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

Table 1 Summary of existing computational methods for the prediction of QSPs

Methods/tools	Year	Method^a	Type	Benchmark dataset^b	Reliable negative dataset	Web server availability
TTAgP1.0 [17]	2019	RF	Single	JFB2019	Yes	No
iTTCA-Hybrid [18]	2018	RF	Single	PC2020	No	Yes
TAP1.0 [19]	2021	QDA	Single	JHB2021	Yes	Yes
iTTCA-RF [20]	2021	RF	Single	PC2020	No	Yes
iTTCA‑MFF [21]	2022	SVM	Single	PC2020	No	No
PSRTTCA [22]	2023	RF	Ensemble	JHB2021	Yes	Yes
StackTTCA	This study	ET	Ensemble	JHB2021	Yes	Yes

^aET Extremely randomized trees, QDA Quadratic discriminant analysis, RF Random forest, SVM Support vector machine
^bThe JFB2019, PC2020, and JHB2021 datasets (TTCAs, non-TTCAs) consist of (553, 369), (470, 318), and (592, 592), respectively

ISSN: 1471-2105