Martin Larralde
PhD Student
Now Postdoctoral Researcher at IDIAP Research Institute

Martin Larralde was a PhD student in the lab from 2019-09-01 to 2026-10-31, where he worked on discovering biosynthetic gene clusters in the gut microbiome and developing robust software. He is now a postdoctoral researcher in Lausanne, CH, working on human-centered health AI.

Research

Inferring gene functions (using AI)

Gut microbial secondary metabolism

Tools

Enzyme Motif Miner: Geometric matching of catalytic motifs in protein structures.

PyOrthoANI, PyFastANI, PySkANI: Python interface to OrthoANI, FastANI, and skani; methods for computing average nucleotide identity.

IGUA: Fast, flexible gene cluster family delineation with IGUA.

CHAMOIS: Machine learning inference of natural product chemistry.

PyHMMER: Cython bindings and Python interface to HMMER3.

Pyrodigal: Python bindings and interface to Prodigal, an efficient method for gene prediction in prokaryotes.

GECCO: Gene Cluster prediction with Conditional Random Fields

Papers

Fast, flexible gene cluster family delineation with IGUA

Investigating Enzyme Function by Geometric Matching of Catalytic Motifs

Meta-analysis reveals microbiome signatures for colorectal cancer that are universal across age groups and sequencing methods

Secondary bile acid production by gut bacteria promotes Western diet-associated colorectal cancer

PyOrthoANI, PyFastANI, and Pyskani: a suite of Python libraries for computation of average nucleotide identity

[PREPRINT] Machine learning inference of natural product chemistry across biosynthetic gene cluster types

Heterologous Expression of a Cryptic BGC from Bilophila sp. Provides Access to a Novel Family of Antibacterial Thiazoles

Metagenomic global survey and in-depth genomic analyses of Ruminococcus gnavus reveal differences across host lifestyle and health status

[PREPRINT] Long-term fasting remodels gut microbial metabolism and host metabolism

PyHMMER: a Python library binding to HMMER for efficient sequence analysis

proGenomes3: approaching one million accurately and consistently annotated high-quality prokaryotic genomes

Biosynthetic potential of the global ocean microbiome

Pyrodigal: Python bindings and interface to Prodigal, an efficient method for gene prediction in prokaryotes

[PREPRINT] Accurate de novo identification of biosynthetic gene clusters with GECCO

Talks

Optimizing venerable bioinformatics software: A profile-guided approach

Accurate de novo identification of biosynthetic gene clusters with GECCO

Posters

High-performance annotation of biological sequence profiles