Applying deep learning technology for the large-scale curation of symptoms from unstructured EHR clinical notes accurately predicts the differential signals of COVID-19 diagnosis over the week preceding typical PCR testing.
An integrative approach, combining genetic mouse and large-scale human genetics studies, was used to reveal a novel role for the Bcl-2 protein Bid in maintenance of mitochondrial function that alters susceptibility to myocardial infarction.
Text mining of complete EHRs for 14,017 diabetes patients and subsequent clustering led to phenotypically deep clusters, showing distinct glycemic profiles, comorbidities, and SNP association patterns.
In vivo dopamine neuron imaging-based neuroprotective small molecule screen in larval zebrafish and mechanistic investigation using conditional CRISPR knockout and cell-type-specific RNA-seq analysis, coupled with cross-species analyses including human clinical data interrogation, uncover potential disease-modifying therapeutics for Parkinson's disease (PD).
Large-scale retrospective analysis suggests medications and dietary supplements, such as rosuvastatin, ezetimibe, ubiquinone, risedronate, vitamin D, and magnesium, are associated with a lower rate of severe COVID-19 disease.