TABLE 2.

ORF prediction and evaluation related calculation tools.

Name	Characteristics	Website	References
CPC	Use sequence features and support vector machines (SVM) to evaluate the protein coding potential of transcripts; assessing the scope, quality, integrity of ORFs	http://cpc.cbi.pku.edu.cn	Kong et al. (2007)
sORF finder	Package for identifying sORF with high encoding potential	http://evolver.psc.riken.jp/	Hanada et al. (2010)
PhyloCSF	Based on the formal statistical comparison of phylogenetic codon models, the nucleotide sequence alignment of multiple species is analyzed to determine whether it may represent a conserved protein coding region; it can delimit likely protein-coding ORFs within transcript models that include untranslated regions	http://compbio.mit.edu/PhyloCSF	Lin et al. (2011)
RNAcode	Comparison of conserved regions in coding and non-coding regions in sequence data and evaluation of coding potential; analysis of sORF or bifunctional RNAs	http://wash.github.com/rnacode	Washietl et al. (2011)
CNCI	Classification of protein-coding and long non-coding transcripts using sequence intrinsic composition (adjacent nucleotide triplets) (SVM-based)	http://www.bioinfo.org/software/cnci	Sun L et al. (2013)
CPAT	The coding potential assessment tool uses a permutation-free logistic regression model that can ORFs size and coverage to be assessed	http://code.google.com/p/cpat/	Wang T et al. (2013)
iSeeRNA	Identification of long intergenic non-coding RNA (lincRNA) transcripts in transcriptome sequencing data (SVM-based)	http://www.myogenesisdb.org/iSeeRNA	Sun K et al. (2013)
PLEK	Efficient alignment-free computational tool for differentiating coding and non-coding transcripts in RNA-seq transcriptomes of species lacking a reference genome (SVM-based)	https://sourceforge.net/projects/plek/files/	Li et al. (2014)
LncRNA-ID	The tool calculates the coding potential of transcripts based on a machine learning model (random forest) and multiple features	https://github.com/zhangy72/LncRNA-ID	Achawanantakun et al. (2015)
lncRNA-MFDL	By fusing multiple features and using deep learning classification algorithms to identify human lncRNA, coding and long non-coding RNA can be quickly distinguished	http://compgenomics.utsa.edu/lncRNA_MDFL/	Fan and Zhang, (2015)
COME	A multi-feature-based coding potential calculation tool for lncRNA coding potential assessment	https://github.com/lulab/COME	Hu et al. (2017)
CPC2	A fast and accurate coding potential calculator based on intrinsic sequence features for ORF feature evaluation (SVM-based)	http://cpc2.cbi.pku.edu.cn	Kang et al. (2017)
CNIT	A tool for identifying protein coding and long non-coding transcripts based on intrinsic sequence composition (upgraded version of CNCI)	http://cnit.noncode.org/CNIT	Guo et al. (2019)
ORF Finder	A software provided by NCBI that performs six-frame translation of a nucleotide sequence, allowing all possible ORFs to be inferred	https://www.ncbi.nlm.nih.gov/orffinder/	Sayers et al. (2021)