Mechanistic Interpretability of Fine-Tuned Protein Language Models for Nanobody Thermostability Prediction

Clicks: 13
ID: 329330
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #935 of 983 articles by views in BMC Bioinformatics

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 983 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
MOTIVATION: While Protein Language Models (PLMs) fine-tuned on biophysical data achieve high predictive accuracy, the physical principles underlying their predictions remain obscure. Deciphering these representations offers a unique opportunity to not only interpret model decisions but also to discover novel biophysical insights governing protein properties. Here, we present a framework using Sparse Autoencoders (SAEs) to extract mechanistic knowledge from PLMs fine-tuned for nanobody thermostability. RESULTS: We fine-tuned the ESM-2 model on the nanobody thermostability dataset, achieving superior performance compared to significantly larger state-of-the-art models. SAE analysis successfully decomposed the model's dense embeddings into sparse, interpretable features without loss of predictive accuracy. We characterized these features through both global and local analyses. Global analysis provided an aggregate map of position-dependent feature contributions, whereas local analysis identified specific residue-level patterns, including known determinants such as the VHH-tetrad and critical disulfide bonds, as well as candidate stabilizing residues. Free Energy Perturbation calculations supported the structural plausibility of selected residue-level hypotheses. These results show that SAE-based interpretation can generate testable, structurally grounded hypotheses for rational protein engineering. AVAILABILITY: The data and source code of the proposed method are available at GitHub (https://github.com/matsunagalab/paper_nanobody-thermostability-sae) and Zenodo (DOI: 10.5281/zenodo.18012027). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Reference Key
openalex_W7213874224 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Taihei Murakami, Yuki Hashidate, Yasuhiro Matsunaga
Are you one of these authors? Claim your profile
Journal BMC Bioinformatics
Year 2026
DOI
10.1093/bioinformatics/btag685
URL
https://doi.org/10.1093/bioinformatics/btag685
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.