Cocrystal Prediction Using Machine Learning Models and Descriptors
Cocrystals are of much interest in industrial application as well as academic research, and screening of suitable coformers for active pharmaceutical ingredients is the most crucial and challenging step in cocrystal development. Recently, machine learning techniques are attracting researchers in man...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/3/1323 |
| _version_ | 1827604912417013760 |
|---|---|
| author | Medard Edmund Mswahili Min-Jeong Lee Gati Lother Martin Junghyun Kim Paul Kim Guang J. Choi Young-Seob Jeong |
| author_facet | Medard Edmund Mswahili Min-Jeong Lee Gati Lother Martin Junghyun Kim Paul Kim Guang J. Choi Young-Seob Jeong |
| author_sort | Medard Edmund Mswahili |
| collection | DOAJ |
| description | Cocrystals are of much interest in industrial application as well as academic research, and screening of suitable coformers for active pharmaceutical ingredients is the most crucial and challenging step in cocrystal development. Recently, machine learning techniques are attracting researchers in many fields including pharmaceutical research such as quantitative structure-activity/property relationship. In this paper, we develop machine learning models to predict cocrystal formation. We extract descriptor values from simplified molecular-input line-entry system (SMILES) of compounds and compare the machine learning models by experiments with our collected data of 1476 instances. As a result, we found that artificial neural network shows great potential as it has the best accuracy, sensitivity, and F1 score. We also found that the model achieved comparable performance with about half of the descriptors chosen by feature selection algorithms. We believe that this will contribute to faster and more accurate cocrystal development. |
| first_indexed | 2024-03-09T06:09:59Z |
| format | Article |
| id | doaj.art-018972f63982469ea0ad44489910aabc |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T06:09:59Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-018972f63982469ea0ad44489910aabc2023-12-03T11:58:59ZengMDPI AGApplied Sciences2076-34172021-02-01113132310.3390/app11031323Cocrystal Prediction Using Machine Learning Models and DescriptorsMedard Edmund Mswahili0Min-Jeong Lee1Gati Lother Martin2Junghyun Kim3Paul Kim4Guang J. Choi5Young-Seob Jeong6Department of ICT Convergence, Soonchunhyang University, Asan-si 31538, KoreaDepartment of Pharmaceutical Engineering, Soonchunhyang University, Asan-si 31538, KoreaDepartment of ICT Convergence, Soonchunhyang University, Asan-si 31538, KoreaDepartment of Future Convergence Technology, Soonchunhyang University, Asan-si 31538, KoreaDepartment of Medical Science, Soonchunhyang University, Asan-si 31538, KoreaDepartment of Pharmaceutical Engineering, Soonchunhyang University, Asan-si 31538, KoreaDepartment of ICT Convergence, Soonchunhyang University, Asan-si 31538, KoreaCocrystals are of much interest in industrial application as well as academic research, and screening of suitable coformers for active pharmaceutical ingredients is the most crucial and challenging step in cocrystal development. Recently, machine learning techniques are attracting researchers in many fields including pharmaceutical research such as quantitative structure-activity/property relationship. In this paper, we develop machine learning models to predict cocrystal formation. We extract descriptor values from simplified molecular-input line-entry system (SMILES) of compounds and compare the machine learning models by experiments with our collected data of 1476 instances. As a result, we found that artificial neural network shows great potential as it has the best accuracy, sensitivity, and F1 score. We also found that the model achieved comparable performance with about half of the descriptors chosen by feature selection algorithms. We believe that this will contribute to faster and more accurate cocrystal development.https://www.mdpi.com/2076-3417/11/3/1323descriptormachine learningfeature selectioncocrystal prediction |
| spellingShingle | Medard Edmund Mswahili Min-Jeong Lee Gati Lother Martin Junghyun Kim Paul Kim Guang J. Choi Young-Seob Jeong Cocrystal Prediction Using Machine Learning Models and Descriptors Applied Sciences descriptor machine learning feature selection cocrystal prediction |
| title | Cocrystal Prediction Using Machine Learning Models and Descriptors |
| title_full | Cocrystal Prediction Using Machine Learning Models and Descriptors |
| title_fullStr | Cocrystal Prediction Using Machine Learning Models and Descriptors |
| title_full_unstemmed | Cocrystal Prediction Using Machine Learning Models and Descriptors |
| title_short | Cocrystal Prediction Using Machine Learning Models and Descriptors |
| title_sort | cocrystal prediction using machine learning models and descriptors |
| topic | descriptor machine learning feature selection cocrystal prediction |
| url | https://www.mdpi.com/2076-3417/11/3/1323 |
| work_keys_str_mv | AT medardedmundmswahili cocrystalpredictionusingmachinelearningmodelsanddescriptors AT minjeonglee cocrystalpredictionusingmachinelearningmodelsanddescriptors AT gatilothermartin cocrystalpredictionusingmachinelearningmodelsanddescriptors AT junghyunkim cocrystalpredictionusingmachinelearningmodelsanddescriptors AT paulkim cocrystalpredictionusingmachinelearningmodelsanddescriptors AT guangjchoi cocrystalpredictionusingmachinelearningmodelsanddescriptors AT youngseobjeong cocrystalpredictionusingmachinelearningmodelsanddescriptors |