Feature combination networks for the interpretation of statistical machine learning models: Application to Ames mutagenicity

Journal of Cheminformatics

Volumn 6, Issue 1, 2014, Pages

  Webb, Samuel J ^a,b   Hanser, Thierry ^a   Howlin, Brendan ^b   Krause, Paul ^b   Vessey, Jonathan D ^a  

^a LHASA LIMITED   (United Kingdom)

^b UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

Interpretable; Interpretation; Machine learning; Mutagenicity; QSAR

Indexed keywords

EID: 84899072790     PISSN: None     EISSN: 17582946     Source Type: Journal    
DOI: 10.1186/1758-2946-6-8     Document Type: Article

References (41)

1. Drug discovery, design and development. Silverman RB, The organic chemistry of drug design and drug action Amsterdam: Elsevier Academic Press 2 2004
2. Automating knowledge discovery for toxicity prediction using jumping emerging pattern mining. Sherhod R, Gillet VJ, Judson PN, Vessey JD, J Chem Inf Model 2012 52 3074 3087
3. A New emerging pattern mining algorithm and its application in supervised classification. Garcia-Borroto M, Martinez-Trinidad JF, Carrasco-Ochoa JA, Proceedings Pacific-Asia conference on knowledge discovery and data mining Berlin Heidelberg: Springer, Zaki MJ, Jeffrey XY, Ravindran B, Pudi V, 2010 150 157
4. Automatic knowledge extraction from chemical structures: the case of mutagenicity prediction. Ferrari T, Cattaneo D, Gini G, Golbamaki Bakhtyari N, Manganaro A, Benfenati E, SAR QSAR Environ Res 2013 24 631 649
5. Rule extraction from a mutagenicity data set using adaptively grown phylogenetic-like trees. Bacha PA, Gruver HS, Den Hartog BK, Tamura SY, Nutt RF, J Chem Inf Comput Sci 2002 42 1104 1111
6. Rule extraction: where Do We Go from here? Craven M, Shavlik J, [ http://www.biostat.wisc.edu/craven/papers/rule-ex-position.pdf ]
7. Barakat N, Diederich J, Learning-based rule-extraction from support vector machines Location: Alexandria, Egypt: The 14th International Conference on Computer Theory and applications ICCTA'2004 2004 http://espace.library.uq. edu.au/view/UQ:9625
8. Building precise classifiers with automatic rule extraction. Huber K, Berthold MR, Proceedings. Int. Conf. Neural Networks, ICNN'95 1995 1263 1268
9. Neural network rule extraction to detect credit card fraud. Ryman-tubb NF, Krause P, Engineering applications of neural networks Springer: Berlin Heidelberg, Iliadis L, Jayne C, 2011
10. Interpreting computational neural network QSAR models: a measure of descriptor importance. Guha R, Jurs PC, J Chem Inf Model 2005 45 800 806
11. On the physical interpretation of QSAR models. Stanton DT, J Chem Inf Comput Sci 2005 43 1423 1433
12. Visual interpretation of Kernel-based prediction models. Hansen K, Baehrens D, Schroeter T, Rupp R, Müller KR, Mol Inform 2011 30 817 826
13. Interpretation of nonlinear QSAR models applied to Ames mutagenicity data. Carlsson L, Helgee EA, Boyer S, J Chem Inf Model 2009 49 2551 2558
14. Hierarchical QSAR technology based on the Simplex representation of molecular structure. Kuz'min VE, Artemenko AG, Muratov EN, J Comput Aided Mol Des 2008 22 403 421
15. Group-based QSAR (G-QSAR): mitigating interpretation challenges in QSAR. Ajmani S, Jadhav K, Kulkarni SA, QSAR Comb Sci 2009 28 36 51
16. Interpreting computational neural network quantitative structure-activity relationship models: a detailed interpretation of the weights and biases. Guha R, Stanton DT, Jurs PC, J Chem Inf Model 2005 45 1109 1121
17. An approach to the interpretation of backpropagation neural network models in QSAR studies. Baskin II, Ait AO, Halberstam NM, Palyulin VA, Zefirov NS, SAR QSAR Environ Res 2002 13 35 41
18. Extraction and visualization of potential pharmacophore points using support vector machines: application to ligand-based virtual screening for COX-2 inhibitors. Franke L, Byvatov E, Werz O, Steinhilber D, Schneider P, Schneider G, J Med Chem 2005 48 6997 7004
19. Similarity maps-a visualization strategy for molecular fingerprints and machine-learning methods. Riniker S, Landrum, J Cheminf 2013 5 43
20. Interpretable Ames mutagenicity predictions using statistical learning techniques [abstract]. Webb SJ, Krause P, Vessey JD, Handbook of abstracts Tallin, Estonia: QSAR2012 2012 http://qsar2012.ut.ee/
21. Interpretation of statistical machine learning models for Ames mutagenicity [abstract]. Webb SJ, Hanser T, Howlin B, Krause P, Vessey JD, Book of abstracts Sixth Joint Sheffield Conference on Chemoinformatics Sheffield, UK: The 6th Joint Sheffield Conference on Chemoinformatics 2013 http://cisrg.shef.ac.uk/shef2013/
22. Universal approach for structural interpretation of QSAR/QSPR models. Polishchuk PG, Kuz'min VE, Artemenko AG, Muratov EN, Mol Inform 2013 32 843 853
23. The Ames Salmonella/microsome mutagenicity assay. Mortelmans K, Zeiger E, Mutat Res Mol Mech Mutagen 2000 455 29 60
24. An improved bacterial test system for the detection and classification of mutagens and carcinogens. Ames BN, Proc Natl Acad Sci 1973 70 782 786
25. An investigation into pharmaceutically relevant mutagenicity data and the influence on Ames predictive potential. McCarren P, Springer C, Whitehead L, J Cheminf 2011 3 51
26. OECD guideline for testing of chemicals Test No. 471 Jul 1997. [ http://www.oecd-ilibrary.org/environment/test-no-471-bacterial-reverse-mutation- test-9789264071247-en ]
27. KNIME: the Konstanz information miner. Berthold MR, Cebron N, Dill F, Gabriel TR, Kötter T, Meinl T, Ohl P, Sieb C, Thiel K, Wiswedel B, Preisach C, Burkhardt H, Schmidt-Thieme L, Decker R, Data analysis, machine learning and applications Berlin Heidelberg: Springer, Preisach C, Burkhardt H, Schmidt-Thieme L, Decker R, 2008 319 326
28. RDKit: open-source cheminformatics. Landrum G, [ http://www.rdkit.org/ ]
29. The chemistry development Kit (CDK): an open-source java library for chemo- and bioinformatics. Steinbeck C, Han Y, Kuhn S, Horlacher O, Luttmann E, Willighagen E, J Chem Inf Comput Sci 2003 43 493 500
30. ChemAxon, "Standardizer and structure checker, part of the ChemAxon JChem package Budapest, Hungary: Chemaxon 2011
31. Benchmark data set for in silico prediction of Ames mutagenicity. Hansen K, Mika S, Schroeter T, Sutter A, ter Laak A, Steger-Hartmann T, Heinrich N, Müller KR, J Chem Inf Model 2009 49 2077 2081
32. Chemical carcinogenesis research information system (CCRIS). [ http://toxnet.nlm.nih.gov/cgi-bin/sis/htmlgen?CCRIS ]
33. Bethsesda: national library of medicine (US), TOXNET. [ http://toxnet.nlm.nih.gov/ ]
34. Derivation and validation of toxicophores for mutagenicity prediction. Kazius J, McGuire R, Bursi R, J Med Chem 2005 48 312 320
35. Predictive toxicology: benchmarking molecular descriptors and statistical methods. Feng J, Lurati L, Ouyang H, Robinson T, Wang Y, Yuan S, Young SS, J Chem Inf Comput Sci 2003 43 1463 1470
36. Data mining and machine learning techniques for the identification of mutagenicity inducing substructures and structure activity relationships of noncongeneric compounds. Helma C, Cramer T, Kramer S, De Raedt L, J Chem Inf Comput Sci 2004 44 1402 1411
37. Carcinogenic potency database. Gold LS, Slone TH, Ames BN, Manley NB, Garfinkel GB, Rohrbach L, Handbook of carcinogenic potency and genotoxicity databases Boca Raton: CRC Press, Gold L, Zeiger E, 1997 1 106
38. Vitic nexus. [ https://www.lhasalimited.org/vitic-nexus/ ]
39. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Bradley AP, Pattern Recognit 1997 30 1145 1159
40. Developing the applicability domain of in silico models: relevance, importance and methods. Hewitt M, Ellison CM, In silico toxicology Cambridge: RSC Publishing, Cronin MTD, Madden JC, 2010 301 330
41. "Detection of carcinogens as mutagens in the salmonella/microsome test: assay of 300 chemicals: discussion. McCann J, Proc Natl Acad Sci 1976 73 950 954