ArticlePacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention.
Article in Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 11 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
11 citing papers in PubMed.
- Article
- Phylogenetic corrections and higher-order sequence statistics in protein families: Potts vs multiple sequence alignment transformer machine learning models.Physical review research · 2025Article
- Nucleotide dependency analysis of genomic language models detects functional elements.Nature genetics · 2025Article
- How the technologies behind self-driving cars, social networks, ChatGPT, and DALL-E2 are changing structural biology.BioEssays : news and reviews in molecular, cellular and developmental biology · 2025Review
- Protein language models learn evolutionary statistics of interacting sequence motifs.Proceedings of the National Academy of Sciences of the United States of America · 2024Article
- Artificial Intelligence Learns Protein Prediction.Cold Spring Harbor perspectives in biology · 2024Review
- Kinetic coevolutionary models predict the temporal emergence of HIV-1 resistance mutations under drug selection pressure.Proceedings of the National Academy of Sciences of the United States of America · 2024Article
- Article
- End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman.Bioinformatics (Oxford, England) · 2023Article
- Protein language models trained on multiple sequence alignments learn phylogenetic relationships.Nature communications · 2022Article
- Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
8 authors.
Funding
Abstract
The established approach to unsupervised protein contact prediction estimates coevolving positions using undirected graphical models. This approach trains a Potts model on a Multiple Sequence Alignment. Increasingly large Transformers are being pretrained on unlabeled, unaligned protein sequence databases and showing competitive performance on protein contact prediction. We argue that attention is a principled model of protein interactions, grounded in real properties of protein family data. We introduce an energy-based attention layer, factored attention, which, in a certain limit, recovers a Potts model, and use it to contrast Potts and Transformers. We show that the Transformer leverages hierarchical signal in protein family databases not captured by single-layer models. This raises the exciting possibility for the development of powerful structured models of protein family databases.
Indexed as
Identifiers
34890134PMC8752338What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.