Predicting Molecular Phenotypes with Single Cell RNA Sequencing Data: an Assessment of Unsupervised Machine Learning Models

TL;DR

This study evaluates various unsupervised machine learning models applied to single cell RNA sequencing data to classify treatment-resistant tumor phenotypes, identifying effective clustering approaches for potential clinical applications.

Contribution

It provides a comprehensive assessment of multiple clustering algorithms on scRNAseq data for tumor phenotype classification, proposing an optimized pipeline for clinical research.

Findings

K-Means, Ward, and BIRCH achieved ~80% accuracy in tumor vs. non-tumor classification.

The pipeline effectively distinguishes molecular subtypes and patient IDs.

Optimized models can aid understanding of cancer cell behavior in clinical settings.

Abstract

According to the National Cancer Institute, there were 9.5 million cancer-related deaths in 2018. A challenge in improving treatment is resistance in genetically unstable cells. The purpose of this study is to evaluate unsupervised machine learning on classifying treatment-resistant phenotypes in heterogeneous tumors through analysis of single cell RNA sequencing(scRNAseq) data with a pipeline and evaluation metrics. scRNAseq quantifies mRNA in cells and characterizes cell phenotypes. One scRNAseq dataset was analyzed (tumor/non-tumor cells of different molecular subtypes and patient identifications). The pipeline consisted of data filtering, dimensionality reduction with Principal Component Analysis, projection with Uniform Manifold Approximation and Projection, clustering with nine approaches (Ward, BIRCH, Gaussian Mixture Model, DBSCAN, Spectral, Affinity Propagation, Agglomerative Clustering, Mean Shift, and K-Means), and evaluation. Seven models divided tumor versus non-tumor cells and molecular subtype while six models classified different patient identification (13 of which were presented in the dataset); K-Means, Ward, and BIRCH often ranked highest with ~80% accuracy on the tumor versus non-tumor task and ~60% for molecular subtype and patient ID. An optimized classification pipeline using K-Means, Ward, and BIRCH models was evaluated to be most effective for further analysis. In clinical research where there is currently no standard protocol for scRNAseq analysis, clusters generated from this pipeline can be used to understand cancer cell behavior and malignant growth, directly affecting the success of treatment.