AUTHOR=Zhou Liqian , Peng Xinhuai , Zeng Lijun , Peng Lihong 

TITLE=Finding potential lncRNA–disease associations using a boosting-based ensemble learning model

JOURNAL=Frontiers in Genetics

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2024.1356205

DOI=10.3389/fgene.2024.1356205

ISSN=1664-8021

ABSTRACT=lncRNAs have been taken as potential prognostic biomarkers of cancers. Identification of associations between lncRNAs and diseases helps capture potential biomarkers and design efficient therapeutic options for diseases. Wet experiments for identifying these associations are costly and laborious. Here, we developed LDA-SABC, a novel boosting-based framework for lncRNA-disease association (LDA) prediction. LDA-SABC extracts LDA features based on singular value decomposition and classifies lncRNA-disease pairs (LDPs) through incorporating LightGBM and AdaBoost with convolutional neural network. The LDA-SABC performance was evaluated under 5-fold cross validations on lncRNAs, diseases, and LDPs. It obviously outperformed four other classical LDA inference methods (SDLDA, LDNFSGB, LDASR, and IPCAF) through precision, recall, accuracy, F1 score, AUC, and AUPR. Based on the LDA-SABC accurate LDA prediction performance, we used it to find potential lncRNA biomarkers for lung cancer. The results elucidated that 7SK and HULC could have relationship with NSCLC and LUAD, respectively.LDA-SABC is publicly available at https://github.com/plhhnu/LDA-SABC.