Dataset Information

CRlncRC: a machine learning-based method for cancer-related long noncoding RNA identification using integrated features.

ABSTRACT:

Background

Long noncoding RNAs (lncRNAs) are widely involved in the initiation and development of cancer. Although some computational methods have been proposed to identify cancer-related lncRNAs, there is still a demanding to improve the prediction accuracy and efficiency. In addition, the quick-update data of cancer, as well as the discovery of new mechanism, also underlay the possibility of improvement of cancer-related lncRNA prediction algorithm. In this study, we introduced CRlncRC, a novel Cancer-Related lncRNA Classifier by integrating manifold features with five machine-learning techniques.

Results

CRlncRC was built on the integration of genomic, expression, epigenetic and network, totally in four categories of features. Five learning techniques were exploited to develop the effective classification model including Random Forest (RF), Naïve bayes (NB), Support Vector Machine (SVM), Logistic Regression (LR) and K-Nearest Neighbors (KNN). Using ten-fold cross-validation, we showed that RF is the best model for classifying cancer-related lncRNAs (AUC = 0.82). The feature importance analysis indicated that epigenetic and network features play key roles in the classification. In addition, compared with other existing classifiers, CRlncRC exhibited a better performance both in sensitivity and specificity. We further applied CRlncRC to lncRNAs from the TANRIC (The Atlas of non-coding RNA in Cancer) dataset, and identified 121 cancer-related lncRNA candidates. These potential cancer-related lncRNAs showed a certain kind of cancer-related indications, and many of them could find convincing literature supports.

Conclusions

Our results indicate that CRlncRC is a powerful method for identifying cancer-related lncRNAs. Machine-learning-based integration of multiple features, especially epigenetic and network features, had a great contribution to the cancer-related lncRNA prediction. RF outperforms other learning techniques on measurement of model sensitivity and specificity. In addition, using CRlncRC method, we predicted a set of cancer-related lncRNAs, all of which displayed a strong relevance to cancer as a valuable conception for the further cancer-related lncRNA function studies.

SUBMITTER: Zhang X

PROVIDER: S-EPMC6311943 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Gastric cancer (GC) remains one of the most malignant tumors around the world, and an accurate model that reliably predicts survival and therapeutic efficacy is urgently needed. As a novel predictor for prognosis in a variety of cancers, immune-related long noncoding RNA pairs (IRlncRNAPs) have been reported to predict tumor prognosis. Herein, we integrated an IRlncRNAPs model to predict the clinical outcome, immune features, and chemotherapeutic efficacy of GC. Methods: Based on the GC data obtained from The Cancer Genome Atlas (TCGA) database and the Immunology Database and Analysis Portal (ImmPort), differentially expressed immune-related long noncoding RNAs (DEIRlncRNAs) were identified. Least absolute shrinkage and selection operator (LASSO) regression and Cox regression analysis were used to select the most appropriate overall survival (OS)-related IRlncRNAPs to develop a prognostic signature. The riskScore of each sample was calculated by comparing the long noncoding RNA expression level in each IRlncRNAP. Based on the riskScore for each patient, GC patients were divided into high- and low-risk groups. Then, the correlation of the signature and riskScore with OS, clinical features, immune cell infiltration, immune-related gene (IRG) expression and chemotherapeutic efficacy in GC was analyzed. Results: A total of 107 DEIRlncRNAs were identified which formed 4297 IRlncRNAPs. Fifteen OS-related IRlncRNAPs were selected to develop a prognostic model. GC patients could be accurately classified into high- and low-risk groups according to the riskScore of the prognostic model. The 1-, 2-, 3-, and 5-year receiver operating characteristic (ROC) curves for the riskScore were drawn and the area under the curve (AUC) values were found to be 0.788, 0.810, 0.825, and 0.868, respectively, demonstrating a high sensitivity and accuracy of this prognostic signature. Moreover, the immune-related riskScore was an independent risk factor. Patients showed a poorer outcome within the high-risk group. In addition, the riskScore was found to be significantly correlated with the clinical features, immune infiltration status, IRG expression, and chemotherapeutic efficacy in GC. Conclusion: The prognostic model of IRlncRNAPs offers great promise in predicting the prognosis, immune infiltration status, and chemotherapeutic efficacy in GC, which might be helpful for the selection of chemo- and immuno-therapy of GC.

Project description:BackgroundDespite the high commercial fisheries value and ecological importance as prey item for higher marine predators, very limited taxonomic work has been done on cephalopods in Malaysia. Due to the soft-bodied nature of cephalopods, the identification of cephalopod species based on the beak hard parts can be more reliable and useful than conventional body morphology. Since the traditional method for species classification was time-consuming, this study aimed to develop an automated identification model that can identify cephalopod species based on beak images.MethodsA total of 174 samples of seven cephalopod species were collected from the west coast of Peninsular Malaysia. Both upper and lower beaks were extracted from the samples and the left lateral views of upper and lower beak images were acquired. Three types of traditional morphometric features were extracted namely grey histogram of oriented gradient (HOG), colour HOG, and morphological shape descriptor (MSD). In addition, deep features were extracted by using three pre-trained convolutional neural networks (CNN) models which are VGG19, InceptionV3, and Resnet50. Eight machine learning approaches were used in the classification step and compared for model performance.ResultsThe results showed that the Artificial Neural Network (ANN) model achieved the best testing accuracy of 91.14%, using the deep features extracted from the VGG19 model from lower beak images. The results indicated that the deep features were more accurate than the traditional features in highlighting morphometric differences from the beak images of cephalopod species. In addition, the use of lower beaks of cephalopod species provided better results compared to the upper beaks, suggesting that the lower beaks possess more significant morphological differences between the studied cephalopod species. Future works should include more cephalopod species and sample size to enhance the identification accuracy and comprehensiveness of the developed model.