Biology subjects

Bachas, S.

Publications and source records attributed to Bachas, S..

5 recordsLinked to original sources

bioRxiv2026

Language Modeling Materializes a World Model of Protein Biology

Proteins are fundamental to life. The full extent of their biology is beyond our ability to characterize with experimental approaches in the physical laboratory. Accurate digital representations could accelerate the discovery of protein biology through virtual experiments. We propose language modeling to learn unified and general representations that can be scaled to all of protein biology. Building on these representations, we develop a structure prediction model that exceeds the performance of established methods for biomolecular complex prediction across benchmarks, including for the interactions of antibodies with their targets. A simple search procedure yields high experimental success rates for the discovery of proteins with nanomolar binding affinities for both miniproteins and single-chain antibodies, a modality critical for therapeutic design. Study of the concepts in the language models representation space reveals a systematic organization aligned with the reductionist understanding of proteins developed through empirical science. Leveraging this organization, we generate a comprehensive map of protein biology encompassing over 6.8 billion sequences and 1.1 billion predicted structures, identifying connections across known and unknown biology. As a whole, this shows language modeling as a powerful substrate for representing the biology of proteins, operating across scales from the prediction and design of protein interactions at the atomic level, to identifying properties of proteins at different levels of granularity and abstraction, to the scale of mapping connections between proteins across billions of years of evolution.

bioinformatics↗

bioRxiv2025

Iterative Epitope Expansion Enables Structure-Guided de novoDesign of IgE-Binding Miniproteins Targeting the FcεRI Interface

Designing de novo protein binders to multidomain assemblies remains challenging due to their structural complexity, conformational diversity, and broad functional epitopes. Here, we present an iterative epitope-expansion strategy that enables structure-guided design of compact miniproteins targeting human immunoglobulin E (IgE). Direct attempts to design binders against the full Fc{varepsilon}RI-binding interface of IgE produced candidates with poor in silico confidence and limited experimental success. Instead, by first targeting a nearby, geometrically tractable seed epitope on the IgE C{varepsilon}3 domain, we obtained initial binders that served as anchors for progressive, structure-guided expansion toward the full receptor-binding interface. Iteration through an integrated AI-human-wet-lab design loop yielded a second-round miniprotein with approximately 30-fold improved affinity and substantial structural overlap with the Fc{varepsilon}RI-binding site. Alanine-scanning mutagenesis confirmed that loss-of-function substitutions mapped precisely to the designed binding interfaces, validating the structural models. Polyspecificity profiling revealed that two of three binders exhibited low off-target binding comparable to antibody benchmarks, whereas one design displayed elevated polyspecificity that was strongly amplified upon Fc fusion. Notably, a previously published high-affinity miniprotein benchmark exhibited similar format-dependent liabilities, underscoring an underappreciated developability risk in the de novo miniprotein literature. Competition assays further demonstrated that two binders occupy regions of IgE that overlap with the Fc{varepsilon}RI binding interface, as evidenced by loss of miniprotein binding when Fc{varepsilon}RI is pre-bound to IgE Fc, consistent with the intended design geometry. Together, these results establish epitope expansion as a generalizable strategy for steering generative protein design toward challenging multidomain epitopes and highlight the necessity of tightly coupled AI-human-experimental workflows for achieving both functional specificity and developability in de novo binder discovery.

bioengineering↗

bioRxiv2023

In vitro validated antibody design against multiple therapeutic antigens using generative inverse folding

Deep learning approaches have demonstrated the ability to design protein sequences given backbone structures [1, 2, 3, 4, 5]. While these approaches have been applied in silico to designing antibody complementarity-determining regions (CDRs), they have yet to be validated in vitro for designing antibody binders, which is the true measure of success for antibody design. Here we describe IgDesign, a deep learning method for antibody CDR design, and demonstrate its robustness with successful binder design for 8 therapeutic antigens. The model is tasked with designing heavy chain CDR3 (HCDR3) or all three heavy chain CDRs (HCDR123) using native backbone structures of antibody-antigen complexes, along with the antigen and antibody framework (FWR) sequences as context. For each of the 8 antigens, we design 100 HCDR3s and 100 HCDR123s, scaffold them into the native antibodys variable region, and screen them for binding against the antigen using surface plasmon resonance (SPR). As a baseline, we screen 100 HCDR3s taken from the models training set and paired with the native HCDR1 and HCDR2. We observe that both HCDR3 design and HCDR123 design outperform this HCDR3-only baseline. IgDesign is the first experimentally validated antibody inverse folding model. It can design antibody binders to multiple therapeutic antigens with high success rates and, in some cases, improved affinities over clinically validated reference antibodies. Antibody inverse folding has applications to both de novo antibody design and lead optimization, making IgDesign a valuable tool for accelerating drug development and enabling therapeutic design. The data generated in this study serve as a useful benchmark of diverse antibody-antigen interactions. We use this data to benchmark self-consistency RMSD (scRMSD), using ABodyBuilder2 [6], ABodyBuilder3 [7], and ESMFold [8], as a metric for assessing binding. We open source the code for IgDesign and the SPR datasets. Code and datasets can be found at https://github.com/AbSciBio/igdesign.

synthetic biology↗

bioRxiv2023

Unlocking de novo antibody design with generative artificial intelligence

Generative AI has the potential to redefine the process of therapeutic antibody discovery. In this report, we describe and validate deep generative models for the de novo design of antibodies against human epidermal growth factor receptor (HER2) without additional optimization. The models enabled an efficient workflow that combined in silico design methods with high-throughput experimental techniques to rapidly identify binders from a library of [~]106 heavy chain complementarity-determining region (HCDR) variants. We demonstrated that the workflow achieves binding rates of 10.6% for HCDR3 and 1.8% for HCDR123 designs and is statistically superior to baselines. We further characterized 421 diverse binders using surface plasmon resonance (SPR), finding 71 with low nanomolar affinity similar to the therapeutic anti-HER2 antibody trastuzumab. A selected subset of 11 diverse high-affinity binders were functionally equivalent or superior to trastuzumab, with most demonstrating suitable developability features. We designed one binder with [~]3x higher cell-based potency compared to trastuzumab and another with improved cross-species reactivity1. Our generative AI approach unlocks an accelerated path to designing therapeutic antibodies against diverse targets.

synthetic biology↗

bioRxiv2022

Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness

Traditional antibody optimization approaches involve screening a small subset of the available sequence space, often resulting in drug candidates with suboptimal binding affinity, developability or immunogenicity. Based on two distinct antibodies, we demonstrate that deep contextual language models trained on high-throughput affinity data can quantitatively predict binding of unseen antibody sequence variants. These variants span a KD range of three orders of magnitude over a large mutational space. Our models reveal strong epistatic effects, which highlight the need for intelligent screening approaches. In addition, we introduce the modeling of "naturalness", a metric that scores antibody variants for similarity to natural immunoglobulins. We show that naturalness is associated with measures of drug developability and immunogenicity, and that it can be optimized alongside binding affinity using a genetic algorithm. This approach promises to accelerate and improve antibody engineering, and may increase the success rate in developing novel antibody and related drug candidates.

bioinformatics↗