Biology subjects

McPartlon, M.

Publications and source records attributed to McPartlon, M..

7 recordsLinked to original sources

bioRxiv2025

Drug-like antibody design against challenging targets with atomic precision

Computational antibody design has seen rapid progress, with high success rates enabling direct translation to characterization without any high-throughput screening required. In this work, we markedly expand the scope of de novo antibody design by applying our state-of-the-art Chai-2 platform to design drug-like antibodies in full-length monoclonal format. We find that >86% of these full-length mAbs have strong developability profiles on par with therapeutic antibodies. We further show that experimentally determined structures of Chai-2 designs closely match their in silico predictions, demonstrating that Chai-2 produces atomically accurate models of designed antibodies. Building on these foundational capabilities, we showcase two potential applications of Chai-2 against different targets: designing functional antibodies mediating GPCR agonism, and highly specific antibodies selectively binding tumor-specific neoepitopes. Taken together, this work brings new flexibility to modern discovery pipelines, accelerating the path from in silico design to functional validation across both conventional and challenging targets. Beyond reducing the cost and timelines associated with large screening campaigns, in silico design can now open new frontiers for creative, targeted therapeutics that address unmet clinical needs.

molecular biology↗

bioRxiv2025

Zero-shot antibody design in a 24-well plate

Despite breakthroughs in protein design enabled by artificial intelligence, reliably designing functional antibodies from scratch has remained an elusive challenge. Recent works show promise but still require large-scale experimental screening of thousands to millions of designs to reliably identify hits. In this work, we introduce Chai-2, a multimodal generative model that achieves a 16% hit rate in fully de novo antibody design, representing an over 100-fold improvement compared to previous computational methods. We prompt Chai-2 to design[≤] 20 antibodies or nanobodies to 52 diverse targets, completing the workflow from AI design to wet-lab validation in under two weeks. Crucially, none of these targets have a preexisting antibody or nanobody binder in the Protein Data Bank. Remarkably, in just a single round of experimental testing, we find at least one successful hit for 50% of targets, often with strong affinities and favorable drug-like profiles. Beyond antibody design, Chai-2 achieves a 68% wet-lab success rate in miniprotein design - routinely yielding picomolar binders. The high success rate of Chai-2 enables rapid experimental validation and characterization of novel antibodies in under two weeks, paving the way toward a new era of rapid and precise atomic-level molecular engineering. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=56 SRC="FIGDIR/small/663018v1_ufig1.gif" ALT="Figure 1"> View larger version (38K): org.highwire.dtl.DTLVardef@69655borg.highwire.dtl.DTLVardef@17d44dborg.highwire.dtl.DTLVardef@133b7ddorg.highwire.dtl.DTLVardef@6c4319_HPS_FORMAT_FIGEXP M_FIG 52 antigens targeted by Chai-2. Blue boxes indicate targets with at least one successful binder out of [≤]20 assayed designs, representing 50% of the tested targets. Date: June 30, 2025 C_FIG

synthetic biology↗

bioRxiv2024

Chai-1: Decoding the molecular interactions of life

We introduce Chai-1, a multi-modal foundation model for molecular structure prediction that performs at the state-of-the-art across a variety of tasks relevant to drug discovery. Chai-1 can optionally be prompted with experimental restraints (e.g. derived from wet-lab data) which boosts performance by double-digit percentage points. Chai-1 can also be run in single-sequence mode with-out MSAs while preserving most of its performance. We release Chai-1 model weights and inference code as a Python package for non-commercial use and via a web interface where it can be used for free including for commercial drug discovery purposes.

synthetic biology↗

bioRxiv2024

PINDER: The protein interaction dataset and evaluation resource

Protein-protein interactions (PPIs) are fundamental to understanding biological processes and play a key role in therapeutic advancements. As deep-learning docking methods for PPIs gain traction, benchmarking protocols and datasets tailored for effective training and evaluation of their generalization capabilities and performance across real-world scenarios become imperative. Aiming to overcome limitations of existing approaches, we introduce PINDER, a comprehensive annotated dataset that uses structural clustering to derive non-redundant interface-based data splits and includes holo (bound), apo (unbound), and computationally predicted structures. PINDER consists of 2,319,564 dimeric PPI systems (and up to 25 million augmented PPIs) and 1,955 high-quality test PPIs with interface data leakage removed. Additionally, PINDER provides a test subset with 180 dimers for comparison to AlphaFold-Multimer without any interface leakage with respect to its training set. Unsurprisingly, the PINDER benchmark reveals that the performance of existing docking models is highly overestimated when evaluated on leaky test sets. Most importantly, by retraining DiffDock-PP on PINDER interface-clustered splits, we show that interface cluster-based sampling of the training split, along with the diverse and less leaky validation split, leads to strong generalization improvements.

bioinformatics↗

bioRxiv2023

Deep Learning for Flexible and Site-Specific Protein Docking and Design

Protein complexes are vital to many biological processes and their understanding can lead to the development of new drugs and therapies. Although the structure of individual protein chains can now be predicted with high accuracy, determining the three-dimensional structure of a complex remains a challenge. Protein docking, the task of computationally determining the structure of a protein complex given the unbound structures of its components (and optionally binding site information), provides a way to predict protein complex structure. Traditional docking methods rely on empirical scoring functions and rigid body simulations to predict the binding poses of two or more proteins. However, they often make unrealistic assumptions about input structures, and are not effective at accommodating conformational flexibility or binding site information. In this work, we present DockGPT (Generative Protein Transformer for Docking), an end-to-end deep learning method for flexible and site-specific protein docking that allows conformational flexibility and can effectively make use of binding site information. Tested on multiple benchmarks with unbound and predicted monomer structures as input, we significantly outperform existing methods in both accuracy and running time. Our performance is especially pronounced for antibody-antigen complexes, where we predict binding poses with high accuracy even in the absence of binding site information. Finally, we highlight our methods generality by extending it to simultaneously dock and co-design the sequence and structure of antibody complementarity determining regions targeting a specified epitope.

bioinformatics↗

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

AttnPacker: An end-to-end deep learning method for rotamer-free protein side-chain packing

Protein side-chain packing (PSCP), the task of determining amino acid side-chain conformations, has important applications to protein structure prediction, refinement, and design. Many methods have been proposed to resolve this problem, but their accuracy is still unsatisfactory. To address this, we present AttnPacker, an end-to-end, SE(3)-equivariant deep graph transformer architecture for the direct prediction of side-chain coordinates. Unlike existing methods, AttnPacker directly incorporates backbone geometry to simultaneously compute all amino acid side-chain atom coordinates without delegating to a rotamer library, or performing expensive conformational search or sampling steps. Tested on the CASP13 and CASP14 native and non-native protein backbones, AttnPacker predicts side-chain conformations with RMSD significantly lower than the best side-chain packing methods (SCWRL4, FASPR, Rosetta Packer, and DLPacker), and achieves even greater improvements on surface residues. In addition to RMSD, our method also achieves top performance in side-chain dihedral prediction across both data sets.

bioinformatics↗