salvatoreloguercio

cov2vec

cov2vec is a systematic effort to obtain SARS CoV-2 genome embeddings by encoding viral genomes with protein language models.

VSProjector

Covid19_data

Download, filter and process mutation data (from CNCB) and cases/deaths (from John Hopkins Resource).

DAE_imputation

dbgapr_dev

Test dbgapr, a dbGaP data organizer

Genome-wide-Imputation-Autoencoders

Accurate and Cost-effective Imputation of Genotypes at Whole Genome Level with Sparse Denoising Autoencoders

Genotype_Imputation_Pipeline

Final version of the pipeline for processing TOPMED and other dbGaP datasets, includes: automatic identification of reference genome build and selection of correct chain file, mapping to GRCh37 reference build, initial quality control, ancestry analysis, post-ancestry quality control, phasing, imputation, post-imputation quality control.

Imputation_Autoencoder

Deep learning algorithm for imputation of genetic variants

RepSeqPipe

A pipeline for processing Repertoire Sequencing (Rep-seq) data

salvatoreloguercio.github.io

sl

TOPMed_ref

Building a TOPMed gr38 reference panel.

ukbb_imaging

UKBB imaging data processing

VSProjector_CoV2

VSPsnap

Gaussian Process Regression on SARS-CoV2 data ( Genotype / Infectivity rate/ Fatality rate ).