Rafael Peres da Silva

This paper demonstrates direct high-throughput sequencing of non-canonical bases using nanopore sequencing and bootstrapped learning, achieving high accuracy and specificity in basecalling.

MetageNN improves taxonomic classification of long-read sequencing data by using a neural network that is robust to sequencing errors and missing genomes, outperforming existing methods in sensitivity and speed.

The paper uses single-cell RNA-seq data to predict drug responses and combinations by analyzing intra-tumor transcriptomic heterogeneity in cancer cell lines.

TUGDA reduces negative transfer in drug response prediction by adapting in vitro models to in vivo settings through uncertainty-guided domain adaptation.