Dear Aditya, we have recently put together some material that might be helpful to get started, have a look at: https://github.com/volkamerlab/teachopencadd Talktorials T004<https://projects.volkamerlab.org/teachopencadd/talktorials/T004_compound_similarity.html> and T007<https://projects.volkamerlab.org/teachopencadd/talktorials/T007_compound_activity_machine_learning.html> might be of special interest.
Best, Andrea ---- Prof. Dr. Andrea Volkamer In silico Toxicology and Structural Bioinformatics<https://volkamerlab.org/>, Institute of Physiology, Charité Universitätsmedizin Berlin Campus Mitte: Virchowweg 6, 10117 Berlin Phone: +49 30 - 450 528 504 E-Mail: andrea.volka...@charite.de<mailto:andrea.volka...@charite.de> ________________________________ Von: Aditya Sahay [adi.saha...@outlook.com] Gesendet: Dienstag, 12. Januar 2021 21:10 An: rdkit-discuss@lists.sourceforge.net Betreff: [ext] [Rdkit-discuss] Rdkit Machine Learning Project Hi, I have recently enrolled in a programme to use Python in Cheminformatics. As part of my programme, I have a mini-project to use rdkit package for machine learning (scikit-learn). I have been provided with a data set of molecules (provided as SMILES) with various properties in a .csv file. My main task is to use machine learning methods (Random Forests, SVM, Neural networks) to explore the data set. Can anyone provide any guidance on how to begin or any resources to use? Thanks Sent from Mail<https://go.microsoft.com/fwlink/?LinkId=550986> for Windows 10
_______________________________________________ Rdkit-discuss mailing list Rdkit-discuss@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
