Massively Multitask Networks for Drug Discovery
This work addresses the need for more efficient drug discovery by leveraging multitask learning, though it is incremental as it builds on existing multitask frameworks with new empirical studies.
The paper tackled the problem of improving predictive accuracy in drug discovery by using massively multitask neural networks, achieving significantly better results than single-task methods and showing that predictive power improves with additional tasks and data, with a dataset of nearly 40 million measurements across over 200 biological targets.
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.