Neural Potts Model

Tom Sercu, Robert Verkuil, Joshua Meier, Brandon Amos, Zeming Lin, Caroline Chen, Jason Liu, Yann LeCun, Alexander Rives

Keywords: proteins, potts model, unsupervised learning, amortized optimization, structure prediction

Abstract: We propose the Neural Potts Model objective as an amortized optimization problem. The objective enables training a single model with shared parameters to explicitly model energy landscapes across multiple protein families. Given a protein sequence as input, the model is trained to predict a pairwise coupling matrix for a Potts model energy function describing the local evolutionary landscape of the sequence. Couplings can be predicted for novel sequences. A controlled ablation experiment assessing unsupervised contact prediction on sets of related protein families finds a gain from amortization for low-depth multiple sequence alignments; the result is then confirmed on a database with broad coverage of protein sequences.

One-sentence Summary: We propose the Neural Potts Model objective, which enables a single feedforward model to learn the Potts Model energy landscape across many protein families.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=66asXq-uXEq