☰ Navigation

Download datasets

This study used a total of 37 datasets.
Max length: The maximum length of any peptide sequence within the dataset.
Min length: The minimum length of any peptide sequence within the dataset.
Train positive: The number of bioactive peptides used for model training.
Train negative: The number of non-bioactive peptides used for model training.
Test positive: The number of bioactive peptides used for model evaluation.
Test negative: The number of non-bioactive peptides used for model evaluation.
Note: In the provided Excel file, peptide bioactivity is encoded as follows:

· 0 = Bioactive (Positive)

· 1 = Non-bioactive (Negative)

Download all Dataset

No.	Activity	Max length	Min length	Train positive	Train negative	Test positive	Test negative	Download
1	Anti-hypertensive	81	5	931	931	386	386	Download training set Download test set
2	DPP-IV inhibitory	90	2	532	532	133	133	Download training set Download test set
3	Bitter	39	2	256	256	64	64	Download training set Download test set
4	Umami	39	2	112	241	28	61	Download training set Download test set
5	Anti-microbial	180	11	3876	9552	2584	6369	Download training set Download test set
6	Anti-malarial main	183	2	111	1708	28	427	Download training set Download test set
7	Anti-malarial alternative	81	2	111	542	28	135	Download training set Download test set
8	Quorum sensing	64	5	200	200	20	20	Download training set Download test set
9	Anti-cancer main	50	3	689	689	172	172	Download training set Download test set
10	Anti-cancer alternative	50	3	776	776	194	194	Download training set Download test set
11	Anti-MRSAs trains	70	11	118	678	30	169	Download training set Download test set
12	Tumor t cell antigens	20	8	442	442	111	111	Download training set Download test set
13	Blood–brain barrier	50	5	326	326	99	99	Download training set Download test set
14	Anti-parasitic activity	254	5	255	1863	46	46	Download training set Download test set
15	Neuro peptide	100	5	1940	1940	485	485	Download training set Download test set
16	Anti-bacterial	30	3	4540	5809	1112	1475	Download training set Download test set
17	Anti-fungal activity	100	4	1168	1168	291	291	Download training set Download test set
18	Anti-angio activity	67	11	107	107	28	28	Download training set Download test set
19	Anti-viral activity	51	4	3272	3272	818	818	Download training set Download test set
20	Toxicity	50	13	1621	1663	312	270	Download training set Download test set
21	Anti-inflammatory peptides	30	7	690	1009	173	253	Download training set Download test set
22	Anti-oxidant activity	20	2	848	848	212	212	Download training set Download test set
24	IL-5 inducing peptides main	20	9	1525	6027	382	1552	Download training set Download test set
25	IL-5 inducing peptides alternative	20	9	1525	1526	382	381	Download training set Download test set
26	IL-6 inducing peptides	25	8	292	2393	73	598	Download training set Download test set
27	IL-13 inducing peptides	35	8	250	2326	63	582	Download training set Download test set
28	Anti-tubercular Peptides RD	61	5	199	199	47	47	Download training set Download test set
29	Cell-penetrating	61	10	364	369	98	85	Download training set Download test set
29	Cell-penetrating MLCCP	61	6	573	574	157	2184	Download training set Download test set
30	Tumor-homing peptides main	31	4	521	521	130	130	Download training set Download test set
31	Tumor-homing peptides small	10	4	375	375	94	94	Download training set Download test set
32	Anti-coronavirus activity	100	6	649	651	65	2231	Download training set Download test set
33	Viral integrase inhibitory peptides VINIP	58	8	110	650	12	71	Download training set Download test set
34	Viral integrase inhibitory peptides INI	62	8	110	459	12	51	Download training set Download test set
35	Anti-diabetic	41	11	188	188	48	48	Download training set Download test set
36	Biofilm inhibitory	54	5	201	80	10	10	Download training set Download test set
37	Hemolytic	100	5	433	423	663	1999	Download training set Download test set

The dataset size of bioactive peptides

37 datasets are divided into four categories: Disease Related, Antimicrobial Related, Immune Related, and Peptide Property. Click on the buttons to switch.
Train_pos:positive samples in the training set.
Train_neg:negative samples in the training set.
Test_pos:positive samples in the independent test set.
Test_neg:negative samples in the independent test set.

The amino acid composition of bioactive peptides

The figure describes the distribution of amino acid participation, where darker shades of orange represent higher proportions in the dataset.
Train_pos:positive samples in the training set.
Train_neg:negative samples in the training set.
Test_pos:positive samples in the independent test set.
Test_neg:negative samples in the independent test set.

The length distribution of peptides

The wider the violin plot, the more dispersed the amino acids of that length; the narrower it is, the more concentrated the amino acids of that length.
Train_pos:positive samples in the training set.
Train_neg:negative samples in the training set.
Test_pos:positive samples in the independent test set.
Test_neg:negative samples in the independent test set.