Sequence-Only Prediction of Antibody Fab Thermostability Using Protein Language Model Embeddings
Sennett, M.
Show abstract
Antibody developability is a critical consideration in therapeutic manufacturing, with conformational stability--measured by melting temperature (Tm)--being a key determinant of manufacturability. Traditional experimental approaches to assess Tm are costly and low-throughput, while statistical models offer limited predictive power and generalizability. In this study, we present a scalable, sequence-only machine learning (ML) approach to predict the thermostability of antigen-binding fragments (Fabs) using embeddings from IgBERT, a protein language model fine-tuned on antibody sequences. We trained a Random Forest regressor on 133 proprietary antibody sequences with measured Fab Tm values, achieving a Pearson correlation coefficient (PCC) of 0.77 on a held-out internal test set. When applied to a Jain set of clinical-stage therapeutics, the model retained predictive power (PCC = 0.28), outperforming baseline statistical and sequence-similarity methods. Embedding proximity in t-SNE space correlated with prediction accuracy, suggesting that model generalizability is influenced by distributional similarity rather than sequence identity. Our results demonstrate that PLM-derived embeddings encode biophysical features relevant to Fab thermostability and offer a fast, interpretable, and scalable route to de-risk antibody lead candidates.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Towards guided mutagenesis: Gaussian process regression predicts MHC class II antigen mutant binding 94%
- Cycledesigner Leveraging RFdiffusion and HighFold to Design Cyclic Peptide Binders for Specific Targets 94%
- Disentangling the contribution of each descriptive characteristic of every single mutation to its functional effects 93%
Similar papers in this journal
- Accurate and Rapid Prediction of Protein pKa: Protein Language Models Reveal the Sequence-pKa Relationship 94%
- BioStructNet: Structure-Based Network with Transfer Learning for Predicting Biocatalyst Functions 94%
- KaMLs for Predicting Protein pKa Values and Ionization States: Are Trees All You Need? 93%
Similar papers in this journal
Similar papers in this journal
- Towards generalizable prediction of antibody thermostability using machine learning on sequence and structure features 96%
- Prediction of Antibody Non-Specificity using Protein Language Models and Biophysical Parameters 94%
- AbDesign: Database of point mutants of antibodies with associated structures reveals poor generalization of binding predictions from machine learning models. 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.