Violin plots of R<sup>2</sup> between predictions and measurements in SAGE, with testing R<sup>2</sup> from each PrediXcan repository included for benchmarking.
Domain:
healthcareRecord type:
paper
Creator:
KevAngMarWal
Host:
The prediction weights used here are, from left to right: GTEx v6p, GTEx v7, DGN, MESA African Americans, MESA African Americans and Hispanics, MESA Caucasians, and all MESA subjects. Test R2 from model training in GTEx 7 and MESA (“test_R2_avg” in PredictDB) appear on the right and provide a performance baseline. R2 for SAGE cluster heavily near zero, while testing R2 from each repository are more evenly distributed.
(TIFF)
Similar
Prediction R<sup>2</sup> between populations in GEUVADIS for genes with positive correlation between predictions and measurements.Evaluation of Geophagy Clay Capacity in Adsorbing Cd<sup>2+</sup> and Pb<sup>2+</sup> for Water Treatment in Southeast NigeriaEstimated wildlife populations in national parks (data available for 61,462 km<sup>2</sup> of the ∼64,000 km<sup>2</sup>), game management areas (GMAs, data available for 159,654 km<sup>2</sup> of the ∼166,000 km<sup>2</sup>) (together ‘protected area network’) and game ranches (5,829 km<sup>2</sup>) in Zambia (excluding species of bushbuck size and smaller, and hippopotamuses for which count data were not available).Seasonal food consumption patterns and dietary diversity of rural preschool Ghanaian and Malawian children<sup>2</sup><sup>3</sup>Provinces of Zimbabwe included in the KnowM<sup>M</sup> study*.The Image of Ethiopian-Axumite Kingship as Reflected in the Greek Axumite Royal Inscriptions (2<sup>nd</sup>—6<sup>th</sup> Centuries)