Inferring multi-target QSAR models with taxonomy-based multi-task learning

Abstract

BackgroundA plethora of studies indicate that the development of multi-target drugs is beneficial for complex diseases like cancer. Accurate QSAR models for each of the desired targets assist the optimization of a lead candidate by the prediction of affinity profiles. Often, the targets of a multi-target drug are sufficiently similar such that, in principle, knowledge can be transferred between the QSAR models to improve the model accuracy. In this study, we present two different multi-task algorithms from the field of transfer learning that can exploit the similarity between several targets to transfer knowledge between the target specific QSAR models.ResultsWe evaluated the two methods on simulated data and a data set of 112 human kinases assembled from the public database ChEMBL. The relatedness between the kinase targets was derived from the taxonomy of the humane kinome. The experiments show that multi-task learning increases the performance compared to training separate models on both types of data given a sufficient similarity between the tasks. On the kinase data, the best multi-task approach improved the mean squared error of the QSAR models of 58 kinase targets.ConclusionsMulti-task learning is a valuable approach for inferring multi-target QSAR models for lead optimization. The application of multi-task learning is most beneficial if knowledge can be transferred from a similar task with a lot of in-domain knowledge to a task with little in-domain knowledge. Furthermore, the benefit increases with a decreasing overlap between the chemical space spanned by the tasks.

Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning

“…The present work uses transfer learning 49,50 to train an ML potential that is accurate, transferable, extensible, and therefore, broadly applicable. In transfer learning, one begins with a model trained on data from one task and then retrains the model on data from a different, but related task, often yielding high accuracy predictions [51][52][53] even when data is sparsely available. In our application, we begin by training a neural network on a large quantity of lower-accuracy DFT data (the ANI-1x dataset with 5M non-equilibrium molecular conformations 25 ), and then we retrain to a much smaller dataset (about 500k intelligently selected conformations from ANI-1x) at the CCSD(T)/CBS level of accuracy.…”

Outsmarting Quantum Chemistry Through Transfer Learning

“…The present work uses transfer learning 49,50 to train an ML potential that is accurate, transferable, extensible, and therefore, broadly applicable. In transfer learning, one begins with a model trained on data from one task and then retrains the model on data from a different, but related task, often yielding high accuracy predictions [51][52][53] even when data is sparsely available. In our application, we begin by training a neural network on a large quantity of lower-accuracy DFT data (the ANI-1x dataset with 5M molecular conformations 45 ), and then we retrain to a much smaller dataset (about 500k select conformations from ANI-1x) at the CCSD(T)/CBS level of accuracy.…”

Harnessing Big Data for Systems Pharmacology

“…The Bayesian network is a probabilistic graphic model that represents a set of biological measurements and their dependencies. Multitask learning that learns several related problems together at the same time using a shared representation of multiple data modalities has proved to be a valuable approach for inferring multitarget quantitative structure-activity relationship models for lead optimization (62). The advances in big data technology provide new opportunities for model combination.…”