Closed cyrusmaher closed 3 years ago
@cyrusmaher
Thank you for your feedback!
New molecules could be directly predicted here: http://admet.scbdd.com
Feature generation could be done by using tools below, you can get here: http://www.scbdd.com: [1]. Jie Dong, Dong-Sheng Cao, Hong-Yu Miao, Shao Liu, Bai-Chuan Deng, Yong-Huan Yun, Ning-Ning Wang, Ai-Ping Lu, Wen-Bin Zeng, Alex Chen. ChemDes: an integrated web-based platform for molecular descriptor and fingerprint computation. Journal of Cheminformatics 2015, 7:60
[2]. Dong J, Yao Z J, Zhang L, et al. PyBioMed: a python library for various molecular representations of chemicals, proteins and DNAs and their interactions[J]. Journal of cheminformatics, 2018, 10(1): 16.
[3]. Jie Dong, Zhi-Jiang Yao, Ming Wen, Min-Feng Zhu, Ning-Ning Wang, Hong-Yu Miao, Ai-Ping Lu, Wen-Bin Zeng and Dong-Sheng Cao. BioTriangle: a web-accessible platform for generating various molecular representations for chemicals, proteins, DNAs/RNAs and their interactions. Journal of Cheminformatics 2016, 8:34
[4] Dong J, Zhu M F, Yun Y H, et al. BioMedR: an R/CRAN package for integrated data analysis pipeline in biomedical study[J]. Briefings in Bioinformatics, 2019.
Thanks @ifyoungnet! I don't see that the exact configuration and feature ordering used by the models could be confidently reproduced, even using these resources. Are there other users I could talk to who have successfully used these models on new molecules?
Which descriptors are required by the model can be found here: http://admet.scbdd.com/home/modeling_process/
Descriptors could be calculated by using: http://projects.scbdd.com/pybiomed.html
@cyrusmaher
Hi, could you enable feature generation from smiles strings? This would allow predictions on new molecules and would be quite helpful. Thank you!