DyAb: sequence-based antibody design and property prediction in a low-data regime

Protein therapeutic design and property prediction are frequently hampered by data scarcity. Here we propose a model, DyAb, that addresses these issues by leveraging a pair-wise representation to predict differences in binding affinity, rather than absolute values. DyAb is built on top of a pre-trained protein language model and achieves a Spearman rank correlation of up to 0.85 on binding affinity prediction across monoclonal antibodies targeting three different antigens (EGFR, IL-6, and an internal target), given as few as 100 training data. We employ DyAb in two design contexts: as a ranking model to score combinations of known mutations, and combined with a genetic algorithm to generate new sequences. Our method consistently generates antibody variants with high binding rates, including designs that improve on the binding affinity of the lead molecule by more than ten-fold. DyAb represents a powerful tool for optimizing antibody binding affinity in low data regimes common in early-stage drug development.

Authors

Institutions

Publication Details

Journal
mAbs
Published
2026-08-28
DOI
https://doi.org/10.1080/19420862.2026.2717460
Citations
1
Primary Topic
Monoclonal and Polyclonal Antibodies Research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

DyAb: sequence-based antibody design and property prediction in a low-data regime

Andrew M. Watkins, Jennifer L. Hofmann, Yan Wu, Wei‐Ching Liang et al.
1 citations
mAbs
Monoclonal and Polyclonal Antibodies Research
article

DyAb: sequence-based antibody design and property prediction in a low-data regime

Andrew M. Watkins, Jennifer L. Hofmann, Yan Wu, Wei‐Ching Liang, Andrew Leaver‐Fay, Franziska Seeger, Joshua Yao-Yu Lin, James R. Kiefer, Richard Bonneau, Nataša Tagasovska, Vladimir Gligorijević, Edith Lee, Nathan C. Frey, Kyunghyun Cho, Pedro O. Pinheiro, Stefania Vasilaki
article en
1 citations

Abstract

Protein therapeutic design and property prediction are frequently hampered by data scarcity. Here we propose a model, DyAb, that addresses these issues by leveraging a pair-wise representation to predict differences in binding affinity, rather than absolute values. DyAb is built on top of a pre-trained protein language model and achieves a Spearman rank correlation of up to 0.85 on binding affinity prediction across monoclonal antibodies targeting three different antigens (EGFR, IL-6, and an internal target), given as few as 100 training data. We employ DyAb in two design contexts: as a ranking model to score combinations of known mutations, and combined with a genetic algorithm to generate new sequences. Our method consistently generates antibody variants with high binding rates, including designs that improve on the binding affinity of the lead molecule by more than ten-fold. DyAb represents a powerful tool for optimizing antibody binding affinity in low data regimes common in early-stage drug development.

mAbsVol. 18(1)
Canadian Institute for Advanced Research (CA), Courant Institute of Mathematical Sciences (US), Roche (Sweden) (SE), New York University (US)
Salt Science Research Foundation, Genentech
Openalex Percentile: Top 100%
Monoclonal and Polyclonal Antibodies Research
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.