Tomasz Konopka

This paper introduces mlensemble, a software package that corrects machine learning models by calibrating ensembles to new data, improving performance across different datasets and applications.

The paper analyzes somatic substitutions in non-unique regions of the human genome across 2,658 cancers, revealing hidden mutations in coding sequences and regulatory elements.

The paper evaluates how well machine-learning models capture ontology relationships and suggests ways to improve curation using these models.

The paper reduces the dimensionality of phenotypic data from 53,000 mouse models to visualize gene function diversity and highlights challenges in embedding sparse phenotypic data.

The paper integrates gene essentiality data from human and mouse screens to classify genes into FUSIL categories, identifying developmental lethal genes associated with rare diseases.