lncRNA Blog lncRNA Research and Industry News
Discovering new long non-coding RNAs (lncRNAs) has been a fundamental step in lncRNA-related research. Nowadays, many machine learning-based tools have been developed for lncRNA identification. However, many methods predict lncRNAs using sequence-derived features alone, which tend to display unstable performances on different species. Moreover, the majority of tools cannot be re-trained or tailored by users and neither can the features be customized or integrated to meet researchers’ requirements.
In this study, researchers from Jilin University comprehensively reviewed and evaluated features extracted from sequence-intrinsic composition, secondary structure and physicochemical property. An integrated platform named LncFinder is also developed to enhance the performance and promote the research of lncRNA identification. LncFinder includes a novel lncRNA predictor using the heterologous features the researchers designed. Experimental results show that this method outperforms several state-of-the-art tools on multiple species with more robust and satisfactory results. Researchers can additionally employ LncFinder to extract various classic features, build classifier with numerous machine learning algorithms and evaluate classifier performance effectively and efficiently. LncFinder can reveal the properties of lncRNA and mRNA from various perspectives and further inspire lncRNA-protein interaction prediction and lncRNA evolution analysis. It is anticipated that LncFinder can significantly facilitate lncRNA-related research, especially for the poorly explored species.
Framework of this study
Data sets used in our experiments are collected from GENCODE and Ensembl. Only one transcript from each gene is used. In addition to sequence-intrinsic composition, features are also extracted from multi-scale secondary structure and EIIP-based physicochemical property using two feature selection schemes. Evaluated with 10-fold CV and ROC curve, the optimal feature combination and machine learning algorithm are obtained to develop a new method for lncRNA identification. This method is benchmarked against five popular tools on five species, and it is finally included in LncFinder, which is a highly flexible package for lncRNA identification and analysis. LncFinder is published as R package as well as web server.
Availability – LncFinder is released as R package (https://CRAN.R-project.org/package=LncFinder). A web server (http://bmbl.sdstate.edu/lncfinder/) is also developed to maximize its availability.
