netDx: Software for building interpretable patient classifiers by multi-'omic data integration using patient similarity networks

Abstract

Patient classification based on clinical and genomic data will further the goal of precision medicine. Interpretability is of particular relevance for models based on genomic data, where sample sizes are relatively small (in the hundreds), increasing overfitting risk netDx is a machine learning method to integrate multi-modal patient data and build a patient classifier. Patient data are converted into networks of patient similarity, which is intuitive to clinicians who also use patient similarity for medical diagnosis. Features passing selection are integrated, and new patients are assigned to the class with the greatest profile similarity. netDx has excellent performance, outperforming most machine-learning methods in binary cancer survival prediction. It handles missing data – a common problem in real-world data – without requiring imputation. netDx also has excellent interpretability, with native support to group genes into pathways for mechanistic insight into predictive features. The netDx Bioconductor package provides multiple workflows for users to build custom patient classifiers. It provides turnkey functions for one-step predictor generation from multi-modal data, including feature selection over multiple train/test data splits. Workflows offer versatility with custom feature design, choice of similarity metric; speed is improved by parallel execution. Built-in functions and examples allow users to compute model performance metrics such as AUROC, AUPR, and accuracy. netDx uses RCy3 to visualize top-scoring pathways and the final integrated patient network in Cytoscape. Advanced users can build more complex predictor designs with functional building blocks used in the default design. Finally, the netDx Bioconductor package provides a novel workflow for pathway-based patient classification from sparse genetic data.

A Detailed Catalogue of Multi-Omics Methodologies for Identification of Putative Biomarkers and Causal Molecular Networks in Translational Cancer Research

“…On the other hand, netDx [ 107 , 164 ] is a recently published Bioconductor R package, which provides a novel methodology of implementing patient similarity networks for efficient patient classification, which has been shown to outperform other machine learning approaches. It can integrate heterogeneous patient data from clinical to omics layers, while implementing machine learning algorithms for robust feature selection.…”

“…Running netDx with 1 CPU took about 72 minutes for this dataset with defined settings (see Materials and Methods section). The aim of applying netDx was to obtain patient similarity networks (PSN) and group patients based on a multi-omics profile [ 164 ]. The PSN networks consist of nodes which represent the patients connected by edges representing the weighted pairwise similarities between patients.…”

“…Integrated patient similarity network for binary stratification of IGHV status based on multi-omic data (green—IGHV mutation, blue—no IGHV mutation). Each node in this network corresponds to a CLL patient and each edge corresponds to weights displaying the average similarity across all features passing feature selection [ 164 ]. This network was generated by implemented functions of netDx and visualized by Cytoscape.…”