Back to main menu

Datasets (which are, in contrast to other dataset lists, available in a structural format)
This list will be expanded continuously. Please don't hesitate to make published datasets publicly available here.

Currently available: 44 Datasets
Note: The Briem/Lessel and Hert/Willett Dataset are only available as MDDR ID's due to license reasons. Please contact MDL for further information on the database. The datasets have nonethless been included here because they are standard datasets for similarity searching. - Andreas

Binary (active/inactive) datasets
QSAR datasets
QSPR datasets
Toxicity datasets
Metabolism datasets
Permeability datasets
Docking datasets
Mechanistic datasets
Mixed/Other datasets

Binary (active/inactive) datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Fontaine Factor Xa Data Set 290+145 (Training/Test Set) Factor Xa Inhibitors used for binary classification (<10nM and >1microM), but real-valued Ki values are also given in the file Fabien Fontaine, Manuel Pastor, Ismael Zamora, and Ferran Sanz. Anchor-GRIND: Filling the Gap between Standard 3D QSAR and the GRid-INdependent Descriptors. J. Med. Chem. 2005 48 (7), 2687 - 2694 - linkout Dataset High - Original Author Data Datasets in SD and SMILES Format with binary classification (<1nM/>10microM Ki) and real-valued Ki data

Jorisson/Gilson Data Set 50 CDK2 Inhibitors
50 COX2 Inhibitors
50 FXa Inhibitors
50 PDE5 Inhibitors
50 A1A Antagonists
Plus Decoy Structures Robert N. Jorissen and Michael K. Gilson. Virtual Screening of Molecular Databases Using a Support Vector Machine. J. Chem. Inf. Model. 2005 45 (3), 549 -561 - linkout Dataset High - Original Author Data Datasets in SD Format; please read readme.txt. Courtesy of Robert N. Jorissen and Michael K. Gilson.

Briem/Lessel Data Set 49 5HT3 Ligands
40 ACE Inhibitors
111 HMG-CoA Inhibitors
134 PAF Antagonists
49 TXA2 Antagonists
574 "Inactives" (other activities) Hans Briem and Uta F Lessel, Perspect Drug Discov. Des. 2000 (20), 231-244. - linkout Dataset High - Original Author Data Courtesy of Uta Lessel
MDDR ID's only due to license agreement - needs MDDR database for retrieval of structures

Hert/Willett Data Set 752 5HT3 Antagonists
827 5HT1A Agonists
359 5HT Reuptake Inhibitors
395 D2 Antagonists
1130 Renin Inhibitors
943 Angiotensin AT1 Antagonists
803 Thrombin Inhbitors
1246 Substance P Inhibitors
750 HIV Protease Inhibitors
636 Cyclooxygenase Inhibitors
452 Protein Kinase C Inhibitors
Total Size: 102,535 Compounds Jerome Hert, Peter Willett, David J Wilton, Pierre Acklin, Kamal Azzaoui, Edgar Jacoby and Ansgar Schuffenhauer. Comparison of Fingerprint-Based Methods for Virtual Screening Using Multiple Bioactive Reference Structures, J Chem Inf Comp Sci 2004, 44, 1177 - 1185. - linkout Dataset High - Original Author Data Courtesy of Jerome Hert and Peter Willett
MDDR ID's only due to license agreement - needs MDDR database for retrieval of structures

Jacobsson Data Set 146 ER alpha ligands
54 AChE ligands
60 MMP-3 ligands
129 Factor Xa ligands Micael Jacobsson, Per Lidén, Eva Stjernschantz, Henrik Boström and Ulf Norinder, J. Med. Chem., 2003, 46, 5781-5789. - linkout http://www.compumine.com/ research/scoring.html High - Original Author Data -

Stahl Data Set 128 COX2 Inhibitors
55 Estrogen Receptor Ligands
43 Gelastinase A and General MMP Ligands
17 Neuraminidase Inhibitors
25 p38 MAP Kinase Inhibitors
67 Thrombin Inhibitors Stahl M and Rarey M. 2001. J. Med. Chem. 44, 1035-1042. - linkout Dataset (SMILES) High - Original Author Data Courtesy of Martin Stahl - negative dataset available upon request

QSAR datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Guha PDGFR Inhibitors dataset 79 Compounds with activity data R. Guha and P. Jurs. The Development of Linear, Ensemble and Non-linear Models for the Prediction and Interpretation of the Biological Activity of a Set of PDGFR Inhibitors. J. Chem. Inf. Comput. Sci. 2004, 44 (6), 2179-2189. - linkout Dataset
(Please right click/save if you can open TGZ files directly) High - Original Author Data Tarball contains descriptors in desc.pickle.plasma, activities in plasma.depv and a directory hin/ containing 79 structures in Hyperchem HIN format. Courtesy of R. Guha.

Guha Artemisinin QSAR dataset 179 Compounds with activity data R. Guha and P. Jurs. The Development of QSAR Models To Predict and Interpret the Biological Activity of Artemisinin Analogues. J. Chem. Inf. Comput. Sci. 2004 (44), 1440-1449. - linkout Dataset High - Original Author Data MOL format with activity data in separate text file. Courtesy of R. Guha.

Patterson Neighbourhood Behaviour Data Sets 20 QSAR datasets from David Patterson's Neighbourhood Behaviour Paper with nM activity data David E Patterson, Richard D Cramer, Allan M Ferguson, Robert D Clark, Laurence W Weinberger. Neighbourhood Behaviour: A Useful Concept for Validation of "Molecular Diversity" Descriptors. J. Med. Chem. 1996 (39) 3049 - 3059. - linkout Dataset High - Original Author Data SD format with activity data. Courtesy of David Patterson.

Sutherland Data Set 405 Benzodiazepine Receptor Ligands / IC50
467 Cox2 Inhibitors / IC50
756 DHFR inhibitors (of P. carinii DHFR) with IC50
616 nonredundant ER ligands from National Toxicology Program of the NIH with binding affinities relative to beta-estradiol
393 ER ligands selected from literature (see reference for details) with binding affinities relative to beta-estradiol Jeffrey J. Sutherland, Lee A. O'Brien, and Donald F. Weaver. Spline-Fitting with a Genetic Algorithm: A Method for Developing Classification Structure-Activity Relationships. J. Chem. Inf. Comput. Sci. 2003 (43) 1906 - 1915. - linkout http://pubs3.acs.org/ acs/journals/supporting_information.page? in_manuscript=ci034143r High - Original Author Data -

Steroid Data Set 31 Steroids with Corticosteroid Binding Globulin (CBG) receptor affinity E.A. Coats, Perspect. Drug Discov. Des., 1998, 3, 199-213. - linkout www2.chemie.uni-erlangen.de/services/steroids/ High - Original Author Data (Corrected Structures!) -

Benzodiazepine Data Set 245 Benzodiazepine receptor ligands with no common substructure F.R.Burden, M.G.Ford, D.C.Whitley and D.A.Winkler, J.Chem.Inf.Comp.Sci., 2000, 40, 1423-1430. - linkout http://www.disat.unimib.it/ chm/Datasets.htm High - Original Author Data -

Muscarinic Data Set 162 Muscarinic M1 receptor ligands with no common substructure B.S.Orlek, F.E.Blaney, F.Brown, M.S.G.Clark, M.S.Hadley, J.Hatcher, G.J. Riley, H.E.Rosenberg, H.J.Wadsworth and P.Wyman, J.Med.Chem., 1991, 34, 2726-2735. - linkout http://www.disat.unimib.it/ chm/Datasets.htm High - Original Author Data -

Dopamine D2 Data Set 26 Dopamine D2 receptor agonists - http://www.qsar.org/resource/ datasets/martin2.htm High - Original Author Data -

Bohm Serin Protease Inhibitor Data Set Inhibitors of Thrombin/ Trypsin/ Factor Xa with activity data, Training set (72 Compounds), Test Set (16 Compounds) M. Bohm, J. Sturzebecher, G. Klebe, J. Med. Chem., 1999, 42, 458 - 477. - linkout Dataset (MOL/SDF) Low - Check Before Use Drawn Manually - Please Check for Errors Before Use

Benzodiazepine Inverse Agonist Data Set 37 beta-Carbolenes, Pyridodiindoles and CGS compounds binding to Benzodiazepine Inverse Agonist Site B. D. Silverman and Daniel. E. Platt, J. Med. Chem. 1996, 39, 2129-2140 - linkout Dataset (SD File) Low - Check Before Use Drawn Manually - Please Check for Errors Before Use

4 QSAR Data Sets Inhibitors of ACE, GPB, THER, THR J.J. Sutherland, L.A. O'Brien and D. F. Weaver, J. Med. Chem. 2004, 47, 5541 - 5554 - linkout http://pubs3.acs.org/ acs/journals/supporting_information.page? in_manuscript=jm0497141 High - Original Author Data Original Information Supplied by Authors

QSPR datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Karthikeyan Melting Point Dataset Melting Points for 4173 Training Set Molecules and 277 Test Set Compounds (Drug-Like) Karthikeyan, M.; Glen, R.C.; Bender, A. General melting point prediction based on a diverse compound dataset and artificial neural networks. J. Chem. Inf. Model.; 2005; 45(3); 581-590. - linkout Dataset (7MB; Excel File with Structures in SMILES Format, Melting Points and MOE 2D and 3D Descriptors) High - Original Author Data

Bergstrom Melting Point Dataset Melting Point Data for 185 Training Set and 92 Test Set Compounds (Drug-Like) Bergstrom, C. A. S.; Norinder, U.; Luthman, K.; Artursson, P. Molecular Descriptors Influencing Melting Point and Their Role in Classification of Solid Drugs. J. Chem. Inf. Comput. Sci.; (Article); 2003; 43(4); 1177-1185. - linkout Dataset High - Original Author Data

Huuskonen Data Set Aequeous Solubility Data for
Training Set (1033 Compounds)
Test Set 1 (258 Compounds)
Test Set 2 (21 Compounds) Jarmo Huuskonen, J. Chem. Inf. Comput. Sci., 2000, 40, 773-777. - linkout Dataset (SMILES) High - Original Author Data Please acknowledge Jarmo Huuskonen in publications

Solubility Data Set Aequeous Solubility Data for 1144 low molecular weight compounds John S. Delaney, J. Chem. Inf. Comput. Sci., 2004, 44, 1000 - 1005. - linkout http://pubs.acs.org/ subscribe/journals/jcisd8/suppinfo/ ci034243x/ci034243xsi20040112_053635.txt High - Original Author Data. But some problems encountered (see right column!) Structures in SMILES format with solubility in M/L - some structures with solubility 1E-10 have < (smaller than) sign missing!

Toxicity datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Amicbase 300 Dataset 300 Structures with Mouse oral/ip LD50 Data http://www.informatics.indiana.edu/ djwild/datasets/index.html Access Structures High - Original Author Data SD format with activity data in SD tags

Benigni/Vari Carcinogenicity Dataset 774 Structures with Mouse/Rat Carconogenicity (TD50) Data http://progetti.iss.it/ binary/ampp/cont/ Presentation.1105610472.pdf Access Structures High - Original Author Data SMILES and SD format, carcinogenicity data in Excel file

Bursi Mutagenicity Dataset 4337 Compounds with Mutagenicity (AMES) Classification Kazius, J.; McGuire, R.; Bursi, R. Derivation and Validation of Toxicophores for Mutagenicity Prediction. J. Med. Chem. 2005, 48(1), 312-320 - linkout Access Structures High - Original Author Data SD format plus binary classification

ACD DSSTox Databases 11 Datasets in total:
EPA Water Disinfection by-Products with Carcinogenicity Estimates (DBCAN)
Fathead minnow Acute Toxicity Database
Fathead minnow Acute Toxicity database - Defined Parent structures only
CPDB Summary Table - Dogs
CPDB (Carcinogenic Potency Database) Summary Table - Hamsters
CPDB Summary Table - Non-Human Primates
CPDB Summary Table - Rats and Mice
CPDB Summary Table - Rats and Mice - Defined Organic Structures Only
CPDB Summary Table - Rats and Mice - Defined Organic Structures Only
NCTRER (National Center for Toxicological Research Estrogen Receptor Binding Database) Defined Organic Parent 3D Structures
NCTRER_ Defined Organic Parent Structures
NCTRER_ Defined Organic Parent Structures
Various - see dataset page here http://www.acdlabs.com/ download/db/weblibdb.html High - Original Data SD and CFD (Chem Folder) Format

Helma CPDB Mutagenicity Subset 684 compounds with mutagenicity data - "cleaned" subset of CPDB Christoph Helma, Tobias Cramer, Stefan Kramer, Luc De Raedt. J. Chem. Inf. Comput. Sci. 2004 (ASAP Article) - linkout http://pubs3.acs.org/acs/
journals/supporting_information.page?
in_manuscript=ci034254q High - Original Author Data SMILES Format plus activity data

National Toxicology Program Dataset 503 Structures with carcinogenicity data for male/female mouse and male/female rat See the web site of the National Toxicology Program (link) for further details http://www.predictive-toxicology.org/data/ntp/ High - Original Data Data in SMILES format + Activity in txt format

FDA's Carcinogenicity Studies with Rats and Mice 281 SMILES structures with carcinogenicity data for male/female rat and male/female mouse Joseph F. Contrera, Abigail C. Jacobs and Joseph J. DeGeorge, Regulatory Toxicology and Pharmacology 1997, 25(2), 130-145 - linkout http://www.predictive-toxicology.org/data/fda/ High - Original Data Data in SMILES format + Activity in txt format

Carcinogenic Potency Database (CPDB) 1451 chemicals with results from chronic, long-term animal cancer tests Various - see http://potency.berkeley.edu/ listofpubs.topic.html for details http://potency.berkeley.edu/ cpdb.html High - Original Data Data in SMILES format + Lots of additional information

Fathead Minnow Acute Toxicity Dataset 617 acute LC50 values and 225 associated behavioral assessments, 72 joint toxic action experiments with the fathead minnow Russom, C.L., S.P. Bradbury, S.J. Broderius, D.E. Hammermeister and R.A. Drummond. Predicting modes of action from chemical structure: Acute toxicity in the fathead minnow (Pimephales promelas). Environmental Toxicology and Chemistryi, 1997, 16(5): 948-967. - linkout http://www.epa.gov/med/ Prods_Pubs/fathead_minnow.htm High - Original Data Data in SMILES format + Activities

hERG Data Set Compounds with HERG K+ channel blocking activity, Training Set (31 Compounds) and Test Set (6 Compounds) . Cavalli, E. Poluzzi, F. De Ponti, M. Recanatini, J. Med. Chem. 2002 (45) 2844-2853. - linkout Dataset (SMILES Format) Low - Please Check Drawn Manually - Please Check for Errors Before Use

Tox/Mutagenicity Data Set 278 Substituted Benzenes with acute Toxicity Data
1863 Compounds with Mutagenicity Data
8885 Compounds from the NCI Yeast Anticancer Drug Screen data set
NCI AntiHIV Drug Screen data set Jun Feng et al, J. Chem. Inf Comput. Sci., 2003 (43) 1463-1470. linkout http://www.niss.org/ publications.html High - Original Data -

Developmental Toxicity Data Set 175 chemicals with indications of developmental toxicity (without regard to type of effect) in several species (4 classes) F.R. Jelovsek, D.R. Mattison, D.R. and J.J. Chen, Obset. Gynecol. 74, 624-636. linkout http://ecb.jrc.it/cgi-bin/
reframer.pl?A=ECB&B=
/DOCUMENTS/QSAR/QSAR_DATASETS/ High - Original Data -

Endocrine Disruptor Data Set 106 chemicals with endocrine disrupting potential in 4 classes linkout http://ecb.jrc.it/cgi-bin/
reframer.pl?A=ECB&B=
/DOCUMENTS/QSAR/QSAR_DATASETS/> High - Original Data -

Metabolism datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Cytochrome P450 Dataset Diverse set of 13 azole antifungal compounds with Cytochrome P450-14alphaDM inhibition constants Tanaji T. Talele and Vithal M. Kulkarni, J. Chem. Inf. Comput. Sci. 1999 (39) 204-210. - linkout Dataset (SD Files) Low - Please Check Drawn Manually - Please Check for Errors Before Use

Permeability datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Li Blood-Brain-Barrier Penetration Set 415 molecules with Binary Blood-Brain-Barrier Penetration Data (Penetrating/Non-Penetrating) with References Hu Li, Chun Wei Yap, Choong Yong Ung, Ying Xue, Zhi Wei Cao and Yu Zong Chen, J. Chem. Inf. Model. 2005 (ASAP Article) - linkout Download Dataset High - Original Author Data 415 Structures in SMILES Format With Binary Penetration Classification (p/n) and References

Hou Caco-2 Data Set 110 Structurally Diverse Molecules (77+23) with Caco-2 Permeability Data T. J. Hou, W. Zhang, K. Xia, X. B. Qiao, and X. J. Xu, J. Chem. Inf. Comput. Sci. (ASAP Article) - linkout http://pubs3.acs.org/ acs/journals/ supporting_information.page? in_manuscript=ci049884m High - Original Author Data -

Ekins Caco-2 Data Set 28 Inhibitors of Rhinovirus Replication with Caco-2 Permeability Data Sean Ekins, Gregory L. Durst, Robert E. Stratford, David A. Thorner, Richard Lewis, Richard J. Loncharich, and James H. Wikel, J. Chem. Inf. Comput. Sci 2001 (41) 1578 - 1586. - linkout Dataset (SD File) Low - Please Check Drawn Manually - Please Check for Errors Before Use

Blood-Brain-Barrier Data Set Blood-Brain-Barrier Penetration Data for Training Set (57 Compounds) and Test Set (13 Compounds) Ruifeng Liu, Hongmao Sun, and Sung-Sau So, J. Chem. Inf Comput Sci. 2001 (41) 1623 - 1632. - linkout Dataset Low - Please Check Drawn Manually - Please Check for Errors Before Use

Docking datasets top

Name Activity Reference Dataset Trust Level Comment

CCDC/Astex data set 305 Protein/Ligand complexes with manually assigned protonation states J. Willem M. Nissink, Chris Murray, Mike Hartshorn, Marcel L. Verdonk, Jason C. Cole, and Robin Taylor. Proteins 2002 (49) 457 - 471. - linkout http://www.ccdc.cam.ac.uk/ products/life_sciences/ validate/astex/ High - Original Data Extended version of GOLD data set

GOLD Data Set 100+34 Protein/Ligand complexes G. Jones, P. Willett, R. C. Glen, A. R. Leach and R. Taylor, J. Mol. Biol 1997 (267) 727-748. - linkout http://www.ccdc.cam.ac.uk/ products/life_sciences/validate/ gold_validation/value.html High - Original Data Original GOLD data set (100 complexes) plus extension (34 complexes)

Mechanistic datasets top

Name Activity Reference Dataset Trust Level Comment

Anti-cancer Agent Mechanism Database 122 compounds with anti-cancer activity and reasonably well known mechanism of action against 60 cell lines Weinstein et al., Science, 1992, 258, 447. - linkout http://dtp.nci.nih.gov/docs/ cancer/searches/standard_mechanism.html High - Original Data -

Mixed/other datasets top

Name Activity/Property Reference Dataset/Linkout Trust Level Comment

Epoxide-Enantioselectivity Data Set 28 Epoxides with associated enatioselectivity ratios S. Funar-Timofei et Al., J. Chem. Inf. Comput. Sci., 2003, 43, 934-940. - linkout Dataset Low - Please Check Drawn Manually - Please Check for Errors Before Use

NCI Data Set 32,557 2D structures with cancer test data
42,689 2D structures with AIDS test data
23,031 2D structures with both cancer and AIDS test data http://dtp.nci.nih.gov/ docs/cancer/cancer_data.html http://cactus.nci.nih.gov/ ncidb2/download.html High - Original Data -