Table 1. Post-transcriptional features quantified in modeled genes.

mRNA annotation	Spearman's correlation	p-value	Data source
5UTR length	-0.006	0.8	The human genome browser at UCSC. Genome Res 2002.
CDS length	-0.008	0.8	The human genome browser at UCSC. Genome Res 2002.
3UTR length	-0.005	0.9	The human genome browser at UCSC. Genome Res 2002.
Folding energy upstream to aTIS	0.02	0.6	The Vienna RNA websuite. Nucleic Acids Res 2008.
Folding energy downstream to aTIS	0.02	0.6	The Vienna RNA websuite. Nucleic Acids Res 2008.
Half life	0.03	0.4	Conserved principles of mammalian transcriptional regulation revealed by RNA half-life. Nucleic Acids Res 2009.
Decay rate	-0.05	0.1	Decay rates of human mRNAs: correlation with functional characteristics and sequence attributes. Genome Res 2003.
Initiation (FACS-seq)	-0.03	0.4	Quantitative analysis of mammalian translation initiation sites by FACS-seq. Mol Syst Biol 2014.
tRNA adaptation index	0.04	0.1	Solving the riddle of codon usage preferences: a test for translational selection. Nucleic Acids Res 2004.
uTIS no. (GTI-seq)	0.10	2 10−3	Global mapping of translation initiation sites in mammalian cells at single-nucleotide resolution. Proc Natl Acad Sci U S A. 2012.
uTIS no. (QTI-seq)	0.12	4 10−5	Quantitative profiling of initiating ribosomes in vivo. Nat Methods. 2015.

Spearman’s correlation coefficients of the improvement in prediction accuracy obtained by the RBP^plus model relative the RNA^only model with several mRNA features are reported along with corresponding p-values and data source.