Identification of potential tissue-specific cancer biomarkers and development of cancer versus normal genomic classifiers

Abstract

Machine learning techniques for cancer prediction and biomarker discovery can hasten cancer detection and significantly improve prognosis. Recent “OMICS” studies which include a variety of cancer and normal tissue samples along with machine learning approaches have the potential to further accelerate such discovery. To demonstrate this potential, 2,175 gene expression samples from nine tissue types were obtained to identify gene sets whose expression is characteristic of each cancer class. Using random forests classification and ten-fold cross-validation, we developed nine single-tissue classifiers, two multi-tissue cancer-versus-normal classifiers, and one multi-tissue normal classifier. Given a sample of a specified tissue type, the single-tissue models classified samples as cancer or normal with a testing accuracy between 85.29% and 100%. Given a sample of non-specific tissue type, the multi-tissue bi-class model classified the sample as cancer versus normal with a testing accuracy of 97.89%. Given a sample of non-specific tissue type, the multi-tissue multi-class model classified the sample as cancer versus normal and as a specific tissue type with a testing accuracy of 97.43%. Given a normal sample of any of the nine tissue types, the multi-tissue normal model classified the sample as a particular tissue type with a testing accuracy of 97.35%. The machine learning classifiers developed in this study identify potential cancer biomarkers with sensitivity and specificity that exceed those of existing biomarkers and pointed to pathways that are critical to tissue-specific tumor development. This study demonstrates the feasibility of predicting the tissue origin of carcinoma in the context of multiple cancer classes.

Differential gene expression analysis reveals novel genes and pathways in pediatric septic shock patients

“…Affymetrix probes were mapped to the genes using the information provided in the Affymetrix database (hgu133plus2.db). We used average expression values when multiple probes mapped to the same gene 19 .…”

“…To this end, gene expression data from 181 samples from PICU within the first 24 hours were analyzed using multiple statistical testing methods to identify gene biomarkers. The gene expression profiles discovered by this statistical approach may lead to new insights into genetic biomarkers for successful septic shock diagnosis 19 . Using functional geneset enrichment analysis, we validated the known septic shock-related genes, pathways and functional groups, and identified the unexplored septic shock-related genes, and functional groups.…”

Integration of multiple types of genetic markers for neuroblastoma may contribute to improved prediction of the overall survival

“…These findings were not confirmed in another study [ 35 ], which has shown a slight advantage of SVM. Nevertheless, both algorithms are still used for building predictive models for gene expression, and some new reports show a relative advantage of Random Forest over SVM on various sets of problems [ 36 , 37 ].…”

Artificial Intelligence (AI)-Based Systems Biology Approaches in Multi-Omics Data Analysis of Cancer

“…Employing the supervised learning algorithm and RF over nine tissue types, Mohammed et al have shown successful classification between normal and cancer tissues when tissue type is specified as well as non-specified. They further identified genes as potential biomarkers and critical pathways for different tissue types ( 43 ).…”