Stephen Nayfach

The paper presents a global virome atlas, UHGV, and identifies genomic factors influencing phage-host interactions.

The paper investigates the evolutionary relationship between HK97-fold viruses and encapsulins, finding bidirectional transitions through procapsids.

This paper introduces Protein2PAM, a deep learning model that predicts CRISPR-Cas PAM specificity from protein sequences, enabling the design of Cas variants with tailored PAM recognition.

Scaling sparse Mixture-of-Experts protein language models up to 46B parameters on 1.5T curated tokens broadens viable protein generation across families and amplifies gains from laboratory preference alignment.

This paper introduces proseLM, a protein design method that adapts language models with structural and functional context, improving residue recovery and experimental performance in genome editing and antibody design.

Language models trained on over one million mined CRISPR operons generated Cas9-like effectors and matching guide RNAs, and an AI-designed editor is reported to edit the human genome precisely.

geNomad identifies and annotates mobile genetic elements in sequencing data, discovering millions of new viruses and plasmids in public metagenomes.

Maast efficiently genotypes SNPs from thousands of microbial strains by reducing redundancy and improving speed and accuracy compared to existing methods.

MIDAS2 improves metagenomic analysis by enhancing SNV and CNV detection with custom databases and paired-end reads, enabling efficient genotyping of large sample sets.

This paper introduces GT-Pro, a tool for ultra-fast and accurate SNP calling in metagenomes, enabling strain-level analysis of the human gut microbiome.

CheckV estimates completeness of metagenome-assembled viral contigs against GenBank plus 76,262 metagenome-derived complete genomes and trims host flanks; 86.9% of IMG/VR contigs were low-quality.

This study performs a meta-analysis of gut metagenomes to identify microbiome features associated with health and disease across multiple conditions.

The paper identifies and prioritizes conserved protein families with no known domains using metagenomics data and phylogenetic analysis.

The paper identifies microbial genes associated with gut colonization and disease by using phylogenetic correction in metagenomic data analysis.

This paper develops ShotMAP, a metagenome annotation pipeline, and evaluates its performance on marine and gut microbiome data, finding functional differences in Crohn's disease patients.