D. Marks

Protein design for evaluating vaccines against future viral variation

The paper designs SARS-CoV-2 Spike proteins with novel mutations to evaluate vaccine effectiveness against future viral variants using a deep learning model.

Machine learning prediction of enzyme optimum pH

This study develops and evaluates machine learning models to predict enzyme optimum pH, finding that language model embeddings significantly improve prediction accuracy, leading to the release of the EpHod model.

Learning from pre-pandemic data to forecast viral escape

This paper develops EVEscape, a framework predicting viral escape mutations using historical data and structural information, showing it can forecast SARS-CoV-2 variants as effectively as experimental methods.

Non-identifiability and the Blessings of Misspecification in Models of Molecular Fitness

This paper shows that fitness cannot be reliably estimated from sequence data alone and that current models work well due to misspecification, not accuracy.

Dormant spores sense amino acids through the B subunits of their germination receptors

The paper identifies GerAB as the L-alanine sensor in spores, showing mutations in its ligand-binding pocket impair germination and substitutions enable response to other amino acids.

Chromosome-level Thlaspi arvense genome provides new tools for translational research and for a newly domesticated cash cover crop of the cooler climates

The paper presents a chromosome-level genome assembly of Thlaspi arvense and uses it to analyze genetic variation and gene structure differences between accessions.

Gene edited fluorescent cerebral organoids to study human brain function and disease

The paper introduces a method using gene-edited fluorescent cerebral organoids to study human brain function and disease by reducing inter-organoid variability through mixed cell line labeling.

Interaction specificity of clustered protocadherins inferred from sequence covariation and structural analysis

The paper uses sequence coevolution and structural analysis to model interaction specificity of clustered protocadherins and predict isoform-specific interactions.

Cryo-electron microscopy structure of the lipid droplet-formation protein seipin

The paper reports the cryo-EM structure of D. melanogaster seipin and proposes a model for its role in lipid droplet formation.