On the amyloid datasets used for training PAFIG ­ how (not) to extend the experimental dataset of hexapeptides

BMC Bioinformatics

Table 1 Statistical distribution of Pafig training dataset

Residue position	1	2	3	4	5	6
K	1.5	1.5	1.5	1.5	1.5	1.4
R	0.7	0.7	0.7	0.8	0.8	0.7
D	0.9	0.9	0.9	0.8	0.8	0.9
E	1.3	1.3	1.3	1.3	1.3	1.8
N	1.1	1.0	1.1	1.0	1.0	1.0
Q	0.9	0.9	1.0	1.0	0.9	0.9
P	0.7	0.7	0.6	0.7	0.6	0.6
H	1.0	1.1	1.1	1.0	1.1	1.0
M	0.8	0.7	0.7	0.7	0.8	0.7
C	0.5	0.6	0.6	0.6	0.6	0.5
S	1.3	0.8	0.8	0.8	0.9	0.9
T	1.1	1.7	1.0	1.0	1.0	1.0
F	1.2	1.2	1.2	1.2	1.2	1.1
W	0.9	1.0	0.9	0.9	0.9	0.8
Y	1.2	1.2	1.2	1.2	1.2	1.5
V	1.1	1.1	1.6	1.1	1.2	1.1
L	0.7	0.7	0.8	0.7	0.7	0.7
I	0.8	0.8	0.8	1.4	1.4	0.8
G	1.1	1.0	1.0	1.0	1.1	1.1
A	0.9	0.9	1.0	1.0	1.0	0.9

Statistical distribution of Pafig full training dataset, including all positive and negative hexapeptides, normalized versus frequencies of aminoacid occurrence in all proteins deposited in UniProt. The expected values for a well balanced training dataset should equal 1. The values above 1 denote over-representation of a residue at the specific location of training hexapeptides, values below 1 show under-representation. The bias from STVIIE is in bold.

ISSN: 1471-2105