Skip to main content

Table 1 Summary of the data sets

From: Automatic design of decision-tree induction algorithms tailored to flexible-receptor docking data

Ligand

# Instances

# Attributes

# Classes

Class Distribution

NADH

2,823

268 (97)

5

205-1020-374-903-321

ETH

3,043

268 (108)

5

160-512-2131-226-14

PIF

3,042

268 (106)

5

7-223-2616-173-23

TCL

2,837

268 (78)

5

19-158-1866-645-149

INH

2,953

268 (89)

5

12-260-2420-175-86

JPM

2,786

268 (80)

5

5-201-1835-323-421

  1. Table1 presents the summary of the flexible-receptor docking data sets used in the experiments. Number os instances represents the total of valid docking results, out of 3,100. Number of attributes shows the total of selected attributes, in parenthesis, from the initial 268. Class distributions are regarding the five FEB classes, respectively: excellent, good, regular, weak, negligible.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us