Tyler N. Starr
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tyler N. Starr has a total of 521 co-authors. Here are the top co-authors by number of shared publications:
- Jesse D. Bloom
Basic Sciences Division and Computational Biology Program, Fred Hutchinson Cancer Center, Seattle, USA
43 shared publications - Allison J. Greaney
Basic Sciences Division and Computational Biology Program, Fred Hutchinson Cancer Center
29 shared publications - David Veesler
University of Washington
16 shared publications - Davide Corti
Humabs BioMed SA, a subsidiary of Vir Biotechnology, Bellinzona, Switzerland
11 shared publications - Alexandra C. Walls
Department of Biochemistry, University of Washington, Seattle, WA 98195, USA
10 shared publications - Adam S. Dingens
Basic Sciences Division, Fred Hutchinson Cancer Research Center, Seattle, USA
8 shared publications
Latest Publications
- Open Access
- 16 September 2026
- Published by Springer Nature in Nature Microbiology
- Vol. 11 (10) , 2839-2852
Aminopeptidase N is a receptor for hedgehog merbecoviruses
- 16 September 2026
- Published by Springer Nature in Nature Microbiology
- Vol. 11 (10) , 2839-2852
Open AccessAminopeptidase N is a receptor for hedgehog merbecoviruses
- Open Access
- 22 June 2026
- Published by Public Library of Science (PLoS) in PLOS Pathogens
- Vol. 22 (6) , e1014074
Deep mutational scanning of recent SARS-CoV-2 variants highlights changing amino acid preferences within epistatic hotspot residues
Deep mutational scans across receptor-binding domains (RBDs) of diverging SARS-CoV-2 variants reveal ongoing changes to the effects of mutations, a phenomenon known as epistasis. Careful accounting for these altered mutational effects is important in viral surveillance and forecasting, and more broadly, for understanding the impacts of epistasis on real-world viral evolutionary trajectories. Using a yeast-display RBD deep mutational scanning (DMS) platform, we measure the impacts of virtually all single amino acid mutations and single-residue deletions in the Omicron KP.3.1.1 and LP.8.1 RBDs on folded RBD expression and binding affinity for the human ACE2 receptor. Our comprehensive maps reveal patterns of evolutionary accessibility and constraint at single-residue resolution and, when compared to prior datasets, highlight sites whose amino acid preferences continue to change across viral variants. Notably, sites 455, 456, and 493 – which have exhibited repeated substitutions and epistatic dependencies across Omicron subvariants going back to BA.1 – again demonstrate altered patterns of mutational accessibility and constraint. Therefore, it appears that these hotspots of repeated RBD evolution have not yet converged on fixed amino acid solutions but instead remain sites of ongoing epistatic reconfiguration. We compare our measurements of direct RBD:ACE2 affinity with recently published measurements of mutation impacts on ACE2 binding in the full quaternary spike context, which also integrates the effects of spike conformational dynamics; our analysis uncovers mutations like H505W that could favor adoption of the down/closed RBD conformation as a viral strategy for future antigenic evolution.
- 22 June 2026
- Published by Public Library of Science (PLoS) in PLOS Pathogens
- Vol. 22 (6) , e1014074
Open AccessDeep mutational scanning of recent SARS-CoV-2 variants highlights changing amino acid preferences within epistatic hotspot residues
Deep mutational scans across receptor-binding domains (RBDs) of diverging SARS-CoV-2 variants reveal ongoing changes to the effects of mutations, a phenomenon known as epistasis. Careful accounting for these altered mutational effects is important in viral surveillance and forecasting, and more broadly, for understanding the impacts of epistasis on real-world viral evolutionary trajectories. Using a yeast-display RBD deep mutational scanning (DMS) platform, we measure the impacts of virtually all single amino acid mutations and single-residue deletions in the Omicron KP.3.1.1 and LP.8.1 RBDs on folded RBD expression and binding affinity for the human ACE2 receptor. Our comprehensive maps reveal patterns of evolutionary accessibility and constraint at single-residue resolution and, when compared to prior datasets, highlight sites whose amino acid preferences continue to change across viral variants. Notably, sites 455, 456, and 493 – which have exhibited repeated substitutions and epistatic dependencies across Omicron subvariants going back to BA.1 – again demonstrate altered patterns of mutational accessibility and constraint. Therefore, it appears that these hotspots of repeated RBD evolution have not yet converged on fixed amino acid solutions but instead remain sites of ongoing epistatic reconfiguration. We compare our measurements of direct RBD:ACE2 affinity with recently published measurements of mutation impacts on ACE2 binding in the full quaternary spike context, which also integrates the effects of spike conformational dynamics; our analysis uncovers mutations like H505W that could favor adoption of the down/closed RBD conformation as a viral strategy for future antigenic evolution.
- Open Access
- 29 April 2026
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 123 (18)
Computational design of an ultrapotent deltacoronavirus miniprotein inhibitor
Multiple spillovers of porcine deltacoronavirus (PDCoV) into humans in Haiti highlight its zoonotic potential and the need for targeted interventions. No approved vaccines or therapeutics are available for use in humans against any DCoVs. Here, we report the de novo design of PDCoV miniprotein inhibitors (aka minibinders, MBs) and show that one of them, MB11, binds with picomolar affinity to the PDCoV receptor-binding domain (RBD). MB11 potently inhibits PDCoV, outcompeting monoclonal antibodies, and cross-reacts with and broadly neutralizes a panel of distantly related DCoVs. We determined a cryoelectron microscopy structure of MB11 bound to the PDCoV RBD which reveals the molecular basis of broad DCoV neutralization through interference with host receptor engagement. Deep mutational scanning of the PDCoV RBD reveals that MB11 has a high barrier to viral escape with only few mutations mediating escape without dampening APN receptor binding. MB11 resists stringent biochemical stresses, including high temperature, low pH, and proteolysis, which may enable delivery to various tissues for viral inhibition. This work delineates a prime candidate for clinical evaluation against PDCoV infection and for pandemic preparedness.
- 29 April 2026
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 123 (18)
Open AccessComputational design of an ultrapotent deltacoronavirus miniprotein inhibitor
Multiple spillovers of porcine deltacoronavirus (PDCoV) into humans in Haiti highlight its zoonotic potential and the need for targeted interventions. No approved vaccines or therapeutics are available for use in humans against any DCoVs. Here, we report the de novo design of PDCoV miniprotein inhibitors (aka minibinders, MBs) and show that one of them, MB11, binds with picomolar affinity to the PDCoV receptor-binding domain (RBD). MB11 potently inhibits PDCoV, outcompeting monoclonal antibodies, and cross-reacts with and broadly neutralizes a panel of distantly related DCoVs. We determined a cryoelectron microscopy structure of MB11 bound to the PDCoV RBD which reveals the molecular basis of broad DCoV neutralization through interference with host receptor engagement. Deep mutational scanning of the PDCoV RBD reveals that MB11 has a high barrier to viral escape with only few mutations mediating escape without dampening APN receptor binding. MB11 resists stringent biochemical stresses, including high temperature, low pH, and proteolysis, which may enable delivery to various tissues for viral inhibition. This work delineates a prime candidate for clinical evaluation against PDCoV infection and for pandemic preparedness.
- Open Access
- 7 April 2026
- Published by eLife Sciences Publications, Ltd in eLife
- Vol. 15
Separating selection from mutation in antibody language models
Antibodies are encoded by nucleotide sequences that are generated by V(D)J recombination and evolve according to mutation and selection processes. Existing antibody language models, however, focus exclusively on antibodies as strings of amino acids and are fitted using standard language modeling objectives such as masked or autoregressive prediction. In this paper, we first show that fitting models using this objective implicitly incorporates nucleotide-level mutation processes as part of the protein language model, which degrades performance when predicting effects of mutations on functional properties of antibodies. To address this limitation, we devise a new framework: a deep amino acid selection model (DASM) that learns the selection effects of amino acid mutations while explicitly factoring out the nucleotide-level mutation process. By fitting selection as a separate term from the mutation process, the DASM exclusively quantifies functional effects: effects that change some aspect of the function of the antibody. This factorization leads to substantially improved performance on standard functional benchmarks. Moreover, our model is an order of magnitude smaller and multiple orders of magnitude faster to evaluate than existing approaches, as well as being readily interpretable.
- 7 April 2026
- Published by eLife Sciences Publications, Ltd in eLife
- Vol. 15
Open AccessSeparating selection from mutation in antibody language models
Antibodies are encoded by nucleotide sequences that are generated by V(D)J recombination and evolve according to mutation and selection processes. Existing antibody language models, however, focus exclusively on antibodies as strings of amino acids and are fitted using standard language modeling objectives such as masked or autoregressive prediction. In this paper, we first show that fitting models using this objective implicitly incorporates nucleotide-level mutation processes as part of the protein language model, which degrades performance when predicting effects of mutations on functional properties of antibodies. To address this limitation, we devise a new framework: a deep amino acid selection model (DASM) that learns the selection effects of amino acid mutations while explicitly factoring out the nucleotide-level mutation process. By fitting selection as a separate term from the mutation process, the DASM exclusively quantifies functional effects: effects that change some aspect of the function of the antibody. This factorization leads to substantially improved performance on standard functional benchmarks. Moreover, our model is an order of magnitude smaller and multiple orders of magnitude faster to evaluate than existing approaches, as well as being readily interpretable.
- Open Access
Deep mutational scanning of recent SARS-CoV-2 variants highlights changing amino acid preferences within epistatic hotspot residues
Deep mutational scans across receptor-binding domains (RBDs) of diverging SARS-CoV-2 variants reveal ongoing changes to the effects of mutations, a phenomenon known as epistasis. Careful accounting for these altered mutational effects is important in viral surveillance and forecasting, and more broadly, for understanding the impacts of epistasis on real-world viral evolutionary trajectories. Using a yeast-display RBD deep mutational scanning (DMS) platform, we measure the impacts of virtually all single amino acid mutations and single-residue deletions in the Omicron KP.3.1.1 and LP.8.1 RBDs on folded RBD expression and binding affinity for the human ACE2 receptor. Our comprehensive maps reveal patterns of evolutionary accessibility and constraint at single-residue resolution and when compared to prior datasets, highlight sites whose amino acid preferences continue to change across viral variants. Notably, sites 455, 456, and 493 – which have exhibited repeated substitutions and epistatic dependencies across Omicron subvariants going back to BA.1 – again demonstrate altered patterns of mutational accessibility and constraint. Therefore, it appears that these hotspots of repeated RBD evolution have not yet converged on fixed amino acid solutions, but instead remain sites of ongoing epistatic reconfiguration. We compare our measurements of direct RBD:ACE2 affinity with recently published measurements of mutation impacts on ACE2 binding in the full quaternary spike context, which also integrates the effects of spike conformational dynamics; our analysis uncovers mutations like H505W that could favor adoption of the down/closed RBD conformation as a viral strategy for future antigenic evolution.
Open AccessDeep mutational scanning of recent SARS-CoV-2 variants highlights changing amino acid preferences within epistatic hotspot residues
Deep mutational scans across receptor-binding domains (RBDs) of diverging SARS-CoV-2 variants reveal ongoing changes to the effects of mutations, a phenomenon known as epistasis. Careful accounting for these altered mutational effects is important in viral surveillance and forecasting, and more broadly, for understanding the impacts of epistasis on real-world viral evolutionary trajectories. Using a yeast-display RBD deep mutational scanning (DMS) platform, we measure the impacts of virtually all single amino acid mutations and single-residue deletions in the Omicron KP.3.1.1 and LP.8.1 RBDs on folded RBD expression and binding affinity for the human ACE2 receptor. Our comprehensive maps reveal patterns of evolutionary accessibility and constraint at single-residue resolution and when compared to prior datasets, highlight sites whose amino acid preferences continue to change across viral variants. Notably, sites 455, 456, and 493 – which have exhibited repeated substitutions and epistatic dependencies across Omicron subvariants going back to BA.1 – again demonstrate altered patterns of mutational accessibility and constraint. Therefore, it appears that these hotspots of repeated RBD evolution have not yet converged on fixed amino acid solutions, but instead remain sites of ongoing epistatic reconfiguration. We compare our measurements of direct RBD:ACE2 affinity with recently published measurements of mutation impacts on ACE2 binding in the full quaternary spike context, which also integrates the effects of spike conformational dynamics; our analysis uncovers mutations like H505W that could favor adoption of the down/closed RBD conformation as a viral strategy for future antigenic evolution.
- Open Access
- 5 March 2026
- Published by eLife Sciences Publications, Ltd in eLife preprints
- Vol. 15
Separating selection from mutation in antibody language models
Antibodies are encoded by nucleotide sequences that are generated by V(D)J recombination and evolve according to mutation and selection processes. Existing antibody language models, however, focus exclusively on antibodies as strings of amino acids and are fitted using standard language modeling objectives such as masked or autoregressive prediction. In this paper, we first show that fitting models using this objective implicitly incorporates nucleotide-level mutation processes as part of the protein language model, which degrades performance when predicting effects of mutations on functional properties of antibodies. To address this limitation, we devise a new framework: a Deep Amino acid Selection Model (DASM) that learns the selection effects of amino-acid mutations while explicitly factoring out the nucleotide-level mutation process. By fitting selection as a separate term from the mutation process, the DASM exclusively quantifies functional effects: effects that change some aspect of the function of the antibody. This factorization leads to substantially improved performance on standard functional benchmarks. Moreover, our model is an order of magnitude smaller and multiple orders of magnitude faster to evaluate than existing approaches, as well as being readily interpretable.
- 5 March 2026
- Published by eLife Sciences Publications, Ltd in eLife preprints
- Vol. 15
Open AccessSeparating selection from mutation in antibody language models
Antibodies are encoded by nucleotide sequences that are generated by V(D)J recombination and evolve according to mutation and selection processes. Existing antibody language models, however, focus exclusively on antibodies as strings of amino acids and are fitted using standard language modeling objectives such as masked or autoregressive prediction. In this paper, we first show that fitting models using this objective implicitly incorporates nucleotide-level mutation processes as part of the protein language model, which degrades performance when predicting effects of mutations on functional properties of antibodies. To address this limitation, we devise a new framework: a Deep Amino acid Selection Model (DASM) that learns the selection effects of amino-acid mutations while explicitly factoring out the nucleotide-level mutation process. By fitting selection as a separate term from the mutation process, the DASM exclusively quantifies functional effects: effects that change some aspect of the function of the antibody. This factorization leads to substantially improved performance on standard functional benchmarks. Moreover, our model is an order of magnitude smaller and multiple orders of magnitude faster to evaluate than existing approaches, as well as being readily interpretable.
- Open Access
Separating selection from mutation in antibody language models
Antibodies are encoded by nucleotide sequences that are generated by V(D)J recombination and evolve according to mutation and selection processes. Existing antibody language models, however, focus exclusively on antibodies as strings of amino acids and are fitted using standard language modeling objectives such as masked or autoregressive prediction. In this paper, we first show that fitting models using this objective implicitly incorporates nucleotide-level mutation processes as part of the protein language model, which degrades performance when predicting effects of mutations on functional properties of antibodies. To address this limitation, we devise a new framework: a Deep Amino acid Selection Model (DASM) that learns the selection effects of amino-acid mutations while explicitly factoring out the nucleotide-level mutation process. By fitting selection as a separate term from the mutation process, the DASM exclusively quantifies functional effects: effects that change some aspect of the function of the antibody. This factorization leads to substantially improved performance on standard functional benchmarks. Moreover, our model is an order of magnitude smaller and multiple orders of magnitude faster to evaluate than existing approaches, as well as being readily interpretable.
Open AccessSeparating selection from mutation in antibody language models
Antibodies are encoded by nucleotide sequences that are generated by V(D)J recombination and evolve according to mutation and selection processes. Existing antibody language models, however, focus exclusively on antibodies as strings of amino acids and are fitted using standard language modeling objectives such as masked or autoregressive prediction. In this paper, we first show that fitting models using this objective implicitly incorporates nucleotide-level mutation processes as part of the protein language model, which degrades performance when predicting effects of mutations on functional properties of antibodies. To address this limitation, we devise a new framework: a Deep Amino acid Selection Model (DASM) that learns the selection effects of amino-acid mutations while explicitly factoring out the nucleotide-level mutation process. By fitting selection as a separate term from the mutation process, the DASM exclusively quantifies functional effects: effects that change some aspect of the function of the antibody. This factorization leads to substantially improved performance on standard functional benchmarks. Moreover, our model is an order of magnitude smaller and multiple orders of magnitude faster to evaluate than existing approaches, as well as being readily interpretable.
- Open Access
- 30 July 2025
- Published by Oxford University Press (OUP) in Molecular Biology and Evolution
- Vol. 42 (8)
A Sitewise Model of Natural Selection on Individual Antibodies via a Transformer–Encoder
During affinity maturation, antibodies are selected for their ability to fold and to bind a target antigen between rounds of somatic hypermutation. Previous studies have identified patterns of selection in antibodies using B cell repertoire sequencing data. However, these studies are constrained by needing to group many sequences or sites to make aggregate predictions. In this paper, we develop a transformer–encoder selection model of maximum resolution: given a single antibody sequence, it predicts the strength of selection on each amino acid site. Specifically, the model predicts for each site whether evolution will be slower than expected relative to a model of the neutral mutation process (purifying selection) or faster than expected (diversifying selection). We show that the model does an excellent job of modeling the process of natural selection on held out data, and does not need to be enormous or trained on vast amounts of data to perform well. The patterns of purifying vs diversifying natural selection do not neatly partition into the complementarity-determining vs framework regions: for example, there are many sites in framework that experience strong diversifying selection. There is a weak correlation between selection factors and solvent accessibility. When considering evolutionary shifts down a tree of antibody evolution, affinity maturation generally shifts sites towards purifying natural selection, however this effect depends on the region, with the biggest shifts toward purifying selection happening in the third complementarity-determining region. We observe distinct evolution between gene families but a limited relationship between germline diversity and selection strength.
- 30 July 2025
- Published by Oxford University Press (OUP) in Molecular Biology and Evolution
- Vol. 42 (8)
Open AccessA Sitewise Model of Natural Selection on Individual Antibodies via a Transformer–Encoder
During affinity maturation, antibodies are selected for their ability to fold and to bind a target antigen between rounds of somatic hypermutation. Previous studies have identified patterns of selection in antibodies using B cell repertoire sequencing data. However, these studies are constrained by needing to group many sequences or sites to make aggregate predictions. In this paper, we develop a transformer–encoder selection model of maximum resolution: given a single antibody sequence, it predicts the strength of selection on each amino acid site. Specifically, the model predicts for each site whether evolution will be slower than expected relative to a model of the neutral mutation process (purifying selection) or faster than expected (diversifying selection). We show that the model does an excellent job of modeling the process of natural selection on held out data, and does not need to be enormous or trained on vast amounts of data to perform well. The patterns of purifying vs diversifying natural selection do not neatly partition into the complementarity-determining vs framework regions: for example, there are many sites in framework that experience strong diversifying selection. There is a weak correlation between selection factors and solvent accessibility. When considering evolutionary shifts down a tree of antibody evolution, affinity maturation generally shifts sites towards purifying natural selection, however this effect depends on the region, with the biggest shifts toward purifying selection happening in the third complementarity-determining region. We observe distinct evolution between gene families but a limited relationship between germline diversity and selection strength.
- Open Access
Replaying germinal center evolution on a quantified affinity landscape
Darwinian evolution of immunoglobulin genes within germinal centers (GCs) underlies the progressive increase in antibody affinity following antigen exposure. Whereas the cellular mechanics of how competition between B cells produces increases in affinity are well established, the evolutionary dynamics of this process are less clear. We developed an experimental evolution model where we “replay” over one hundred monoclonal GC reactions, assigning affinities to each cell using deep mutational scanning. Our data reveal how GCs achieve predictable outcomes by means of noisy but persistent selection on an affinity landscape whose exploration is heavily constrained by somatic hypermutation biases. We infer a fitness landscape that quantitatively recapitulates the affinity maturation trajectory of our clone and find that apparent features of GC selection such as permissiveness to low-affinity lineages and rapid plateauing of affinity are likely artifacts of survivorship biases that distort our view of how B cell affinity progresses over time.
Open AccessReplaying germinal center evolution on a quantified affinity landscape
Darwinian evolution of immunoglobulin genes within germinal centers (GCs) underlies the progressive increase in antibody affinity following antigen exposure. Whereas the cellular mechanics of how competition between B cells produces increases in affinity are well established, the evolutionary dynamics of this process are less clear. We developed an experimental evolution model where we “replay” over one hundred monoclonal GC reactions, assigning affinities to each cell using deep mutational scanning. Our data reveal how GCs achieve predictable outcomes by means of noisy but persistent selection on an affinity landscape whose exploration is heavily constrained by somatic hypermutation biases. We infer a fitness landscape that quantitatively recapitulates the affinity maturation trajectory of our clone and find that apparent features of GC selection such as permissiveness to low-affinity lineages and rapid plateauing of affinity are likely artifacts of survivorship biases that distort our view of how B cell affinity progresses over time.
- Open Access
Isolation and escape mapping of broadly neutralizing antibodies against emerging delta-coronaviruses