Feature Selection Strategies for Deep Learning-Based Classification in Ultra-High-Dimensional Genomic Data.

The advancement of high-throughput sequencing has revolutionised genomic research by generating large amounts of data. However, Whole-Genome Sequencing is associated with a statistical challenge known as the p >> n problem. We classified 1825 individuals into five breeds based on 11,915,233 SNPs.

Bacteria associated with Zn-hyperaccumulators Arabidopsis halleri and Arabidopsis arenosa from Zn-Pb-Cd waste heaps in Poland as promising tools for bioremediation.

To identify metal adapted bacteria equipped with traits positively influencing the growth of two hyperaccumulator plant species Arabidopsis arenosa and Arabidopsis halleri, we isolated bacteria inhabiting rhizosphere and vegetative tissues (roots, basal and stem leaves) of plants growing on two old Zn-Pb-Cd waste heaps in Bolesław and Bukowno (S. Poland), and characterized their potential plant growth promoting (PGP) traits as well as determined metal concentrations in rhizosphere and plant tissues. To determine taxonomic position of 144 bacterial isolates, 16S rDNA Sanger sequencing was used.