Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites
Само за регистроване кориснике
2018
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Aripiprazole and ziprasidone are atypical antipsychotic drugs with the effect on positive and negative symptoms of schizophrenia, mania, and mixed states of bipolar disorder. Hansen's solubility parameters, (d), (p), and (h), which account for dispersive, polarizable, and hydrogen bonding contributions to the overall cohesive energy of a compound, are often used to assess pharmacokinetic properties of drugs. However, no data exist of solubility parameters for the drugs of interest in this study. Therefore, in the present study, partial least square regression (PLS), artificial neural networks (ANNs), regression trees (RT), boosted trees (BT), and random forests (RF) were applied to estimate Hansen's solubility parameters of ziprasidone, aripiprazole, and their impurities/metabolic derivatives, targeting their biopharmaceutical classes and absorption routes. A training set of 47 structurally diverse and pharmacologically active compounds and 290 molecular descriptors and pharmaceuticall...y important properties were used to build the prediction models. The modeling approaches were compared by the sum of ranking differences, using the consensus values as a reference for the unknowns and the experimentally determined values as a gold standard for the calibration set. In both instances, the PLS models, together with ANNs, demonstrated better performance than RT, BT and especially RF. Based on the best scored models, we were able to pinpoint the most probable absorption sites for each drug and the corresponding metabolite, i.e., the upper parts of the gastrointestinal tract, small intestine, or absorption along entire length of gastrointestinal tract.
Кључне речи:
artificial neural network (ANN) / drug absorption / Hansen's solubility parameters / partial least square regression (PLS) / sum of ranking difference (SRD)Извор:
Journal of Chemometrics, 2018, 32, 4Издавач:
- Wiley, Hoboken
Финансирање / пројекти:
- Синтеза, квантитативни однос између структуре и дејства, физичко-хемијска карактеризација и анализа фармаколошки активних супстанци (RS-MESTD-Basic Research (BR or ON)-172033)
DOI: 10.1002/cem.2996
ISSN: 0886-9383
WoS: 000430668000007
Scopus: 2-s2.0-85040642229
Институција/група
PharmacyTY - JOUR AU - Obradović, Darija AU - Andrić, Filip AU - Zlatović, Mario AU - Agbaba, Danica PY - 2018 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/3036 AB - Aripiprazole and ziprasidone are atypical antipsychotic drugs with the effect on positive and negative symptoms of schizophrenia, mania, and mixed states of bipolar disorder. Hansen's solubility parameters, (d), (p), and (h), which account for dispersive, polarizable, and hydrogen bonding contributions to the overall cohesive energy of a compound, are often used to assess pharmacokinetic properties of drugs. However, no data exist of solubility parameters for the drugs of interest in this study. Therefore, in the present study, partial least square regression (PLS), artificial neural networks (ANNs), regression trees (RT), boosted trees (BT), and random forests (RF) were applied to estimate Hansen's solubility parameters of ziprasidone, aripiprazole, and their impurities/metabolic derivatives, targeting their biopharmaceutical classes and absorption routes. A training set of 47 structurally diverse and pharmacologically active compounds and 290 molecular descriptors and pharmaceutically important properties were used to build the prediction models. The modeling approaches were compared by the sum of ranking differences, using the consensus values as a reference for the unknowns and the experimentally determined values as a gold standard for the calibration set. In both instances, the PLS models, together with ANNs, demonstrated better performance than RT, BT and especially RF. Based on the best scored models, we were able to pinpoint the most probable absorption sites for each drug and the corresponding metabolite, i.e., the upper parts of the gastrointestinal tract, small intestine, or absorption along entire length of gastrointestinal tract. PB - Wiley, Hoboken T2 - Journal of Chemometrics T1 - Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites VL - 32 IS - 4 DO - 10.1002/cem.2996 ER -
@article{ author = "Obradović, Darija and Andrić, Filip and Zlatović, Mario and Agbaba, Danica", year = "2018", abstract = "Aripiprazole and ziprasidone are atypical antipsychotic drugs with the effect on positive and negative symptoms of schizophrenia, mania, and mixed states of bipolar disorder. Hansen's solubility parameters, (d), (p), and (h), which account for dispersive, polarizable, and hydrogen bonding contributions to the overall cohesive energy of a compound, are often used to assess pharmacokinetic properties of drugs. However, no data exist of solubility parameters for the drugs of interest in this study. Therefore, in the present study, partial least square regression (PLS), artificial neural networks (ANNs), regression trees (RT), boosted trees (BT), and random forests (RF) were applied to estimate Hansen's solubility parameters of ziprasidone, aripiprazole, and their impurities/metabolic derivatives, targeting their biopharmaceutical classes and absorption routes. A training set of 47 structurally diverse and pharmacologically active compounds and 290 molecular descriptors and pharmaceutically important properties were used to build the prediction models. The modeling approaches were compared by the sum of ranking differences, using the consensus values as a reference for the unknowns and the experimentally determined values as a gold standard for the calibration set. In both instances, the PLS models, together with ANNs, demonstrated better performance than RT, BT and especially RF. Based on the best scored models, we were able to pinpoint the most probable absorption sites for each drug and the corresponding metabolite, i.e., the upper parts of the gastrointestinal tract, small intestine, or absorption along entire length of gastrointestinal tract.", publisher = "Wiley, Hoboken", journal = "Journal of Chemometrics", title = "Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites", volume = "32", number = "4", doi = "10.1002/cem.2996" }
Obradović, D., Andrić, F., Zlatović, M.,& Agbaba, D.. (2018). Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites. in Journal of Chemometrics Wiley, Hoboken., 32(4). https://doi.org/10.1002/cem.2996
Obradović D, Andrić F, Zlatović M, Agbaba D. Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites. in Journal of Chemometrics. 2018;32(4). doi:10.1002/cem.2996 .
Obradović, Darija, Andrić, Filip, Zlatović, Mario, Agbaba, Danica, "Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites" in Journal of Chemometrics, 32, no. 4 (2018), https://doi.org/10.1002/cem.2996 . .