csORF-finder: an effective ensemble learning framework for accurate identification of multi-species coding short open reading frames

Abstract

Short open reading frames (sORFs) refer to the small nucleic fragments no longer than 303 nt in length that probably encode small peptides. To date, translatable sORFs have been found in both untranslated regions of messenger ribonucleic acids (RNAs; mRNAs) and long non-coding RNAs (lncRNAs), playing vital roles in a myriad of biological processes. As not all sORFs are translated or essentially translatable, it is important to develop a highly accurate computational tool for characterizing the coding potential of sORFs, thereby facilitating discovery of novel functional peptides. In light of this, we designed a series of ensemble models by integrating Efficient-CapsNet and LightGBM, collectively termed csORF-finder, to differentiate the coding sORFs (csORFs) from non-coding sORFs in Homo sapiens, Mus musculus and Drosophila melanogaster, respectively. To improve the performance of csORF-finder, we introduced a novel feature encoding scheme named trinucleotide deviation from expected mean (TDE) and computed all types of in-frame sequence-based features, such as i-framed-3mer, i-framed-CKSNAP and i-framed-TDE. Benchmarking results showed that these features could significantly boost the performance compared to the original 3-mer, CKSNAP and TDE features. Our performance comparisons showed that csORF-finder achieved a superior performance than the state-of-the-art methods for csORF prediction on multi-species and non-ATG initiation independent test datasets. Furthermore, we applied csORF-finder to screen the lncRNA datasets for identifying potential csORFs. The resulting data serve as an important computational repository for further experimental validation. We hope that csORF-finder can be exploited as a powerful platform for high-throughput identification of csORFs and functional characterization of these csORFs encoded peptides.

miPEPPred-FRL: A Novel Method for Predicting Plant MiRNA-Encoded Peptides Using Adaptive Feature Representation Learning

“…In addition to Arabidopsis thaliana and Fabaceae species, 23 experimentally validated miPEPs found in various plant species ,,− are also collected as positive samples of independent testing data set 3. As for negative samples, considering the coding ability of ncRNAs, a common pipeline is to extract sORF sequences of true ncRNAs and then translate them into pseudopeptide sequences. ,, The snRNA and snoRNA sequences are finally selected because no peptides encoded by these RNAs are discovered; i.e., they have no coding ability. Specifically, the corresponding sequences of various plant species are downloaded from the RNAcentral () database, and ORF Finder is then employed to extract pseudopeptide sequences.…”

“…On the one hand, predicting the coding potential of sORFs could be an indication of whether the target sORFs can encode small peptides or not. sORFPred and csORF-finder have been proven to be effective for predicting the coding sORFs. Additionally, unlike the above methods which aim to handle sORF sequences only, several methods have been devised to distinguish between coding and noncoding transcripts.…”

sOCP: a framework predicting smORF coding potential based on TIS and in-frame features and effectively applied in the human genome

“…CPPred distinguishes coding RNAs and ncRNAs based on support vector machine (SVM) classifier and sequence features of RNA [ 24 ], while DeepCPP uses a conventional neural network (CNN) model [ 25 ]. The csORF-finder evaluated the coding potential of sORF in multiple species with in-frame sequence features [ 26 ]. Besides methods aimed at human and other mammals, the smORF prediction also goes ahead in plants, such as sORFPred [ 27 ], and in prokaryotes, such as PsORFs, sORFPredictor and ProsmORF-pred [ 28–30 ].…”

ABLNCPP: Attention Mechanism-Based Bidirectional Long Short-Term Memory for Noncoding RNA Coding Potential Prediction

“…However, the subsequence embedding method ignores the sequential information at joins between subsequences. Inspired by the i-framed features mentioned in csORF-Finder, 32 we propose a novel approach called NOLTE to represent ncRNA sequences as lowdimensional dense vectors. The overview of generating embeddings is illustrated in Figure 2.…”