MicroICS: predictive phenotyping of Listeria monocytogenes biofilms from three-dimensional structural features
6 affiliations
- 1Department of Biotechnology, Jožef Stefan Institute, Ljubljana, Slovenia
- 2Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia
- 3Department of Applied Statistics, Institute of Mathematics and Basic Science, Hungarian University of Agriculture and Life Sciences (MATE), Budapest, Hungary
- 4Department of Condensed Matter Physics, Jožef Stefan Institute, Ljubljana, Slovenia
- 5Centre for Advanced Optical Microscopies, Jožef Stefan Institute, Ljubljana, Slovenia
- 6University of Ljubljana, Veterinary Faculty, Institute of Microbiology and Parasitology, Ljubljana, Slovenia
Abstract
Biofilms underpin microbial survival, yet their three-dimensional structure remains difficult to quantify systematically. We present the Microbial Image Classification Suite (MicroICS), an open-source framework for predictive phenotyping of microbial communities from 3D biofilm images. MicroICS consists of three independent but interoperable modules: feature extraction from 3D biofilm images, machine learning-based classification, and an inference module for applying trained models to new, unseen images. Each module can be run independently, and the classification module accepts externally generated features, enabling integration with existing quantitative image analysis tools. As a pilot study, we demonstrate the framework using eight epidemiologically diverse Listeria monocytogenes strains, with strain differentiation and trait-based grouping as proof-of-principle tasks. MicroICS extracted over 2,700 quantitative structural features from Syto 9-labelled biofilm images. An optimised random forest model achieved human baseline-level accuracy in strain classification on previously unseen images, including biofilms experimentally perturbed by food extracts. BiofilmQ-derived features incorporated into the classification module yielded higher accuracy with fewer features than either tool alone, confirming the framework’s extensibility. Extending the framework to clonal complex-based clinical grouping demonstrates utility beyond strain identity. MicroICS is applicable to any organism or condition for which suitable 3D biofilm images can be obtained.
Related
- Proximity labeling of the Listeria monocytogenes surface reveals pathogen control of a host deubiquitinase
- Protopanaxatriol Inhibits Listeria monocytogenes Infection Through a Multi-Target Virulence Suppression Strategy
- Impaired adaptation to smoke-derived phenolic compounds in Listeria monocytogenes CC204 from smoked salmon and trout
- Viable but Nonculturable Listeria monocytogenes May Resuscitate After Transfer From Stainless Steel Biofilms to Vacuum-Packed Smoked Herring
- Quantitative Phenotyping of Ion Fluxes in Tip-Growing Cells Under Varying Growth Regimes: A Data Analysis Protocol
BibTeX
@article{janez2026microics,
title = {{MicroICS: predictive phenotyping of Listeria monocytogenes biofilms from three-dimensional structural features}},
author = {Nika Janež and Blaž Škrlj and Aljaž Osojnik and Márta Ladányi and Martin Breskvar and Matej Petković and Boštjan Kokot and Petra Čotar and Bojan Papić and Majda Golob and Tjaša Peternel and Jerica Sabotič},
journal = {NPJ Biofilms and Microbiomes},
year = {2026},
month = jul,
doi = {10.1038/s41522-026-01083-8},
url = {https://doi.org/10.1038/s41522-026-01083-8},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - MicroICS: predictive phenotyping of Listeria monocytogenes biofilms from three-dimensional structural features
AU - Nika Janež
AU - Blaž Škrlj
AU - Aljaž Osojnik
AU - Márta Ladányi
AU - Martin Breskvar
AU - Matej Petković
AU - Boštjan Kokot
AU - Petra Čotar
AU - Bojan Papić
AU - Majda Golob
AU - Tjaša Peternel
AU - Jerica Sabotič
PY - 2026
DA - 2026/07/08
JO - NPJ Biofilms and Microbiomes
DO - 10.1038/s41522-026-01083-8
UR - https://doi.org/10.1038/s41522-026-01083-8
AB - Biofilms underpin microbial survival, yet their three-dimensional structure remains difficult to quantify systematically. We present the Microbial Image Classification Suite (MicroICS), an open-source framework for predictive phenotyping of microbial communities from 3D biofilm images. MicroICS consists of three independent but interoperable modules: feature extraction from 3D biofilm images, machine learning-based classification, and an inference module for applying trained models to new, unseen images. Each module can be run independently, and the classification module accepts externally generated features, enabling integration with existing quantitative image analysis tools. As a pilot study, we demonstrate the framework using eight epidemiologically diverse Listeria monocytogenes strains, with strain differentiation and trait-based grouping as proof-of-principle tasks. MicroICS extracted over 2,700 quantitative structural features from Syto 9-labelled biofilm images. An optimised random forest model achieved human baseline-level accuracy in strain classification on previously unseen images, including biofilms experimentally perturbed by food extracts. BiofilmQ-derived features incorporated into the classification module yielded higher accuracy with fewer features than either tool alone, confirming the framework’s extensibility. Extending the framework to clonal complex-based clinical grouping demonstrates utility beyond strain identity. MicroICS is applicable to any organism or condition for which suitable 3D biofilm images can be obtained.
SN - 2055-5008
ER -