MétaCan
Menu
Back to cohort
Record W4408177377 · doi:10.1016/j.sbi.2025.103027

Language models for protein design

2025· review· en· W4408177377 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueCurrent Opinion in Structural Biology · 2025
Typereview
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicMachine Learning in Bioinformatics
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsProtein designComputational biologyComputer scienceLinguisticsBiologyProtein structureBiochemistryPhilosophy

Abstract

fetched live from OpenAlex

The recent surge of large language models has shown that machines are capable of reading, understanding, and communicating through language, even sometimes displaying capabilities surpassing those of humans. Proteins can be represented as strings of amino acids akin to words in a sentence, and the same principles of language modeling can be used to learn informative representations for protein structure prediction, design, and property prediction. In this review, we will focus on applications of language modeling to protein design. We will first cover the foundations of protein language modeling and discuss recent advances such as context-conditioned design and structure integration. We also consider current shortcomings and promising avenues of research for protein language modeling to facilitate future development of improved protein language models for design.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.991
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.066
GPT teacher head0.414
Teacher spread0.348 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it