MétaCan
Menu
Back to cohort
Record W4411005336 · doi:10.1101/2025.05.30.656964

Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models

2025· preprint· en· W4411005336 on OpenAlexaff
Yuanxi Yu, Fan Jiang, Xinzhu Ma, Bozitao Zhong, Wanli Ouyang, Guisheng Fan, Haiying Yu, Liang Hong, Mingchen Li

Bibliographic record

VenuebioRxiv (Cold Spring Harbor Laboratory) · 2025
Typepreprint
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicProtein Structure and Dynamics
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersCentre Scientifique et Technique du BâtimentShanghai Jiao Tong UniversityScience and Technology Commission of Shanghai Municipality
KeywordsVenusStability (learning theory)MutationComputer scienceAstrobiologyChemistryPhysicsMachine learningBiochemistry

Abstract

fetched live from OpenAlex

Abstract In-silico prediction of protein mutant stability, measured by the difference in Gibbs free energy change (ΔΔ G ), is fundamental for protein engineering. Current sequence-to-label methods typically employ the two-stage pipeline: ( i ) encoding mutant sequences using neural networks ( e . g ., transformers), followed by ( ii ) the ΔΔ G regression from the latent representations. Although these methods have demonstrated promising performance, their dependence on specialized neural network encoders significantly increases the complexity. Additionally, the requirement to individually compute latent representations for each mutant site negatively impacts computational efficiency and poses the risk of overfitting . This work proposes the Venus-M axwell framework, which reformulates mutation ΔΔ G prediction as a sequence-to-landscape task. In Venus-M axwell , mutations of a protein and their corresponding ΔΔ G values are organized into a landscape matrix, allowing our framework to learn the ΔΔ G landscape of a protein with a single forward and backward pass during training. Besides, to facilitate future works, we also curated a large-scale ΔΔ G dataset with strict controls on data leakage and redundancy to ensure robust evaluation. Venus-M axwell is compatible with multiple protein language models and enables these models for accurate and efficient ΔΔ G prediction. For example, when integrated with the ESM-IF, Venus-M axwell achieves higher accuracy than ThermoMPNN with 10× faster in inference speed (despite having 50× more parameters than ThermoMPNN). The training codes, model weights, and datasets are publicly available at https://github.com/ai4protein/Venus-MAXWELL .

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.008
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.002
Open science0.0030.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

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 head0.009
GPT teacher head0.224
Teacher spread0.216 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuebioRxiv (Cold Spring Harbor Laboratory)Same topicProtein Structure and DynamicsFrench-language works237,207