Biology subjects

Ucar, T.

Publications and source records attributed to Ucar, T..

5 recordsLinked to original sources

bioRxiv2026

BoltzProt-1: Towards Efficient De Novo Binder Design with Good Developability

Designing binders against novel protein targets remains a central challenge in computational drug discovery. Here we introduce BoltzProt-1, a pipeline for generating protein binders, including nanobodies, with improved hit rates and favorable developability properties. At its core lie a refined iteration of BoltzGens generative model and a novel protein-protein interaction prediction model, BoltzPPI. Employing BoltzPPI instead of BoltzGens standard structure-prediction confidence metrics to rank nanobody (VHH) designs increases the confirmed-binder hit rate from 3.3% to 8.0% across 10 novel targets. Assessed on 10 additional targets used in prior literature, the BoltzProt-1 pipeline obtains nanobody screening hits for 7 of 10 targets, surpassing the 6 of 10 previously reported by Chai-2. Finally, evaluating the developability of BoltzProt-1-designed nanobodies in terms of stability, aggregation, purity, polyspecificity and hydrophobicity reveals that 58% of its confirmed binders pass every criterion, exceeding both BoltzGen (40%) and clinical-stage VHH controls (21%). O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=104 SRC="FIGDIR/small/733997v1_ufig1.gif" ALT="Figure 1"> View larger version (39K): org.highwire.dtl.DTLVardef@d86de1org.highwire.dtl.DTLVardef@115da7eorg.highwire.dtl.DTLVardef@1bbb4e9org.highwire.dtl.DTLVardef@626a68_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2025

BoltzGen: Toward Universal Binder Design

We introduce BoltzGen, an all-atom generative model for designing proteins and peptides across all modalities to bind a wide range of biomolecular targets. BoltzGen builds strong structural reasoning capabilities about target-binder interactions into its generative design process. This is achieved by unifying design and structure prediction, resulting in a single model that also reaches state-of-the-art folding performance. BoltzGens generation process can be controlled with a flexible design specification language over covalent bonds, structure constraints, binding sites, and more. We experimentally validate these capabilities in eight diverse design campaigns with functional and affinity readouts across 26 targets. In our experiments, binder modalities span from nanobodies to disulfide-bonded peptides, and targets from disordered proteins to small molecules. In particular, we identify nanobody binders for novel targets with low similarity to proteins with already known bound structures. We release model weights, data, and both inference and training code at: https://github.com/HannesStark/boltzgen.

bioengineering↗

bioRxiv2025

BLOSUM Is All You Learn - Generative Antibody Models Reflect Evolutionary Priors

Generative models have emerged as powerful tools for antibody sequence design, with recent studies demonstrating that log-likelihood scores from these models can correlate with binding affinity and potentially serve as effective ranking metrics. This raises a fundamental question: why should log-likelihood scores from generative models correlate with binding affinity? In this work, we investigate the biochemical basis of these model-derived log-likelihoods by comparing them with classical evolutionary similarity metrics. We find that BLOSUM similarity scores between designed and parental antibody sequences correlate strongly with measured binding affinity--on par with the predictive performance of a state-of-the-art diffusion-based generative model. Moreover, these BLOSUM scores also align closely with log-likelihoods from multiple generative models, suggesting that such models may be implicitly learning evolutionary priors encoded in substitution matrices. When computed with respect to a known binder, both BLO-SUM scores and log-likelihoods act as approximate measures of sequence distance from that reference. As this distance increases, the likelihood of a candidate being a binder decreases, explaining the observed correlation between these scores and binding affinity. In contrast, similarity scores based on position weight matrices (PWMs) and position-specific scoring matrices (PSSMs), which do not rely on knowledge of the parental sequence, show weaker and less consistent alignment with binding affinity, with performance depending on the background sequence data. Additionally, using consensus sequences in place of parental sequences to compute BLOSUM scores largely eliminates the observed correlation with affinity, underscoring the context-specific nature of the correlations. These findings highlight the potential of interpretable, evolution-inspired metrics to complement generative modeling in anti-body design, offering insights into both model behavior and biological relevance.

bioengineering↗

bioRxiv2024

Benchmarking Generative Models for Antibody Design

Generative models trained on antibody sequences and structures have shown great potential in advancing machine learning-assisted antibody engineering and drug discovery. Current state-of-the-art models are primarily evaluated using two categories of in silico metrics: sequence-based metrics, such as amino acid recovery (AAR), and structure-based metrics, including root-mean-square deviation (RMSD), predicted alignment error (pAE), and interface predicted template modeling (ipTM). While metrics such as pAE and ipTM have been shown to be useful filters for experimental success, there is no evidence that they are suitable for ranking, particularly for antibody sequence designs. Furthermore, no reliable sequence-based metric for ranking has been established. In this work, using real-world experimental data from fourteen diverse datasets, we extensively benchmark a range of generative models, including LLM-style, diffusion-based, and graph-based models. We show that log-likelihood scores from these generative models have promising correlation with experimentally measured binding affinities, suggesting that log-likelihood can potentially serve as a reliable metric for ranking antibody sequence designs. Additionally, we scale up one of the diffusion-based models by training it on a large and diverse synthetic dataset, significantly enhancing its ability to rank antibodies based on their binding affinities. We also evaluate non-log-likelihood-based metrics on ten datasets and find that, while they are less consistent for ranking, they provide complementary information. Structure-, energy-, and sequence-based scores appear to be orthogonal and may be used together to increase the likelihood of experimental success. Our implementation is available at: https://github.com/AstraZeneca/DiffAbXL

bioinformatics↗

bioRxiv2024

IgBlend: Unifying 3D Structures and Sequences in Antibody Language Models

Large language models (LLMs) trained on antibody sequences have shown significant potential in the rapidly advancing field of machine learning-assisted antibody engineering and drug discovery. However, current state-of-the-art antibody LLMs often overlook structural information, which could enable the model to more effectively learn the functional properties of antibodies by providing richer, more informative data. In response to this limitation, we introduce IgBlend, which integrates both the 3D coordinates of backbone atoms (C-alpha, N, and C) and antibody sequences. Our model is trained on a diverse dataset containing over 4 million unique structures and more than 200 million unique sequences, including heavy and light chains as well as nanobodies. We rigorously evaluate IgBlend using established benchmarks such as sequence recovery, complementarity-determining region (CDR) editing and inverse folding and demonstrate that IgBlend consistently outperforms current state-of-the-art models across all benchmarks. Furthermore, experimental validation shows that the models log probabilities correlate well with measured binding affinities.

bioinformatics↗