Anshul Kundaje#1650
Antibody LMs learn what looks antibody-like, but not how selection turns naive germline antibodies into strong binders.
@aakarshv1 and I are excited to share CoSiNE, a model that learns this germline-to-mature process for variant effect prediction and antibody design. (1/8)
Users are excited about the CoSiNE model for antibody maturation and design because they see it as amazing work and are happy to encounter related tools like OASis in the wild.
Please check out our forthcoming ICML paper on learning the BCR affinity maturation process, with applications in variant effect prediction and antibody design.
Antibody LMs learn what looks antibody-like, but not how selection turns naive germline antibodies into strong binders.
@aakarshv1 and I are excited to share CoSiNE, a model that learns this germline-to-mature process for variant effect prediction and antibody design. (1/8)
The resulting samples remain structurally plausible and human-like.
We think this is a promising step toward controllable evolutionary protein design: not just generating sequences de novo, but guiding the processes that produce them. (7/8)
Affinity maturation is how naive antibodies evolve into strong binders, but most antibody LMs ignore it.
@stephenzlu and I built CoSiNE to learn this, beating antibody LMs on VEP and reframing design as guiding evolution, not de novo generation.
Excited to present at ICML!
Antibody LMs learn what looks antibody-like, but not how selection turns naive germline antibodies into strong binders.
@aakarshv1 and I are excited to share CoSiNE, a model that learns this germline-to-mature process for variant effect prediction and antibody design. (1/8)
Traditional antibody language modeling assumes sequences are i.i.d. — ignoring the time-dependent process of affinity maturation.
To address this, CoSiNE explicitly models transitions: how likely is a mature antibody y to arise from a germline precursor x over time t? (2/8)
Huge thanks to my coauthors @aakarshv1 , @koheisanno , @jiarlu , @ematsen , @milind_jagota , and @yun_s_song ! We will be presenting at ICML.
Preprint: https://arxiv.org/abs/2602.18982 Code: https://github.com/thematrixmaster/cosine Blog: https://songlab-cal.github.io/cosine (8/8)
A key challenge is that antibody evolution mixes two signals.
Some mutations are frequent because they are likely under somatic hypermutation. Others occur because the antibodies carrying them are favored by selection.
For VEP & design, we want to separate these effects. (3/8)
CoSiNE achieves this by comparing two likelihoods:
How likely is a mutation under the learned maturation model?
How likely is it under neutral SHM?
The difference gives a selection score: enrichment beyond mutation bias. This improves VEP over transition likelihood. (4/8)
We also explore CoSiNE as a design model.
With predictor guidance sampling, we steer simulated maturation trajectories toward desired properties at inference time, biasing evolution toward antibodies with higher predicted affinity for specific antigens. (6/8)
Importantly, our selection score beats strong antibody and protein LM baselines on zero-shot antibody VEP across binding and expression datasets.
This suggests that learning germline-to-mature evolution adds signal beyond antibody-likeness alone. (5/8)
@stephenzlu @aakarshv1 Amazing workkk
@stephenzlu Always happy to see OASis in the wild! Btw check out promb for a high throughput implementation if you haven’t already
@stephenzlu https://github.com/MSDLLCpapers/promb
Anshul Kundaje#1650Antibody LMs learn what looks antibody-like, but not how selection turns naive germline antibodies into strong binders.
@aakarshv1 and I are excited to share CoSiNE, a model that learns this germline-to-mature process for variant effect prediction and antibody design. (1/8)