Investigating Active Learning and Meta-Learning for Iterative Peptide Design
This work addresses the challenge of slow and data-scarce peptide development for researchers in biochemistry and drug discovery, but it is incremental as it builds on existing methods with mixed results.
The study tackled the problem of inefficient peptide design by testing active learning and meta-learning to reduce the number of experiments needed for predictive modeling, finding that active learning methods performed no better than random choice while meta-learning improved average accuracy across datasets.
Often the development of novel functional peptides is not amenable to high throughput or purely computational screening methods. Peptides must be synthesized one at a time in a process that does not generate large amounts of data. One way this method can be improved is by ensuring that each experiment provides the best improvement in both peptide properties and predictive modeling accuracy. Here, we study the effectiveness of active learning, optimizing experiment order, and meta-learning, transferring knowledge between contexts, to reduce the number of experiments necessary to build a predictive model. We present a multi-task benchmark database of peptides designed to advance these methods for experimental design. Each task is binary classification of peptides represented as a sequence string. We find neither active learning method tested to be better than random choice. The meta-learning method Reptile was found to improve average accuracy across datasets. Combining meta-learning with active learning offers inconsistent benefits.