Biology subjects

Colwell, L.

Publications and source records attributed to Colwell, L..

8 recordsLinked to original sources

bioRxiv2026

A Vast Navigable Protein Sequence Subspace

Fitness landscapes govern evolution. Our empirical understanding of their structure has primarily been informed by evolutionary history. Here, we combine high-throughput DNA synthesis and machine learning, without training on evolutionary priors, to build a high-resolution map of the genome packaging landscape of the Adeno-associated Virus capsid protein. We assay 232,123 mutants around Adeno-Associated Virus 2 (AAV2) including 15 neighborhoods centered on seed sequences within 5-21 mutations of the wild type sequence. Local neighborhoods differ sharply in mutational tolerance and epistatic detail, yet much of the quantitative variation is captured by a simple pattern: sitewise effects transformed by global epistasis. Strikingly, using targeted sampling of only a few thousand mutants, we uncover a vast percolating network of function-preserving ridges embedded within a largely non-functional landscape. These ridges support billions of distinct trajectories of up to 667 steps that connect all sampled neighborhoods through functional single mutations. Designed variants with mutations distinct from the evolutionary background retain packaging at distances where randomly generated mutants rarely survive. These include capsids that combine up to 7 mutations that are largely absent from the evolutionary record, and which are each individually lethal in the 15 diverse backgrounds we tested. Our results reveal rich subspace structure resembling landscape orebodies: reservoirs of highly viable and navigable sequence space defined by simple constraints. These subspaces can be discovered through targeted sampling and can open access to vast troves of proteins that may be valuable for downstream applications such as therapeutics.

evolutionary biology↗

bioRxiv2024

A resource for comparing AF-Cluster and other AlphaFold2 sampling methods

Predicting multiple conformational states of proteins represents a significant open challenge in structural biology. Increasingly many methods have been reported for perturbing and sampling AlphaFold2 (AF2) [1] to achieve multiple conformational states. However, if multiple methods achieve similar results, that does not in itself invalidate any method, nor does it answer why these methods work. Interpreting why deep learning models give the results they do is a critically important endeavor for future model development and appropriate usage. To help the field continue to try to answer these questions, this work addresses misunderstandings and inaccurate conclusions in refs. [2-6]. Deep learning methods development moves quickly, and by no means did we think that the implementation of AF-Cluster in [7] would be the final word on how to sample multiple conformations. However, Porter et al.s primary critique, that AF-Cluster does not use local evolutionary couplings in its MSA clusters, is incorrect. We report here further analysis that underscores our original finding that local evolutionary couplings do indeed play an important role in AF-Cluster predictions, and refute all false claims made against [7].

biophysics↗

bioRxiv2023

High-throughput ML-guided design of diverse single-domain antibodies against SARS-CoV-2

Treating rapidly evolving pathogenic diseases such as COVID-19 requires a therapeutic approach that accommodates the emergence of viral variants over time. Our machine learning (ML)-guided sequence design platform combines high-throughput experiments with ML to generate highly diverse single-domain antibodies (VHHs) that bind and neutralize SARS-CoV-1 and SARS-CoV-2. Crucially, the model, trained using binding data against early SARS-CoV variants, accurately captures the relationship between VHH sequence and binding activity across a broad swathe of sequence space. We discover ML-designed VHHs that exhibit considerable cross-reactivity and successfully neutralize targets not seen during training, including the Delta and Omicron BA.1 variants of SARS-CoV-2. Our ML-designed VHHs include thousands of variants 4-15 mutations from the parent sequence with significantly improved activity, demonstrating that ML-guided sequence design can successfully navigate vast regions of sequence space to unlock and future-proof potential therapeutics against rapidly evolving pathogens.

bioinformatics↗

bioRxiv2022

Tuned Fitness Landscapes for Benchmarking Model-Guided Protein Design

Advancements in DNA synthesis and sequencing technologies have enabled a novel paradigm of protein design where machine learning (ML) models trained on experimental data are used to guide exploration of a protein fitness landscape. ML-guided directed evolution (MLDE) builds on the success of traditional directed evolution and unlocks strategies which make more efficient use of experimental data. Building an MLDE pipeline involves many design choices across the design-build-test-learn loop ranging from data collection strategies to modeling, each of which has a large impact on the success of designed sequences. The cost of collecting experimental data makes benchmarking every component of these pipelines on real data prohibitively difficult, necessitating the development of synthetic landscapes where MLDE strategies can be tested. In this work, we develop a framework called SLIP ("Synthetic Landscape Inference for Proteins") for constructing biologically-motivated synthetic landscapes with tunable difficulty based on Potts models. This framework can be extended to any protein family for which there is a sequence alignment. We show that without tuning, Potts models are easy to optimize. In contrast, our tuning framework provides landscapes sufficiently challenging to benchmark MLDE pipelines. SLIP is open-source and is available at https://github.com/google-research/slip.

synthetic biology↗

bioRxiv2022

Prediction of multiple conformational states by combining sequence clustering with AlphaFold2

AlphaFold2 (AF2) has revolutionized structural biology by accurately predicting single structures of proteins and protein-protein complexes. However, biological function is rooted in a proteins ability to sample different conformational substates, and disease-causing point mutations are often due to population changes of these substates. This has sparked immense interest in expanding AF2s capability to predict conformational substates. We demonstrate that clustering an input multiple sequence alignment (MSA) by sequence similarity enables AF2 to sample alternate states of known metamorphic proteins, including the circadian rhythm protein KaiB, the transcription factor RfaH, and the spindle checkpoint protein Mad2, and score these states with high confidence. Moreover, we use AF2 to identify a minimal set of two point mutations predicted to switch KaiB between its two states. Finally, we used our clustering method, AF-cluster, to screen for alternate states in protein families without known fold-switching, and identified a putative alternate state for the oxidoreductase DsbE. Similarly to KaiB, DsbE is predicted to switch between a thioredoxin-like fold and a novel fold. This prediction is the subject of future experimental testing. Further development of such bioinformatic methods in tandem with experiments will likely have profound impact on predicting protein energy landscapes, essential for shedding light into biological function.

biochemistry↗

bioRxiv2021

ProteInfer: deep networks for protein functional inference

Predicting the function of a protein from its amino acid sequence is a long-standing challenge in bioinformatics. Traditional approaches use sequence alignment to compare a query sequence either to thousands of models of protein families or to large databases of individual protein sequences. Here we instead employ deep convolutional neural networks to directly predict a variety of protein functions - EC numbers and GO terms - directly from an unaligned amino acid sequence. This approach provides precise predictions which complement alignment-based methods, and the computational efficiency of a single neural network permits novel and lightweight software interfaces, which we demonstrate with an in-browser graphical interface for protein function prediction in which all computation is performed on the users personal computer with no data uploaded to remote servers. Moreover, these models place full-length amino acid sequences into a generalised functional space, facilitating downstream analysis and interpretation. To read the interactive version of this paper, please visit https://google-research.github.io/proteinfer/ O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=200 SRC="FIGDIR/small/461077v2_ufig1.gif" ALT="Figure 1"> View larger version (32K): org.highwire.dtl.DTLVardef@74f8f1org.highwire.dtl.DTLVardef@183ae0borg.highwire.dtl.DTLVardef@1754f3org.highwire.dtl.DTLVardef@1ca54f5_HPS_FORMAT_FIGEXP M_FIG C_FIG QR code for the interactive version of this preprint at https://google-research.github.io/proteinfer/

bioinformatics↗

bioRxiv2021

Machine Learning Optimization of Photosynthetic Microbe Cultivation and Recombinant Protein Production

BackgroundArthrospira platensis (commonly known as spirulina) is a promising new platform for low-cost manufacturing of biopharmaceuticals. However, full realization of the platforms potential will depend on achieving both high growth rates of spirulina and high expression of therapeutic proteins. ObjectiveWe aimed to optimize culture conditions for the spirulina-based production of therapeutic proteins. MethodsWe used a machine learning approach called Bayesian black-box optimization to iteratively guide experiments in 96 photobioreactors that explored the relationship between production outcomes and 17 environmental variables such as pH, temperature, and light intensity. ResultsOver 16 rounds of experiments, we identified key variable adjustments that approximately doubled spirulina-based production of heterologous proteins, improving volumetric productivity between 70% to 100% in multiple bioreactor setting configurations. ConclusionAn adaptive, machine learning-based approach to optimize heterologous protein production can improve outcomes based on complex, multivariate experiments, identifying beneficial variable combinations and adjustments that might not otherwise be discoverable within high-dimensional data.

bioengineering↗

bioRxiv2020

Using Single Protein/Ligand Binding Models to Predict Active Ligands for Unseen Proteins

Machine learning models that predict which small molecule ligands bind a single protein target report high levels of accuracy for held-out test data. An important challenge is to extrapolate and make accurate predictions for new protein targets. Improvements in drug-target interaction (DTI) models that address this challenge would have significant impact on drug discovery by eliminating the need for high-throughput screening experiments against new protein targets. Here we propose a data augmentation strategy that addresses this challenge to enable accurate prediction in cases where no experimental data is available. To proceed, we first build single protein-ligand binding models and use these models to predict whether additional ligands bind to each protein. We then use these predictions to augment the experimental data, train standard DTI models, and predict interactions between unseen test proteins and ligands. This approach achieves Area Under the Receiver Operator Characteristic (AUC) > 0.9 consistently on test sets consisting exclusively of proteins and ligands for which the model is given no experimental data. We verify that performance improvements extend to held-out test proteins distant from the training set. Our data augmentation framework can be applied to any DTI model, and enhances performance on a range of simple models.

bioinformatics↗