quality of acute toxicity modeling and raises a discussion about the usage of multi-task approaches for regulation purposes.

In this work, we present graph-convolutional neural networks for the prediction of binding constants of protein−ligand complexes. We derived the model using multi task learning, where the target variables are the dissociation constant (K d ), inhibition constant (K i ), and half maximal inhibitory concentration (IC 50 ). Being rigorously trained on the PDBbind dataset, the model achieves the Pearson correlation coefficient of 0.87 and the RMSE value of 1.05 in pK units, outperforming recently developed 3D convolutional neural network model K deep .

A parametric t-SNE approach based on deep feed-forward neural networks was applied to the chemical space visualization problem.

Derivation of structure–kinetics relationships can help rational design and development of new small-molecule drug candidates with desired residence times. Efforts are now being directed toward the development of efficient computational methods. Currently, there is a lack of solid, high-throughput binding kinetics prediction approaches on bigger datasets. We present a prediction method for binding kinetics based on the machine learning analysis of protein–ligand structural features, which can serve as a baseline for more sophisticated methods utilizing molecular dynamics (MD). We showed that the random forest algorithm is capable of learning the protein binding site secondary structure and backbone/side-chain features to predict the binding kinetics of protein–ligand complexes but still with inferior performance to that of MD-based descriptor analysis. MD simulations had been applied to a limited number of targets and a series of ligands in terms of kinetics analysis, and we believe that the developed approach may guide new studies. The method was trained on a newly curated database of 501 protein–ligand unbinding rate constants, which can also be used for testing and training the binding kinetics prediction models.