Skip to main content
SpringerLink
Log in
Book cover

Encyclopedia of Complexity and Systems Science pp 2113–2139Cite as

Drug Design with Artificial Intelligence Methods

  • Reference work entry

Definition of theSubject

Drug design and development represents a complex andexpensive process that is based on the creative application ofscientific results from various disciplines, including genomics,chemistry, biology, computational chemistry, pharmacology,toxicology, and clinical studies. The average cost of bringinga new drug to market is currently around US$800 million,with a large part of the cost coming from chemicalcompounds that fail in different stages ofdevelopment. Computational simulation of biochemical processesmay guide the drug discovery process through reliable in silicomodels of biochemical properties (aqueous solubility,octanol‐water partition, intestinal absorption,blood‐brain barrier transport, excretion), prediction ofenzyme‐ligand interactions, simulations of cells, tissuesand organisms. In this chapter we review the most importantapplications of artificial intelligence instructure‐activity relationships (SAR) and quantitativestructure‐activity relationships...

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   3,499.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD   549.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Abbreviations

Ant colony optimization:

Ant colony optimization (ACO) is an agent‐based algorithm procedure inspired by the function of ant colonies and the ants search for the optimum path to food sources. The virtual agents are called artificial ants or ants, and the optimization problem is represented as a trial and error search for the optimum path on a weighted graph. The pheromone that is deposited by ants on the trail is represented as weights for graph components (vertices or edges). Each ant generates a solution by moving on the graph and by selecting the next step based on the pheromone level. The pheromone level is updated after each cycle (when all ants found a solution) by adding a pheromone quantity proportional to the quality of the solutions to which it belongs.

Antigen:

An antigen is a molecule (chemical compound, protein or polysaccharide) that induces an immune response. Each pathogen contains specific antigens that are recognized by the immune system. The antigen region that is recognized by the immune system is called an epitope.

Antibody:

An antibody (or immunoglobulin) is a protein used by the immune system to identify bacteria, viruses and other pathogens or foreign molecules. The antibody region that binds antigens is extremely variable, thus allowing the immune system to recognize a large diversity of pathogens. The ability to recognize antigens is improved through successive cycles of antigen presentation, antibody cloning, and hypermutation of the variable region of the antibody.

Artificial immune systems:

Artificial immune systems (AIS) represent a class of optimization algorithms inspired by the components and mechanisms of the biological immune system. AIS simulate the learning and memory capabilities of the immune system to develop computational algorithms for pattern recognition, function optimization, classification, process control, and intrusion detection.

Genetic algorithms:

Genetic algorithms (GA) solve high‐dimensional problems through a Darwinian evolution of a population of individuals, in which each individual (chromosome) represents a possible solution. Depending on the type of the optimization problem, chromosomes may represent the solution in a binary, continuous, or hybrid encoding. Each chromosome has a fitness value that measures the quality of the solution. A population of parents evolves to a generation of children by crossover and mutation.

Particle swarm optimization:

Swarm intelligence (SI) represents a group of distributed intelligence algorithms that solve optimization problems by applying processes inspired by swarming, herding, and flocking of various species. Particle swarm optimization (PSO) simulates the swarming behaviors observed in swarms of bees, flocks of birds, or schools of fish. PSO considers a swarm of particles that start from a random position and have a random velocity. At each step a particle moves to a new position that is determined by its own experience (the best past position) and by the memory of the best particle in the swarm. PSO may be applied to both binary and continuous optimization problems, and its main strength is a fast convergence.

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.

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

  1. HollandJ (1975) Adaptation in Natural and Artificial Systems.University of Michigan Press, AnnArbor

    Google Scholar 

  2. GoldbergDE (1989) Genetic Algorithms in Search, Optimization &Machine Learning. Addison Wesley,Reading

    MATH  Google Scholar 

  3. JonesG (1998) Genetic and evolutionary algorithms. In: Schleyer PvR,Allinger NL, Clark T, Gasteiger J, Kollman PA, Schaefer III HF,Schreiner PR (eds) The Encyclopedia of Computational Chemistry.Wiley, Chichester,pp 1127–1136

    Google Scholar 

  4. TerflothL, Gasteiger J (2001) Neural networks and genetic algorithms indrug design. Drug Discov Today6:S102–S108

    Google Scholar 

  5. vonHomeyer A (2003) Evolutionary algorithms and their applicationsin chemistry. In: Gasteiger J (ed) Handbook of Chemoinformatics,vol 3. Wiley-VCH, Weinheim,pp 1239–1280

    Google Scholar 

  6. DorigoM, Maniezzo V, Colorni A (1996) Ant system: Optimization bya colony of cooperating agents. IEEE Trans Syst Man CybernPart B Cybern 26:29–41

    Google Scholar 

  7. DorigoM, Gambardella LM (1997) Ant colony system: A cooperativelearning approach to the traveling salesman problem. IEEE TransEvol Comput 1:53–66

    Google Scholar 

  8. DorigoM, Di Caro G, Gambardella LM (1999) Ant algorithms for discreteoptimization. Artif Life5:137–172

    Google Scholar 

  9. DorigoM, Stützle T (2004) Ant Colony Optimization. MIT Press,Cambridge

    Google Scholar 

  10. DorigoM, Blum C (2005) Ant colony optimization theory: A survey.Theor Comput Sci 344:243–278

    MathSciNet  MATH  Google Scholar 

  11. KennedyJ, Eberhart R (1995) Particle swarm optimization. Proceedingsof IEEE International Conference on Neural Networks, vol 4.pp 1942–1948

    Google Scholar 

  12. BanksA, Vincent J, Anyakoha C (2007) A review of particle swarmoptimization Part I: background and development. Nat Comput6:467–484

    MathSciNet  MATH  Google Scholar 

  13. BanksA, Vincent J, Anyakoha C (2008) A review of particle swarmoptimization Part II: hybridisation, combinatorial,multicriteria and constrained optimization, and indicativeapplications. Nat Comput7:109–124

    MathSciNet  MATH  Google Scholar 

  14. ChuangLY, Chang HW, Tu CJ, Yang CH (2008) Improved binary PSO forfeature selection using gene expression data. Comput Biol Chem32:29–38

    MATH  Google Scholar 

  15. NamasivayamV, Günther R (2007) PSO@AUTODOCK: A fast flexible moleculardocking program based on swarm intelligence. Chem Biol Drug Des70:475–484

    Google Scholar 

  16. AgrafiotisDK, Cedeño W (2002) Feature selection for structure-activitycorrelation using binary particle swarms. J Med Chem45:1098–1107

    Google Scholar 

  17. HuangJ, Ma G, Muhammad I, Cheng Y (2007) Identifying P-glycoproteinsubstrates using a support vector machine optimized bya particle swarm. J Chem Inf Model47:1638–1647

    Google Scholar 

  18. ShenQ, Shi WM, Yang XP, Ye BX (2006) Particle swarm algorithmtrained neural network for QSAR studies of inhibitors ofplatelet-derived growth factor receptor phosphorylation. Eur JPharm Sci 28:369–376

    ADS  Google Scholar 

  19. HuntJE, Cooke DE (1996) Learning using an artificial immune system.J Netw Comput Appl 19:189–212

    Google Scholar 

  20. deCastro LN, Von Zuben FJ (1999) Artificial immune systems: Part IBasic theory and applications. FEEC/UNICAMP,Brazil

    Google Scholar 

  21. deCastro LN, Von Zuben FJ (2000) Artificial immune systems: PartII A survey of applications. FEEC/UNICAMP,Brazil

    Google Scholar 

  22. TimmisJ, Neal M, Hunt J (2000) An artificial immune system for dataanalysis. Biosystems55:143–150

    Google Scholar 

  23. ChaoDL, Forrest S (2003) Information immune systems. Genet ProgrammEvolv Mach 4:311–331

    Google Scholar 

  24. deCastro LN, Timmis JI (2003) Artificial immune systems asa novel soft computing paradigm. Soft Comput7:526–544

    Google Scholar 

  25. MusilekP, Lau A, Reformat M, Wyard-Scott L (2006) Immune programming.Inf Sci 176:972–1002

    MathSciNet  MATH  Google Scholar 

  26. TimmisJ (2007) Artificial immune systems – Today andtomorrow. Nat Comput 6:1–18

    MathSciNet  MATH  Google Scholar 

  27. ForrestS, Beauchemin C (2007) Computer immunology. Immunol Rev216:176–197

    Google Scholar 

  28. DasguptaD (1999) Artificial Immune Systems and Their Applications.Springer, Berlin

    MATH  Google Scholar 

  29. deCastro LN, Timmis J (2002) Artificial Immune Systems: A NewComputational Intelligence Approach. Springer,Berlin

    MATH  Google Scholar 

  30. TarakanovAO, Skormin VA, Sokolova SP (2003) Immunocomputing: Principlesand Applications. Springer, Berlin

    MATH  Google Scholar 

  31. IshidaY (2004) Immunity-Based Systems. Springer,Berlin

    Google Scholar 

  32. TimmisJ, Bentley P, Hart E (2003) Artificial Immune Systems: SecondInternational Conference, ICARIS 2003, Edinburgh, September1–3. Lecture Notes in Computer Science, vol 2787.Springer, Berlin

    Google Scholar 

  33. NicosiaG, Cutello V, Bentley PJ, Timmis JI (2004) Artificial ImmuneSystems: Third International Conference, ICARIS 2004, Catania,September 13–16. Lecture Notes in Computer Science, vol 3239. Springer, Berlin

    Google Scholar 

  34. JacobC, Pilat ML, Bentley PJ, Timmis J (2005) Artificial ImmuneSystems: 4th International Conference, ICARIS 2005, Banff,August 14–17. Lecture Notes in Computer Science, vol 3627. Springer, Berlin

    Google Scholar 

  35. BersiniH, Carneiro J (2006) Artificial Immune Systems: 5thInternational Conference, ICARIS 2006, Oeiras, September4–6. Lecture Notes in Computer Science, vol 4163.Springer, Berlin

    Google Scholar 

  36. AndoS, Iba H (2004) Classification of gene expression profile usingcombinatory method of evolutionary computation and machinelearning. Genet Programm Evolv Mach5:145–156

    Google Scholar 

  37. BezerraGB, Cançado GMA, Menossi M, de Castro LN, Von Zuben FJ(2005) Recent advances in gene expression data clustering:A case study with comparative results. Genet Mol Res4:514–524

    Google Scholar 

  38. TsankovaD, Georgieva V, Kasabov N (2005) Artificial immune networks asa paradigm for classification and profiling of geneexpression data. J Comput Theor Nanosci2:543–550

    Google Scholar 

  39. ŞahanS, Polat K, Kodaz H, Güneş S (2007) A new hybrid methodbased on fuzzy-artificial immune system and k-nn algorithm forbreast cancer diagnosis. Comput Biol Med37:415–423

    Google Scholar 

  40. PolatK, Güneş S (2008) Computer aided medical diagnosis system basedon principal component analysis and artificial immunerecognition system classifier algorithm. Expert Syst Appl34:773–779

    Google Scholar 

  41. PolatK, Şahan S, Güneş S (2006) A new method to medicaldiagnosis: Artificial immune recognition system (AIRS) withfuzzy weighted pre‐processing and application to ECGarrhythmia. Expert Syst Appl31:264–269

    Google Scholar 

  42. LatifogluF, Şahan S, Kara S, Güneş S (2007) Diagnosis of atherosclerosisfrom carotid artery Doppler signals as a real-world medicalapplication of artificial immune systems. Expert Syst Appl33:786–793

    Google Scholar 

  43. CutelloV, Nicosia G, Pavone M, Timmis J (2007) An immune algorithm forprotein structure prediction on lattice models. IEEE Trans EvolComput 11:101–117

    Google Scholar 

  44. AnileAM, Cutello V, Narzisi G, Nicosia G, Spinella S (2007)Determination of protein structure and dynamics combining immunealgorithms and pattern search methods. Nat Comput6:55–72

    MathSciNet  MATH  Google Scholar 

  45. MorrisGM, Goodsell DS, Halliday RS, Huey R, Hart WE, Belew RK, OlsonAJ (1998) Automated docking using a Lamarckian geneticalgorithm and an empirical binding free energy function. J Comput Chem 19:1639–1662

    Google Scholar 

  46. WangR, Gao Y, Lai LH (2000) LigBuilder: A multi-purpose programfor structure-based drug design. J Mol Model6:498–516

    Google Scholar 

  47. SoSS, Karplus M (1996) Evolutionary optimization in quantitativestructure-activity relationship: An application of geneticneural networks. J Med Chem39:1521–1530

    Google Scholar 

  48. VenkatasubramanianV, Chan K, Caruthers JM (1995) Evolutionary design of moleculeswith desired properties using the genetic algorithm. J Chem InfComput Sci 35:188–195

    Google Scholar 

  49. SundaramA, Venkatasubramanian V (1998) Parametric sensitivity andsearch-space characterization studies of genetic algorithms forcomputer-aided polymer design. J Chem Inf Comput Sci38:1177–1191

    Google Scholar 

  50. GilletVJ, Willett P, Bradshaw J, Green DVS (1999) Selectingcombinatorial libraries to optimize diversity and physicalproperties. J Chem Inf Comput Sci39:169–177

    Google Scholar 

  51. IvanciucO, Ivanciuc T, Cabrol-Bass D (2002) QSAR for dihydrofolatereductase inhibitors with molecular graph structuraldescriptors. J Mol Struct (Theochem)582:39–51

    Google Scholar 

  52. WegnerJK, Fröhlich H, Zell A (2004) Feature selection for descriptorbased classification models, 2. Human intestinal absorption(HIA). J Chem Inf Comput Sci44:931–939

    Google Scholar 

  53. WeberL (1998) Evolutionary combinatorial chemistry: application ofgenetic algorithms. Drug Discov Today3:379–385

    Google Scholar 

  54. WeberL (2005) Current status of virtual combinatorial library design.QSAR Comb Sci 24:809–823

    Google Scholar 

  55. GallopMA, Barrett RW, Dower WJ, Fodor SPA, Gordon EM (1994)Applications of combinatorial technologies to drug discovery, 1.Background and peptide combinatorial libraries. J Med Chem37:1233–1251

    Google Scholar 

  56. GordonEM, Barrett RW, Dower WJ, Fodor SPA, Gallop MA (1994)Applications of combinatorial technologies to drug discovery, 2.Combinatorial organic-synthesis, library screening strategies,and future directions. J Med Chem37:1385–1401

    Google Scholar 

  57. WeberL (1998) Applications of genetic algorithms in moleculardiversity. Curr Opin Chem Biol2:381–385

    Google Scholar 

  58. IllgenK, Enderle T, Broger C, Weber L (2000) Simulated molecularevolution in a full combinatorial library. Chem Biol7:433–441

    Google Scholar 

  59. UgiI, Almstetter M, Bock H, Dömling A, Ebert B, Gruber B,Hanusch-Kompa C, Heck S, Kehagia-Drikos K, Lorenz K, PapathomaS, Raditschnig R, Schmid T, Werner B, von Zychlinski A (1998)MCR XVII. Three types of MCRs and the libraries –Their chemistry of natural events and preparative chemistry.Croat Chem Acta 71:527–547

    Google Scholar 

  60. WeberL (2002) Multi-component reactions and evolutionary chemistry.Drug Discov Today 7:143–147

    Google Scholar 

  61. GlobusA, Lawtonb J, Wipke T (1999) Automatic molecular design usingevolutionary techniques. Nanotechnology10:290–299

    ADS  Google Scholar 

  62. BrownN, McKay B, Gilardoni F, Gasteiger J (2004) A graph-basedgenetic algorithm and its application to the multiobjectiveevolution of median molecules. J Chem Inf Comput Sci44:1079–1087

    Google Scholar 

  63. BrownN, McKay B, Gasteiger J (2006) A novel workflow for theinverse QSPR problem using multiobjective optimization. J Comput Aided Mol Des20:333–341

    ADS  Google Scholar 

  64. LewisRA (2005) A general method for exploiting QSAR models inlead optimization. J Med Chem48:1638–1648

    Google Scholar 

  65. IzrailevS, Agrafiotis D (2001) A novel method for buildingregression tree models for QSAR based on artificial ant colonysystems. J Chem Inf Comput Sci41:176–180

    Google Scholar 

  66. IzrailevS, Agrafiotis DK (2002) Variable selection for QSAR byartificial ant colony systems. SAR QSAR Environ Res13:417–423

    Google Scholar 

  67. ShelokarPS, Jayaraman VK, Kulkarni BD (2004) An ant colony approach forclustering. Anal Chim Acta509:187–195

    Google Scholar 

  68. HeY, Chen D, Zhao W (2006) Ensemble classifier system based on antcolony algorithm and its application in chemical patternclassification. Chemom Intell Lab Syst80:39–49

    Google Scholar 

  69. KorbO, Stützle T, Exner TE (2006) PLANTS: Application of ant colonyoptimization to structure-based drug design. Ant ColonyOptimization and Swarm Intelligence. Proceedings. LNCS, vol 4150. Springer, Berlin, pp 247–258

    Google Scholar 

  70. ShenQ, Jiang JH, Tao JC, Shen GL, Yu RQ (2005) Modified ant colonyoptimization algorithm for variable selection in QSAR modeling:QSAR studies of cyclooxygenase inhibitors. J Chem Inf Model45:1024–1029

    Google Scholar 

  71. GunturiSB, Narayanan R, Khandelwal A (2006) In silico ADME modelling 2:Computational models to predict human serum albumin bindingaffinity using ant colony systems. Bioorg Med Chem14:4118–4129

    Google Scholar 

  72. ShiWM, Shen Q, Kong W, Ye BX (2007) QSAR analysis of tyrosinekinase inhibitor using modified ant colony optimization andmultiple linear regression. Eur J Med Chem42:81–86

    Google Scholar 

  73. KarpenkoO, Shi J, Dai Y (2005) Prediction of MHC class II binders usingthe ant colony search strategy. Artif Intell Med35:147–156

    Google Scholar 

  74. HernandezP, Gras R, Frey J, Appel RD (2003) Popitam: Towards newheuristic strategies to improve protein identification fromtandem mass spectrometry data. Proteomics3:870–878

    Google Scholar 

  75. ShenQ, Shi WM, Kong W, Ye BX (2007) A combination of modifiedparticle swarm optimization algorithm and support vector machinefor gene selection and tumor classification. Talanta71:1679–1683

    Google Scholar 

  76. CallST, Zubarev DY, Boldyrev AI (2007) Global minimum structuresearches via particle swarm optimization. J Comput Chem28:1177–1186

    Google Scholar 

  77. ChangBCH, Ratnaweera A, Halgamuge SK, Watson HC (2004) Particle swarmoptimisation for protein motif discovery. Genet Programm EvolvMach 5:203–214

    Google Scholar 

  78. ChenK, Li T, Cao T (2006) Tribe-PSO: A novel globaloptimization algorithm and its application in molecular docking.Chemom Intell Lab Syst82:248–259

    Google Scholar 

  79. ChenHM, Liu BF, Huang HL, Hwang SF, Ho SY (2007) SODOCK: Swarmoptimization for highly flexible protein-ligand docking. J Comput Chem 28:612–623

    Google Scholar 

  80. CedeñoW, Agrafiotis DK (2003) Using particle swarms for thedevelopment of QSAR models based on K-nearest neighbor andkernel regression. J Comput Aided Mol Des17:255–263

    Google Scholar 

  81. LüJX, Shen Q, Jiang JH, Shen GL, Yu RQ (2004) QSAR analysis ofcyclooxygenase inhibitor using particle swarm optimization andmultiple linear regression. J Pharm Biomed Anal35:679–687

    Google Scholar 

  82. ShenQ, Jiang JH, Jiao CX, Shen GL, Yu RQ (2004) Modified particleswarm optimization algorithm for variable selection in MLR andPLS modeling: QSAR studies of antagonism of angiotensin IIantagonists. Eur J Pharm Sci22:145–152

    Google Scholar 

  83. LinWQ, Jiang JH, Shen Q, Shen GL, Yu RQ (2005) Optimized block-wisevariable combination by particle swarm optimization for partialleast squares modeling in quantitative structure-activityrelationship studies. J Chem Inf Model45:486–493

    Google Scholar 

  84. LinL, Lin WQ, Jiang JH, Shen GL, Yu RQ (2005) QSAR analysis ofsubstituted bis[(acridine‐4‐carboxamide)propyl]methylamines using optimized block-wisevariable combination by particle swarm optimization for partialleast squares modeling. Eur J Pharm Sci25:245–254

    Google Scholar 

  85. HuL, Wu H, Lin W, Jiang J, Yu R (2007) Quantitativestructure-activity relationship studies for the bindingaffinities of imidazobenzodiazepines for the α6benzodiazepine receptor isoform utilizing optimized blockwisevariable combination by particle swarm optimization for partialleast squares modeling. QSAR Comb Sci26:92–101

    Google Scholar 

  86. ShenQ, Jiang JH, Jiao CX, Huan SY, Shen GL, Yu RQ (2004) Optimizedpartition of minimum spanning tree for piecewise modeling byparticle swarm algorithm. QSAR studies of antagonism ofangiotensin II antagonists. J Chem Inf Comput Sci44:2027–2031

    Google Scholar 

  87. LinWQ, Jiang JH, Shen Q, Wu HL, Shen GL, Yu RQ (2005) Piecewisehypersphere modeling by particle swarm optimization in QSARstudies of bioactivities of chemical compounds. J Chem InfModel 45:535–541

    Google Scholar 

  88. LinL, Lin WQ, Jiang JH, Zhou YP, Shen GL, Yu RQ (2005) QSARanalysis of a series of2-aryl(heteroaryl)-2,5-dihydropyrazolo[4,3-c]quinolin-3-(3H)-onesusing piecewise hyper-sphere modeling by particle swarmoptimization. Anal Chim Acta552:42–49

    Google Scholar 

  89. XuL, Jiang JH, Lin WQ, Zhou YP, Wu HL, Shen GL, Yu RQ (2007)Optimized sample-weighted partial least squares. Talanta71:561–566

    Google Scholar 

  90. ShenQ, Jiang JH, Jiao CX, Lin WQ, Shen GL, Yu RQ (2004) Hybridizedparticle swarm algorithm for adaptive structure training ofmultilayer feed-forward neural network: QSAR studies ofbioactivity of organic compounds. J Comput Chem25:1726–1735

    Google Scholar 

  91. ZhouYP, Jiang JH, Lin WQ, Zou HY, Wu HL, Shen GL, Yu RQ (2006)Adaptive configuring of radial basis function network by hybridparticle swarm algorithm for QSAR studies of organic compounds.J Chem Inf Model 46:2494–2501

    Google Scholar 

  92. ZhouYP, Jiang JH, Lin WQ, Xu L, Wu HL, Shen GL, Yu RQ (2007)Artificial neural network-based transformation for nonlinearpartial least-square regression with application to QSARstudies. Talanta 71:848–853

    Google Scholar 

  93. MeissnerM, Schmuker M, Schneider G (2006) Optimized Particle SwarmOptimization (OPSO) and its application to artificial neuralnetwork training. BMC Bioinformatics7:125

    Google Scholar 

  94. IvanciucO (2007) Applications of support vector machines inchemistry. In: Lipkowitz KB, Cundari TR (eds) Reviews inComputational Chemistry, vol 23. Wiley-VCH, Weinheim,pp 291–400

    Google Scholar 

  95. LinWQ, Jiang JH, Zhou YP, Wu HL, Shen GL, Yu RQ (2007) Supportvector machine based training of multilayer feedforward neuralnetworks as optimized by particle swarm algorithm: Applicationin QSAR studies of bioactivity of organic compounds. J ComputChem 28:519–527

    Google Scholar 

  96. TangLJ, Zhou YP, Jiang JH, Zou HY, Wu HL, Shen GL, Yu RQ (2007)Radial basis function network-based transform fora nonlinear support vector machine as optimized bya particle swarm optimization algorithm with application toQSAR studies. J Chem Inf Model47:1438–1445

    Google Scholar 

  97. deCastro LN (2004) Dynamics of an artificial immune network. J Exp Theor Artif Intell16:19–39

    MATH  Google Scholar 

  98. BezerraGB, de Castro LN, Von Zuben FJ (2004) A hierarchical immunenetwork applied to gene expression data. In: Nicosia G, CutelloV, Bentley PJ, Timmis JI (eds) Artificial Immune Systems: ThirdInternational Conference, ICARIS 2004. Catania, September13–16. LNCS, vol 3239. Springer,Berlin, pp 14–27

    Google Scholar 

  99. WatkinsA, Timmis J, Boggess L (2004) Artificial immune recognitionsystem (AIRS): An immune-inspired supervised learning algorithm.Genet Programm Evolv Mach5:291–317

    Google Scholar 

  100. MengL, van der Putten P, Wang H (2005) A comprehensivebenchmark of the artificial immune recognition system (AIRS).Advanced Data Mining and Applications, Proceedings Lecture Notesin Artificial Intelligence, vol 3584. pp 575–582

    Google Scholar 

  101. WatkinsAB (2001) AIRS: A resource limited artificial immuneclassifier. Department of Computer Science, vol MS.Mississippi State University,pp 81

    Google Scholar 

  102. WatkinsAB (2005) Exploiting immunological metaphors in the developmentof serial, parallel and distributed learning algorithms. Ph D, University of Kent,pp 314

    Google Scholar 

  103. deCastro LN, Von Zuben FJ (2000) The clonal selection algorithmwith engineering applications. In: Whitley D, Goldberg D,Cantu-Paz E, Spector L, Parmee I, Beyer HG (eds) GECCO-2000:Proceedings of the Genetic and Evolutionary ComputationConference, July 10–12. Las Vegas, Morgan Kaufmann,pp 36–37

    Google Scholar 

  104. deCastro LN, Von Zuben FJ (2002) Learning and optimization usingthe clonal selection principle. IEEE Trans Evol Comput6:239–251

    Google Scholar 

  105. BrownleeJ (2005) Clonal selection theory & CLONAG. The clonalselection classification algorithm (CSCA). Centre forIntelligent Systems and Complex Processes (CISCP), Faculty ofInformation and Communication Technologies (ICT), SwinburneUniversity of Technology (SUT).Victoria

    Google Scholar 

  106. CarterJH (2000) The immune system as a model for patternrecognition and classification. J Am Med Inf Assoc7:28–41

    Google Scholar 

  107. BrownleeJ (2005) Immunos-81. The misunderstood artificial immune system.Centre for Intelligent Systems and Complex Processes (CISCP),Faculty of Information and Communication Technologies (ICT),Swinburne University of Technology (SUT).Victoria

    Google Scholar 

  108. WittenIH, Frank E (2005) Data Mining: Practical Machine Learning Toolsand Techniques, 2nd edn. Morgan Kaufmann, San Francisco,pp 525

    Google Scholar 

  109. BrownleeJ (2005) Artificial immune recognition system(AIRS). A review and analysis. Centre for IntelligentSystems and Complex Processes (CISCP), Faculty of Informationand Communication Technologies (ICT), Swinburne University ofTechnology (SUT). Victoria

    Google Scholar 

  110. WatkinsA, Timmis J (2002) Artificial immune recognition system (AIRS):Revisions and refinements. Artificial Immune Systems: FirstInternational Conference, ICARIS 2002. University of Kent atCanterbury, pp 173–181

    Google Scholar 

  111. FenichelRR, Malik M, Antzelevitch C, Sanguinetti M, Roden DM, Priori SG,Ruskin JN, Lipicky RJ, Cantilena LR (2004) Drug-induced torsadesde pointes and implications for drug development. J CardiovascElectrophysiol 15:475–495

    Google Scholar 

  112. IvanciucO (2006) Artificial immune system classification of drug-inducedtorsade de pointes with AIRS (artificial immune recognitionsystem). Internet Electron J Mol Des5:488–502

    Google Scholar 

  113. IvanciucO (2007) Artificial immune systems in drug design:Structure-activity relationships for torsade de pointes withAIRS (artificial immune recognition system). Internet ElectronJ Mol Des 6:47–62

    Google Scholar 

  114. StenbergP, Luthman K, Artursson P (2000) Virtual screening of intestinaldrug permeability. J Control Release65:231–243

    Google Scholar 

  115. PonceYM, Pérez MAC, Zaldivar VR, Sanz MB, Mota DS, Torrens F (2005)Prediction of intestinal epithelial transport of drug in(Caco-2) cell culture from molecular structure using in silicoapproaches during early drug discovery. Internet Electron J MolDes 4:124–150

    Google Scholar 

  116. LinnankoskiJ, Makela JM, Ranta VP, Urtti A, Yliperttula M (2006)Computational prediction of oral drug absorption based onabsorption rate constants in humans. J Med Chem49:3674–3681

    Google Scholar 

  117. IyerM, Tseng YJ, Senese CL, Liu J, Hopfinger AJ (2007) Predictionand mechanistic interpretation of human oral drug absorptionusing MI-QSAR analysis. Mol Pharmaceutics4:218–231

    Google Scholar 

  118. IvanciucO (2006) Artificial immune system prediction of the humanintestinal absorption of drugs with AIRS (artificial immunerecognition system). Internet Electron J Mol Des5:515–529

    Google Scholar 

  119. IvanciucO (2007) Feature Selection in AIRS (Artificial ImmuneRecognition System) Structure-Activity Relationships. InternetElectron J Mol Des 6:331–344

    Google Scholar 

  120. CrivoriP, Reinach B, Pezzetta D, Poggesi I (2006) Computational modelsfor identifying potential P-glycoprotein substrates andinhibitors. Mol Pharmaceutics3:33–44

    Google Scholar 

  121. KaiserD, Terfloth L, Kopp S, Schulz J, de Laet R, Chiba P, Ecker GF,Gasteiger J (2007) Self-organizing maps for identification of newinhibitors of P-glycoprotein. J Med Chem50:1698–1702

    Google Scholar 

  122. IvanciucO (2006) Artificial immune systems in drug design: Recognitionof P-glycoprotein substrates with AIRS (artificial immunerecognition system). Internet Electron J Mol Des5:542–554

    Google Scholar 

  123. IvanciucO (2006) Structure-activity relationships with artificial immunesystems: Classification of benzodiazepine receptor ligands withAIRS, CLONALG, CSCA, and IMMUNOS. Internet Electron J Mol Des5:585–604

    Google Scholar 

  124. VerhaarHJM, Solbé J, Speksnijder J, van Leeuwen CJ, Hermens JLM (2000)Classifying environmental pollutants: Part 3. Externalvalidation of the classification system. Chemosphere40:875–883

    Google Scholar 

  125. IvanciucO (2003) Aquatic toxicity prediction for polar and nonpolarnarcotic pollutants with support vector machines. InternetElectron J Mol Des 2:195–208

    Google Scholar 

  126. IvanciucO (2007) Artificial immune systems in aquatic toxicology:Structure-activity relationships for the mechanism of toxicaction with AIRS (artificial immune recognition system).Internet Electron J Mol Des6:13–28

    Google Scholar 

  127. IvanciucO (2007) Drug design with artificial immune systems:Structure-activity relationships for glycogen phosphorylase Binhibitors with CLONALG (clonal selection algorithm). InternetElectron J Mol Des 6:311–319

    Google Scholar 

  128. IvanciucO (2007) Structure-activity relationships in aquatic toxicologywith artificial immune systems: Mechanism of toxic actionclassification of polar and nonpolar narcotic pollutants withCLONALG (clonal selection algorithm). Internet Electron J MolDes 6:106–114

    Google Scholar 

  129. IvanciucO (2007) Artificial immune systems structure-activityrelationships for estrogen receptor ligands with CSCA (clonalselection classification system). Internet Electron J Mol Des6:81–89

    Google Scholar 

  130. IvanciucO (2007) Artificial immune systems in the virtual screening ofdihydrofolate reductase inhibitors with CSCA (clonal selectionclassification system). Internet Electron J Mol Des6:253–261

    Google Scholar 

  131. IvanciucO (2007) Drug design with artificial immune systems:Classification of angiotensin converting enzyme inhibitors withCSCA (clonal selection classification system). InternetElectron J Mol Des 6:135–143

    Google Scholar 

  132. IvanciucO (2007) Artificial immune systems in structure-activityrelationships: Classification of thermolysin inhibitors withCSCA (clonal selection classification system). InternetElectron J Mol Des 6:209–217

    Google Scholar 

  133. IvanciucO (2007) Structure-activity relationships foracetylcholinesterase inhibitors with the IMMUNOS artificialimmune system. Internet Electron J Mol Des6:167–175

    Google Scholar 

  134. IvanciucO (2007) Virtual screening of cyclooxygenase-2 inhibitors withthe IMMUNOS artificial immune system. Internet Electron J MolDes 6:200–208

    Google Scholar 

  135. IvanciucO (2007) Structure-activity relationships with the IMMUNOSartificial immune system for thrombin inhibitors. InternetElectron J Mol Des 6:262–270

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biochemistry and Molecular Biology, University of Texas Medical Branch, Galveston, USA

    Ovidiu Ivanciuc

Authors
  1. Ovidiu Ivanciuc
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. RAMTECH LIMITED, 122 Escalle Lane, Larkspur, CA, 94939, USA

    Robert A. Meyers Ph. D. (Editor-in-Chief) (Editor-in-Chief)

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag

About this entry

Cite this entry

Ivanciuc, O. (2009). Drug Design with Artificial Intelligence Methods. In: Meyers, R. (eds) Encyclopedia of Complexity and Systems Science. Springer, New York, NY. https://doi.org/10.1007/978-0-387-30440-3_133

Download citation

Publish with us

Policies and ethics

Search

Navigation