Pregled bibliografske jedinice broj: 1232712
Prediction of Drug-Kinase Binding Affinities with Focus on Conserved Protein Kinase Domain
Prediction of Drug-Kinase Binding Affinities with Focus on Conserved Protein Kinase Domain // ISMB/ECCB 2021 (29th Annual Conference)
Virtual Event, 2021. (poster, međunarodna recenzija, neobjavljeni rad, znanstveni)
CROSBI ID: 1232712 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Prediction of Drug-Kinase Binding Affinities with
Focus on Conserved Protein Kinase Domain
Autori
Oršolić, Davor ; Lučić, Bono ; Stepanić, Višnja ; Šmuc, Tomislav
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, neobjavljeni rad, znanstveni
Skup
ISMB/ECCB 2021 (29th Annual Conference)
Mjesto i datum
Virtual Event, 25.07.2021. - 30.07.2021
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
kinase ; binding affinity
Sažetak
Previous approaches implemented on drug-kinase binding affinity benchmark datasets show poor performance on rigorous test scenarios with unseen small compounds or protein kinase targets - thus limiting their real-world application. We represent methodology which relies on an ensemble approach, XGBoost trained on fingerprint based and protein kinase domain sequence-based similarity features - and graph convolutional networks (GCN) as more advanced representation learning predictive methodology. To assess the uncertainty surrounding model predictions, we defined a structure-based applicability domain with a focus on density of compound space in the training set.
Izvorni jezik
Engleski
Znanstvena područja
Biotehnologija, Interdisciplinarne biotehničke znanosti
POVEZANOST RADA
Projekti:
EK-KF-KK.01.1.1.01.0002 - Bioprospecting Jadranskog mora (Jerković, Igor; Dragović-Uzelac, Verica; Šantek, Božidar; Čož-Rakovac, Rozelinda; Kraljević Pavelić, Sandra; Jokić, Stela, EK ) ( CroRIS)
Ustanove:
Institut "Ruđer Bošković", Zagreb
