The Knowledge-Gradient Algorithm for Sequencing Experiments in Drug Discovery

We present a new technique for adaptively choosing the sequence of molecular compounds to test in drug discovery. Beginning with a base compound, we consider the problem of searching for a chemical derivative of the molecule that best treats a given disease. The problem of choosing molecules to test to maximize the expected quality of the best compound discovered may be formulated mathematically as a ranking-and-selection problem in which each molecule is an alternative. We apply a recently developed algorithm, known as the knowledge-gradient algorithm, that uses correlations in our Bayesian prior distribution between the performance of different alternatives (molecules) to dramatically reduce the number of molecular tests required, but it has heavy computational requirements that limit the number of possible alternatives to a few thousand. We develop computational improvements that allow the knowledge-gradient method to consider much larger sets of alternatives, and we demonstrate the method on a problem with 87,120 alternatives.

[1]  Luc De Raedt,et al.  Active Learning for High Throughput Screening , 2008, Discovery Science.

[2]  Gunnar Rätsch,et al.  Active Learning with Support Vector Machines in the Drug Discovery Process , 2003, J. Chem. Inf. Comput. Sci..

[3]  Wei-Ning Yang,et al.  Using Common Random Numbers and Control Variates in Multiple-Comparison Procedures , 1991, Oper. Res..

[4]  Bruce E. Stuckman,et al.  A global search method for optimizing nonlinear systems , 1988, IEEE Trans. Syst. Man Cybern..

[5]  Hakan S. Sazak,et al.  Wiley Encyclopedia of Operations Research and Management Science , 2013 .

[6]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[7]  Warren B. Powell,et al.  The Knowledge-Gradient Policy for Correlated Normal Beliefs , 2009, INFORMS J. Comput..

[8]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[9]  Michael James Sasena,et al.  Flexibility and efficiency enhancements for constrained global design optimization with kriging approximations. , 2002 .

[10]  Michael K. Gilson,et al.  Virtual Screening of Molecular Databases Using a Support Vector Machine , 2005, J. Chem. Inf. Model..

[11]  Chun-Hung Chen,et al.  Simulation Allocation for Determining the Best Design in the Presence of Correlated Sampling , 2007, INFORMS J. Comput..

[12]  A. Brix.  Bayesian Data Analysis, 2nd edn , 2005 .

[13]  A. C. Brown,et al.  V.—On the Connection between Chemical Constitution and Physiological Action. Part. I.—On the Physiological Action of the Salts of the Ammonium Bases, derived from Strychnia, Brucia, Thebaia, Codeia, Morphia, and Nicotia , 1870, Transactions of the Royal Society of Edinburgh.

[14]  Gunnar Rätsch,et al.  Active Learning in the Drug Discovery Process , 2001, NIPS.

[15]  N. Zheng,et al.  Global Optimization of Stochastic Black-Box Systems via Sequential Kriging Meta-Models , 2006, J. Glob. Optim..

[16]  J. Blake,et al.  On the Connection between Chemical Constitution and Physiological Action , 1886, Nature.

[17]  P. Frazier.  Learning with Dynamic Programming , 2011 .

[18]  Stephen E. Chick,et al.  New Two-Stage and Sequential Procedures for Selecting the Best Simulated System , 2001, Oper. Res..

[19]  J. Hsu.  Multiple Comparisons: Theory and Methods , 1996 .

[20]  D. Dennis,et al.  SDO : A Statistical Method for Global Optimization , 1997 .

[21]  Meir Glick,et al.  Streamlining lead discovery by aligning in silico and high-throughput screening. , 2006, Current opinion in chemical biology.

[22]  Louis Anthony Cox,et al.  Wiley encyclopedia of operations research and management science , 2011 .

[23]  T R Fraser,et al.  On the Connection Between Chemical Constitution and Physiological Action , 1886, Nature.

[24]  Jack P. C. Kleijnen.  Design and Analysis of Simulation Experiments , 2007 .

[25]  Ashwin Srinivasan,et al.  Drug Design by Machine Learning , 1995, Machine Intelligence 15.

[26]  Enver Yücesan,et al.  Discrete-event simulation optimization using ranking, selection, and multiple comparison procedures: A survey , 2003, TOMC.

[27]  Tapabrata Maiti,et al.  Bayesian Data Analysis (2nd ed.) (Book) , 2004 .

[28]  Singh,et al.  Quantitative structure-property relationships in pharmaceutical research - Part 1. , 2000, Pharmaceutical science & technology today.

[29]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[30]  Jonas Mockus,et al.  On Bayesian Methods for Seeking the Extremum , 1974, Optimization Techniques.

[31]  A. G. Perevozchikov.  The approximation of generalized stochastic gradients of random regular functions , 1992 .

[32]  B. Nelson,et al.  Using common random numbers for indifference-zone selection and multiple comparisons in simulation , 1995 .

[33]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[34]  G. Keserű,et al.  Integration of virtual and high throughput screening in lead discovery settings. , 2011, Combinatorial chemistry & high throughput screening.

[35]  Robert D. Kleinberg,et al.  Online decision problems with large strategy sets , 2005 .

[36]  Warren B. Powell,et al.  Approximate Dynamic Programming - Solving the Curses of Dimensionality , 2007 .

[37]  Harold J. Kushner,et al.  A new method of locating the maximum point of an arbitrary multipeak curve in the presence of noise , 1963 .

[38]  Jürgen Bajorath,et al.  Integration of virtual and high-throughput screening , 2002, Nature Reviews Drug Discovery.

[39]  Shane G. Henderson,et al.  Comparing two systems: Beyond common random numbers , 2008, 2008 Winter Simulation Conference.

[40]  Chun-Hung Chen,et al.  A gradient approach for smartly allocating computing budget for discrete event simulation , 1996, Proceedings Winter Simulation Conference.

[41]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[42]  R Katz,et al.  Application of the Free-Wilson technique to structurally related series of homologues. Quantitative structure-activity relationship studies of narcotic analgetics. , 1977, Journal of medicinal chemistry.

[43]  Barry L. Nelson,et al.  A fully sequential procedure for indifference-zone selection in simulation , 2001, TOMC.

[44]  S. Gupta,et al.  Bayesian look ahead one-stage sampling allocations for selection of the best population , 1996 .

[45]  Warren B. Powell,et al.  A Knowledge-Gradient Policy for Sequential Information Collection , 2008, SIAM J. Control. Optim..

[46]  Stephen E. Chick,et al.  New Procedures to Select the Best Simulated System Using Common Random Numbers , 2001, Manag. Sci..

[47]  A. ilinskas,et al.  One-Dimensional global optimization for observations with noise , 2005 .

[48]  D. Dennis,et al.  A statistical method for global optimization , 1992, [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics.

[49]  C. Hansch,et al.  p-σ-π Analysis. A Method for the Correlation of Biological Activity and Chemical Structure , 1964 .

[50]  Jürgen Branke,et al.  Sequential Sampling to Myopically Maximize the Expected Value of Information , 2010, INFORMS J. Comput..

[51]  Warren B. Powell,et al.  Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics) , 2007 .

[52]  Leslie Pack Kaelbling,et al.  Learning in embedded systems , 1993 .

[53]  S. Free,et al.  A MATHEMATICAL CONTRIBUTION TO STRUCTURE-ACTIVITY STUDIES. , 1964, Journal of medicinal chemistry.