Multi-task Neural Networks for QSAR Predictions

Abstract

Although artificial neural networks have occasionally been used for Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) studies in the past, the literature has of late been dominated by other machine learning techniques such as random forests. However, a variety of new neural net techniques along with successful applications in other domains have renewed interest in network approaches. In this work, inspired by the winning team's use of neural networks in a recent QSAR competition, we used an artificial neural network to learn a function that predicts activities of compounds for multiple assays at the same time. We conducted experiments leveraging recent methods for dealing with overfitting in neural networks as well as other tricks from the neural networks literature. We compared our methods to alternative methods reported to perform well on these tasks and found that our neural net methods provided superior performance.

References in corpus (3)

• Scikit-learn: Machine Learning in Python
• Improving neural networks by preventing co-adaptation of feature detectors
• Practical Bayesian Optimization of Machine Learning Algorithms

Cited by in corpus (29)

• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Deep learning for molecular design - a review of the state of the art
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• Massively Multitask Networks for Drug Discovery
• Gradient-based Hyperparameter Optimization through Reversible Learning
• TopologyNet: Topology based deep convolutional neural networks for biomolecular property predictions
• Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening
• Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
• An Integrated Transfer Learning and Multitask Learning Approach for Pharmacokinetic Parameter Prediction
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
• Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Errors for Deep Neural Networks
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• Toxicity Prediction using Deep Learning
• Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretation
• SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
• Simulations meet Machine Learning in Structural Biology
• Deep Learning for Computational Chemistry
• Light Gradient Boosting Machine as a Regression Method for Quantitative Structure-Activity Relationships
• DeepCCI: End-to-end Deep Learning for Chemical-Chemical Interaction Prediction
• Multimodal Deep Neural Networks using Both Engineered and Learned Representations for Biodegradability Prediction
• A Comparative Analysis of the Ensemble Methods for Drug Design
• Deep Neural Networks for Detecting Statistical Model Misspecifications. The Case of Measurement Invariance
• Discovering Molecular Functional Groups Using Graph Convolutional Neural Networks
• Deep Cross Residual Learning for Multitask Visual Recognition
• Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions
• Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
• Research and development of MolAICal for drug design via deep learning and classical programming
• Comparison of multi-task convolutional neural network (MT-CNN) and a few other methods for toxicity prediction
• Relational dynamic memory networks