TY  - JOUR
AU  - Erić, Slavica
AU  - Kalinić, Marko
AU  - Ilić, K.
AU  - Zloh, Mire
PY  - 2014
UR  - https://farfar.pharmacy.bg.ac.rs/handle/123456789/2133
AB  - P-glycoprotein (P-gp/ABCB1) and breast cancer resistance protein (BCRP/ABCG2) are two members of the adenosine triphosphate (ATP) binding cassette (ABC) family of transporters which function as membrane efflux transporters and display considerable substrate promiscuity. Both are known to significantly influence the absorption, distribution and elimination of drugs, mediate drug-drug interactions and contribute to multiple drug resistance (MDR) of cancer cells. Correspondingly, timely characterization of the interaction of novel leads and drug candidates with these two transporters is of great importance. In this study, several computational classification models for prediction of transport and inhibition of P-gp and BCRP, respectively, were developed based on newly compiled and critically evaluated experimental data. Artificial neural network (ANN) and support vector machine (SVM) ensemble based models were explored, as well as knowledge-based approaches to descriptor selection. The average overall classification accuracy of best performing models was 82% for P-gp transport, 88% for BCRP transport, 89% for P-gp inhibition and 87% for BCRP inhibition, determined across an array of different test sets. An analysis of substrate overlap between P-gp and BCRP was also performed. The accuracy, simplicity and interpretability of the proposed models suggest that they could be of significant utility in the drug discovery and development settings.
PB  - Taylor & Francis Ltd, Abingdon
T2  - Saudi Pharmaceutical Journal
T1  - Computational classification models for predicting the interaction of drugs with P-glycoprotein and breast cancer resistance protein
VL  - 25
IS  - 12
SP  - 955
EP  - 982
DO  - 10.1080/1062936X.2014.976265
ER  - 

@article{
author = "Erić, Slavica and Kalinić, Marko and Ilić, K. and Zloh, Mire",
year = "2014",
abstract = "P-glycoprotein (P-gp/ABCB1) and breast cancer resistance protein (BCRP/ABCG2) are two members of the adenosine triphosphate (ATP) binding cassette (ABC) family of transporters which function as membrane efflux transporters and display considerable substrate promiscuity. Both are known to significantly influence the absorption, distribution and elimination of drugs, mediate drug-drug interactions and contribute to multiple drug resistance (MDR) of cancer cells. Correspondingly, timely characterization of the interaction of novel leads and drug candidates with these two transporters is of great importance. In this study, several computational classification models for prediction of transport and inhibition of P-gp and BCRP, respectively, were developed based on newly compiled and critically evaluated experimental data. Artificial neural network (ANN) and support vector machine (SVM) ensemble based models were explored, as well as knowledge-based approaches to descriptor selection. The average overall classification accuracy of best performing models was 82% for P-gp transport, 88% for BCRP transport, 89% for P-gp inhibition and 87% for BCRP inhibition, determined across an array of different test sets. An analysis of substrate overlap between P-gp and BCRP was also performed. The accuracy, simplicity and interpretability of the proposed models suggest that they could be of significant utility in the drug discovery and development settings.",
publisher = "Taylor & Francis Ltd, Abingdon",
journal = "Saudi Pharmaceutical Journal",
title = "Computational classification models for predicting the interaction of drugs with P-glycoprotein and breast cancer resistance protein",
volume = "25",
number = "12",
pages = "955-982",
doi = "10.1080/1062936X.2014.976265"
}

Erić, S., Kalinić, M., Ilić, K.,& Zloh, M.. (2014). Computational classification models for predicting the interaction of drugs with P-glycoprotein and breast cancer resistance protein. in Saudi Pharmaceutical Journal
Taylor & Francis Ltd, Abingdon., 25(12), 955-982.
https://doi.org/10.1080/1062936X.2014.976265

Erić S, Kalinić M, Ilić K, Zloh M. Computational classification models for predicting the interaction of drugs with P-glycoprotein and breast cancer resistance protein. in Saudi Pharmaceutical Journal. 2014;25(12):955-982.
doi:10.1080/1062936X.2014.976265 .

Erić, Slavica, Kalinić, Marko, Ilić, K., Zloh, Mire, "Computational classification models for predicting the interaction of drugs with P-glycoprotein and breast cancer resistance protein" in Saudi Pharmaceutical Journal, 25, no. 12 (2014):955-982,
https://doi.org/10.1080/1062936X.2014.976265 . .

TY  - CONF
AU  - Petrić, M.
AU  - Ilić, K.
AU  - Tasić, Ljiljana
PY  - 2009
UR  - https://farfar.pharmacy.bg.ac.rs/handle/123456789/1264
AB  - OBJECTIVES: To investigate drug use six months before (SMBP) and during preg-
nancy (DP) among Serbian pregnant women (SPW). METHODS: Pharmacy based
cross-sectional survey was conducted among SPW between March through April
2009. Specially designed questionnaire was used for collecting data on socio-demo-
graphics, health status, and drug (Rx and over the counter) use. Vitamin and iron
supplements were not included in the analysis. RESULTS: 260 SPW completed the
questionnaire. 69.6% of SPW were 25–34 years old, 75.8% lived in the city area, the
majority were high school or college graduates, and 55.4% were pregnant with their
first child. 9.4% of SPW had a chronic disease. There was not a statistically significant
decrease in the percentage of SPW taking drugs DP compared to SMBP (53.9% and
53.0%, respectively), as well as in an average number of drugs taken (1.54 o 0.73 and
1.45 o 0.66 drugs/women, respectively (range 1 to 4 before and during pregnancy)).
The most frequently used drug classes by SPW were: analgetics/antipyretics, hormones,
antiinfectives, tocolitics and anti-hypertensives (25.5%, 25.5%, 19.7%, 13.7%, and
7.3%, respectively). The most frequently used analgetic/antipyretic was paracetamol
(62.83%), while the most frequently used anti-infectives were penicillins and cepha-
losporins (77.0%). The only used tocolitics were fenoterol and hexoprenaline and the
only used hormones were dydrogesterone and progesterone. Drugs that were used
belonged to these FDA fetal risk categories B, C, and D (diazepam, alprazolam and
diclofenac in the 3 rd trimester) (52.6%, 26.3%, and 15.8% respectively). SPW did not
use drugs in the FDA category X. Before pregnancy folic acid usage was low (5.5%
PW) while during the 1st, 2nd and 3rd trimester of pregnancy usage was 69.96%,
15.05%, 5.93%, respectively. CONCLUSIONS: Differences in drug use DP and
SMBP among SPW was negligible. The most frequently used drug classes during
pregnancy were: analgetics/antipyretics, hormones, antiinfectives, tocolitics and
antihypertensives.
PB  - Elsevier
C3  - Value in Health
T1  - Drug use before and during pregnancy in republic of Serbia
VL  - 12
IS  - 7
SP  - A296
EP  - A296
DO  - 10.1016/S1098-3015(10)74452-1
ER  - 

@conference{
author = "Petrić, M. and Ilić, K. and Tasić, Ljiljana",
year = "2009",
abstract = "OBJECTIVES: To investigate drug use six months before (SMBP) and during preg-
nancy (DP) among Serbian pregnant women (SPW). METHODS: Pharmacy based
cross-sectional survey was conducted among SPW between March through April
2009. Specially designed questionnaire was used for collecting data on socio-demo-
graphics, health status, and drug (Rx and over the counter) use. Vitamin and iron
supplements were not included in the analysis. RESULTS: 260 SPW completed the
questionnaire. 69.6% of SPW were 25–34 years old, 75.8% lived in the city area, the
majority were high school or college graduates, and 55.4% were pregnant with their
first child. 9.4% of SPW had a chronic disease. There was not a statistically significant
decrease in the percentage of SPW taking drugs DP compared to SMBP (53.9% and
53.0%, respectively), as well as in an average number of drugs taken (1.54 o 0.73 and
1.45 o 0.66 drugs/women, respectively (range 1 to 4 before and during pregnancy)).
The most frequently used drug classes by SPW were: analgetics/antipyretics, hormones,
antiinfectives, tocolitics and anti-hypertensives (25.5%, 25.5%, 19.7%, 13.7%, and
7.3%, respectively). The most frequently used analgetic/antipyretic was paracetamol
(62.83%), while the most frequently used anti-infectives were penicillins and cepha-
losporins (77.0%). The only used tocolitics were fenoterol and hexoprenaline and the
only used hormones were dydrogesterone and progesterone. Drugs that were used
belonged to these FDA fetal risk categories B, C, and D (diazepam, alprazolam and
diclofenac in the 3 rd trimester) (52.6%, 26.3%, and 15.8% respectively). SPW did not
use drugs in the FDA category X. Before pregnancy folic acid usage was low (5.5%
PW) while during the 1st, 2nd and 3rd trimester of pregnancy usage was 69.96%,
15.05%, 5.93%, respectively. CONCLUSIONS: Differences in drug use DP and
SMBP among SPW was negligible. The most frequently used drug classes during
pregnancy were: analgetics/antipyretics, hormones, antiinfectives, tocolitics and
antihypertensives.",
publisher = "Elsevier",
journal = "Value in Health",
title = "Drug use before and during pregnancy in republic of Serbia",
volume = "12",
number = "7",
pages = "A296-A296",
doi = "10.1016/S1098-3015(10)74452-1"
}

Petrić, M., Ilić, K.,& Tasić, L.. (2009). Drug use before and during pregnancy in republic of Serbia. in Value in Health
Elsevier., 12(7), A296-A296.
https://doi.org/10.1016/S1098-3015(10)74452-1

Petrić M, Ilić K, Tasić L. Drug use before and during pregnancy in republic of Serbia. in Value in Health. 2009;12(7):A296-A296.
doi:10.1016/S1098-3015(10)74452-1 .

Petrić, M., Ilić, K., Tasić, Ljiljana, "Drug use before and during pregnancy in republic of Serbia" in Value in Health, 12, no. 7 (2009):A296-A296,
https://doi.org/10.1016/S1098-3015(10)74452-1 . .