A visual approach for analysis and inference of molecular activity spaces

Table 1 Data set description—data set sizes discriminated by positives and negatives within training/testing data split

Target protein name	Uniprot ID	Training set		Test set		Mean distance	Distance std. dev.
Target protein name	Uniprot ID	Positives	Negatives	Positives	Negatives	Mean distance	Distance std. dev.
Sigma non-opioid intracellular receptor 1 (SIGMAR1)	Q99720	46	135	10	35	0.79	0.13
Histamine H1 receptor (HRH1)	P35367	184	783	46	195	0.83	0.08
Potassium voltage-gated channel subfamily H member 2 (HERG)	Q12809	39	1142	12	283	0.84	0.06
D(1B) dopamine receptor (DRD5)	P21918	41	231	5	62	0.80	0.10

Includes the average computational distance between compounds of each data set and its respective standard deviation

ISSN: 1758-2946