CFPLncLoc: A multi-label lncRNA subcellular localization prediction based on Chaos game representation and centralized feature pyramid

There is increasing evidence that the subcellular localization of long noncoding RNAs (lncRNAs) can provide valuable insights into their biological functions. In terms of transcriptomes, lncRNAs were usually found in multiple subcellular localizations. Although several computational methods have been developed to predict the subcellular localization of lncRNAs, few of them were designed for lncRNAs that have multiple subcellular localizations. In this study, we propose a novel deep learning model, called CFPLncLoc, which uses chaos game representation (CGR) images of lncRNA sequences to predict multi-label lncRNA subcellular localization. CFPLncLoc utilizes image update strategy (IUS) to enhance the relative feature representation of the CGR images. To extract higher-level features from CGR images, CFPLncLoc introduces the multi-scale feature fusion (MFF) model, centralized feature pyramid (CFP), from the field of computer vision (CV). Ablation studies confirmed the contribution of the IUS and CFP in improving the prediction performance. Statistical test results verify that CFPLncLoc outperforms existing state-of-the-art predictors under the evaluation metric MaAUC on the hold-out/independent test set. The source code can be obtained from https://github.com/ShengWang-XTU/CFPLncLoc.