Massively Multitask Networks for Drug Discovery

2015/02/06 by Bharath Ramsundar, Ramsundar, Bharath, Steven Kearnes +12 · 16 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · Mathematics · #Cell Image Analysis Techniques #Computational Drug Discovery Methods #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Neural and Evolutionary Computing (cs.NE) #cs.LG #cs.NE #stat.ML

paper · pdf · doi:10.48550/arxiv.1502.02072

Preliminary work. Under review by the International Conference on Machine Learning (ICML)

arxiv created 2015/02/06 · openalex publication_date 2015/02/06 · arxiv updated 2015/02/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Massively multitask neural architectures provide a learning framework for drug discovery that synthesizes information from many distinct biological sources. To train these architectures at scale, we gather large amounts of data from public sources to create a dataset of nearly 40 million measurements across more than 200 biological targets. We investigate several aspects of the multitask framework by performing a series of empirical studies and obtain some interesting results: (1) massively multitask networks obtain predictive accuracies significantly better than single-task methods, (2) the predictive power of multitask networks improves as additional tasks and data are added, (3) the total amount of data and the total number of tasks both contribute significantly to multitask improvement, and (4) multitask networks afford limited transferability to tasks not in the training set. Our results underscore the need for greater data sharing and further algorithmic innovation to accelerate the drug discovery process.

Citations

• Multi-task Neural Networks for QSAR Predictions
• Recommendations for evaluation of computational methods

Cited by

• Multi-Task Learning for Metal Alloy Property Prediction: An Empirical Study of Negative Transfer and Mitigation Strategies
• Task-Specific Sparse Feature Masks for Molecular Toxicity Prediction with Chemical Language Models
• Multi-task GINN-LP for Multi-target Symbolic Regression
• When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
• Enhancing Learning Path Recommendation via Multi-task Learning
• Black-Box Privacy Attacks on Shared Representations in Multitask Learning
• Harnessing Geometric Constraints from Emotion Labels to improve Face Verification
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
• Accelerating Parameter Initialization in Quantum Chemical Simulations via LSTM-FC-VQE
• MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Toxicity Prediction using Deep Learning
• Attribution Methods Reveal Flaws in Fingerprint-Based Virtual Screening
• Making Graph Neural Networks Worth It for Low-Data Molecular Machine Learning
• BERT Learns (and Teaches) Chemistry

Related

• Modeling Industrial ADMET Data with Multitask Networks
• Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
• Neural scaling laws for phenotypic drug discovery
• Towards Unified AI Drug Discovery with Multiple Knowledge Modalities
• Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery