Pregled bibliografske jedinice broj: 1191316
Machine learning determined models of inhibitory activities for fluorinated Cinchona alkaloids
Machine learning determined models of inhibitory activities for fluorinated Cinchona alkaloids // 6. Simpozij studenata doktorskih studija PMF-a: Knjiga sažetaka / 6th Faculty of Science PhD Student Symposium: Book of Abstracts / Schneider, Petra (ur.).
Zagreb: Prirodoslovno-matematički fakultet Sveučilišta u Zagrebu, 2022. str. 164-165 (predavanje, domaća recenzija, sažetak, znanstveni)
CROSBI ID: 1191316 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Machine learning determined models of inhibitory
activities for fluorinated Cinchona alkaloids
Autori
Mikelić, Ana ; Ramić, Alma ; Primožič, Ines ; Hrenar, Tomica
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni
Izvornik
6. Simpozij studenata doktorskih studija PMF-a: Knjiga sažetaka / 6th Faculty of Science PhD Student Symposium: Book of Abstracts
/ Schneider, Petra - Zagreb : Prirodoslovno-matematički fakultet Sveučilišta u Zagrebu, 2022, 164-165
ISBN
978-953-6076-93-2
Skup
6. Simpozij studenata doktorskih studija PMF-a = 6th Faculty of Science PhD Student Symposium
Mjesto i datum
Zagreb, Hrvatska, 23.04.2022. - 24.04.2022
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Domaća recenzija
Ključne riječi
inhibitory activity, Cinchona alkaloids, machine learning, principal component analysis, potential energy surfaces, ab initio molecular dynamics, multivariate linear regression
Sažetak
A series of 25 fluorinated Cinchona alkaloids derivatives was theoretically investigated by calculation of their potential energy surfaces (PES). PES for all compounds were sampled by performing molecular dynamics simulations [1] and then decomposed by principal component analysis. Each PES was represented by three points in the newly determined reduced space. These points were used as independent variables for establishing activity/PES regression models whereas previously measured inhibitory activities towards human acetyl- and butyrylcholinesterase were used as dependent variables. Multivariate linear regression models were built by applying an extensive machine learning protocol where linear combinations of original variables as well as their higherorder polynomial terms were used. Leave-one-out cross- validation (LOO-CV) was used to validate obtained models [2, 3]. Optimal activity/PES models were selected based on the adjusted R 2, predicted R 2 and the LOO-CV mean squared error (Figure 1).
Izvorni jezik
Engleski
Znanstvena područja
Kemija
POVEZANOST RADA
Projekti:
HRZZ-IP-2016-06-3775 - Aktivnošću i in silico usmjeren dizajn malih bioaktivnih molekula (ADESIRE) (Hrenar, Tomica, HRZZ - 2016-06) ( CroRIS)
Ustanove:
Prirodoslovno-matematički fakultet, Zagreb