Machine Learning based Classification of Ocular Pathogens using Host-transcriptomic Signatures: a proof-of-concept
Abstract
Background. Diagnosis of infectious keratitis, uveitis, and endophthalmitis is constrained by the scarcity of pathogen-derived material in small-volume ocular specimens. The host transcriptome is an abundant alternative signal: infection elicits pathogen-class-specific transcriptional responses that may permit pathogen identification without direct detection. We tested this premise as a proof of concept using publicly available in-vitro infection RNA seq. We assembled 330 human RNA-seq samples (177 infected, 153 mock) spanning six pathogens (Herpes Simplex Virus-1, Human Cytomegalovirus Virus, Aspergillus Fumigatus, Candida Albicans, Pseudomonas Aeruginosa, Mycobacterium Tuberculosis) across 36 BioProjects and 24 host cell types. Results. Per-study differential expression yielded a robust-gene feature matrix. Pathogen classification was evaluated with Random Forest under leave-one-study-out (grouped) cross-validation and contrasted against random cross-validation to quantify study-level information leakage. Under random (non-grouped) cross-validation, balanced accuracy reached 0.85–0.92 across gene panel sizes (8–700 + genes). Under honest, leakage-corrected leave-one-group-out validation, balanced accuracy was lower than random cross-validation and remained stable across panel sizes and gene-selection strategies, peaking at 0.70 (60–100 gene panel) and averaging 0.519–0.60 across the full range of gene sets tested (8 to 9,942 genes; chance level = 0.14 for 7 classes). Unsupervised UMAP visualization of the robust gene set showed distinct clustering by pathogen and by pathogen class (viral, fungal, bacterial), with cross-kingdom pathogen pairs showing more distinct separation than within-kingdom comparisons. Conclusions. Beyond established diagnostics such as PCR and metagenomics, host transcriptomic signatures analyzed via machine learning offer a promising alternative approach to pathogen classification, achieving balanced accuracy substantially above chance under rigorous, study-independent validation. These findings support the feasibility of host-transcriptome-based diagnostic classification, with dataset provenance as the primary current limitation to clinical translation.
Related
- Rapid Species-Level Classification of Urinary Pathogens from Raw LC-MS/MS Signals Using Machine Learning.
- Multi-Platform Transcriptomic Classification of LUAD Driver Mutation Subtypes via Heterogeneous Ensemble Learning
- Stage-Stratified Explainable Machine Learning Identifies a Reproducible Transcriptomic Classifier with Stage-Dependent Feature Importance in Colorectal Cancer: A Multi-Cohort Study with Saudi Population Contextualisation
- Exploratory Integration of Metabolomics and Machine Learning Identifies Candidate Signatures of Spontaneous Preterm Birth
- Timing and Context Features in Machine Learning Classification of Inter-Patient ECG Heartbeats on the MIT-BIH Benchmark
BibTeX
@misc{plumber¹2026machine,
title = {{Machine Learning based Classification of Ocular Pathogens using Host-transcriptomic Signatures: a proof-of-concept}},
author = {Maria Taher Plumber¹ and Ratnesh Kumar and Tejabhiram Yadavalli},
howpublished = {Research Square},
year = {2026},
month = oct,
doi = {10.21203/rs.3.rs-11233042/v1},
url = {https://doi.org/10.21203/rs.3.rs-11233042/v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Machine Learning based Classification of Ocular Pathogens using Host-transcriptomic Signatures: a proof-of-concept
AU - Maria Taher Plumber¹
AU - Ratnesh Kumar
AU - Tejabhiram Yadavalli
PY - 2026
DA - 2026/10/27
PB - Research Square
DO - 10.21203/rs.3.rs-11233042/v1
UR - https://doi.org/10.21203/rs.3.rs-11233042/v1
AB - Background. Diagnosis of infectious keratitis, uveitis, and endophthalmitis is constrained by the scarcity of pathogen-derived material in small-volume ocular specimens. The host transcriptome is an abundant alternative signal: infection elicits pathogen-class-specific transcriptional responses that may permit pathogen identification without direct detection. We tested this premise as a proof of concept using publicly available in-vitro infection RNA seq. We assembled 330 human RNA-seq samples (177 infected, 153 mock) spanning six pathogens (Herpes Simplex Virus-1, Human Cytomegalovirus Virus, Aspergillus Fumigatus, Candida Albicans, Pseudomonas Aeruginosa, Mycobacterium Tuberculosis) across 36 BioProjects and 24 host cell types. Results. Per-study differential expression yielded a robust-gene feature matrix. Pathogen classification was evaluated with Random Forest under leave-one-study-out (grouped) cross-validation and contrasted against random cross-validation to quantify study-level information leakage. Under random (non-grouped) cross-validation, balanced accuracy reached 0.85–0.92 across gene panel sizes (8–700 + genes). Under honest, leakage-corrected leave-one-group-out validation, balanced accuracy was lower than random cross-validation and remained stable across panel sizes and gene-selection strategies, peaking at 0.70 (60–100 gene panel) and averaging 0.519–0.60 across the full range of gene sets tested (8 to 9,942 genes; chance level = 0.14 for 7 classes). Unsupervised UMAP visualization of the robust gene set showed distinct clustering by pathogen and by pathogen class (viral, fungal, bacterial), with cross-kingdom pathogen pairs showing more distinct separation than within-kingdom comparisons. Conclusions. Beyond established diagnostics such as PCR and metagenomics, host transcriptomic signatures analyzed via machine learning offer a promising alternative approach to pathogen classification, achieving balanced accuracy substantially above chance under rigorous, study-independent validation. These findings support the feasibility of host-transcriptome-based diagnostic classification, with dataset provenance as the primary current limitation to clinical translation.
SN - 2693-5015
ER -