prikaz prve stranice dokumenta On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks
  Preuzmi
PDF 4.53 MB
Znanstveni rad - Izvorni znanstveni rad
On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks
Biomedicines, 11 (2023), 2; 1-22. https://doi.org/10.3390/biomedicines11020284
Baressi Šegota, Sandi; Lorencin, Ivan; Kovač, Zoran; Car, Zlatan

Citirajte ovaj rad

Baressi Šegota, S., Lorencin, I., Kovač, Z. i Car, Z. (2023). On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks. Biomedicines, 11. (2), 1-22. doi: 10.3390/biomedicines11020284

Baressi Šegota, Sandi, et al. "On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks." Biomedicines, vol. 11, br. 2, 2023, str. 1-22. https://doi.org/10.3390/biomedicines11020284

Baressi Šegota, Sandi, Ivan Lorencin, Zoran Kovač i Zlatan Car. "On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks." Biomedicines 11, br. 2 (2023): 1-22. https://doi.org/10.3390/biomedicines11020284

Baressi Šegota, S., et al. (2023) 'On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks', Biomedicines, 11(2), str. 1-22. doi: 10.3390/biomedicines11020284

Baressi Šegota S, Lorencin I, Kovač Z, Car Z. On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks. Biomedicines [Internet]. 2023. [pristupljeno 03.04.2024.];11(2):1-22. doi: 10.3390/biomedicines11020284

S. Baressi Šegota, I. Lorencin, Z. Kovač i Z. Car, "On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks", Biomedicines, vol. 11, br. 2, str. 1-22, 2023. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:271:218377. [Citirano: 03.04.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:271:218377
Prijavite se u repozitorij kako biste mogli spremiti objekt u svoju listu.
Podaci o radu
Naslov (engleski)On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks
AutorSandi Baressi Šegota
MBZ: 397955
AutorIvan Lorencin
MBZ: 380265
AutorZoran Kovač
AutorZlatan Car
MBZ: 259465
Autorova ustanovaSveučilište u Rijeci
(Fakultet dentalne medicine)
Znanstveno / umjetničko
područje, polje i grana		BIOMEDICINA I ZDRAVSTVO
Dentalna medicina
Znanstveno / umjetničko
područje, polje i grana		TEHNIČKE ZNANOSTI
Računarstvo
Znanstveno / umjetničko
područje, polje i grana		TEHNIČKE ZNANOSTI
Temeljne tehničke znanosti
Znanstveno / umjetničko
područje, polje i grana		INTERDISCIPLINARNA PODRUČJA ZNANOSTI
Biotehnologija u biomedicini (prirodno područje, biomedicina i zdravstvo, biotehničko područje)
Sažetak (engleski)
In the case of pandemics such as COVID-19, the rapid development of medicines addressing the symptoms is necessary to alleviate the pressure on the medical system. One of the key steps in medicine evaluation is the determination of pIC50 factor, which is a negative logarithmic expression of the half maximal inhibitory concentration (IC50). Determining this value can be a lengthy and complicated process. A tool allowing for a quick approximation of pIC50 based on the molecular makeup of medicine could be valuable. In this paper, the creation of the artificial intelligence (AI)-based model is performed using a publicly available dataset of molecules and their pIC50 values. The modeling algorithms used are artificial and convolutional neural networks (ANN and CNN). Three approaches are tested—modeling using just molecular properties (MP), encoded SMILES representation of the molecule, and the combination of both input types. Models are evaluated using the coefficient of determination (R2) and mean absolute percentage error (MAPE) in a five-fold cross-validation scheme to assure the validity of the results. The obtained models show that the highest quality regression (R2¯¯¯¯=0.99, σR2¯¯¯¯=0.001 ; MAPE¯¯¯¯¯¯¯¯¯¯¯=0.009%, σMAPE¯¯¯¯¯¯¯¯¯¯¯¯=0.009), by a large margin, is obtained when using a hybrid neural network trained with both MP and SMILES.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran - međunarodna recenzija
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaBiomedicines
Brojčani podacivol. 11, br. 2, str. 1-22
p-ISSN2227-9059
DOIhttps://doi.org/10.3390/biomedicines11020284
URN:NBNurn:nbn:hr:271:218377
Datum objave publikacije2023
URL dokumentahttp://bib.irb.hr/1246979
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Imenovanje 4.0 međunarodna (CC BY 4.0)
Datum i vrijeme pohrane2023-01-31 12:03:54