Microbial Ecological Signatures Predict Pathogen Emergence and Multidrug Resistance in Cystic Fibrosis Airways up to a Year in Advance

Chronic infections in cystic fibrosis (CF) emerge from gradual ecological transitions in the airway microbiome, yet early predictive markers remain poorly defined. We developed a new autoencoder-based framework that outperforms read-based or metagenome-assembled genome-based analyses at capturing the continuum from health-associated commensals to pathogen-dominated, antibiotic-tolerant communities. This improvement is achieved by integrating taxonomic and functional data from 127 sputum and bronchoalveolar lavage metagenomes from 64 people with CF into latent "Clusters of Phylogeny and Functions" (COPFs). Coupled with gradient-boosted random forests, COPFs predicted <i>Pseudomonas aeruginosa</i> colonisation, multidrug resistance, and impending infection up to a year before clinical detection. The multidrug-resistant <i>P. aeruginosa</i> signature showed the same resistance-mechanism evolution as found in laboratory experiments. The inclusion of eukaryotic markers revealed persistent <i>Aspergillus fumigatus</i> signatures even during culture-negative intervals. Applying our South Australian-trained model to over 1,000 global metagenomes from 22 independent CF datasets, we achieved 94% accuracy in predicting <i>P. aeruginosa</i> status across platforms and geographies, validating the model's universal utility. Our results demonstrate that combining datasets with deep learning reveals conserved ecological and metabolic mechanisms in disease progression, transforming metagenomics into a predictive framework for managing chronic infections.

Authors

Institutions

Publication Details

Journal
medRxiv
Published
2026-01-02
DOI
https://doi.org/10.64898/2025.12.28.25342520
Primary Topic
Cystic Fibrosis Research Advances
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Microbial Ecological Signatures Predict Pathogen Emergence and Multidrug Resistance in Cystic Fibrosis Airways up to a Year in Advance

Carl D. Watson, Vijini Mallawaarachchi, Michael P. Doane, Susanna R. Grigson et al.
medRxiv
Cystic Fibrosis Research Advances
article

Microbial Ecological Signatures Predict Pathogen Emergence and Multidrug Resistance in Cystic Fibrosis Airways up to a Year in Advance

Carl D. Watson, Vijini Mallawaarachchi, Michael P. Doane, Susanna R. Grigson, Feargal J. Ryan, Bhavya Papudeshi, Laura K. Inglis, Sarah K. Giles, Hubertus Jersmann, Robert A. Edwards, George Bouras, Clarice Harker, Riley J. Hodgson, Thomas Goddard, Renee Green, Shawn D. Peddle, James G. Mitchell, Elizabeth A. Dinsdale, Jonathan R. Iredell, Nicholas Falk, Peter Speck, Michael Roach, Craig Liddicoat, Emma N. Kerr, Belinda C. Martin, Katrine Whiteson, Abbey Hutton, Andrew Tai, Barbara Drigo, Ryan D. Hesse, Morgyn S. Warner, Christopher Keneally, A.B. Tarasenko, Emily Hopkins, Judith Morton, John Wong, Ieuan ES Evans, Art Hussnain, Qi Yang, Chee Y Ooi, Przemysaw Decewicz, Jessica AP Carlson-Jones
article en

Abstract

Chronic infections in cystic fibrosis (CF) emerge from gradual ecological transitions in the airway microbiome, yet early predictive markers remain poorly defined. We developed a new autoencoder-based framework that outperforms read-based or metagenome-assembled genome-based analyses at capturing the continuum from health-associated commensals to pathogen-dominated, antibiotic-tolerant communities. This improvement is achieved by integrating taxonomic and functional data from 127 sputum and bronchoalveolar lavage metagenomes from 64 people with CF into latent "Clusters of Phylogeny and Functions" (COPFs). Coupled with gradient-boosted random forests, COPFs predicted <i>Pseudomonas aeruginosa</i> colonisation, multidrug resistance, and impending infection up to a year before clinical detection. The multidrug-resistant <i>P. aeruginosa</i> signature showed the same resistance-mechanism evolution as found in laboratory experiments. The inclusion of eukaryotic markers revealed persistent <i>Aspergillus fumigatus</i> signatures even during culture-negative intervals. Applying our South Australian-trained model to over 1,000 global metagenomes from 22 independent CF datasets, we achieved 94% accuracy in predicting <i>P. aeruginosa</i> status across platforms and geographies, validating the model's universal utility. Our results demonstrate that combining datasets with deep learning reveals conserved ecological and metabolic mechanisms in disease progression, transforming metagenomics into a predictive framework for managing chronic infections.

medRxiv
South Australia Pathology (AU), Australian Centre for Plant Functional Genomics (AU), Commonwealth Scientific and Industrial Research Organisation (AU), The University of Sydney (AU), New South Wales Department of Health (AU), Royal Adelaide Hospital (AU), The University of Queensland (AU), Flinders University (AU), University of California, Irvine (US), Women's and Children's Hospital (AU), Wine Australia (AU), UNSW Sydney (AU), Basil Hetzel Institute (AU), Mayne Pharma (Australia) (AU), Prince Charles Hospital (AU), Sydney Children's Hospital (AU), Westmead Institute for Medical Research (AU), University of Warsaw (PL), The University of Adelaide (AU)
Australian Government, National Institutes of Health, Medical Research Council, National Health and Medical Research Council, National Institute of Diabetes and Digestive and Kidney Diseases
Life in Land
Openalex Percentile: Top 99%
Cystic Fibrosis Research Advances
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.