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

Modified linear regression predicts drug-target interactions accurately

K. Buza, L. Peška, J. Koller,

. 2020 ; 15 (4) : e0230726. [pub] 20200406

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc20025087

State-of-the-art approaches for the prediction of drug-target interactions (DTI) are based on various techniques, such as matrix factorisation, restricted Boltzmann machines, network-based inference and bipartite local models (BLM). In this paper, we propose the framework of Asymmetric Loss Models (ALM) which is more consistent with the underlying chemical reality compared with conventional regression techniques. Furthermore, we propose to use an asymmetric loss model with BLM to predict drug-target interactions accurately. We evaluate our approach on publicly available real-world drug-target interaction datasets. The results show that our approach outperforms state-of-the-art DTI techniques, including recent versions of BLM.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc20025087
003      
CZ-PrNML
005      
20201222155042.0
007      
ta
008      
201125s2020 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1371/journal.pone.0230726 $2 doi
035    __
$a (PubMed)32251481
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Buza, Krisztian $u Faculty of Informatics, ELTE - Eötvös Loránd University, Budapest, Hungary. Center for the Study of Complexity, Babes-Bolyai University, Cluj Napoca, Romania.
245    10
$a Modified linear regression predicts drug-target interactions accurately / $c K. Buza, L. Peška, J. Koller,
520    9_
$a State-of-the-art approaches for the prediction of drug-target interactions (DTI) are based on various techniques, such as matrix factorisation, restricted Boltzmann machines, network-based inference and bipartite local models (BLM). In this paper, we propose the framework of Asymmetric Loss Models (ALM) which is more consistent with the underlying chemical reality compared with conventional regression techniques. Furthermore, we propose to use an asymmetric loss model with BLM to predict drug-target interactions accurately. We evaluate our approach on publicly available real-world drug-target interaction datasets. The results show that our approach outperforms state-of-the-art DTI techniques, including recent versions of BLM.
650    _2
$a výpočetní biologie $x metody $7 D019295
650    _2
$a lineární modely $7 D016014
650    12
$a cílená molekulární terapie $7 D058990
650    _2
$a léčivé přípravky $x metabolismus $7 D004364
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Peška, Ladislav $u Department of Software Engineering, Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic.
700    1_
$a Koller, Júlia $u Institute of Genomic Medicine and Rare Disorders, Semmelweis University, Budapest, Hungary.
773    0_
$w MED00180950 $t PloS one $x 1932-6203 $g Roč. 15, č. 4 (2020), s. e0230726
856    41
$u https://pubmed.ncbi.nlm.nih.gov/32251481 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20201125 $b ABA008
991    __
$a 20201222155039 $b ABA008
999    __
$a ok $b bmc $g 1599232 $s 1115773
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2020 $b 15 $c 4 $d e0230726 $e 20200406 $i 1932-6203 $m PLoS One $n PLoS One $x MED00180950
LZP    __
$a Pubmed-20201125

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace