Biology subjects

Kollasch, A. W.

Publications and source records attributed to Kollasch, A. W..

6 recordsLinked to original sources

bioRxiv2026

Machine Learning enables efficient and effective affinity maturation of nanobodies

Antibodies can bind their targets with exquisite potency and selectivity due in part to large antibody-target protein-protein interaction surface areas. Despite the very large size and diversity of synthetic libraries, in vitro sorting alone tends to yield binders with modest affinities. By analogy to the in vivo affinity maturation in the natural immune system, these initial hits are typically affinity matured in vitro to achieve high affinity binding. However, affinity maturation campaigns can be laborious, often requiring multiple selection rounds and strategies for each clone to be optimized. Here, we investigated whether one could accelerate the discovery of optimized binders using machine learning on sequencing data from single selection sorts of affinity maturation yeast-display campaigns. Our results show that sparse sequencing data from a single sorting round can predict sequences that are enriched after multiple rounds. We also find that linear models outperform deep neural networks and semi-supervised approaches in ranking validated affinity-enhancing substitutions. Linear models are also more interpretable, offering insights into residue preferences that can be leveraged for further engineering. We use our models to design and select optimized nanobody binders to relaxin family peptide receptor 1 (RXFP1), yielding multiple improved binders including 3 sub nanomolar binders with the best exhibiting a [~]2500-fold improvement over WT.

bioinformatics↗

bioRxiv2025

Breaking Through Biology's Data Wall: Expanding the Known Tree of Life by Over 10x using a Global Biodiscovery Pipeline

Advancements in the life sciences have always been built upon our collective understanding of life on Earth. Now, the rise of generative biology - the use of AI foundation models to design, generate, and annotate proteins, pathways and therapeutics - is creating unprecedented demand for large, diverse biological sequence datasets. While a limited subset of such data can be generated in clinical or laboratory settings, the vast majority of the training data for unsupervised models must be sourced from the natural world - the product of nearly four billion years of evolutionary history. However, the public databases that currently supply this data, while foundational to research, were established to aggregate results from academic experiments, not as training datasets for machine learning. Their human-centric data structure limits model performance due to redundancy, taxonomic and geographic bias, limited biological context, and inconsistent provenance. With 68% of all sequence data in the SRA database coming from just 5 species, this is one of the most severe class imbalance problems ever encountered in AI. Legal and infrastructural constraints further exacerbate this bottleneck. To address these limitations and support scalable model training, we introduce BaseData: the largest and fastest-growing biological sequence database ever built, and the first purpose-built for training foundation models. As of late 2024, BaseData contained 9.8 billion novel genes, representing more than a 10-fold expansion in known protein diversity after accounting for redundancy. BaseData also contains more than 1 million species not represented in other genomic databases. Its partnership-driven data supply chain across 26 countries and autonomous regions enables growth of up to 2 billion novel genes per month, far exceeding public repositories. All data is collected under benefit sharing agreements using standardized protocols and structured using graph-based, ontology-rich metadata that preserves evolutionary context. BaseData represents a new, ethically-grounded infrastructure for training biological foundation models, complementing public efforts and enabling the next era of generative biology. Short AbstractProgress of AI in biology is now being limited by the availability of high-quality biological sequence data from nature. To get past this data wall, we introduce BaseData, a new biological database built on top of a global, scalable biodiscovery pipeline. As of 2024, BaseData had already expanded the known protein universe by over 10x.

genomics↗

bioRxiv2025

High-Throughput Machine Learning-Aided Antibody Discovery for Cell Surface Antigens

Machine learning (ML) has the potential to revolutionize antibody design and selection, but its success depends on access to extensive, well-curated datasets of antibody-antigen interactions. To address this need, we developed a synthetic Fab yeast display library optimized for seamless ML integration, focusing on sequence diversity within the CDRH3 loop. The library incorporates key sequence features derived from human B cell repertoires essential for efficient antibody generation captured in a compact antigen recognition module (ARM) format. Built using the VH1-69 heavy chain and four light chains, the library was evaluated against ten human and murine cell surface antigens, including PD-L1, TIGIT, and ROBO1. This approach yielded hundreds of antibodies with robust biophysical properties, validated for functional performance in flow cytometry and immunohistochemistry. Furthermore, ML analysis identified additional antibodies for ROBO2 and PD-L2 from the aggregate sequencing data, demonstrating utility for hybrid in silico and experimental workflows. We provide a publicly accessible dataset comprising more than 68,000 Fab sequences and 486 characterized antibodies. This study establishes an ML-compatible framework designed to accelerate and streamline antibody discovery and development.

biophysics↗

bioRxiv2023

ProteinGym: Large-Scale Benchmarks for Protein Design and Fitness Prediction

Predicting the effects of mutations in proteins is critical to many applications, from understanding genetic disease to designing novel proteins that can address our most pressing challenges in climate, agriculture and healthcare. Despite a surge in machine learning-based protein models to tackle these questions, an assessment of their respective benefits is challenging due to the use of distinct, often contrived, experimental datasets, and the variable performance of models across different protein families. Addressing these challenges requires scale. To that end we introduce ProteinGym, a large-scale and holistic set of benchmarks specifically designed for protein fitness prediction and design. It encompasses both a broad collection of over 250 standardized deep mutational scanning assays, spanning millions of mutated sequences, as well as curated clinical datasets providing high-quality expert annotations about mutation effects. We devise a robust evaluation framework that combines metrics for both fitness prediction and design, factors in known limitations of the underlying experimental methods, and covers both zero-shot and supervised settings. We report the performance of a diverse set of over 70 high-performing models from various subfields (eg., alignment-based, inverse folding) into a unified benchmark suite. We open source the corresponding codebase, datasets, MSAs, structures, model predictions and develop a user-friendly website that facilitates data access and analysis.

synthetic biology↗

bioRxiv2022

TranceptEVE: Combining Family-specific and Family-agnostic Models of Protein Sequences for Improved Fitness Prediction

Modeling the fitness landscape of protein sequences has historically relied on training models on family-specific sets of homologous sequences called Multiple Sequence Alignments. Many proteins are however difficult to align or have shallow alignments which limits the potential scope of alignment-based methods. Not subject to these limitations, large protein language models trained on non-aligned sequences across protein families have achieved increasingly high predictive performance - but have not yet fully bridged the gap with their alignment-based counterparts. In this work, we introduce TranceptEVE - a hybrid method between family-specific and family-agnostic models that seeks to build on the relative strengths from each approach. Our method gracefully adapts to the depth of the alignment, fully relying on its autoregressive transformer when dealing with shallow alignments and leaning more heavily on the family-specific models for proteins with deeper alignments. Besides its broader application scope, it achieves state-of-the-art performance for mutation effects prediction, both in terms of correlation with experimental assays and with clinical annotations from ClinVar.

genetics↗

bioRxiv2019

Accelerating Protein Design Using Autoregressive Generative Models

The ability to design functional sequences and predict effects of variation is central to protein engineering and biotherapeutics. State-of-art computational methods rely on models that leverage evolutionary information but are inadequate for important applications where multiple sequence alignments are not robust. Such applications include the prediction of variant effects of indels, disordered proteins, and the design of proteins such as antibodies due to the highly variable complementarity determining regions. We introduce a deep generative model adapted from natural language processing for prediction and design of diverse functional sequences without the need for alignments. The model performs state-of-art prediction of missense and indel effects and we successfully design and test a diverse 105-nanobody library that shows better expression than a 1000-fold larger synthetic library. Our results demonstrate the power of the alignment-free autoregressive model in generalizing to regions of sequence space traditionally considered beyond the reach of prediction and design.

systems biology↗