PersonaDrive: A Method for the Identification and Prioritization of Personalized Cancer Drivers

CanSeer: a translational methodology for developing personalized cancer models and therapeutics

Computational modeling and analysis of biomolecular network models annotated with omics data are emerging as a versatile tool for designing personalized therapies. Current endeavors aimed at employing in silico models towards personalized cancer therapeutics remain limited in providing all-in-one approach that ascertains actionable targets, re-positions FDA (Food and Drug Administration) approved drugs, furnishes quantitative cues on therapy responses such as efficacy and cytotoxic effect, and identifies novel drug combinations. Here we propose "CanSeer"-a methodology for developing personalized therapeutics. CanSeer employs patient-specific genetic alterations and RNA-seq data to annotate in silico models followed by dynamical network analyses towards assessment of treatment responses. To exemplify, three use cases involving paired samples, unpaired samples, and cancer samples only, of lung squamous cell carcinoma (LUSC) patients are provided. CanSeer reveals the effectiveness of repositioned drugs along with the identification of several novel LUSC treatment combinations including Afuresertib + Palbociclib, Dinaciclib + Trametinib, Afatinib + Oxaliplatin, Ulixertinib + Olaparib, etc.

Enhancing Molecular Network-Based Cancer Driver Gene Prediction Using Machine Learning Approaches: Current Challenges and Opportunities

Cancer is a complex disease driven by mutations in the genes that play critical roles in cellular processes. The identification of cancer driver genes is crucial for understanding tumorigenesis, developing targeted therapies and identifying rational drug targets. Experimental identification and validation of cancer driver genes are time-consuming and costly. Studies have demonstrated that interactions among genes are associated with similar phenotypes. Therefore, identifying cancer driver genes using molecular network-based approaches is necessary. Molecular network-based random walk-based approaches, which integrate mutation data with protein-protein interaction networks, have been widely employed in predicting cancer driver genes and demonstrated robust predictive potential. However, recent advancements in deep learning, particularly graph-based models, have provided novel opportunities for enhancing the prediction of cancer driver genes. This review aimed to comprehensively explore how machine learning methodologies, particularly network propagation, graph neural networks, autoencoders, graph embeddings, and attention mechanisms, improve the scalability and interpretability of molecular network-based cancer gene prediction.

Identifying cooperating cancer driver genes in individual patients through hypergraph random walk

OBJECTIVE

Identifying cancer driver genes, especially rare or patient-specific cancer driver genes, is a primary goal in cancer therapy. Although researchers have proposed some methods to tackle this problem, these methods mostly identify cancer driver genes at single gene level, overlooking the cooperative relationship among cancer driver genes. Identifying cooperating cancer driver genes in individual patients is pivotal for understanding cancer etiology and advancing the development of personalized therapies.

METHODS

Here, we propose a novel Personalized Cooperating cancer Driver Genes (PCoDG) method by using hypergraph random walk to identify the cancer driver genes that cooperatively drive individual patient cancer progression. By leveraging the powerful ability of hypergraph in representing multi-way relationships, PCoDG first employs the personalized hypergraph to depict the complex interactions among mutated genes and differentially expressed genes of an individual patient. Then, a hypergraph random walk algorithm based on hyperedge similarity is utilized to calculate the importance scores of mutated genes, integrating these scores with signaling pathway data to identify the cooperating cancer driver genes in individual patients.

RESULTS

The experimental results on three TCGA cancer datasets (i.e., BRCA, LUAD, and COADREAD) demonstrate the effectiveness of PCoDG in identifying personalized cooperating cancer driver genes. These genes identified by PCoDG not only offer valuable insights into patient stratification correlating with clinical outcomes, but also provide an useful reference resource for tailoring personalized treatments.

CONCLUSION

We propose a novel method that can effectively identify cooperating cancer driver genes for individual patients, thereby deepening our understanding of the cooperative relationship among personalized cancer driver genes and advancing the development of precision oncology.

Exploring gene-patient association to identify personalized cancer driver genes by linear neighborhood propagation

BACKGROUND

Driver genes play a vital role in the development of cancer. Identifying driver genes is critical for diagnosing and understanding cancer. However, challenges remain in identifying personalized driver genes due to tumor heterogeneity of cancer. Although many computational methods have been developed to solve this problem, few efforts have been undertaken to explore gene-patient associations to identify personalized driver genes.

RESULTS

Here we propose a method called LPDriver to identify personalized cancer driver genes by employing linear neighborhood propagation model on individual genetic data. LPDriver builds personalized gene network based on the genetic data of individual patients, extracts the gene-patient associations from the bipartite graph of the personalized gene network and utilizes a linear neighborhood propagation model to mine gene-patient associations to detect personalized driver genes. The experimental results demonstrate that as compared to the existing methods, our method shows competitive performance and can predict cancer driver genes in a more accurate way. Furthermore, these results also show that besides revealing novel driver genes that have been reported to be related with cancer, LPDriver is also able to identify personalized cancer driver genes for individual patients by their network characteristics even if the mutation data of genes are hidden.

CONCLUSIONS

LPDriver can provide an effective approach to predict personalized cancer driver genes, which could promote the diagnosis and treatment of cancer. The source code and data are freely available at https://github.com/hyr0771/LPDriver .

A Graph Convolution Network-Based Model for Prioritizing Personalized Cancer Driver Genes of Individual Patients

Cancer driver genes are mutated genes that play a key role in the growth of cancer cells. Accurately identifying the cancer driver genes helps us understand cancer's pathogenesis and develop effective treatment strategies. However, cancers are highly heterogeneous diseases; patients with the same cancer type may have different genomic characteristics and clinical symptoms. Hence, it is urgent to devise effective methods to identify personalized cancer driver genes of individual patients to help determine whether a patient can be treated with a certain targeted drug. This work presents a method for predicting personalized cancer Driver genes of individual patients based on Graph Convolution Networks and Neighbor Interactions called NIGCNDriver. NIGCNDriver first constructs a gene-sample association matrix using the associations between a sample and its known driver genes. Then, it employs graph convolution models on the gene-sample network to aggregate neighbor node features, and themself features, and then combines with the element-wise level interactions between neighbors to learn new feature representations for the samples and gene nodes. Finally, a linear correlation coefficient decoder is used to reconstruct the association between the sample and the mutant gene, enabling the prediction of a personalized driver gene for the individual sample. We applied the NIGCNDriver method to predict cancer driver genes for individual samples in the TCGA and cancer cell line datasets. The results show that our method outperforms the baseline methods in cancer driver gene prediction for individual samples.

Sparse canonical correlation to identify breast cancer related genes regulated by copy number aberrations

BACKGROUND

Copy number aberrations (CNAs) in cancer affect disease outcomes by regulating molecular phenotypes, such as gene expressions, that drive important biological processes. To gain comprehensive insights into molecular biomarkers for cancer, it is critical to identify key groups of CNAs, the associated gene modules, regulatory modules, and their downstream effect on outcomes.

METHODS

In this paper, we demonstrate an innovative use of sparse canonical correlation analysis (sCCA) to effectively identify the ensemble of CNAs, and gene modules in the context of binary and censored disease endpoints. Our approach detects potentially orthogonal gene expression modules which are highly correlated with sets of CNA and then identifies the genes within these modules that are associated with the outcome.

RESULTS

Analyzing clinical and genomic data on 1,904 breast cancer patients from the METABRIC study, we found 14 gene modules to be regulated by groups of proximally located CNA sites. We validated this finding using an independent set of 1,077 breast invasive carcinoma samples from The Cancer Genome Atlas (TCGA). Our analysis of 7 clinical endpoints identified several novel and interpretable regulatory associations, highlighting the role of CNAs in key biological pathways and processes for breast cancer. Genes significantly associated with the outcomes were enriched for early estrogen response pathway, DNA repair pathways as well as targets of transcription factors such as E2F4, MYC, and ETS1 that have recognized roles in tumor characteristics and survival. Subsequent meta-analysis across the endpoints further identified several genes through the aggregation of weaker associations.

CONCLUSIONS

Our findings suggest that sCCA analysis can aggregate weaker associations to identify interpretable and important genes, modules, and clinically consequential pathways.