Computational Antibody Papers
Filter by tags
developability
Filter by published year
2026
TitleKey points
- Novel dataset of 160 VHH-Fc profiled across 10 biophysical assays.
- They demonstrated that tabular neural networks (TabICLv2, TabPFN v2.5) trained solely on 559 IgG heavy chains outperform intra-format VHH-Fc models in zero-shot predictions, showing that training data scale outweighs structural divergence between scaffolds.
- Surface-driven properties transfer with high accuracy, heparin binding (rho=.82), hydrophobicity (HIC, rho=.63), and self-association (AC-SINS, rho=0.62), whereas thermostability (Tm2, rho=0.16) remains scaffold-dependent and requires direct measurement.
- Augmenting models with simple surface property inputs (HIC and HAC) boosts prediction accuracy for complex liabilities like polyreactivity (PR-CHO, rho = 0.40 to 0.51).
2026-08-28
Aligning protein-generative models to experimental fitness with ProteinDPO
- developability
- language models
- Novel way (ProteinDPO) to apply pre-trained models to biophysical readouts.
- ProteinDPO is the first framework to apply Direct Preference Optimization (introducing a novel scalar-weighted DPO objective) to align protein generative models with experimental biophysical data, without overfitting like traditional supervised fine-tuning.
- Despite training exclusively on small monomeric stabilities, ProteinDPO generalizes zero-shot to accurately rank the thermal melting temperatures of multichain antibodies and score antibody-antigen binding affinities.
- Applied to H5N1 influenza hemagglutinin, it generated stabilized variants yielding up to a 32C improvement in thermal stability while retaining strong nanomolar binding affinity to broadly neutralizing anti-HA antibodies.
2026-08-21
A blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability
- binding prediction
- developability
- ngs
- Results from the antibody discovery competition, where ML methods faced off with experimental baselines.
- Participating organizations were evaluated across three tasks on a SARS-CoV-2 receptor-binding domain (RBD) dataset: (1) in silico affinity maturation by modifying non-HCDR3 CDRs using sequencing outputs, (2) affinity ranking of candidates within three HCDR3-clustered sequence datasets, and (3) out-of-library CDR optimization/design to generate novel high-affinity binders not present in the sequencing data.
- For lead optimization, top ML methods matched experimental performance by producing sub-100 pM binders (top ML design: 95 pM vs. best experimental control: 113 pM), though overall ML submissions underperformed relative to experimental sorting libraries. Notably, a simple non-ML statistical consensus baseline also achieved a highly competitive 540 pM affinity without using machine learning.
- For sequence ranking within HCDR3 clusters, almost all ML algorithms performed worse than random clone picking; only 9.8%-13.8% of ML submissions beat the cluster baseline clone compared to 39% from random selection. Additionally, out-of-library ML designs yielded a high proportion of non-binders (30.4%) and top-ranked affinity hits frequently suffered from severe biophysical developability failures.
- ML is genuinely useful for timeline reduction during lead optimization and affinity maturation, replacing 2-3 weeks of physical combination library construction with an in silico step when provided with deep, biologically grounded experimental datasets.
- Pretrained protein language models (PLMs) paired with structure-aware modules (e.g., pairformers) showed utility in exploring novel out-of-library sequence spaces. However, current ML models lack cross-task generalization, struggle with local epistasis, and fail to reliably co-optimize affinity alongside multiparametric biophysical developability.
2026-07-13
Decoding Bispecific Antibody Developability: Design Rules and Predictive Models from a 160-Member Library
- developability
- Developability characterization of multispecific antibodies, for the purposes of training machine learning models
- To map out developer behavior, the researchers used advanced diversity-sampling algorithms to select 160 unique bispecific combinations from 65 parental antibodies, capturing a vast spectrum of biophysical profiles.
- Developability traits don’t transfer uniformly from parent to child; while hydrophobicity and charge are highly predictable, critical flaws like self-association often emerge unexpectedly as "outliers" when the two arms interact.
- The study revealed that thermostability is strictly format-driven, meaning it cannot be reliably predicted from parental data and must be measured directly on the final multi-specific construct.
- Very fast antibody modeling, FlashABB, with applications to developability screening.
- FlashABB accurately performs sota antibody antibody structure prediction in just 5 ms, making it faster than protein language models can even generate sequence embeddings, by completely discarding traditional pair representations in favor of an inner-product-based, linear-memory "Flashpoint Attention" (FPA) algorithm.
- Featuring roughly 7.2 million parameters trained on 8,395 SAbDab structures, the model is strictly forced to run on float32 precision to avoid the catastrophic numerical cancellation errors that heavily degrade 16-bit float implementations during distance calculations.
- Eliminating the structural compute bottleneck allows developers to scale downstream analysis to millions of sequences; using the variant tool FlashTAP, teams can filter out liability flags and predict therapeutic developability metrics for 100 antibodies per second.
- Having said that, CDR-H3 is still sota - so in the region of 2.5A, but it gets there way faster.
2026-04-30
Large scale developability benchmarking dataset from Amazon AWS and Gray Lab
- developability
- Generation of a large-scale, heterogeneous antibody developability dataset for AI benchmarking.
- Built from 50 seed antibodies with up to 99 engineered variants each, resulting in thousands of unique, wet-lab-validated sequences.
- Assesses six critical developability traits: expression, purity, thermostability, aggregation, polyreactivity, and hydrophobicity.
- Benchmark results are currently accessible via Amazon Bio Discovery, with further findings slated for a formal publication later this year.
2026-04-24
BOAT: Navigating the Sea of In Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization
- protein design
- developability
- Case study & framework how to tie together available computational annotators to perform cross reactivity optimization for a VHH.
- It replaces inefficient, sequential screening pipelines with a multi-objective Bayesian optimization loop. It uses a Gaussian process surrogate model coupled with a genetic algorithm to navigate complex sequence spaces and identify Pareto-optimal candidates.
- The framework is model-agnostic; users must provide and validate the in silico "oracles" (predictive models) relevant to their specific optimization goals. Objectives are defined by selecting and potentially weighting these interchangeable scoring functions.
- The authors rigorously benchmarked BOAT against standard genetic algorithms and generative baselines (like LaMBO-2). Testing relied on computational benchmarks, including comparing results against exhaustive "ground truth" Pareto fronts in limited search spaces.
- The study did not perform wetlab validation. Because the framework relies entirely on in silico oracles as proxies, the final experimental success of the optimized candidates is ultimately tied to the predictive quality of the models the user selects.
2026-04-17
Biologically-Grounded Multi-Encoder Architectures as Developability Oracles for Antibody Design
- developability
- Training of a baseline developability predictor on the Gingko dataset.
- Utilized the GDPal benchmark from Ginkgo Bioworks, consisting of 242 therapeutic IgGs across five assays: HIC, AC-SINS, PR_CHO, Titer, and Tm2.
- Employed frozen ESM-Cambrian encoders (up to 6B parameters) to generate embeddings, which were processed by property-specific attention decoders (Self, Self+Cross, or Bidirectional Cross) and a prediction head.
- Achieved significant improvements over baselines in 3/5 properties: expression titer (+20%), thermal stability (+18%), and polyreactivity (+12%).
- Optimal attention schemes differ by property; self-attention alone suffices for aggregation-related traits (HIC, PR_CHO), while bidirectional cross-attention is required for properties involving inter-chain compatibility (Titer, Tm2).
2026-03-27
Application of protein language models for antibody developability prediction
- developability
- Analysis of developability data from 33 internal Biogen programs, covering 18,540 antibodies.
- Focused on three dimensions: hydrophobicity (HIC), polyspecificity (PSR), and self-association (AC-SINS).
- Labeled subsets included 4,594 (PSR), 1,792 (HIC), and 7,727 (AC-SINS) sequences.
- Benchmarked three PLMs: ESM2 (general-purpose), plus IgBert and IgT5 (antibody-specific).
- Domain-adaptive fine-tuning consistently boosted antibody-specific PLMs, but often degraded ESM2 performance.
- Antibody-specific PLMs generally provided better embeddings for PSR and AC-SINS, while ESM2 remained highly competitive for HIC.
- Perplexity was only weakly correlated in aggregate, but showed significant association with PSR/AC-SINS failure when controlled for a fixed light chain
2026-02-26
Ginkgo Datapoints Antibody Developability Competition outcomes: limited model performance and a call for data standardization
- developability
- Results of the Gingko developability competition.
- Benchmarked 113 teams on predicting five key developability traits: hydrophobicity, thermostability, self-association, expression titer, and polyreactivity.
- Models were trained on the GDPa1 dataset (246 antibodies) and blindly tested on GDPa3 (80 diverse antibodies from OAS).
- While cross-validation (CV) results were promising, performance plummeted on the test set e.g., self-association dropped from a 0.653 CV Spearman's rho to 0.356.
- Hydrophobicity was the most predictable (rho = 0.708), while expression titer was the most challenging (rho = 0.310).
- Winning models varied by assay; for example, team AbDevelop won for self-interaction, while microcrisprtm2 led in thermostability.