Machine Learning of Three-Dimensional Protein Structures to Predict the Functional Impacts of Genome Variation.

Research in the human genome sciences generates a substantial amount of genetic data for hundreds of thousands of individuals, which concomitantly increases the number of variants of unknown significance (VUS). Bioinformatic analyses can successfully reveal rare variants and variants with clear associations with disease-related phenotypes. These studies have had a significant impact on how clinical genetic screens are interpreted and how patients are stratified for treatment. There are few, if any, computational methods for variants comparable to biological activity predictions. To address this gap, we developed a machine learning method that uses protein three-dimensional structures from AlphaFold to predict how a variant will influence changes to a gene's downstream biological pathways. We trained state-of-the-art machine learning classifiers to predict which protein regions will most likely impact transcriptional activities of two proto-oncogenes, nuclear factor erythroid 2 (NFE2L2)-related factor 2 (NRF2) and c-Myc. We have identified classifiers that attain accuracies higher than 80%, which have allowed us to identify a set of key protein regions that lead to significant perturbations in c-Myc or NRF2 transcriptional pathway activities.

Assessment of Cr, Ni and Pb Pollution in Rural Agricultural Soils of Tonalite-Trondjhemite Series in Central India.

Chromium (Cr), nickel (Ni) and lead (Pb) contamination was investigated in wheat cultivated rain-fed and irrigated rural agricultural soils (n = 31) of Tonalite-Trondjhemite Series in Central India. The soil sampling was carried out by using stratified random sampling method. The mean concentrations of Cr, Ni and Pb were 54.8, 38.1 and 68.9 mg/kg, respectively. The average values of enrichment factor (EF), geoaccumulation index (I geo ) and contamination factor (CF) followed the order as: Pb > Ni > Cr. Distribution patterns of soil parent material and weathering processes govern mineral enrichments, irrespective of rainfed or irrigated agricultural practices. Principal component analysis (PCA) showed strong loading of Cr and Ni (PC1) and Pb and clay (PC3). The strong loading on Cr and Ni indicates soils are originating from basic and volcanic rocks in the study area. The strong loading of Pb and clay indicates Pb is strongly adsorbed on clay minerals and Fe-oxides. The cancer risk (CR) index showed negligible carcinogenic risk to the residing population. However, hazard index (HI) values for children exceed the safe limit (HI > 1) for Cr and Pb. Spatial distribution of pollution load index suggest highest pollution in the northeastern part of the district. The study revealed that geogenically enriched soils of the area are suitable for agricultural activities under present conditions.

Micronutrient Fractionation in Coal Mine-Affected Agricultural Soils, India.

Assessment of the anthropogenic impacts on bioavailability, mobility, immobility and toxicity of four micronutrients (Cu, Fe, Mn, and Zn) were carried out by Community Bureau of Reference (BCR) fractionation scheme in agricultural soils (n = 10) around Jharia coalfield, eastern India. The relative abundance of micronutrients was as follows: Fe > Mn > Zn > Cu. The enrichment factor was >1 for Zn (6.1) and Cu (1.8) near coal mining area indicated toward soil pollution due to coal mining activities and application of inorganic fertilizers. The I geo values of micronutrients were <0 suggest no pollution with respect to Cu, Fe, Mn and Zn. Correlation analysis showed geogenic origin of soil micronutrients and derived mainly from weathering of minerals present in the parent rock. The mean values of Cu, Mn and Zn were less than certified reference material indicating highly leached agricultural soils in the study region. BCR fractionation of micronutrients showed that a single element could not reveal all types of chemical reactions occurring in soil consortium.