Martín Beracochea

The paper introduces BioSIFTR, a tool that uses shallow shotgun sequencing and biome-specific databases to generate accurate taxonomic and functional profiles, validated against deep sequencing data.

MAP annotates mobilome elements and their functional cargo in prokaryotic (meta)genomic assemblies, enabling identification of composite elements like ARG-carrying integrons.

FAIRyMAGs provides a modular, FAIR-compliant Galaxy pipeline for generating and analyzing metagenome-assembled genomes, improving accessibility and reproducibility in genome-resolved metagenomics.

This study develops a machine learning framework to predict memory requirements for metagenomic assembly, improving efficiency in high-performance computing environments.

The paper introduces a scalable pipeline for grouping protein sequences into families, showing it matches curated databases and scales linearly with input size.

PIMENTO identifies and removes primer sequences from amplicon sequencing data to enable large-scale variant calling.

Mettannotator is a scalable Nextflow pipeline for prokaryotic genome annotation, capable of handling both known and novel taxa, and it produces GFF files for downstream analysis.

The Open MetaGenomic (OMG) corpus combines 3.1T base pairs and 3.3B protein coding sequences in mixed amino-acid and nucleotide format to pretrain the genomic language model gLM2.

VIRify identifies and classifies viral contigs and prophages from metagenomic data with high accuracy across prokaryotic and eukaryotic viruses.