Institute for Global Food Security · Queen's University Belfast

Welcome to the CreeveyLab

We are a computational biology group working on microbial communities — developing machine learning/AI and bioinformatics tools to explore metagenomic data, AMR, ruminant biology, food systems, and environmental change.

Explore Our Research Meet the Team

Machine learning as a new lens on microbial genomics

We're applying machine learning and deep learning to genomic and metagenomic data — from predicting antimicrobial resistance and optimizing sustainable agriculture, to understanding complex microbial ecosystems and driving environmental biotechnology.

Machine Learning Predictive Modeling Genomics

Research Areas

Five interconnected areas, each drawing on machine learning and bioinformatics to ask how microbes work — and why it matters.

Antimicrobial Resistance & One Health

Understanding how AMR develops and spreads across human, animal, and environmental microbiomes using machine learning, computational, and phylogenetic approaches.

AMRMachine LearningOne HealthMetagenomics

Sustainable Food Systems & Agriculture

Developing AI solutions and computational approaches to transform agri-food systems for sustainability and resilience.

AIAgricultureLivestockFood Security

Environmental Microbiology & Biotechnology

Exploring bacteriophage applications and methanogen biology to address environmental challenges and climate change.

Phage TherapyMetagenomicsClimateMethanogens

Phylogenomics

Reconstructing evolutionary histories and inferring relationships across the tree of life using large-scale genomic datasets and novel computational approaches.

PhylogeneticsComparative GenomicsEvolutionSupertrees

Methodological Development

Creating novel machine learning frameworks, bioinformatics tools, pipelines, and multi-omics integration approaches for microbiome and genomics research.

Machine LearningBioinformaticsMulti-OmicsPipelines
View All Research

Our Team

An interdisciplinary group of computational biologists, machine learning researchers, bioinformaticians, and microbiologists based at the Institute for Global Food Security, Queen's University Belfast.

Meet the Team

Software

We write open-source bioinformatics and machine learning tools — here's a sample.

Amply

A computational pipeline for identifying novel Antimicrobial Peptides (AMPs) from any form of digital biological data, for synthesis and screening against multi-drug resistant bacteria and fungi.

↗ Website

Apply Decision Tree

A tool for easy implementation of j48 decision trees from WEKA on novel datasets, developed to streamline machine learning workflows in bioinformatics.

↗ GitHub

AQUA

Automated Quality Improvement for multiple sequence alignments. Automatically identifies the most reliable alignment for a given protein family using MUSCLE, MAFFT, RASCAL, and NORMD.

↗ Website

CatSequences

A tool for concatenating multiple FASTA alignments for supermatrix phylogenetic analyses, part of a general phylogenomics software suite.

↗ GitHub

Clann

Construction of supertrees and exploration of phylogenomic information from partially overlapping datasets. Implements optimal phylogenetic supertree methods.

↗ Website

Clan Check

Analyses single-copy phylogenetic trees to assess compatibility with user-defined groupings (clans) in unrooted trees — ideal for large-scale phylogenomic analyses.

↗ GitHub
View All Tools

News

event

Biological Diversity Research Showcase at QUB School of Biological Sciences

Chris organised and hosted the inaugural Biological Diversity Research Showcase as Theme Lead for the Sustaining Ecosystems and Biodiversity Theme at the QUB School of Biological Sciences, timed to coincide with the UN International Day for Biological Diversity. The event brought together researchers from across the school to exchange ideas and celebrate the breadth of biodiversity research at Queen’s. Keynote speaker Dr. Cathy Maguire headlined a packed programme of talks and discussions. Hopefully the first of many annual events.

software

Clann V5.1: Modernising phylogenetic supertree inference

A substantial update to Clann, the maximum likelihood supertree inference tool. V5.1 introduces proper ML optimality criteria based on Steel & Rodrigo (2008), Robinson–Foulds distance scoring, ML topology tests (Kishino–Hasegawa and Shimodaira–Hasegawa), parallel heuristic search, source-tree weighting schemes, supertree landscape clustering analysis, and a modernised interactive CLI. The codebase has been fully refactored into modular components. The project has been revived after years of dormancy—legacy phylogenetics methods deserve a second life.

publication

Coping with ineffective overlap in multilocus phylogenetics

This paper addresses a fundamental challenge in multilocus phylogenetics — how to handle cases where different genes cover different subsets of taxa, leading to ineffective overlap. Published in Systematic Biology.

All News

Interested in joining us?

We're always happy to hear from people curious about machine learning, computational biology, bioinformatics, and microbial genomics — whether you're looking for a PhD, a postdoc, or just want to talk science. Drop Chris an email.