Supplementary material for doctoral dissertation: Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms
Апстракт
Dataset for mixed QSPR modeling.
The response modeling procedure, which simultaneously considered method parameters, solvent-related descriptors, and structural properties of the analytes, required organizing data into a matrix. The X matrix (Table A.1) refers to the (J × K) LC–ESI(+)/MS data collected for a set of analytes under different working conditions. The total number of rows (J) corresponds to the total number of endpoints (measurements performed). It refers to the number of rows (N) of the Box-Behnken (BBD) experimental matrix that are repeated over C analytes. The rows of the (N x S) BBD matrix show all possible combinations of settings for the factors represented in the columns S. The X matrix comprised a total of K columns, with S columns corresponding to experimental factors, P columns representing solvent-related properties, M columns representing molecular descriptors, and one L column corresponding to response-dependent variable. For the C compounds considered in our ...study, the molecular descriptors make up a (C x M) Q matrix. Repeated application of the BBD matrix over the C compounds augmented property matrix Q.
Кључне речи:
Box-Behnken Design / Molecular Descriptors / Signal response prediction / AripiprazoleИзвор:
Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms, 2023Издавач:
- University of Belgrade - Faculty of Pharmacy
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200161 (Универзитет у Београду, Фармацеутски факултет) (RS-MESTD-inst-2020-200161)
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200135 (Универзитет у Београду, Технолошко-металуршки факултет) (RS-MESTD-inst-2020-200135)
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200287 (Иновациони центар Технолошко-металуршког факултета у Београду доо) (RS-MESTD-inst-2020-200287)
Напомена:
- Dataset for: https://doi.org/10.1016/j.jpba.2023.115422
- Related to published version: https://farfar.pharmacy.bg.ac.rs/handle/123456789/4881
- Related to dataset: https://farfar.pharmacy.bg.ac.rs/handle/123456789/4880
- Related to dataset: https://farfar.pharmacy.bg.ac.rs/handle/123456789/4884
Повезане информације:
- Повезани садржај
https://doi.org/10.1016/j.jpba.2023.115422 - Повезани садржај
https://farfar.pharmacy.bg.ac.rs/handle/123456789/4881 - Повезани садржај
https://farfar.pharmacy.bg.ac.rs/handle/123456789/4880 - Повезани садржај
https://farfar.pharmacy.bg.ac.rs/handle/123456789/4884
Колекције
Институција/група
PharmacyTY - DATA AU - Krmar, Jovana PY - 2023 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/4883 AB - Dataset for mixed QSPR modeling. The response modeling procedure, which simultaneously considered method parameters, solvent-related descriptors, and structural properties of the analytes, required organizing data into a matrix. The X matrix (Table A.1) refers to the (J × K) LC–ESI(+)/MS data collected for a set of analytes under different working conditions. The total number of rows (J) corresponds to the total number of endpoints (measurements performed). It refers to the number of rows (N) of the Box-Behnken (BBD) experimental matrix that are repeated over C analytes. The rows of the (N x S) BBD matrix show all possible combinations of settings for the factors represented in the columns S. The X matrix comprised a total of K columns, with S columns corresponding to experimental factors, P columns representing solvent-related properties, M columns representing molecular descriptors, and one L column corresponding to response-dependent variable. For the C compounds considered in our study, the molecular descriptors make up a (C x M) Q matrix. Repeated application of the BBD matrix over the C compounds augmented property matrix Q. PB - University of Belgrade - Faculty of Pharmacy T2 - Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms T1 - Supplementary material for doctoral dissertation: Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms UR - https://hdl.handle.net/21.15107/rcub_farfar_4883 ER -
@misc{ author = "Krmar, Jovana", year = "2023", abstract = "Dataset for mixed QSPR modeling. The response modeling procedure, which simultaneously considered method parameters, solvent-related descriptors, and structural properties of the analytes, required organizing data into a matrix. The X matrix (Table A.1) refers to the (J × K) LC–ESI(+)/MS data collected for a set of analytes under different working conditions. The total number of rows (J) corresponds to the total number of endpoints (measurements performed). It refers to the number of rows (N) of the Box-Behnken (BBD) experimental matrix that are repeated over C analytes. The rows of the (N x S) BBD matrix show all possible combinations of settings for the factors represented in the columns S. The X matrix comprised a total of K columns, with S columns corresponding to experimental factors, P columns representing solvent-related properties, M columns representing molecular descriptors, and one L column corresponding to response-dependent variable. For the C compounds considered in our study, the molecular descriptors make up a (C x M) Q matrix. Repeated application of the BBD matrix over the C compounds augmented property matrix Q.", publisher = "University of Belgrade - Faculty of Pharmacy", journal = "Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms", title = "Supplementary material for doctoral dissertation: Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms", url = "https://hdl.handle.net/21.15107/rcub_farfar_4883" }
Krmar, J.. (2023). Supplementary material for doctoral dissertation: Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms. in Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms University of Belgrade - Faculty of Pharmacy.. https://hdl.handle.net/21.15107/rcub_farfar_4883
Krmar J. Supplementary material for doctoral dissertation: Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms. in Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms. 2023;. https://hdl.handle.net/21.15107/rcub_farfar_4883 .
Krmar, Jovana, "Supplementary material for doctoral dissertation: Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms" in Prediction of Retention and Ionization Behavior of Selected Analytes in Micellar Liquid Chromatography and Mass Spectrometry Using Machine Learning Algorithms (2023), https://hdl.handle.net/21.15107/rcub_farfar_4883 .