Paired-Sample and Pathway-Anchored MLOps Framework for Robust Transcriptomic Machine Learning in Small Cohorts

Abstract

BackgroundNinety percent of the 65,000 human diseases are infrequent, collectively affecting [~] 400 million people, substantially limiting cohort accrual. This low prevalence constrains the development of robust transcriptome-based machine learning (ML) classifiers. Standard data-driven classifiers typically require cohorts of over 100 subjects per group to achieve clinical accuracy while managing high-dimensional input ([~]25,000 transcripts). These requirements are infeasible for micro-cohorts of [~]20 individuals, where overfitting becomes pervasive. ObjectiveTo overcome these constraints, we developed a classification method that integrates three enabling strategies: (i) paired-sample transcriptome dynamics, (ii) N-of-1 pathway-based analytics, and (iii) reproducible machine learning operations (MLOps) for continuous model refinement. MethodsUnlike ML approaches relying on a single transcriptome per subject, within-subject paired-sample designs -- such as pre-versus post-treatment or diseased versus adjacent-normal tissue -- effectively control intra-individual variability under isogenic conditions and within-subject environmental exposures (e.g. smoking history, other medications, etc.), improve signal-to-noise ratios, and, when pre-processed as single-subject studies (N-of-1), can achieve statistical power comparable to that obtained in animal models. Pathway-level N-of-1 analytics further reduces each samples high-dimensional profile into [~]4,000 biologically interpretable features, annotated with effect sizes, dispersion, and significance. Complementary MLOps practices--automated versioning, continuous monitoring, and adaptive hyperparameter tuning--improve model reproducibility and generalization. ResultsIn two case studies--human rhinovirus infection versus matched healthy controls (n=16 training; 3 test) and breast cancer tissues harboring TP53 or PIK3CA mutations versus adjacent normal tissue (n=27 training; 9 test)--this approach achieved 90% precision and recall on an unseen breast cancer test set and 92% precision with 90% recall in rhinovirus fivefold cross-validation. Incorporating paired-sample dynamics boosted precision by 8.8% and recall by 6%, while the MLOps workflow yielded additional gains of 14.5% and 12.5%, respectively. Moreover, our method identified 42 critical gene sets (pathways) for rhinovirus response and 21 for cancer mutation status. ConclusionsThese proof-of-concept results support the utility of integrating intra-subject dynamics, "biological knowledge"-based feature reduction (pathway-level feature reduction grounded in prior biological knowledge; e.g., N-of-1-pathways analytics), and reproducible MLOps workflows can overcome cohort-size limitations in infrequent disease, offering a scalable, interpretable solution for high-dimensional transcriptomic classification. Future work will extend these advances across various therapeutic and small-cohort designs.