Benjamin Livesey

The paper compares variant effect predictors and MAVEs to understand their agreement and disagreement in assessing genetic variant impacts.

The paper shows that disease-associated variants in alternative protein isoforms can cause structural mutations, emphasizing the need to consider tissue-specific expression and full-length transcripts in variant interpretation.

This study evaluates 97 variant effect predictors using DMS experiments and finds strong correlation between their performance in functional assays and clinical variant classification.

The paper uses deep mutational scanning to quantify PAX6:DNA binding and predict clinical outcomes of variants, finding most pathogenic mutations affect DNA binding.

This study evaluates ancestry bias in variant effect predictors and finds disparities in their performance across different populations.

This study benchmarks 55 variant effect predictors using deep mutational scanning data from 26 human proteins, finding that unsupervised methods like EVE and ESM-1v perform best, while supervised methods like VARITY show improved handling of data circularity.

The paper compares protein stability predictors with DMS-derived functional scores, finding FoldX and Rosetta show strong correlations, especially when considering intermolecular interactions.

The paper examines how mutations at different protein interfaces correlate with disease, finding significant variation in pathogenicity across interface types and highlighting discrepancies in computational prediction tools.

The paper examines how different mutation types affect protein structure and finds that non-LOF mutations are underpredicted by current tools.

This study benchmarks 46 variant effect predictors using deep mutational scanning data, finding DMS superior to top predictors and highlighting DeepSequence's effectiveness.