Christoffer Nellåker

Biologically-Inspired Digital Histology for Deep Phenotyping of Placental Composition Changes Across Major Lesion Types

The paper uses a deep learning pipeline to analyze placental histology and identifies cellular and structural changes across different lesion types.

Genome-wide analysis identifies 66 variants underlying anatomical variation in human neuroendocrine structures and reveals links to testosterone

This study identifies 66 genetic variants linked to neuroendocrine structure volumes and links some to testosterone levels using UK Biobank data.

The genetic architecture of changes in adiposity during adulthood

This study identifies six novel genetic loci associated with BMI change over adulthood using UK Biobank health records, finding lower heritability for BMI change compared to baseline BMI.

HAPPY: A deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images

HAPPY quantifies cell and tissue variability in placenta histology images, providing metrics that align with clinical experts and reveal deviations in placental infarction.

Inherited variants in CHD3 demonstrate variable expressivity in Snijders Blok-Campeau syndrome

The paper shows inherited CHD3 variants cause Snijders Blok-Campeau syndrome with variable expressivity, overlapping with de novo variants' phenotypes, and suggests reduced penetrance is not due to expression compensation.

Mutation-specific pathophysiological mechanisms define different neurodevelopmental disorders associated with SATB1 dysfunction

The paper identifies mutation-specific pathophysiological mechanisms in SATB1 variants causing distinct neurodevelopmental disorders.

Machine Learning based histology phenotyping to investigate epidemiologic and genetic basis of adipocyte morphology and cardiometabolic traits

The paper develops a deep learning method for adipocyte phenotyping and finds adipocyte area correlates with BMI but no genome-wide significant genetic associations.