Conformational Oversampling as Data Augmentation for Molecules
العنوان: | Conformational Oversampling as Data Augmentation for Molecules |
---|---|
المؤلفون: | Ece Asilar, Gerhard F. Ecker, Jennifer Hemmerich |
المصدر: | Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions ISBN: 9783030304928 ICANN (Workshop) |
بيانات النشر: | Springer International Publishing, 2019. |
سنة النشر: | 2019 |
مصطلحات موضوعية: | 0303 health sciences, Computer science, business.industry, Overfitting, Machine learning, computer.software_genre, 01 natural sciences, 0104 chemical sciences, 010404 medicinal & biomolecular chemistry, 03 medical and health sciences, Oversampling, Artificial intelligence, business, computer, 030304 developmental biology |
الوصف: | Toxicological datasets tend to be small and imbalanced. This quickly causes models to overfit and disregard the minority class. To solve this issue we generate conformations of molecules. Thereby, we can balance datasets as well as increase their size. Using this approach on the Tox21 Challenge data we observed conformational oversampling to be a viable approach to train datasets, increasing the balanced accuracy of trained models. |
ردمك: | 978-3-030-30492-8 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::4798a1c62e196e9262a987b3d3c11022 https://doi.org/10.1007/978-3-030-30493-5_74 |
حقوق: | OPEN |
رقم الأكسشن: | edsair.doi...........4798a1c62e196e9262a987b3d3c11022 |
قاعدة البيانات: | OpenAIRE |
ردمك: | 9783030304928 |
---|