Table 1. Open in new tab Distribution of...

Set	Target residue	Train	Independent test	CD-HIT threshold
Primary^a	S + T	154 220	800 329	5.19:1	16 964	85 057	5.01:1	0.5
Y	27 077	123 918	4.57:1	3054	13 347	4.37:1	0.5
Chlamydomonas reinhardtii	S + T	17 345	460 015	26.52:1	4338	115 005	26.51:1	N/A
A549	S + T	N/A	N/A	N/A	1144	1049	0.92:1	0.3

Set	Target residue	Train	Independent test	CD-HIT threshold
Primary^a	S + T	154 220	800 329	5.19:1	16 964	85 057	5.01:1	0.5
Y	27 077	123 918	4.57:1	3054	13 347	4.37:1	0.5
Chlamydomonas reinhardtii	S + T	17 345	460 015	26.52:1	4338	115 005	26.51:1	N/A
A549	S + T	N/A	N/A	N/A	1144	1049	0.92:1	0.3

Table 1.

Distribution of train and independent test sets for the three datasets and target residues (prior to balancing).

Set	Target residue	Train			Independent test			CD-HIT threshold
		No. of P-sites	No. of NP-sites	Ratio (NP:P)	No. of P-sites	No. of NP-sites	Ratio (NP:P)
Primary^a	S + T	154 220	800 329	5.19:1	16 964	85 057	5.01:1	0.5
Primary^a	Y	27 077	123 918	4.57:1	3054	13 347	4.37:1	0.5
Chlamydomonas reinhardtii	S + T	17 345	460 015	26.52:1	4338	115 005	26.51:1	N/A
A549	S + T	N/A	N/A	N/A	1144	1049	0.92:1	0.3

Set	Target residue	Train			Independent test			CD-HIT threshold
		No. of P-sites	No. of NP-sites	Ratio (NP:P)	No. of P-sites	No. of NP-sites	Ratio (NP:P)
Primary^a	S + T	154 220	800 329	5.19:1	16 964	85 057	5.01:1	0.5
Primary^a	Y	27 077	123 918	4.57:1	3054	13 347	4.37:1	0.5
Chlamydomonas reinhardtii	S + T	17 345	460 015	26.52:1	4338	115 005	26.51:1	N/A
A549	S + T	N/A	N/A	N/A	1144	1049	0.92:1	0.3

The adopted DeepPSP dataset, after reverse translation, is referred to as the primary dataset. The number of sites in both the S + T and Y sets in this dataset differs from those reported in the DeepPSP paper due to the loss of some sequences during the translation process.

This Feature Is Available To Subscribers Only