Mathematical correction for fingerprint similarity measures to improve chemical retrieval.

Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Abstract Text:

S Joshua Swamidass,Pierre Baldi,

In many modern chemoinformatics systems, molecules are represented by long binary fingerprint vectors recording the presence or absence of particular features or substructures, such as labeled paths or trees, in the molecular graphs. These long fingerprints are often compressed to much shorter fingerprints using a simple modulo operation. As the length of the fingerprints decreases, their typical density and overlap tend to increase, and so does any similarity measure based on overlap, such as the widely used Tanimoto similarity. Here we show that this correlation between shorter fingerprints and higher similarity can be thought of as a systematic error introduced by the fingerprint folding algorithm and that this systematic error can be corrected mathematically. More precisely, given two molecules and their compressed fingerprints of a given length, we show how a better estimate of their uncompressed overlap, hence of their similarity, can be derived to correct for this bias. We show how the correction can be implemented not only for the Tanimoto measure but also for all other commonly used measures. Experiments on various data sets and fingerprint sizes demonstrate how, with a negligible computational overhead, the correction noticeably improves the sensitivity and specificity of chemical retrieval.

Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Publishing Authors By Initials

SJ Swamidass,P Baldi,

For similar natural sciences: mathematics research abstracts see: natural sciences: mathematics research

PUBMED ID PMID:

MEDLINE DATE: 2007 May-Jun

Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Journal Published:

PUBLICATION TYPE: Research Support, U.S. Gov't,

Journal: Journal of chemical information and modeling

VOLUME: 47

Page Numbers: 952-64

Journal Abbreviation:

ISSN: 1549-9596

DAY: 20

MONTH: 04

YEAR: 2007

Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 101230060

Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Keywords Mesh Terms:

KEYWORDS: Mathematics

MESH TERMS: methods

Chemical & Substance for Abstract: Mathematical correction for fingerprint similarity measures to improve chemical retrieval. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Mathematical correction for fingerprint similarity measures to improve chemical retrieval.

AFFILIATION: Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, Irvine, California 92697-3435, USA.

Country: United States

AGENCY: United States NLM

GRANT: LM-07443-01

ACRONYM: LM

MEDLINETA: J Chem Inf Model

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Mathematical correction for fingerprint similarity measures to improve chemical retrieval Related Publications

• Adjuvant electrochemotherapy for the treatment of incompletely excised spontaneous canine sarcomas.
• Biphasic pulses enhance bleomycin efficacy in a spontaneous canine perianal tumors model.
• Bounds and algorithms for fast exact searches of chemical fingerprints in linear and sublinear time.
• Cell-cycle molecules in mesothelioma: an overview.
• ChemDB update--full-text search and virtual chemical space.
• Concentric hypertrophy of the left ventricle in resistance-trained athletes: 742: may 31 3:30 PM 3:45 PM.
• Cutaneous T-cell lymphoma in an African hedgehog (Atelerix albiventris).
• Distribution of the serine protease HtrA1 in normal human tissues.
• Effects of rumen-protected choline supplementation in periparturient dairy goats.
• Electrochemotherapy for localized lymphoma: a preliminary study in companion animals.
• From protein microarrays to diagnostic antigen discovery: a study of the pathogen Francisella tularensis.
• Gradient descent learning algorithm overview: a general dynamical systems perspective.
• How noisy and replicable are DNA microarry data?
• Improved residue contact prediction using support vector machines and a large feature set.
• Local control and distant metastasis after electrochemotherapy of a canine anal melanoma.
• Mathematical correction for fingerprint similarity measures to improve chemical retrieval.
• Minimizing the overlap problem in protein NMR: a computational framework for precision amino acid labeling.
• On the role of breastfeeding in health promotion and the prevention of allergic diseases.
• One- to four-dimensional kernels for virtual screening and the prediction of physical, chemical, and biological properties.
• Patterns of tumor response in canine and feline cancer patients treated with electrochemotherapy: preclinical data for the standardization of this treatment in pets and humans.
• Potential role of electrochemotherapy for the treatment of soft tissue sarcoma: first insights from preclinical studies in animals.
• Reduced Leg Blood Flow during Submaximal Exercise in Type 2 Diabetes.
• Reduction in aerobic capacity and cardiac output in diabetic adolescents: 747: may 31 4:45 PM 5:00 PM.
• Surgery and electrochemotherapy of a high-grade soft tissue sarcoma in a dog.
• TMBpro: secondary structure, beta-contact and tertiary structure prediction of transmembrane beta-barrel proteins.
• The fixed-size Luria-Delbruck model with a nonzero death rate.
• Two-dimensional phase unwrapping by quad-tree decomposition.
• [Not Available.]
• [Origin and evolution of social insurance legislation in Italy.]
• [Use of polythiolactic acids in the prevention and treatment of chronic mercury poisoning.]