Learning Deep Architectures for Interaction Prediction in Structure-based Virtual Screening

Abstract

We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each compound separately. These fingerprints are further transformed non-linearly, their inner-product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E and PDBBind databases.

Workshop on Machine Learning in Computational Biology. 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain Extended version published in Computers in Biology and Medicine and available online: http://www.sciencedirect.com/science/article/pii/S0010482517302974

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• Massively Multitask Networks for Drug Discovery

Cited by in corpus (4)

• Decoding Drug Discovery: Exploring A-to-Z In silico Methods for Beginners
• Regression Enrichment Surfaces: a Simple Analysis Technique for Virtual Drug Screening Models
• Simulating Execution Time of Tensor Programs using Graph Neural Networks
• ParaVS: A Simple, Fast, Efficient and Flexible Graph Neural Network Framework for Structure-Based Virtual Screening