StackTTCA: a stacking ensemble learning-based framework for accurate and high-throughput identification of tumor T cell antigens

Table 2 Summary of 12 different feature encodings along with their corresponding description and dimension

Order	Descriptors^a	Description	Dimension	References
1	AAC	Frequency of 20 amino acids	20	[26]
2	AAI	Different biochemical and biophysical properties extracted from the AAindex database	531	[27, 28]
3	APAAC	Amphiphilic pseudo-amino acid composition	22	[27, 28]
4	CTD	Composition, transition and distribution	147	[27, 28]
5	DPC	Frequency of 400 dipeptides	400	[27, 28]
6	PCP	Different biochemical and biophysical properties extracted from the AAindex database	11	[27, 28]
7	PAAC	Pseudo amino acid composition	21	[27, 28]
8	RSacid	Reduced amino acid sequences according to acidity	32	[29]
9	RScharge	Reduced amino acid sequences according to charge	50	[29]
10	RSDHP	Reduced amino acid sequences according to DHP	32	[29]
11	RSpolar	Reduced amino acid sequences according to polarity	32	[29]
12	RSsecond	Reduced amino acid sequences according to secondary structure	40	[29]

^aAAC Amino acid composition, AAI Amino acid index database, APAAC Pseudo amino acid composition, CTD Composition–transition–distribution, DPC Dipeptide composition, PCP Physicochemical properties, PACC Pseudo amino acid composition, RS Reduced amino acid sequences

ISSN: 1471-2105