Claire D. McWhite

This paper shows that biological concepts can be represented as directions in foundation model embeddings, enabling interpretable and reusable analysis of diverse biological properties.

The paper introduces CORAL, a deep learning framework for RNA-protein interaction prediction that improves generalization and interpretability through cross-attention mechanisms.

The paper identifies MITH1 as a protein that anchors thylakoid membranes into the pyrenoid condensate, revealing how membranes are integrated into biomolecular condensates.

The paper reconstructs the protein interactome of the Last Eukaryotic Common Ancestor and identifies new human gene-disease associations for bone density and congenital birth defects.

VerteBrain maps conserved brain protein interactions across five vertebrate species, revealing novel complexes and disease mechanisms.

The paper analyzes somatic mutations across tissues and individuals using exome sequencing data from GTEx donors, identifying 8,470 variants and providing insights into mutation rates and mechanisms.

The paper identifies proteoform truncations in human and plant proteomes and describes their functional implications and evolutionary conservation.

The paper identifies polarity domains in Arabidopsis stomatal lineage cells and their associated proteins using proteomics and structural modeling, revealing their role in cell division and pore formation.

This paper introduces a novel multiple sequence alignment method using protein language models to improve alignment accuracy in the twilight zone of sequence similarity.

This study defines the RBC proteome and interactome using mass spectrometry and machine learning, revealing key biological processes and structural models.

The paper introduces DIF-FRAC, a label-free method to identify RNA-associated proteins in vertebrate tissues, revealing novel RAPs and RNA-enriched organelles.

The paper maps protein complexes across 13 plant species, revealing conserved and novel assemblies with agricultural relevance.

The paper synthesizes over 9,000 mass spectrometry experiments to create hu.MAP, a comprehensive human protein complex map with improved accuracy and coverage of disease-associated proteins.

The paper estimates gene ages with uncertainty by analyzing algorithmic variation and provides consensus gene ages with error distributions for multiple eukaryotic models.