Prasad Patil

The paper curates 49 TB transcriptomic datasets into a resource to assess gene signature replicability and demonstrates improved diagnostic accuracy through ensembling.

This study compares gene set scoring methods with original models for TB gene signatures, finding that gene set scoring can achieve equivalent or better performance than original models.

This paper proposes a pairwise imputation strategy to retain predictive features when combining genomic datasets, showing improved performance over using only common features.

The paper evaluates the impact of two-step batch correction on gene expression analysis and proposes strategies to mitigate its effects on statistical inference.

The paper introduces a hierarchical resampling method for multi-study prediction, showing improved performance in neurochemical sensing applications.

This paper develops an ensemble learning approach to improve genomic classifiers by integrating predictions across batches rather than removing batch effects from merged data, showing better performance in independent validation.

The paper develops a DNA methylation-based risk score for cardiovascular disease and shows it predicts risk independently of traditional factors.

This paper develops tree-weighting methods for multi-study ensemble learning, showing improved robustness and feature interpretation in genomic datasets.