Data-Driven Prediction of the Formation of Co-Amorphous Systems
Co-amorphous systems (COAMS) have raised increasing interest in the pharmaceutical industry, since they combine the increased solubility and/or faster dissolution of amorphous forms with the stability of crystalline forms. However, the choice of the co-former is critical for the formation of a COAMS...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Pharmaceutics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4923/15/2/347 |
| _version_ | 1797618722901327872 |
|---|---|
| author | Elisabeth Fink Michael Brunsteiner Stefan Mitsche Hartmuth Schröttner Amrit Paudel Sarah Zellnitz-Neugebauer |
| author_facet | Elisabeth Fink Michael Brunsteiner Stefan Mitsche Hartmuth Schröttner Amrit Paudel Sarah Zellnitz-Neugebauer |
| author_sort | Elisabeth Fink |
| collection | DOAJ |
| description | Co-amorphous systems (COAMS) have raised increasing interest in the pharmaceutical industry, since they combine the increased solubility and/or faster dissolution of amorphous forms with the stability of crystalline forms. However, the choice of the co-former is critical for the formation of a COAMS. While some models exist to predict the potential formation of COAMS, they often focus on a limited group of compounds. Here, four classes of combinations of an active pharmaceutical ingredient (API) with (1) another API, (2) an amino acid, (3) an organic acid, or (4) another substance were considered. A model using gradient boosting methods was developed to predict the successful formation of COAMS for all four classes. The model was tested on data not seen during training and predicted 15 out of 19 examples correctly. In addition, the model was used to screen for new COAMS in binary systems of two APIs for inhalation therapy, as diseases such as tuberculosis, asthma, and COPD usually require complex multidrug-therapy. Three of these new API-API combinations were selected for experimental testing and co-processed via milling. The experiments confirmed the predictions of the model in all three cases. This data-driven model will facilitate and expedite the screening phase for new binary COAMS. |
| first_indexed | 2024-03-11T08:17:33Z |
| format | Article |
| id | doaj.art-0973c790c94149b094e60132fa7be065 |
| institution | Directory Open Access Journal |
| issn | 1999-4923 |
| language | English |
| last_indexed | 2024-03-11T08:17:33Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Pharmaceutics |
| spelling | doaj.art-0973c790c94149b094e60132fa7be0652023-11-16T22:38:42ZengMDPI AGPharmaceutics1999-49232023-01-0115234710.3390/pharmaceutics15020347Data-Driven Prediction of the Formation of Co-Amorphous SystemsElisabeth Fink0Michael Brunsteiner1Stefan Mitsche2Hartmuth Schröttner3Amrit Paudel4Sarah Zellnitz-Neugebauer5Research Center Pharmaceutical Engineering, Inffeldgasse 13, 8010 Graz, AustriaCeleris Therapeutics GmbH, Salzamtsgasse 7, 8010 Graz, AustriaInstitute of Electron Microscopy and Nanoanalysis (FELMI), Graz University of Technology, Steyrergasse 17, 8010 Graz, AustriaInstitute of Electron Microscopy and Nanoanalysis (FELMI), Graz University of Technology, Steyrergasse 17, 8010 Graz, AustriaResearch Center Pharmaceutical Engineering, Inffeldgasse 13, 8010 Graz, AustriaResearch Center Pharmaceutical Engineering, Inffeldgasse 13, 8010 Graz, AustriaCo-amorphous systems (COAMS) have raised increasing interest in the pharmaceutical industry, since they combine the increased solubility and/or faster dissolution of amorphous forms with the stability of crystalline forms. However, the choice of the co-former is critical for the formation of a COAMS. While some models exist to predict the potential formation of COAMS, they often focus on a limited group of compounds. Here, four classes of combinations of an active pharmaceutical ingredient (API) with (1) another API, (2) an amino acid, (3) an organic acid, or (4) another substance were considered. A model using gradient boosting methods was developed to predict the successful formation of COAMS for all four classes. The model was tested on data not seen during training and predicted 15 out of 19 examples correctly. In addition, the model was used to screen for new COAMS in binary systems of two APIs for inhalation therapy, as diseases such as tuberculosis, asthma, and COPD usually require complex multidrug-therapy. Three of these new API-API combinations were selected for experimental testing and co-processed via milling. The experiments confirmed the predictions of the model in all three cases. This data-driven model will facilitate and expedite the screening phase for new binary COAMS.https://www.mdpi.com/1999-4923/15/2/347machine learninggradient boostingco-amorphousmolecular descriptorsinhalation therapy |
| spellingShingle | Elisabeth Fink Michael Brunsteiner Stefan Mitsche Hartmuth Schröttner Amrit Paudel Sarah Zellnitz-Neugebauer Data-Driven Prediction of the Formation of Co-Amorphous Systems Pharmaceutics machine learning gradient boosting co-amorphous molecular descriptors inhalation therapy |
| title | Data-Driven Prediction of the Formation of Co-Amorphous Systems |
| title_full | Data-Driven Prediction of the Formation of Co-Amorphous Systems |
| title_fullStr | Data-Driven Prediction of the Formation of Co-Amorphous Systems |
| title_full_unstemmed | Data-Driven Prediction of the Formation of Co-Amorphous Systems |
| title_short | Data-Driven Prediction of the Formation of Co-Amorphous Systems |
| title_sort | data driven prediction of the formation of co amorphous systems |
| topic | machine learning gradient boosting co-amorphous molecular descriptors inhalation therapy |
| url | https://www.mdpi.com/1999-4923/15/2/347 |
| work_keys_str_mv | AT elisabethfink datadrivenpredictionoftheformationofcoamorphoussystems AT michaelbrunsteiner datadrivenpredictionoftheformationofcoamorphoussystems AT stefanmitsche datadrivenpredictionoftheformationofcoamorphoussystems AT hartmuthschrottner datadrivenpredictionoftheformationofcoamorphoussystems AT amritpaudel datadrivenpredictionoftheformationofcoamorphoussystems AT sarahzellnitzneugebauer datadrivenpredictionoftheformationofcoamorphoussystems |