biostudies-literatureUnknownGoddard TRNIDDK NIH HHSChronic 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 detectmedRxiv : the preprint server for health sciences2025.12.28.25342520https://www.ebi.ac.uk/biostudies/studies/S-EPMC12772665biostudies-literatureMicrobial Ecological Signatures Predict Pathogen Emergence and Multidrug Resistance in Cystic Fibrosis Airways up to a Year in Advance.PMC12772665RC2 DK116713Warner MSHodgson RJKerr ENRoach MJKeneally CWatson CDPeddle SDDecewicz PGiles SKFalk NWRyan FJTarasenko AOoi CYGoddard TRHarker CMEdwards RAHopkins ESpeck PGBouras GMallawaarachchi VDinsdale EAHesse RDJudith MInglis LKIredell JRPapudeshi BDrigo BMartin BDoane MPJohn WWhiteson KLMitchell JGLiddicoat CGreen RAndrew TGrigson SRCarlson-Jones JAHussnain AJersmann HPHutton AYang QEvans IEfalseMicrobial 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 detect2026-01-01T00:00:00Z2026 Jan2026-06-16T03:19:09.361Z2026-06-16T03:09:53.728ZS-EPMC127726654150348910.64898/2025.12.28.25342520