Identifying driver genes for individual patients through inductive matrix completion

Abstract

Motivation The driver genes play a key role in the evolutionary process of cancer. Effectively identifying these driver genes is crucial to cancer diagnosis and treatment. However, due to the high heterogeneity of cancers, it remains challenging to identify the driver genes for individual patients. Although some computational methods have been proposed to tackle this problem, they seldom consider the fact that the genes functionally similar to the well-established driver genes may likely play similar roles in cancer process, which potentially promotes the driver gene identification. Thus, here we developed a novel approach of IMCDriver to promote the driver gene identification both for cohorts and individual patients. Results IMCDriver first considers the well-established driver genes as prior information, and adopts the using multi-omics data (e.g., somatic mutation, gene expression and protein-protein interaction) to compute the similarity between patients/genes. Then, IMCDriver prioritizes the personalized mutated genes according to their functional similarity to the well-established driver genes via Inductive Matrix Completion. Finally, IMCDriver identifies the highly rank-ordered genes as the personalized driver genes. The results on five cancer datasets from TCGA show that our IMCDriver outperforms other existing state-of-the-art methods both in the cohort and patient-specific driver gene identification. IMCDriver also reveals some novel driver genes that potentially drive cancer development. In addition, even for the driver genes rarely mutated among a population, IMCDriver can still identify them and prioritize them with high priorities. Availability Code available at https://github.com/NWPU-903PR/IMCDriver Supplementary information Supplementary data are available at Bioinformatics online.

Prioritization of cancer driver gene with prize-collecting steiner tree by introducing an edge weighted strategy in the personalized gene interaction network

“…Recently some newer methods such as IMCDriver [ 18 ] has been proposed to predict personalized driver genes. However, these methods are the supervised learning methods, which need the information of known driver genes in benchmark data.…”

Unsupervised Multi-Omics Data Integration Methods: A Comprehensive Review

“…Before completing the association matrix with IMC, a top-kk nearest neighbor model is applied to denoise the integrated similarity matrix. See ( Ou-Yang et al, 2022 ) for a comprehensive review of matrix factorization methods for biomedical link prediction, including, IMCDriver ( Zhang et al, 2021 ) and DisoFun ( Wang et al, 2020 ).…”

Network Control Models With Personalized Genomics Data for Understanding Tumor Heterogeneity in Cancer

“…On the other hand, the functional characteristics of cancer mutations in population cohorts are different from those observed in individual cancer patient data with complex and unclear dynamics. Therefore, considering that network techniques such as random walk with restart (RWR) ( 60 ), network diffusion ( 19 , 61 ), subnetwork enrichment analysis ( 62 ), matrix completion ( 63 ) and network structure control ( 6 , 64 – 66 ) to predict cancer driver genes at the biological network level by incorporating the knowledge of pathways, protein-protein interactions, can deal with high-dimensional data having a small sample size, researchers proposed some network algorithms for predicting personalized driver genes of individual patients ( 14 , 15 , 67 ). Although these algorithms can predict personalized driver genes with important biological functions, they do not consider dynamic changes in the structure of the personalized gene interaction network, thereby leading to false-positive results and affecting the accuracy of driver gene identification.…”