Matt Thomson
YOU?
Author Swipe
View article: 1131 Spatially-guided therapy predictions with morpheus
1131 Spatially-guided therapy predictions with morpheus Open
View article: Pretrained protein language models choose between sequence novelty and structural completeness
Pretrained protein language models choose between sequence novelty and structural completeness Open
Protein language models (PLMs) have gained increasing acceptance in tasks ranging from variant effect prediction in disease to optimization and de novo design of proteins with improved stability, target-binding affinity, and catalytic perf…
View article: Geometry-dependent defect merging induces bifurcated dynamics in active networks
Geometry-dependent defect merging induces bifurcated dynamics in active networks Open
Cytoskeletal networks can repair defects to maintain structural integrity. However, the mechanisms and dynamics of defect merging remain poorly understood. Here, we report a geometry-tunable merging mechanism in microtubule-motor networks …
View article: Rapid discovery of new-to-nature protein domains by novelty-first forcing of language models
Rapid discovery of new-to-nature protein domains by novelty-first forcing of language models Open
Approximations for the existence and extent of physically permissible protein structures beyond those found in nature vary wildly. As predicted structure databases swell thanks to abundant sequence data and generative protein design models…
View article: Boundaries Program Deformation in Isolated Active Networks
Boundaries Program Deformation in Isolated Active Networks Open
Cellular structures must organize themselves within strict physical constraints, operating with finite resources and well-defined boundaries. Classical systems demonstrate only passive responses to boundaries, from surface energy minimizat…
View article: Designing signaling environments to modulate neural progenitor cell differentiation with regulatory network models
Designing signaling environments to modulate neural progenitor cell differentiation with regulatory network models Open
During development, progenitors integrate external signaling cues to control differentiation. How combinatorial signal inputs modulate fate decisions and the underlying molecular information processing logic remains elusive. In this study,…
View article: Reverse Engineering the Evolutionary Logic of Cytoskeletal Dynamics
Reverse Engineering the Evolutionary Logic of Cytoskeletal Dynamics Open
Living cells perform tasks by generating mechanical force through networks of protein filaments that are actively organized by molecular motors. Eukaryotic genomes encode diverse motor protein variants with distinct biochemical properties,…
View article: Force Propagation in Active Cytoskeletal Networks
Force Propagation in Active Cytoskeletal Networks Open
Conventional materials science establishes clear structure–function relationships: grain boundaries modulate strength by blocking dislocations, and defect density limits conductivity through electron scattering. Active matter presents a fu…
View article: Designing biochemical circuits with tree search
Designing biochemical circuits with tree search Open
Discovering biochemical circuits that exhibit a desired behavior is an outstanding problem in biological engineering. The traditional approach of enumerating every possible circuit topology becomes intractable for circuits with more than f…
View article: Designing biochemical circuits with tree search
Designing biochemical circuits with tree search Open
Discovering biochemical circuits that exhibit a desired behavior is an outstanding problem in biological engineering. The traditional approach of enumerating every possible circuit topology becomes intractable for circuits with more than f…
View article: Author response: Designing biochemical circuits with tree search
Author response: Designing biochemical circuits with tree search Open
View article: Revealing a coherent cell state landscape across single cell datasets with CONCORD
Revealing a coherent cell state landscape across single cell datasets with CONCORD Open
Revealing the underlying cell-state landscape from single-cell data requires overcoming the critical obstacles of batch integration, denoising, and dimensionality reduction. Here, we present CONCORD, a unified framework that simultaneously…
View article: Identifying perturbations that boost T-cell infiltration into tumours via counterfactual learning of their spatial proteomic profiles
Identifying perturbations that boost T-cell infiltration into tumours via counterfactual learning of their spatial proteomic profiles Open
View article: Dynamic flow control through active matter programming language
Dynamic flow control through active matter programming language Open
View article: Designing biochemical circuits with tree search
Designing biochemical circuits with tree search Open
Discovering biochemical circuits that exhibit a desired behavior is an outstanding problem in biological engineering. The traditional approach of enumerating every possible circuit topology becomes intractable for circuits with more than f…
View article: Benchmarking protein language models for protein crystallization
Benchmarking protein language models for protein crystallization Open
The problem of protein structure determination is usually solved by X-ray crystallography. Several in silico deep learning methods have been developed to overcome the high attrition rate, cost of experiments and extensive trial-and-error s…
View article: Designing Signaling Environments To Modulate Neural Progenitor Cell Differentiation With Regulatory Network Modelss
Designing Signaling Environments To Modulate Neural Progenitor Cell Differentiation With Regulatory Network Modelss Open
View article: Control of spatio-temporal patterning via cell growth in a multicellular synthetic gene circuit
Control of spatio-temporal patterning via cell growth in a multicellular synthetic gene circuit Open
A major goal in synthetic development is to build gene regulatory circuits that control patterning. In natural development, an interplay between mechanical and chemical communication shapes the dynamics of multicellular gene regulatory cir…
View article: Spatial transcriptomics defines injury specific microenvironments and cellular interactions in kidney regeneration and disease
Spatial transcriptomics defines injury specific microenvironments and cellular interactions in kidney regeneration and disease Open
View article: Benchmarking Protein Language Models for Protein Crystallization
Benchmarking Protein Language Models for Protein Crystallization Open
The problem of protein structure determination is usually solved by X-ray crystallography. Several in silico deep learning methods have been developed to overcome the high attrition rate, cost of experiments and extensive trial-and-error s…
View article: Author Correction: Engineering programmable material-to-cell pathways via synthetic notch receptors to spatially control differentiation in multicellular constructs
Author Correction: Engineering programmable material-to-cell pathways via synthetic notch receptors to spatially control differentiation in multicellular constructs Open
View article: Automated construction of cognitive maps with visual predictive coding
Automated construction of cognitive maps with visual predictive coding Open
Humans construct internal cognitive maps of their environment directly from sensory inputs without access to a system of explicit coordinates or distance measurements. Although machine learning algorithms like simultaneous localization and…
View article: Engineering programmable material-to-cell pathways via synthetic notch receptors to spatially control differentiation in multicellular constructs
Engineering programmable material-to-cell pathways via synthetic notch receptors to spatially control differentiation in multicellular constructs Open
View article: Patterning and folding of intestinal villi by active mesenchymal dewetting
Patterning and folding of intestinal villi by active mesenchymal dewetting Open
Tissue folds are structural motifs critical to organ function. In the intestine, bending of a flat epithelium into a periodic pattern of folds gives rise to villi, finger-like protrusions that enable nutrient absorption. However, the molec…
View article: Unexplored regions of the protein sequence-structure map revealed at scale by a library of foldtuned language models
Unexplored regions of the protein sequence-structure map revealed at scale by a library of foldtuned language models Open
The combinatorial scale of amino-acid sequence-space has traditionally precluded substantive study of the full protein sequence-structure map. It remains unknown, for instance, how much of the vast uncharted landscape of far-fromnatural se…
View article: Commensal bacteria promote type I interferon signaling to maintain immune tolerance in mice
Commensal bacteria promote type I interferon signaling to maintain immune tolerance in mice Open
Type I interferons (IFNs) exert a broad range of biological effects important in coordinating immune responses, which have classically been studied in the context of pathogen clearance. Yet, whether immunomodulatory bacteria operate throug…
View article: Spatial transcriptomics defines injury-specific microenvironments in the adult mouse kidney and novel cellular interactions in regeneration and disease
Spatial transcriptomics defines injury-specific microenvironments in the adult mouse kidney and novel cellular interactions in regeneration and disease Open
Kidney injury disrupts the intricate renal architecture and triggers limited regeneration, and injury-invoked inflammation and fibrosis. Deciphering molecular pathways and cellular interactions driving these processes is challenging due to…
View article: TRILL: Orchestrating Modular Deep-Learning Workflows for Democratized, Scalable Protein Analysis and Engineering
TRILL: Orchestrating Modular Deep-Learning Workflows for Democratized, Scalable Protein Analysis and Engineering Open
A bstract Deep-learning models have been rapidly adopted by many fields, partly due to the deluge of data humanity has amassed. In particular, the petabases of biological sequencing data enable the unsupervised training of protein language…
View article: Identifying perturbations that boost T-cell infiltration into tumours via counterfactual learning of their spatial proteomic profiles
Identifying perturbations that boost T-cell infiltration into tumours via counterfactual learning of their spatial proteomic profiles Open
Cancer progression can be slowed down or halted via the activation of either endogenous or engineered T cells and their infiltration of the tumour microenvironment. Here we describe a deep-learning model that uses large-scale spatial prote…
View article: Unraveling cell differentiation mechanisms through topological exploration of single-cell developmental trajectories
Unraveling cell differentiation mechanisms through topological exploration of single-cell developmental trajectories Open
Understanding the circuits that control cell differentiation is a fundamental problem in developmental biology. Single-cell RNA sequencing has emerged as a powerful tool for investigating this problem. However, the reconstruction of develo…