Skip to main content
. 2022 Nov 18;11:giac103. doi: 10.1093/gigascience/giac103

Table 4:

The optimum 74 features contributing to predicting the ISGs

Evolutionary features (2)
Number of human paralogues, average dS within human paraloguesN
Codon usage features (10)
Codon usage: CTA (L)P Codon usage: ATT (I) Codon usage: TAT (Y)
Codon usage: GCG (A)N Codon usage: CAC (H)N Codon usage: TGC (C)
Codon usage: CGT (R) Codon usage: CGA (R) Codon usage: CGG (R)N
Codon usage: AGA (R)P
Genetic composition features (40)
DNA AC content Dinucleotide CpT composition DNA 4-mer CGCG compositionN
DNA 4-mer AATC compositionP DNA 4-mer TCGT composition DNA 4-mer GATG compositionP
DNA 4-mer AACA composition DNA 4-mer TGAG compositionP DNA 4-mer GACC composition
DNA 4-mer ATAT composition DNA 4-mer TGTA composition DNA 4-mer GACG composition
DNA 4-mer ATGT compositionP DNA 4-mer CACG composition DNA 4-mer GAGT compositionP
DNA 4-mer ACAC composition DNA 4-mer CTCC composition DNA 4-mer GTAC composition
DNA 4-mer ACTA composition DNA 4-mer CCAC composition DNA 4-mer GTGT composition
DNA 4-mer ACTC composition DNA 4-mer CCTA composition DNA 4-mer GTGC composition
DNA 4-mer ACCG composition DNA 4-mer CCTC compositionP DNA 4-mer GTGG composition
DNA 4-mer TATG composition DNA 4-mer CCGT composition DNA 4-mer GCAA compositionP
DNA 4-mer TTCT composition DNA 4-mer CGAG composition DNA 4-mer GCTC composition
DNA 4-mer TTCG composition DNA 4-mer CGTG composition DNA 4-mer GCCT composition
DNA 4-mer TTGA composition DNA 4-mer CGCA composition DNA 4-mer GGGG composition
DNA 4-mer TCAT composition
Proteomic composition features (9)
Arginine composition, cysteine compositionP, methionine composition
Basic amino acid composition (R/H/K)P Sulphur amino acid composition (C&M)P
Hydroxyl amino acid composition (S&T)N Small amino acid composition (N/D/C/P/T)N
Large amino acid composition (R/I/L/K/M)P
Uncharged amino acid composition (A/N/C/Q/G/I/L/M/F/P/S/T/W/Y/V)N
Features about human interactome network (3)
Average shortest pathsP, betweenness, neighbourhood connectivityN
Sequence pattern features (8)
SLNP: ATA[AG][TG] SLNP: TAT[AT]T SLNP: T[AT]AAA
SLNP: [ATG]TGTA SLAAP: SxNxE SLAAP: ENE
SLAAP: SVI Co-occurrence of SLAAPs (count)
P

Features are positively associated with the level of upregulation in IFN-α experiments (P < 0.05).

N

Features are negatively associated with the level of upregulation in IFN-α experiments (P < 0.05).