Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Sparse Proteomics Analysis - a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data

TO. Conrad, M. Genzel, N. Cvetkovic, N. Wulkow, A. Leichtle, J. Vybiral, G. Kutyniok, C. Schütte,

. 2017 ; 18 (1) : 160. [pub] 20170309

Jazyk angličtina Země Anglie, Velká Británie

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc17030981

BACKGROUND: High-throughput proteomics techniques, such as mass spectrometry (MS)-based approaches, produce very high-dimensional data-sets. In a clinical setting one is often interested in how mass spectra differ between patients of different classes, for example spectra from healthy patients vs. spectra from patients having a particular disease. Machine learning algorithms are needed to (a) identify these discriminating features and (b) classify unknown spectra based on this feature set. Since the acquired data is usually noisy, the algorithms should be robust against noise and outliers, while the identified feature set should be as small as possible. RESULTS: We present a new algorithm, Sparse Proteomics Analysis (SPA), based on the theory of compressed sensing that allows us to identify a minimal discriminating set of features from mass spectrometry data-sets. We show (1) how our method performs on artificial and real-world data-sets, (2) that its performance is competitive with standard (and widely used) algorithms for analyzing proteomics data, and (3) that it is robust against random and systematic noise. We further demonstrate the applicability of our algorithm to two previously published clinical data-sets.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc17030981
003      
CZ-PrNML
005      
20171030115906.0
007      
ta
008      
171025s2017 enk f 000 0|eng||
009      
AR
024    7_
$a 10.1186/s12859-017-1565-4 $2 doi
035    __
$a (PubMed)28274197
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a enk
100    1_
$a Conrad, Tim O F $u Department of Mathematics, Freie Universität Berlin, Arnimallee 6, Berlin, Germany. conrad@math.fu-berlin.de. Zuse Institute Berlin, Takustr. 7, Berlin, Germany. conrad@math.fu-berlin.de.
245    10
$a Sparse Proteomics Analysis - a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data / $c TO. Conrad, M. Genzel, N. Cvetkovic, N. Wulkow, A. Leichtle, J. Vybiral, G. Kutyniok, C. Schütte,
520    9_
$a BACKGROUND: High-throughput proteomics techniques, such as mass spectrometry (MS)-based approaches, produce very high-dimensional data-sets. In a clinical setting one is often interested in how mass spectra differ between patients of different classes, for example spectra from healthy patients vs. spectra from patients having a particular disease. Machine learning algorithms are needed to (a) identify these discriminating features and (b) classify unknown spectra based on this feature set. Since the acquired data is usually noisy, the algorithms should be robust against noise and outliers, while the identified feature set should be as small as possible. RESULTS: We present a new algorithm, Sparse Proteomics Analysis (SPA), based on the theory of compressed sensing that allows us to identify a minimal discriminating set of features from mass spectrometry data-sets. We show (1) how our method performs on artificial and real-world data-sets, (2) that its performance is competitive with standard (and widely used) algorithms for analyzing proteomics data, and (3) that it is robust against random and systematic noise. We further demonstrate the applicability of our algorithm to two previously published clinical data-sets.
650    _2
$a algoritmy $7 D000465
650    _2
$a studie případů a kontrol $7 D016022
650    _2
$a počítačová simulace $7 D003198
650    _2
$a databáze faktografické $7 D016208
650    _2
$a lidé $7 D006801
650    _2
$a strojové učení $7 D000069550
650    _2
$a teoretické modely $7 D008962
650    _2
$a nádory slinivky břišní $x diagnóza $x genetika $7 D010190
650    _2
$a proteomika $x metody $7 D040901
650    _2
$a reprodukovatelnost výsledků $7 D015203
650    _2
$a spektrometrie hmotnostní - ionizace laserem za účasti matrice $x metody $7 D019032
655    _2
$a časopisecké články $7 D016428
700    1_
$a Genzel, Martin $u Department of Mathematics, Technische Universität Berlin, Düsternbrooker Weg 20, Berlin, Germany.
700    1_
$a Cvetkovic, Nada $u Department of Mathematics, Freie Universität Berlin, Arnimallee 6, Berlin, Germany.
700    1_
$a Wulkow, Niklas $u Department of Mathematics, Freie Universität Berlin, Arnimallee 6, Berlin, Germany.
700    1_
$a Leichtle, Alexander $u Center of Laboratory Medicine, Inselspital - Bern University Hospital, Düsternbrooker Weg 20, Bern, 24105, Switzerland.
700    1_
$a Vybiral, Jan $u Department of Mathematical Analysis, Charles University, Düsternbrooker Weg 20, Prague, Czech Republic.
700    1_
$a Kutyniok, Gitta $u Department of Mathematics, Technische Universität Berlin, Düsternbrooker Weg 20, Berlin, Germany.
700    1_
$a Schütte, Christof $u Department of Mathematics, Freie Universität Berlin, Arnimallee 6, Berlin, Germany. Zuse Institute Berlin, Takustr. 7, Berlin, Germany.
773    0_
$w MED00008167 $t BMC bioinformatics $x 1471-2105 $g Roč. 18, č. 1 (2017), s. 160
856    41
$u https://pubmed.ncbi.nlm.nih.gov/28274197 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20171025 $b ABA008
991    __
$a 20171030115954 $b ABA008
999    __
$a ok $b bmc $g 1254574 $s 992008
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2017 $b 18 $c 1 $d 160 $e 20170309 $i 1471-2105 $m BMC bioinformatics $n BMC Bioinformatics $x MED00008167
LZP    __
$a Pubmed-20171025

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace