Strip mining for molecules
Published 25 June 2003
Mark J. Embrechts, F. Arciniegas, Mucize Eriç Özdemir, Michinari Momma, Curt M. Breneman, Larry O Lockwood
Citations2
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Data strip mining for QSAR modeling is introduced, a general approach for feature selection and predictive modeling based on successive stages of feature elimination done by performing a sensitivity analysis to a predictive model.
Abstract
Quantitative structure-activity relationship (QSAR) problems deal with "in-silico" chemical design for the virtual invention of novel pharmaceuticals. The goal of QSAR is to predict the bioactivities of molecules based on a set of descriptive features. QSAR problems are notoriously challenging for machine learning because a typical QSAR predictive data mining problem set is characterized by a large number of descriptive features (300-1000), often for a relatively small number of molecules (50-300). This paper introduces data strip mining for QSAR modeling. Strip mining is a general approach for feature selection and predictive modeling based on successive stages of feature elimination done by performing a sensitivity analysis to a predictive model.
Keywords
ChemistryComputer Science
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Artificial IntelligenceWrappers for feature subset selection
8,925 Citations1997Ron Kohavi, George H. John
The wrapper method searches for an optimal feature subset tailored to a particular algorithm and a domain and compares the wrapper approach to induction without feature subset selection and to Relief, a filter approach tofeature subset selection.
Analytica Chimica ActaPartial least-squares regression: a tutorial
6,934 Citations1986Paul Geladi, Bruce R. Kowalski
Optimal Brain Damage
2,613 Citations1989Yann LeCun, John S. Denker +1 more
A class of practical and nearly optimal schemes for adapting the size of a neural network by using second-derivative information to make a tradeoff between network complexity and training set error is derived.
SIAM Journal on Scientific and Statistical ComputingThe Collinearity Problem in Linear Regression. The Partial Least Squares (PLS) Approach to Generalized Inverses
2,520 Citations1984Svante Wold, Axel Ruhe +2 more
Journal of Chemical Information and Computer SciencesElectrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State Information
754 Citations1995Lowell H. Hall, Lemont B. Kier
Topics in Current ChemistryTopological indices for structure-activity correlations
325 Citations2007Alexandrù T. Balaban, Ioan Moţoc +2 more
Chemical ReviewsComparative Quantitative Structure−Activity Relationship Studies on Anti-HIV Drugs
248 Citations1999Rajni Garg, Satya P. Gupta +4 more
Sensitivity analysis for minimization of input data dimension for feedforward neural network
199 Citations2002Jacek M. Żurada, A. Malinowski +1 more
The search for redundant data components is performed for networks with continuous outputs and is based on the concept in sensitivity of linearized neural networks, which could lead to smaller networks and reduced-size data vectors.
Journal of Medicinal ChemistryComputation of Brain−Blood Partitioning of Organic Solutes via Free Energy Calculations
198 Citations1996Franco Lombardo, James F. Blake +1 more
The ratio of brain-blood partitioning, log(Cbrain/Cblood) (log BB), of a series of compounds that range from simple solutes to histamine H2 antagonists was correlated with computed solvation free energy in water (delta G degree W).
IEEE Transactions on Neural NetworksData strip mining for the virtual design of pharmaceuticals with neural networks
146 Citations2000Robert Kewley, Mark J. Embrechts +1 more
Elimination of variables through neural network sensitivity analysis and predicting performance through model cross-validation allows the analyst to reduce the number of inputs and improve the model's predictive ability at the same time.
ACS symposium seriesClassical and Three-Dimensional QSAR in Agrochemistry
105 Citations1995
This reviewer found it particularly impressive that, in almost every case, techniques are presented with worked-out examples and in sufficient detail that a reader could not only follow the examples but also actually try out a technique in his or her own research.
Support Vector Machines for Large-Scale Regression Problems
105 Citations2000Ronan Collobert, Samy Bengio
Computers & ChemistryElectron density modeling of large systems using the transferable atom equivalent method
95 Citations1995Curt M. Breneman, Tracy R. Thompson +2 more
The transferable atom equivalent (TAB) modeling method is a resource-efficient alternative to routine HF/SCF ab initio calculations and a brief analysis of the binding of the immunosuppressant drug FK506 with FKBP is presented as an example of large-molecule/small-Molecule interaction modeling using the TAE method.
Journal of Computational ChemistryQSPR analysis of HPLC column capacity factors for a set of high-energy materials using electronic van der waals surface property descriptors computed by transferable atom equivalent method
85 Citations1997Curt M. Breneman, Marlon Rhem
5th Symposium on Multidisciplinary Analysis and OptimizationDerivative-free pattern search methods for multidisciplinary design problems
42 Citations1994J. E. Dennis, Virginia Torczon
An introduction to pattern search methods is given, to describe the features they share by using coordinate search, one of the earliest and best-known (if not as effective)pattern search methods, as an example, and to review some recent developments that suggest that these methods can be extended to handle problems with a mix of continuous and discrete variables-another situation that can arise in MDO problems.
Journal of Medicinal ChemistrySome electronic factors in drug-receptor interactions
32 Citations1968Arthur Cammarata