Definition of the Subject
The process of drug discovery has the goal to identify lead chemicals that have a significant activity against a selected biological target. A disease state may be the result of changes in the structure and function of cell‐signaling receptors, enzymes, hormone receptors, or other functional proteins. The drug target is a protein whose activity is modulated by its interaction with a chemical compound, and thus may control a disease. The lead compounds identified in the drug discovery step are optimized in the drug development phase that results in a small number of chemicals that are evaluated in human clinical trials. The first priority in drug development is to increase the biological activity of a lead compound while preserving its drug‐like properties. The lead compound is expanded into a chemical library that conserves the structure responsible for the biological activity (pharmacophore) and adds chemical groups...
Abbreviations
- Bayesian classifier:
-
Bayes' theorem of conditional probability is a method of statistical inference that represents the basis of several classification machine learning models used in drug design and chemoinformatics to classify libraries of compounds into active and inactive chemicals. A Bayesian classifier considers each structural feature or descriptor independent of the other descriptors, and the probability that a compound is active is proportional to the ratio of active to inactive compounds that have the same structural feature or have the same value for that descriptor. The final probability that a compound is active is computed as the product of all descriptor‐based probabilities. Structural descriptors that are real numbers are usually binned prior to their evaluation with a Bayesian classifier.
- Decision tree:
-
A decision tree is a sequence of rules applied to selected structural descriptors. The training phase comprises the selection of the structural descriptors that are evaluated, the order in which the rules are applied, and the decision taken at each leaf. Usually, each rules evaluates a descriptor (≥ or < than a threshold) and splits the objects into two or more populations. Then each population is selected and the splitting procedure is performed with a new rule, until a stopping condition is met (for example, when all objects in the population belong to the same class). The prediction phase starts from the root node and evaluates each rule on a pathway determined by the outcome (true or false) of the previous rule. When a leaf is reached the algorithm predicts the class of the object (classification trees) or the numerical value of a property (regression trees).
- k‑nearest neighbors:
-
k‑nearest neighbors (k‑NN) is a supervised learning algorithm that predicts the property of an object based on a local interpolation model. In classification, the class of a new object is predicted based on the majority vote of its k nearest neighbors. In regression, the property value for a new object is predicted as an average value of the property values for its k nearest neighbors.
- Lazy learning:
-
Lazy learning is a memory based local learning that defers the computation until a prediction is requested for an object. The first step is to insert the query object into the space of the training objects, and to identify the training objects located in a set neighborhood. The predicted property of the query object is based on an interpolation of the properties of the objects situated in the neighborhood.
- Machine learning:
-
Machine learning is an important field of artificial intelligence, and includes a diversity of methods and algorithms that extract rules and functions from large datasets, such as decision trees, lazy learning, k‑nearest neighbors, Bayesian methods, Gaussian processes, support vector machines, and kernel algorithms. Machine learning algorithms extract information from experimental data by computational and statistical methods and generate a set of rules, functions or procedures that allow them to predict the properties of novel objects that are not included in the learning set.
- Quantitative structure‐activity relationships:
-
Quantitative structure‐activity relationships (QSAR ) represent regression models that define quantitative correlations between the chemical structure of molecules and their physical properties (boiling point, melting point, aqueous solubility), chemical properties and reactivities (chromatographic retention, reaction rate), or biological activities (cell growth inhibition, enzyme inhibition, lethal dose). The fundamental hypotheses of QSAR are that similar chemicals have similar properties, and that small structural changes result in small changes in property values. The general form of a QSAR equation is \( P(i)=f(\mathbf{SD}_{i}) \), where P(i) is a physical, chemical, or biological property of compound i, \( \mathbf{SD}_{i} \) is a vector of structural descriptors of i, and f is a mathematical function such as linear regression, partial least squares, artificial neural networks, or support vector machines. A QSAR model for a property P is based on a dataset of chemical compounds with known values for the property P, and a matrix of structural descriptors computed for all chemicals. The learning (training) of the QSAR model is the process of determining the optimum parameters of the regression function f. After the training phase, a QSAR model may be used to predict the property P for novel compounds that are not present in the learning set of molecules.
- Support vector machines:
-
Support vector machines (SVM) are a class of supervised machine learning methods based on the structural risk minimization and the statistical learning theory of Vapnik. SVM may be applied to data classification and regression, using selected objects (support vectors) to generate the SVM model. Nonlinear classification problems are transformed into linear classification problems by using kernel functions that combine the input space into a higher‐dimensional feature space in which a hyperplane may discriminate the classes. An SVM classification model computes a maximum margin hyperplane that separates the classes in the feature space. The maximal margin hyperplane maximizes the distance to the hyperplane of the closest patterns from the two classes. An SVM regression model builds a regression tube with the property that all objects inside the tube do not contribute to the overall error of the model. The shape of the regression tube is determined by selected objects (support vectors) situated outside the tube.
- Structural descriptor:
-
A structural descriptor (SD) is a numerical value computed from the chemical structure of a molecule, which is invariant to the numbering of the atoms in the molecule. Structural descriptors may be classified as constitutional (counts of molecular fragments, such as rings, functional groups, or atom pairs), topological indices (computed from the molecular graph), geometrical (volume, surface, charged‐surface), quantum (atomic charges, energies of molecular orbitals), and molecular field (such as those used in CoMFA, CoMSIA, or CoRSA).
- Structure‐activity relationships:
-
Structure‐activity relationships (SAR) represent classification models that can discriminate between sets of chemicals that belong to different classes of biological activities, usually active/inactive towards a certain biological receptor. The general form of a SAR equation is \( C(i) = f(\mathbf{SD}_{i}) \), where C(i) is the activity class of compound i (active/inactive, inhibitor/non‐inhibitor, ligand/non‐ligand), \( \mathbf{SD}_{i} \) is a vector of structural descriptors of i, and f is a classification function such as k‑nearest neighbors, linear discriminant analysis, random trees, random forests, Bayesian networks, artificial neural networks, or support vector machines.
Bibliography
Aha DW, Kibler D, Albert MK (1991) Instance‐based learning algorithms. Mach Learn 6:37–66
Ajmani S, Jadhav K, Kulkarni SA (2006) Three‐dimensional QSAR using the k‑nearest neighbor method and its interpretation. J Chem Inf Model 46:24–31
Andres C, Hutter MC (2006) CNS permeability of drugs predicted by a decision tree. QSAR Comb Sci 25:305–309
Alpaydin E (2004) Introduction to machine learning. MIT Press, Cambridge, p 445
Atkeson CG, Moore AW, Schaal S (1997) Locally weighted learning. Artif Intell Rev 11:11–73
Atkeson CG, Moore AW, Schaal S (1997) Locally weighted learning for control. Artif Intell Rev 11:75–113
Arimoto R, Prasad MA, Gifford EM (2005) Development of CYP3A4 inhibition models: comparisons of machine‐learning techniques and molecular descriptors. J Biomol Screen 10:197–205
Balaban AT, Ivanciuc O (1999) Historical development of topological indices. In: Devillers J, Balaban AT (eds) Topological indices and related descriptors in QSAR and QSPR. Gordon & Breach Science Publishers, Amsterdam, pp 21–57
Basak SC, Grunwald GD (1995) Molecular similarity and estimation of molecular properties. J Chem Inf Comput Sci 35:366–372
Basak SC, Bertelsen S, Grunwald GD (1994) Application of graph theoretical parameters in quantifying molecular similarity and structure‐activity relationships. J Chem Inf Comput Sci 34:270–276
Basak SC, Bertelsen S, Grunwald GD (1995) Use of graph theoretic parameters in risk assessment of chemicals. Toxicol Lett 79:239–250
Bayes T (1763) An essay towards solving a problem in the doctrine of chances. Philos Trans Roy Soc London 53:370–418
Bender A, Jenkins JL, Glick M, Deng Z, Nettles JH, Davies JW (2006) “Bayes affinity fingerprints” improve retrieval rates in virtual screening and define orthogonal bioactivity space: when are multitarget drugs a feasible concept? J Chem Inf Model 46:2445–2456
Bender A, Scheiber J, Glick M, Davies JW, Azzaoui K, Hamon J, Urban L, Whitebread S, Jenkins JL (2007) Analysis of pharmacology data and the prediction of adverse drug reactions and off‐target effects from chemical structure. Chem Med Chem 2:861–873
Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin, p 740
Bishop CM (1996) Neural networks for pattern recognition. Oxford University Press, Oxford, p 504
Boid DB (2007) How computational chemistry became important in the pharmaceutical industry. In: Lipkowitz KB, Cundari TR (eds) Reviews in computational chemistry, vol 23. Wiley, Weinheim, pp 401–451
Bonchev D (1983) Information theoretic indices for characterization of chemical structure. Research Studies Press, Chichester
Bonchev D, Rouvray DH (eds) (1991) Chemical graph theory. Introduction and fundamentals. Abacus Press/Gordon & Breach Science Publishers, New York
Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Haussler D (ed) Proc of the 5th annual ACM workshop on computational learning theory. ACM Press, Pittsburgh, pp 144–152
Bottou L, Chapelle O, DeCoste D, Weston J (2007) Large‐scale kernel machines. MIT Press, Cambridge, p 416
Breiman L (2001) Random forests. Mach Learn 45:5–32
Briem H, Günther J (2005) Classifying “kinase inhibitor‐likeness” by using machine‐learning methods. Chem Bio Chem 6:558–566
Cash GG (1999) Prediction of physicochemical properties from Euclidean distance methods based on electrotopological state indices. Chemosphere 39:2583–2591
Chapelle O, Haffner P, Vapnik VN (1999) Support vector machines for histogram‐based image classification. IEEE Trans Neural Netw 10:1055–1064
Cleary JG, Trigg LE (1995) K ∗: an instance‐based learner using and entropic distance measure. In: Prieditis A, Russell SJ (eds) Proc of the 12th international conference on machine learning. Morgan Kaufmann, Tahoe City, pp 108–114
Cohen WW (1995) Fast effective rule induction. In: Prieditis A, Russell SJ (eds) Proc of the 12th international conference on machine learning. Morgan Kaufmann, Tahoe City, pp 115–123
Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297
Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines. Cambridge University Press, Cambridge
DeconinckE, Zhang MH, Coomans D, Vander Heyden Y (2006) Classification treemodels for the prediction of blood-brain barrier passage ofdrugs. J Chem Inf Model 46:1410–1419
Deng Z, Chuaqui C, Singh J (2006) Knowledge‐based design of target‐focused libraries using protein‐ligand interaction constraints. J Med Chem 49:490–500
Doddareddy MR, Cho YS, Koh HY, Kim DH, Pae AN (2006) In silico renal clearance model using classical Volsurf approach. J Chem Inf Model 46:1312–1320
Drucker H, Wu DH, Vapnik VN (1999) Support vector machines for spam categorization. IEEE Trans Neural Netw 10:1048–1054
DuH, Wang J, Watzl J, Zhang X, Hu Z (2008) Classificationstructure‐activity relationship (CSAR) studies forprediction ofgenotoxicity of thiophene derivatives. Toxicol Lett177:10–19
Duda RO, Hart PE, Stork DG (2000) Pattern classification. 2nd edn. Wiley, New York
Ehrman TM, Barlow DJ, Hylands PJ (2007) Virtual screening of chinese herbs with random forest. J Chem Inf Model 47:264–278
Eitrich T, Kless A, Druska C, Meyer W, Grotendorst J (2007) Classification of highly unbalanced CYP450 data of drugs using cost sensitive machine learning techniques. J Chem Inf Model 47:92–103
Ekins S, Balakin KV, Savchuk N, Ivanenkov Y (2006) Insights for human ether-a-go-go-related gene potassium channel inhibition using recursive partitioning and Kohonen and Sammon mapping techniques. J Med Chem 49:5059–5071
Ertl P, Roggo S, Schuffenhauer A (2008) Natural product‐likeness score and its application for prioritization of compound libraries. J Chem Inf Model 48:68–74
Fatemi MH, Gharaghani S (2007) A novel QSAR model for prediction of apoptosis‐inducing activity of 4-aryl-4-H‑chromenes based on support vector machine. Bioorg Med Chem 15:7746–7754
Frank E, Hall M, Trigg L, Holmes G, Witten IH (2004) Data mining in bioinformatics using Weka. Bioinformatics 20:2479–2481
Freund Y, Mason L (1999) The alternating decision tree learning algorithm. In: Bratko I, Dzeroski S (eds) Proc of the 16th international conference on machine learning (ICML (1999)). Morgan Kaufmann, Bled, pp 124–133
Gaines BR, Compton P (1995) Induction of ripple‐down rules applied to modeling large databases. Intell J Inf Syst 5:211–228
Gao JB, Gunn SR, Harris CJ (2003) SVM regression through variational methods and its sequential implementation. Neurocomputing 55:151–167
Gao JB, Gunn SR, Harris CJ (2003) Mean field method for the support vector machine regression. Neurocomputing 50:391–405
Gepp MM, Hutter MC (2006) Determination of hERG channel blockers using a decision tree. Bioorg Med Chem 14:5325–5332
Guha R, Dutta D, Jurs PC, Chen T (2006) Local lazy regression: making use of the neighborhood to improve QSAR predictions. J Chem Inf Model 46:1836–1847
Gute BD, Basak SC (2001) Molecular similarity‐based estimation of properties: a comparison of three structure spaces. J Mol Graph Modell 20:95–109
Gute BD, Basak SC, Mills D, Hawkins DM (2002) Tailored similarity spaces for the prediction of physicochemical properties. Internet Electron J Mol Des 1:374–387
Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46:389–422
Hansch C, Garg R, Kurup A, Mekapati SB (2003) Allosteric interactions and QSAR: on the role of ligand hydrophobicity. Bioorg Med Chem 11:2075–2084
Hastie T, Tibshirani R, Friedman JH (2003) The elements of statistical learning. Springer, Berlin, p 552
Herbrich R (2002) Learning kernel classifiers. MIT Press, Cambridge
Hert J, Willett P, Wilton DJ, Acklin P, Azzaoui K, Jacoby E, Schuffenhauer A (2006) New methods for ligand‐based virtual screening: use of data fusion and machine learning to enhance the effectiveness of similarity searching. J Chem Inf Model 46:462–470
Hoffman B, Cho SJ, Zheng W, Wyrick S, Nichols DE, Mailman RB, Tropsha A (1999) Quantitative structure‐activity relationship modeling of dopamine \( {\text{D}}_{1} \) antagonists using comparative molecular field analysis, genetic algorithms‐partial least‐squares, and K‑nearest neighbor methods. J Med Chem 42:3217–3226
HolteRC (1993) Very simple classification rules perform well on most commonly used datasets. Mach Learn11:63–90
Hou T, Wang J, Zhang W, Xu X (2007) ADME evaluation in drug discovery. 7. Prediction of oral absorption by correlation and classification. J Chem Inf Model 47:208–218
Huang T-M, Kecman V, Kopriva I (2006) Kernel based algorithms for mining huge data sets. Springer, Berlin, p 260
Hudelson MG, Ketkar NS, Holder LB, Carlson TJ, Peng C-C, Waldher BJ, Jones JP (2008) High confidence predictions of drug-drug interactions: predicting affinities for cytochrome P450 2C9 with multiple computational methods. J Med Chem 51:648–654
Itskowitz P, Tropsha A (2005) k‑nearest neighbors QSAR modeling as a variational problem: theory and applications. J Chem Inf Model 45:777–785
Ivanciuc O (2002) Support vector machine classification of the carcinogenic activity of polycyclic aromatic hydrocarbons. Internet Electron J Mol Des 1:203–218
Ivanciuc O (2002) Structure‐odor relationships for pyrazines with support vector machines. Internet Electron J Mol Des 1:269–284
Ivanciuc O (2002) Support vector machine identification of the aquatic toxicity mechanism of organic compounds. Internet Electron J Mol Des 1:157–172
Ivanciuc O (2003) Graph theory in chemistry. In: Gasteiger J (ed) Handbook of chemoinformatics, vol 1. Wiley, Weinheim, pp 103–138
Ivanciuc O (2003) Topological indices. In: Gasteiger J (ed) Handbook of chemoinformatics, vol 3. Wiley, Weinheim, pp 981–1003
Ivanciuc O (2003) Aquatic toxicity prediction for polar and nonpolar narcotic pollutants with support vector machines. Internet Electron J Mol Des 2:195–208
Ivanciuc O (2004) Support vector machines prediction of the mechanism of toxic action from hydrophobicity and experimental toxicity against pimephales promelas and tetrahymena pyriformis. Internet Electron J Mol Des 3:802–821
Ivanciuc O (2005) Support vector regression quantitative structure‐activity relationships (QSAR) for benzodiazepine receptor ligands. Internet Electron J Mol Des 4:181–193
Ivanciuc O (2005) Machine learning applied to anticancer structure‐activity relationships for NCI human tumor cell lines. Internet Electron J Mol Des 4:948–958
Ivanciuc O (2007) Applications of support vector machines in chemistry. In: Lipkowitz KB, Cundari TR (eds) Reviews in computational chemistry, vol 23. Wiley, Weinheim, pp 291–400
John GH, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Besnard P, Hanks S (eds) UAI '95: Proc of the 11th annual conference on uncertainty in artificial intelligence. Morgan Kaufmann, Montreal, pp 338–345
Jorissen RN, Gilson MK (2005) Virtual screening of molecular databases using a support vector machine. J Chem Inf Model 45:549–561
Jurs P (2003) Quantitative structure‐property relationships. In: Gasteiger J (ed) Handbook of chemoinformatics, vol 3. Wiley, Weinheim, pp 1314–1335
Kier LB, Hall LH (1976) Molecular connectivity in chemistry and drug research. Academic Press, New York
Kier LB, Hall LH (1986) Molecular connectivity in structure‐activity analysis. Research Studies Press, Letchworth
Kier LB, Hall LH (1999) Molecular structure description. The electrotopological state. Academic Press, San Diego
Klon AE, Diller DJ (2007) Library fingerprints: a novel approach to the screening of virtual libraries. J Chem Inf Model 47:1354–1365
Klon AE, Glick M, Davies JW (2004) Combination of a naive Bayes classifier with consensus scoring improves enrichment of high‐throughput docking results. J Med Chem 47:4356–4359
Klon AE, Glick M, Thoma M, Acklin P, Davies JW (2004) Finding more needles in the haystack: a simple and efficient method for improving high‐throughput docking results. J Med Chem 47:2743–2749
Klon AE, Lowrie JF, Diller DJ (2006) Improved naïve Bayesian modeling of numerical data for absorption, distribution, metabolism and excretion (ADME) property prediction. J Chem Inf Model 46:1945–1956
Kohavi R (1995) The power of decision tables. In: Lavrac N, Wrobel S (eds) ECML-95 8th european conference on machine learning. Lecture Notes in Computer Science, vol 912. Springer, Heraclion, pp 174–189
Kohavi R (1996) Scaling up the accuracy of naive-Bayes classifiers: a decision‐tree hybrid. In: Simoudis E, Han J, Fayyad UM (eds) Proc of the 2nd international conference on knowledge discovery and data mining (KDD-96). AAAI Press, Menlo Park, pp 202–207
Kononenko I, Kukar M (2007) Machine learning and data mining: introduction to principles and algorithms. Horwood, Westergate, p 454
Konovalov DA, Coomans D, Deconinck E, Vander Heyden Y (2007) Benchmarking of QSAR models for blood‐brain barrier permeation. J Chem Inf Model 47:1648–1656
Kumar R, Kulkarni A, Jayaraman VK, Kulkarni BD (2004) Structure‐activity relationships using locally linear embedding assisted by support vector and lazy learning regressors. Internet Electron J Mol Des 3:118–133
le Cessie S, van Houwelingen JC (1992) Ridge estimators in logistic regression. Appl Statist 41:191–201
Leong MK (2007) A novel approach using pharmacophore ensemble/support vector machine (PhE/SVM) for prediction of hERG liability. Chem Res Toxicol 20:217–226
Lepp Z, Kinoshita T, Chuman H (2006) Screening for new antidepressant leads of multiple activities by support vector machines. J Chem Inf Model 46:158–167
LiH, Yap CW, Ung CY, Xue Y, Cao ZW, Chen YZ (2005) Effect of selectionof molecular descriptors on the prediction of blood‐brain barrier penetrating and nonpenetrating agents by statistical learning methods. J Chem Inf Model 45:1376–1384
Li S, Fedorowicz A, Singh H, Soderholm SC (2005) Application of the random forest method in studies of local lymph node assay based skin sensitization data. J Chem Inf Model 45:952–964
Li W-X, Li L, Eksterowicz J, Ling XB, Cardozo M (2007) Significance analysis and multiple pharmacophore models for differentiating P‑glycoprotein substrates. J Chem Inf Model 47:2429–2438
Liao Q, Yao J, Yuan S (2007) Prediction of mutagenic toxicity by combination of recursive partitioning and support vector machines. Mol Divers 11:59–72
Mangasarian OL, Musicant DR (2000) Robust linear and support vector regression. IEEE Trans Pattern Anal Mach Intell 22:950–955
Mangasarian OL, Musicant DR (2002) Large scale kernel regression via linear programming. Mach Learn 46:255–269
Merkwirth C, Mauser HA, Schulz-Gasch T, Roche O, Stahl M, Lengauer T (2004) Ensemble methods for classification in cheminformatics. J Chem Inf Comput Sci 44:1971–1978
Mitchell TM (1997) Machine learning. McGraw-Hill, Maidenhead, p 432
Müller K-R, Rätsch G, Sonnenburg S, Mika S, Grimm M, Heinrich N (2005) Classifying ‘drug‐likeness’ with kernel‐based learning methods. J Chem Inf Model 45:249–253
Neugebauer A, Hartmann RW, Klein CD (2007) Prediction of protein‐protein interaction inhibitors by chemoinformatics and machine learning methods. J Med Chem 50:4665–4668
Neumann D, Kohlbacher O, Merkwirth C, Lengauer T (2006) A fully computational model for predicting percutaneous drug absorption. J Chem Inf Model 46:424–429
Nidhi, Glick M, Davies JW, Jenkins JL (2006) Prediction of biological targets for compounds using multiple‐category Bayesian models trained on chemogenomics databases. J Chem Inf Model 46:1124–1133
Nigsch F, Bender A, van Buuren B, Tissen J, Nigsch E, Mitchell JBO (2006) Melting point prediction employing k‑nearest neighbor algorithms and genetic parameter optimization. J Chem Inf Model 46:2412–2422
Oloff S, Muegge I (2007) kScore: a novel machine learning approach that is not dependent on the data structure of the training set. J Comput-Aided Mol Des 21:87–95
Oloff S, Zhang S, Sukumar N, Breneman C, Tropsha A (2006) Chemometric analysis of ligand receptor complementarity: Identifying complementary ligands based on receptor information (CoLiBRI). J Chem Inf Model 46:844–851
Palmer DS, O'Boyle NM, Glen RC, Mitchell JBO (2007) Random forest models to predict aqueous solubility. J Chem Inf Model 47:150–158
Pelletier DJ, Gehlhaar D, Tilloy-Ellul A, Johnson TO, Greene N (2007) Evaluation of a published in silico model and construction of a novel Bayesian model for predicting phospholipidosis inducing potential. J Chem Inf Model 47:1196–1205
Platt J (1999) Fast training of support vector machines using sequential minimal optimization. In: Schölkopf B, Burges CJC, Smola AJ (eds) Advances in kernel methods – support vector learning. MIT Press, Cambridge, pp 185–208
Plewczynski D, Spieser SAH, Koch U (2006) Assessing different classification methods for virtual screening. J Chem Inf Model 46:1098–1106
Quinlan R (1993) C4.5: programs for machine learning. Morgan Kaufmann, San Mateo
Ren S (2002) Classifying class I and class II compounds by hydrophobicity and hydrogen bonding descriptors. Environ Toxicol 17:415–423
Ripley BD (2008) Pattern recognition and neural networks. Cambridge University Press, Cambridge, p 416
Rodgers S, Glen RC, Bender A (2006) Characterizing bitterness: identification of key structural features and development of a classification model. J Chem Inf Model 46:569–576
Rusinko A, Farmen MW, Lambert CG, Brown PL, Young SS (1999) Analysis of a large structure/biological activity data set using recursive partitioning. J Chem Inf Comput Sci 39:1017–1026
Sakiyama Y, Yuki H, Moriya T, Hattori K, Suzuki M, Shimada K, Honma T (2008) Predicting human liver microsomal stability with machine learning techniques. J Mol Graph Modell 26:907–915
Schneider N, Jäckels C, Andres C, Hutter MC (2008) Gradual in silico filtering for druglike substances. J Chem Inf Model 48:613–628
Schölkopf B, Smola AJ (2002) Learning with kernels. MIT Press, Cambridge
Schölkopf B, Sung KK, Burges CJC, Girosi F, Niyogi P, Poggio T, Vapnik V (1997) Comparing support vector machines with gaussian kernels to radial basis function classifiers. IEEE Trans Signal Process 45:2758–2765
Schölkopf B, Burges CJC, Smola AJ (1999) Advances in kernel methods: support vector learning. MIT Press, Cambridge
Schroeter TS, Schwaighofer A, Mika S, ter Laak A, Suelzle D, Ganzer U, Heinrich N, Müller K-R (2007) Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules. J Comput-Aided Mol Des 21:485–498
Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge
ShenM, LeTiran A, Xiao Y, Golbraikh A, Kohn H, Tropsha A(2002) Quantitative structure‐activity relationship analysis offunctionalized amino acid anticonvulsant agents using k‑nearest neighbor and simulated annealing PLS methods. J Med Chem 45:2811–2823
Shen M, Xiao Y, Golbraikh A, Gombar VK, Tropsha A (2003) Development and validation of k‑nearest‐neighbor QSPR models of metabolic stability of drug candidates. J Med Chem 46:3013–3020
Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222
Sommer S, Kramer S (2007) Three data mining techniques to improve lazy structure‐activity relationships for noncongeneric compounds. J Chem Inf Model 47:2035–2043
Sorich MJ, McKinnon RA, Miners JO, Smith PA (2006) The importance of local chemical structure for chemical metabolism by human uridine 5'‑diphosphate‐glucuronosyltransferase. J Chem Inf Model 46:2692–2697
Sun H (2005) A naive Bayes classifier for prediction of multidrug resistance reversal activity on the basis of atom typing. J Med Chem 48:4031–4039
Suykens JAK (2001) Support vector machines: a nonlinear modelling and control perspective. Eur J Control 7:311–327
Suykens JAK, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J (2002) Least squares support vector machines. World Scientific, Singapore
Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP (2003) Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci 43:1947–1958
Svetnik V, Wang T, Tong C, A Liaw, Sheridan RP, Song Q (2005) Boosting: an ensemble learning tool for compound classification and QSAR modeling. J Chem Inf Model 45:786–799
Swamidass SJ, Chen J, Phung P, Ralaivola L, Baldi P (2005) Kernels for small molecules and the prediction of mutagenicity, toxicity and anti‐cancer activity. Bioinformatics 21[S1]:i359–i368
Terfloth L, Bienfait B, Gasteiger J (2007) Ligand‐based models for the isoform specificity of cytochrome P450 3A4, 2D6, and 2C9 substrates. J Chem Inf Model 47:1688–1701
Tobita M, Nishikawa T, Nagashima R (2005) A discriminant model constructed by the support vector machine method for HERG potassium channel inhibitors. Bioorg Med Chem Lett 15:2886–2890
Todeschini R, Consonni V (2003) Descriptors from molecular geometry. In: Gasteiger J (ed) Handbook of chemoinformatics, vol 3. Wiley, Weinheim, pp 1004–1033
Tong W, Hong H, Fang H, Xie Q, Perkins R (2003) Decision forest: Combining the predictions of multiple independent decision tree models. J Chem Inf Comput Sci 43:525–531
Tong W, Xie Q, Hong H, Shi L, Fang H, Perkins R (2004) Assessment of prediction confidence and domain extrapolation of two structure‐activity relationship models for predicting estrogen receptor binding activity. Env Health Perspect 112:1249–1254
Trinajstić N (1992) Chemical graph theory. CRC Press, Boca Raton
Urrestarazu Ramos E, Vaes WHJ, Verhaar HJM, Hermens JLM (1998) Quantitative structure‐activity relationships for the aquatic toxicity of polar and nonpolar narcotic pollutants. J Chem Inf Comput Sci 38:845–852
Vapnik VN (1979) Estimation of dependencies based on empirical data. Nauka, Moscow
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10:988–999
Vapnik V, Chapelle O (2000) Bounds on error expectation for support vector machines. Neural Comput 12:2013–2036
Vapnik VN, Chervonenkis AY (1974) Theory of pattern recognition. Nauka, Moscow
Vapnik V, Lerner A (1963) Pattern recognition using generalized portrait method. Automat Remote Control 24:774–780
Varnek A, Kireeva N, Tetko IV, Baskin II, Solov'ev VP (2007) Exhaustive QSPR studies of a large diverse set of ionic liquids: how accurately can we predict melting points? J Chem Inf Model 47:1111–1122
Vogt M, Bajorath J (2008) Bayesian similarity searching in high‐dimensional descriptor spaces combined with Kullback–Leibler descriptor divergence analysis. J Chem Inf Model 48:247–255
von Korff M, Sander T (2006) Toxicity‐indicating structural patterns. J Chem Inf Model 46:536–544
Votano JR, Parham M, Hall LM, Hall LH, Kier LB, Oloff S, Tropsha A (2006) QSAR modeling of human serum protein binding with several modeling techniques utilizing structure‐information representation. J Med Chem 49:7169–7181
Wang J, Du H, Yao X, Hu Z (2007) Using classification structure pharmacokinetic relationship (SCPR) method to predict drug bioavailability based on grid‐search support vector machine. Anal Chim Acta 601:156–163
Watson P (2008) Naïve Bayes classification using 2D pharmacophore feature triplet vectors. J Chem Inf Model 48:166–178
Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco, p 525
Xiao Z, Xiao Y-D, Feng J, Golbraikh A, Tropsha A, Lee K-H (2002) Antitumor agents. 213. Modeling of epipodophyllotoxin derivatives using variable selection k‑nearest neighbor QSAR method. J Med Chem 45:2294–2309
Xue Y, Li ZR, Yap CW, Sun LZ, Chen X, Chen YZ (2004) Effect of molecular descriptor feature selection in support vector machine classification of pharmacokinetic and toxicological properties of chemical agents. J Chem Inf Comput Sci 44:1630–1638
Yamashita F, Hara H, Ito T, Hashida M (2008) Novel hierarchical classification and visualization method for multiobjective optimization of drug properties: application to structure‐activity relationship analysis of cytochrome P450 metabolism. J Chem Inf Model 48:364–369
Yap CW, Chen YZ (2005) Prediction of cytochrome P450 3A4, 2D6, and 2C9 inhibitors and substrates by using support vector machines. J Chem Inf Model 45:982–992
Yap CW, Cai CZ, Xue Y, Chen YZ (2004) Prediction of torsade‐causing potential of drugs by support vector machine approach. Toxicol Sci 79:170–177
Yu G-X, Park B-H, Chandramohan P, Munavalli R, Geist A, Samatova NF (2005) In silico discovery of enzyme‐substrate specificity‐determining residue clusters. J Mol Biol 352:1105–1117
Yue P, Li Z, Moult J (2005) Loss of protein structure stability as a major causative factor in monogenic disease. J Mol Biol 353:459–473
Zhang S, Golbraikh A, Oloff S, Kohn H, Tropsha A (2006) A novel automated lazy learning QSAR (ALL-QSAR) approach: method development, applications, and virtual screening of chemical databases using validated ALL-QSAR models. J Chem Inf Model 46:1984–1995
Zhang S, Golbraikh A, Tropsha A (2006) Development of quantitative structure‐binding affinity relationship models based on novel geometrical chemical descriptors of the protein‐ligand interfaces. J Med Chem 49:2713–2724
Zheng WF, Tropsha A (2000) Novel variable selection quantitative structure‐property relationship approach based on the k‑nearest‐neighbor principle. J Chem Inf Comput Sci 40:185–194
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag
About this entry
Cite this entry
Ivanciuc, O. (2009). Drug Design with Machine Learning. In: Meyers, R. (eds) Encyclopedia of Complexity and Systems Science. Springer, New York, NY. https://doi.org/10.1007/978-0-387-30440-3_135
Download citation
DOI: https://doi.org/10.1007/978-0-387-30440-3_135
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-75888-6
Online ISBN: 978-0-387-30440-3
eBook Packages: Physics and AstronomyReference Module Physical and Materials ScienceReference Module Chemistry, Materials and Physics