This project stores the machine learning model from the paper 'Machine learning and multi-omics data reveal driver gene-based molecular subtypes in hepatocellular carcinoma for precision treatment'

This repository serves as a repository for the supporting code and data derived from the research conducted in this study, intended for the broader scientific community to utilize. The code and data stored here are available for academic use free of charge; any other type of use is strictly prohibited.

✅ This repository primarily focuses on storing machine learning code and software from the paper "Machine learning and multi-omics data reveal driver gene-based molecular subtypes in hepatocellular carcinoma for precision treatment".

✅ **SVM_10**: Machine learning classifier based on the expression of 10 genes.

✅ **SVM_TTK**: Machine learning classifier based on the expression of TTK.

✅ **Subtype-based prognostic models**: prognostic models

✅ We have also packaged these two models into executable software, but due to the file upload size limit on GitHub, we have compressed the software into split volumes.

Introduction

The heterogeneity of Hepatocellular Carcinoma (HCC) poses a barrier to effective treatment. Stratifying highly heterogeneous HCC into molecular subtypes with similar features is crucial for personalized anti-tumor therapies. Although driver genes play pivotal roles in cancer progression, their potential in HCC subtyping has been largely overlooked. This study aims to utilize driver genes to construct HCC subtype models and unravel their molecular mechanisms. Utilizing a novel computational framework, we expanded the initially identified 96 driver genes to 1192 based on mutational aspects and an additional 233 considering driver dysregulation. These genes were subsequently employed as stratification markers for further analyses. A novel multi-omics subtype classification algorithm was developed, leveraging both mutational and expression data of the identified stratification genes. This algorithm successfully categorized HCC into two distinct subtypes, designated as CLASS A and CLASS B, which demonstrated significant differences in survival outcomes. Integration of multi-omics and single-cell data unveiled substantial distinctions between these subtypes at the levels of transcriptomics, mutations, copy number variations, and epigenomics. Moreover, our prognostic model exhibited excellent predictive performance in both training and external validation cohorts. Finally, a 10-gene classification model for these subtypes identified TTK as a promising therapeutic target with robust classification capabilities. This comprehensive study provides a novel perspective on HCC stratification, offering crucial insights for a deeper understanding of its pathogenesis and the development of promising treatment strategies.

Contents of this repository

In this repository, you can find the following folders:

project
├───ML model
│   ├───SVM 10 
│   │   ├───SVM_10 APP
│   │   │   └───APP file
│   ├───SVM TTK
│   │   └───SMV TTK APP
│   │       └───APP file
└───test data

• **ML model**: Stores two classification models, SVM_10 and SVM_TTK.
  • **SVM_10**: Contains the code files and related tutorials for SVM_10.
    • **SVM_10 APP**: Stores the executable program for SVM_10 and related tutorials.
  • **SVM_TTK**: Contains the code files and related tutorials for SVM_TTK.
    • **SVM_TTK APP**: Stores the executable program for SVM_TTK and related tutorials.
• **APP file**: Stores the related executable software. Please note that due to GitHub's file upload size limitations, we have compressed the software into split volumes.
• **Test data**: Contains a set of test data.