Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure.

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Abstract Text:

Darrin P Lewis,Tony Jebara,William Stafford Noble,

MOTIVATION: Drawing inferences from large, heterogeneous sets of biological data requires a theoretical framework that is capable of representing, e.g. DNA and protein sequences, protein structures, microarray expression data, various types of interaction networks, etc. Recently, a class of algorithms known as kernel methods has emerged as a powerful framework for combining diverse types of data. The support vector machine (SVM) algorithm is the most popular kernel method, due to its theoretical underpinnings and strong empirical performance on a wide variety of classification tasks. Furthermore, several recently described extensions allow the SVM to assign relative weights to various datasets, depending upon their utilities in performing a given classification task. RESULTS: In this work, we empirically investigate the performance of the SVM on the task of inferring gene functional annotations from a combination of protein sequence and structure data. Our results suggest that the SVM is quite robust to noise in the input datasets. Consequently, in the presence of only two types of data, an SVM trained from an unweighted combination of datasets performs as well or better than a more sophisticated algorithm that assigns weights to individual data types. Indeed, for this simple case, we can demonstrate empirically that no solution is significantly better than the naive, unweighted average of the two datasets. On the other hand, when multiple noisy datasets are included in the experiment, then the naive approach fares worse than the weighted approach. Our results suggest that for many applications, a naive unweighted sum of kernels may be sufficient. AVAILABILITY: http://noble.gs.washington.edu/proj/seqstruct

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Publishing Authors By Initials

DP Lewis,T Jebara,WS Noble,

For similar information science: computing methodologies: software research abstracts see: information science: computing methodologies: software research

PUBMED ID PMID:

MEDLINE DATE:

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Journal Published:

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

Journal: Bioinformatics (Oxford, England)

VOLUME: 22

Page Numbers: 2753-60

Journal Abbreviation: Bioinformatics

ISSN: 1460-2059

DAY: 11

MONTH: 09

YEAR: 2006

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 9808944

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Keywords Mesh Terms:

KEYWORDS: Software

MESH TERMS: methods

Chemical & Substance for Abstract: Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Information

Substance Name: Proteins

Registry Number: 0

Grant and Affiliation Information for Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure.

AFFILIATION: Department of Computer Science, Columbia University, New York, NY, 10027.

Country: England

AGENCY: United States NHGRI

GRANT: R33 HG003070

ACRONYM: HG

MEDLINETA: Bioinformatics

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure Related Publications

• A field study of the fertility of transported equine semen.
• A structural alignment kernel for protein structures.
• Benefits of sign language interpreting and text alternatives for deaf students' classroom learning.
• Blockade of chronic graft-versus-host disease by alloantigen-induced CD4+CD25+Foxp3+ regulatory T cells in nonlymphopenic hosts.
• CNS progenitor cells and oligodendrocytes are targets of chemotherapeutic agents in vitro and in vivo.
• Chemically diverse toxicants converge on Fyn and c-Cbl to disrupt precursor cell function.
• Comment on "Discrimination of shifts in a soil microbial community associated with TNT-contamination using a functional ANOVA of 16S rRNA hybridized to oligonucleotide microarrays".
• Detection of estrus with cows administered testosterone via injections and/or silastic implants.
• Development of a statistically robust quantification method for microorganisms in mixtures using oligonucleotide microarrays.
• Does external evaluation of laboratories improve patient safety?
• Ethics in the trenches: a multifaceted analysis of the stem cell debate.
• High variability in melting profiles from gel pad arrays.
• Hyaluronan in tissue injury and repair.
• Long term effects of early nutritional support with new enterotropic peptide-based formula vs. standard enteral formula in HIV-infected patients: randomised prospective trial Chlebowski R T, Beall G, Grovenor M, Lillington L, Weintraub N, Ambler C, Richar
• Modeling cardiac ischemia.
• Mutations of the betaN102 residue of HbA not only inhibit the ligand-linked T to Re state transition, but also profoundly affect the properties of the T state itself.
• Noninhibitory PAI-1 enhances plasmin-mediated matrix degradation both in vitro and in experimental nephritis.
• Oligonucleotide microarrays: widely applied--poorly understood.
• PAI-1 as a target in kidney disease.
• Revision of the nonequilibrium thermal dissociation and stringent washing approaches for identification of mixed nucleic acid targets by microarrays.
• Speech perception and localization with adults with bilateral sequential cochlear implants.
• Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure.
• The evidence base of palliative medicine: is inpatient palliative medicine evidence-based?
• The genetic transmission of alcoholism: implications for prevention.
• The maturation of rat brain myelin.
• The role of Toll-like receptors in non-infectious lung injury.
• The role of growth factors and related agents in accelerating fracture healing.
• Unsupervised segmentation of continuous genomic data.
• Use of forensic DNA evidence in prosecutors'offices.
• [Constituents of the essential oil of myrrh.]