An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology
Само за регистроване кориснике
2020
Чланак у часопису (Објављена верзија)

Метаподаци
Приказ свих података о документуАпстракт
Drug absorption is a complex process governed by a number of interrelatedphysicochemical, biopharmaceutical, and pharmacokinetic factors. In order to explore complexrelationships among these factors, multivariate exploratory analysis was performed on thedataset of drugs with diverse bioperformance. The investigated dataset included subset of drugsfor which bioequivalence between solid dosage form and oral solution has been reported, andsubset of drugs described in the literature as low solubility/low permeability compounds.Discriminatory power of hierarchical clustering on principal components was somewhat higherwhen applied on the data subsets of drugs with similar bioperformance, while analysis of theintegrated dataset indicated existence of two groups of drugs with the boundaries reflected in Peffvalue of approximately 2 × 10−4cm/s and Fa and Fm values higher than 85% and 50%,respectively. Majority of the investigated drugs within the integrated dataset were grouped withintheir init...ial subset indicating that overall drug bioperformance is closely related to itsphysicochemical, biopharmaceutical and pharmacokinetic properties. Classification modelsconstructed using the random forest (RF) and support vector machine with polynomial kernelfunction were able to predict food effect based on drug dose/solubility ratio (D/S), effectivepermeability (Peff), percent of dose metabolized (Fm), and elimination half-life (τ1/2). Althoughboth models performed well during training and testing, only RF kept satisfying performancewhen applied on the external dataset (kappa value > 0.4). The results obtained indicate that datamining can be employed as useful tool in biopharmaceutical drug characterization which meritsfurther investigation
Кључне речи:
data mining / drug absorption / food effectИзвор:
APPS Journal, 2020, 22, 1Издавач:
- Springer International Publishing
Финансирање / пројекти:
DOI: 10.1208/s12248-019-0394-y
ISSN: 1550-7416
WoS: 000513843000002
Scopus: 2-s2.0-85076404467
Институција/група
PharmacyTY - JOUR AU - Gatarić, Biljana AU - Parojčić, Jelena PY - 2020 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/3488 AB - Drug absorption is a complex process governed by a number of interrelatedphysicochemical, biopharmaceutical, and pharmacokinetic factors. In order to explore complexrelationships among these factors, multivariate exploratory analysis was performed on thedataset of drugs with diverse bioperformance. The investigated dataset included subset of drugsfor which bioequivalence between solid dosage form and oral solution has been reported, andsubset of drugs described in the literature as low solubility/low permeability compounds.Discriminatory power of hierarchical clustering on principal components was somewhat higherwhen applied on the data subsets of drugs with similar bioperformance, while analysis of theintegrated dataset indicated existence of two groups of drugs with the boundaries reflected in Peffvalue of approximately 2 × 10−4cm/s and Fa and Fm values higher than 85% and 50%,respectively. Majority of the investigated drugs within the integrated dataset were grouped withintheir initial subset indicating that overall drug bioperformance is closely related to itsphysicochemical, biopharmaceutical and pharmacokinetic properties. Classification modelsconstructed using the random forest (RF) and support vector machine with polynomial kernelfunction were able to predict food effect based on drug dose/solubility ratio (D/S), effectivepermeability (Peff), percent of dose metabolized (Fm), and elimination half-life (τ1/2). Althoughboth models performed well during training and testing, only RF kept satisfying performancewhen applied on the external dataset (kappa value > 0.4). The results obtained indicate that datamining can be employed as useful tool in biopharmaceutical drug characterization which meritsfurther investigation PB - Springer International Publishing T2 - APPS Journal T1 - An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology VL - 22 IS - 1 DO - 10.1208/s12248-019-0394-y ER -
@article{ author = "Gatarić, Biljana and Parojčić, Jelena", year = "2020", abstract = "Drug absorption is a complex process governed by a number of interrelatedphysicochemical, biopharmaceutical, and pharmacokinetic factors. In order to explore complexrelationships among these factors, multivariate exploratory analysis was performed on thedataset of drugs with diverse bioperformance. The investigated dataset included subset of drugsfor which bioequivalence between solid dosage form and oral solution has been reported, andsubset of drugs described in the literature as low solubility/low permeability compounds.Discriminatory power of hierarchical clustering on principal components was somewhat higherwhen applied on the data subsets of drugs with similar bioperformance, while analysis of theintegrated dataset indicated existence of two groups of drugs with the boundaries reflected in Peffvalue of approximately 2 × 10−4cm/s and Fa and Fm values higher than 85% and 50%,respectively. Majority of the investigated drugs within the integrated dataset were grouped withintheir initial subset indicating that overall drug bioperformance is closely related to itsphysicochemical, biopharmaceutical and pharmacokinetic properties. Classification modelsconstructed using the random forest (RF) and support vector machine with polynomial kernelfunction were able to predict food effect based on drug dose/solubility ratio (D/S), effectivepermeability (Peff), percent of dose metabolized (Fm), and elimination half-life (τ1/2). Althoughboth models performed well during training and testing, only RF kept satisfying performancewhen applied on the external dataset (kappa value > 0.4). The results obtained indicate that datamining can be employed as useful tool in biopharmaceutical drug characterization which meritsfurther investigation", publisher = "Springer International Publishing", journal = "APPS Journal", title = "An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology", volume = "22", number = "1", doi = "10.1208/s12248-019-0394-y" }
Gatarić, B.,& Parojčić, J.. (2020). An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology. in APPS Journal Springer International Publishing., 22(1). https://doi.org/10.1208/s12248-019-0394-y
Gatarić B, Parojčić J. An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology. in APPS Journal. 2020;22(1). doi:10.1208/s12248-019-0394-y .
Gatarić, Biljana, Parojčić, Jelena, "An Investigation into the Factors Governing Drug Absorption and Food Effect Prediction Based on Data Mining Methodology" in APPS Journal, 22, no. 1 (2020), https://doi.org/10.1208/s12248-019-0394-y . .