Metric Validation and the Receptor-Relevant Subspace Concept. Pearlman, R. S. & Smith, K. M. J.~Chem.~Inf.~Comput.~Sci., 39:28--35, 1999. abstract bibtex Following brief comments regarding the advantages of cell-based diversity algorithms and the selection of low-dimensional chemistry-space metrics needed to implement such algorithms, the notion of metric validation is discussed. Activity-seeded, structure-based clustering is presented as an ideal approach for the validation of either high- or low-dimensional chemistry-space metrics when validation by computer-graphic visualization is not possible. Whereas typical methods for reducing the dimensionality of chemistry-space inevitably discard potentially important information, we present a simple yet novel algorithm for reducing dimensionality by identifying which axes (metrics) convey information related to affinity for a given receptor and which axes can be safely discarded as being irrelevant to the given receptor. This algorithm often reveals a three- or two-dimensional subspace of a (typically six-dimensional) BCUT chemistry-space and, thus, enables computer graphic visualization of the actual coordinates of active compounds and combinatorial libraries. Most significantly, we illustrate the importance of using receptor-relevant distances for identifying near neighbors of lead compounds, comparing libraries, and other diversity-related tasks.
@article{Pearlman:1999aa,
Abstract = { Following brief comments regarding the advantages of cell-based diversity
algorithms and the selection of low-dimensional chemistry-space metrics
needed to implement such algorithms, the notion of metric validation
is discussed. Activity-seeded, structure-based clustering is presented
as an ideal approach for the validation of either high- or low-dimensional
chemistry-space metrics when validation by computer-graphic visualization
is not possible. Whereas typical methods for reducing the dimensionality
of chemistry-space inevitably discard potentially important information,
we present a simple yet novel algorithm for reducing dimensionality
by identifying which axes (metrics) convey information related to
affinity for a given receptor and which axes can be safely discarded
as being irrelevant to the given receptor. This algorithm often reveals
a three- or two-dimensional subspace of a (typically six-dimensional)
BCUT chemistry-space and, thus, enables computer graphic visualization
of the actual coordinates of active compounds and combinatorial libraries.
Most significantly, we illustrate the importance of using receptor-relevant
distances for identifying near neighbors of lead compounds, comparing
libraries, and other diversity-related tasks. },
Author = {Pearlman, R. S. and Smith, K. M.},
Date-Added = {2007-12-11 17:01:03 -0500},
Date-Modified = {2008-04-25 11:50:54 -0400},
Journal = {J.~Chem.~Inf.~Comput.~Sci.},
Keywords = {diversity; cell; binning; bin},
Owner = {rajarshi},
Pages = {28--35},
Timestamp = {2007.04.11},
Title = {Metric Validation and the Receptor-Relevant Subspace Concept},
Volume = {39},
Year = {1999}}
Downloads: 0
{"_id":"ueLZG2htDiLXr6bE4","bibbaseid":"pearlman-smith-metricvalidationandthereceptorrelevantsubspaceconcept-1999","downloads":0,"creationDate":"2016-02-18T13:03:37.798Z","title":"Metric Validation and the Receptor-Relevant Subspace Concept","author_short":["Pearlman, R. S.","Smith, K. M."],"year":1999,"bibtype":"article","biburl":"https://dl.dropboxusercontent.com/u/26998770/main.bib","bibdata":{"bibtype":"article","type":"article","abstract":"Following brief comments regarding the advantages of cell-based diversity algorithms and the selection of low-dimensional chemistry-space metrics needed to implement such algorithms, the notion of metric validation is discussed. Activity-seeded, structure-based clustering is presented as an ideal approach for the validation of either high- or low-dimensional chemistry-space metrics when validation by computer-graphic visualization is not possible. Whereas typical methods for reducing the dimensionality of chemistry-space inevitably discard potentially important information, we present a simple yet novel algorithm for reducing dimensionality by identifying which axes (metrics) convey information related to affinity for a given receptor and which axes can be safely discarded as being irrelevant to the given receptor. This algorithm often reveals a three- or two-dimensional subspace of a (typically six-dimensional) BCUT chemistry-space and, thus, enables computer graphic visualization of the actual coordinates of active compounds and combinatorial libraries. Most significantly, we illustrate the importance of using receptor-relevant distances for identifying near neighbors of lead compounds, comparing libraries, and other diversity-related tasks. ","author":[{"propositions":[],"lastnames":["Pearlman"],"firstnames":["R.","S."],"suffixes":[]},{"propositions":[],"lastnames":["Smith"],"firstnames":["K.","M."],"suffixes":[]}],"date-added":"2007-12-11 17:01:03 -0500","date-modified":"2008-04-25 11:50:54 -0400","journal":"J.~Chem.~Inf.~Comput.~Sci.","keywords":"diversity; cell; binning; bin","owner":"rajarshi","pages":"28--35","timestamp":"2007.04.11","title":"Metric Validation and the Receptor-Relevant Subspace Concept","volume":"39","year":"1999","bibtex":"@article{Pearlman:1999aa,\n\tAbstract = { Following brief comments regarding the advantages of cell-based diversity\n\talgorithms and the selection of low-dimensional chemistry-space metrics\n\tneeded to implement such algorithms, the notion of metric validation\n\tis discussed. Activity-seeded, structure-based clustering is presented\n\tas an ideal approach for the validation of either high- or low-dimensional\n\tchemistry-space metrics when validation by computer-graphic visualization\n\tis not possible. Whereas typical methods for reducing the dimensionality\n\tof chemistry-space inevitably discard potentially important information,\n\twe present a simple yet novel algorithm for reducing dimensionality\n\tby identifying which axes (metrics) convey information related to\n\taffinity for a given receptor and which axes can be safely discarded\n\tas being irrelevant to the given receptor. This algorithm often reveals\n\ta three- or two-dimensional subspace of a (typically six-dimensional)\n\tBCUT chemistry-space and, thus, enables computer graphic visualization\n\tof the actual coordinates of active compounds and combinatorial libraries.\n\tMost significantly, we illustrate the importance of using receptor-relevant\n\tdistances for identifying near neighbors of lead compounds, comparing\n\tlibraries, and other diversity-related tasks. },\n\tAuthor = {Pearlman, R. S. and Smith, K. M.},\n\tDate-Added = {2007-12-11 17:01:03 -0500},\n\tDate-Modified = {2008-04-25 11:50:54 -0400},\n\tJournal = {J.~Chem.~Inf.~Comput.~Sci.},\n\tKeywords = {diversity; cell; binning; bin},\n\tOwner = {rajarshi},\n\tPages = {28--35},\n\tTimestamp = {2007.04.11},\n\tTitle = {Metric Validation and the Receptor-Relevant Subspace Concept},\n\tVolume = {39},\n\tYear = {1999}}\n\n","author_short":["Pearlman, R. S.","Smith, K. M."],"key":"Pearlman:1999aa","id":"Pearlman:1999aa","bibbaseid":"pearlman-smith-metricvalidationandthereceptorrelevantsubspaceconcept-1999","role":"author","urls":{},"keyword":["diversity; cell; binning; bin"],"downloads":0},"search_terms":["metric","validation","receptor","relevant","subspace","concept","pearlman","smith"],"keywords":["diversity; cell; binning; bin"],"authorIDs":[],"dataSources":["c5japf9eAQRaeMS4h"]}