Prediction of miRNA-disease associations based on PCA and cascade forest

Abstract

Background: As a key non-coding RNA molecule, miRNA profoundly affects gene expression regulation and connects to the pathological processes of several kinds of human diseases. However, conventional experimental methods for validating miRNA-disease associations are laborious. Consequently, the development of efficient and reliable computational prediction models is crucial for the identification and validation of these associations.

Results: In this research, we developed the PCACFMDA method to predict the potential associations between miRNAs and diseases. To construct a multidimensional feature matrix, we consider the fusion similarities of miRNA and disease and miRNA-disease pairs. We then use principal component analysis(PCA) to reduce data complexity and extract low-dimensional features. Subsequently, a tuned cascade forest is used to mine the features and output prediction scores deeply. The results of the 5-fold cross-validation using the HMDD v2.0 database indicate that the PCACFMDA algorithm achieved an AUC of 98.56%. Additionally, we perform case studies on breast, esophageal and lung neoplasms. The findings revealed that the top 50 miRNAs most strongly linked to each disease have been validated.

Conclusions: Based on PCA and optimized cascade forests, we propose the PCACFMDA model for predicting undiscovered miRNA-disease associations. The experimental results demonstrate superior prediction performance and commendable stability. Consequently, the PCACFMDA is a potent instrument for in-depth exploration of miRNA-disease associations.

Keywords: Cascade forest; Ensemble learning; PCA; miRNA-disease Association.

Fig. 1

The structure of PCACFMDA

Fig. 2

Cumulative explained variance by principal components

Fig. 3

Decision-making processes in forest

Fig. 4

The ROC and PR curves of PCACFMDA in 5-fold cross-validation

Fig. 5

The ROC and PR curves of PCACFMDA in 10-fold cross-validation

Fig. 6

The ROC and PR curves of different classifiers in 5-fold cross-validation

Fig. 7

The ROC and PR curves of different models in 5-fold cross-validation

Fig. 8

The illustration of heatmap based on esophageal neoplasms-related miRNAs

Fig. 9

Kaplan-Meier plots of hsa-miR-198, hsa-miR-30a, hsa-miR-31, and hsa-let-7b for survival of patients with breast cancer