Identifying New Candidate Genes and Chemicals Related to Prostate Cancer Using a Hybrid Network and Shortest Path Approach

New Approach for Risk Estimation Algorithms of BRCA1/2 Negativeness Detection with Modelling Supervised Machine Learning Techniques

BRCA1/2 gene testing is a difficult, expensive, and time-consuming test which requires excessive work load. The identification of the BRCA1/2 gene mutations is significantly important in the selection of treatment and the risk of secondary cancer. We aimed to develop an algorithm considering all the clinical, demographic, and genetic features of patients for identifying the BRCA1/2 negativity in the present study. An experimental dataset was created with the collection of the all clinical, demographic, and genetic features of breast cancer patients for 20 years. This dataset consisted of 125 features of 2070 high-risk breast cancer patients. All data were numeralized and normalized for detection of the BRCA1/2 negativity in the machine learning algorithm. The performance of the algorithm was identified by studying the machine learning model with the test data. k nearest neighbours (KNN) and decision tree (DT) accuracy rates of 9 features involving Dataset 2 were found to be the most effective. The removal of the unnecessary data in the dataset by reducing the number of features was shown to increase the accuracy rate of algorithm compared with the DT. BRCA1/2 negativity was identified without performing the BRCA1/2 gene test with 92.88% accuracy within minutes in high-risk breast cancer patients with this algorithm, and the test associated result waiting stress, time, and money loss were prevented. That algorithm is suggested be useful in fast performing of the treatment plans of patients and accurately in addition to speeding up the clinical practice.

Identification of Breast Cancer Subtype Specific MicroRNAs Using Survival Analysis to Find Their Role in Transcriptomic Regulation

The microRNA (miRNA) biomolecules have a significant role in the development of breast cancer, and their expression profiles are different in each subtype of breast cancer. Thus, our goal is to use the Next Generation Sequencing provided high-throughput miRNA expression and clinical data in an integrated fashion to perform survival analysis in order to identify breast cancer subtype specific miRNAs, and analyze associated genes and transcription factors. We select top 100 miRNAs for each of the four subtypes, based on the value of hazard ratio and p-value, thereafter, identify 44 miRNAs that are related to all four subtypes, which we call as four-star miRNAs. Moreover, 12, 14, 9, and 15 subtype specific, viz. one-star miRNAs, are also identified. The resulting miRNAs are validated by using machine learning methods to differentiate tumor cases from controls (for four-star miRNAs), and subtypes (for one-star miRNAs). The four-star miRNAs provide 95% average accuracy, while in case of one-star miRNAs 81% accuracy is achieved for HER2-Enriched. Differences in expression of miRNAs between cancer stages is also analyzed, and a subset of eight miRNAs is found, for which expression is increased in stage II relative to stage I, including hsa-miR-10b-5p, which contributes to breast cancer metastasis. Subsequently we prepare regulatory networks in order to identify the interactions among miRNAs, their targeted genes and transcription factors (TFs), that are targeting those miRNAs. In this way, key regulatory circuits are identified, where genes such as TP53, ESR1, BRCA1, MYC, and others, that are known to be important genetic factors for the cause of breast cancer, produce transcription factors that target the same genes as well as interact with the selected miRNAs. To provide further biological validation the Protein-Protein Interaction (PPI) networks are prepared and Kyoto Encyclopedia of Genes and Genomes pathway and gene ontology (GO) enrichment analysis are performed. Among the enriched pathways many are breast cancer-related, such as PI3K-Akt or p53 signaling pathways, and contain proteins such as TP53, also present in the regulatory networks. Moreover, we find that the genes are enriched in GO terms associated with breast cancer. Our results provide detailed analysis of selected miRNAs and their regulatory networks.

Integrating Multiple Data Sources for Combinatorial Marker Discovery: A Study in Tumorigenesis

Identification of combinatorial markers from multiple data sources is a challenging task in bioinformatics. Here, we propose a novel computational framework for identifying significant combinatorial markers ( s) using both gene expression and methylation data. The gene expression and methylation data are integrated into a single continuous data as well as a (post-discretized) boolean data based on their intrinsic (i.e., inverse) relationship. A novel combined score of methylation and expression data (viz., ) is introduced which is computed on the integrated continuous data for identifying initial non-redundant set of genes. Thereafter, (maximal) frequent closed homogeneous genesets are identified using a well-known biclustering algorithm applied on the integrated boolean data of the determined non-redundant set of genes. A novel sample-based weighted support ( ) is then proposed that is consecutively calculated on the integrated boolean data of the determined non-redundant set of genes in order to identify the non-redundant significant genesets. The top few resulting genesets are identified as potential s. Since our proposed method generates a smaller number of significant non-redundant genesets than those by other popular methods, the method is much faster than the others. Application of the proposed technique on an expression and a methylation data for Uterine tumor or Prostate Carcinoma produces a set of significant combination of markers. We expect that such a combination of markers will produce lower false positives than individual markers.

Identifying novel genes and chemicals related to nasopharyngeal cancer in a heterogeneous network

Nasopharyngeal cancer or nasopharyngeal carcinoma (NPC) is the most common cancer originating in the nasopharynx. The factors that induce nasopharyngeal cancer are still not clear. Additional information about the chemicals or genes related to nasopharyngeal cancer will promote a better understanding of the pathogenesis of this cancer and the factors that induce it. Thus, a computational method NPC-RGCP was proposed in this study to identify the possible relevant chemicals and genes based on the presently known chemicals and genes related to nasopharyngeal cancer. To extensively utilize the functional associations between proteins and chemicals, a heterogeneous network was constructed based on interactions of proteins and chemicals. The NPC-RGCP included two stages: the searching stage and the screening stage. The former stage is for finding new possible genes and chemicals in the heterogeneous network, while the latter stage is for screening and removing false discoveries and selecting the core genes and chemicals. As a result, five putative genes, CXCR3, IRF1, CDK1, GSTP1, and CDH2, and seven putative chemicals, iron, propionic acid, dimethyl sulfoxide, isopropanol, erythrose 4-phosphate, β-D-Fructose 6-phosphate, and flavin adenine dinucleotide, were identified by NPC-RGCP. Extensive analyses provided confirmation that the putative genes and chemicals have significant associations with nasopharyngeal cancer.