Skip to main content

Table 1 Statistics for the datasets used in this study

From: MAIP: a web service for predicting blood‐stage malaria inhibitors

Dataset origin

Model name

Dataset size

Number of actives

Number of inactives

Ratio of active to inactive compounds

AZ

AZ

11,574

3272

8302

0.3941

GSK

GSK

2,006,390

13,535

1,992,855

0.0068

Evotec

MMV1

229,429

339

229,090

0.0015

Johns Hopkins

MMV2

2,524

247

2,277

0.1085

MRCT

MMV3

40,059

235

39,824

0.0059

MMV - St. Jude

MMV4

305,810

2,507

303,303

0.0083

MMV5

MMV5

446,465

4,980

441,485

0.0113

MMV6

MMV6

249,444

6,328

243,116

0.0260

MMV7

MMV7

12,732

848

11,884

0.0714

Novartis

Novartis

2,700,975

107,505

2,593,470

0.0415

St. Jude Vendor Library

StJudeVendor

541,403

2,026

539,377

0.0038

St. Jude Screening Set

Validation set

220,691

9,082

211,609

0.0429

MMV test set

Validation set

5,869

1198

4671

0.2565

PubChem

Validation set

91,796

384

91,412

0.0042