PT  - JOURNAL ARTICLE
AU  - Tom Sercu
AU  - Robert Verkuil
AU  - Joshua Meier
AU  - Brandon Amos
AU  - Zeming Lin
AU  - Caroline Chen
AU  - Jason Liu
AU  - Yann LeCun
AU  - Alexander Rives
TI  - Neural Potts Model
AID  - 10.1101/2021.04.08.439084
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.04.08.439084
4099  - http://biorxiv.org/content/early/2021/04/11/2021.04.08.439084.short
4100  - http://biorxiv.org/content/early/2021/04/11/2021.04.08.439084.full
AB  - 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.Competing Interest StatementThe authors have declared no competing interest.