Similar protocols

To access compelling stats and trends, optimize your time and resources and pinpoint new correlations, you will need to subscribe to our premium service.


Pipeline publication

[…] tivity databases are free available, such as PubChem (Wang et al., ), ChEMBL (Gaulton et al., ), and BindingDB (Gilson et al., ). We developed a web server named MetaADEDB that integrates CTD (Davis et al., ), SIDER (Kuhn et al., ), and OFFSIDES (Tatonetti et al., ) with regard to the ADE of drugs (Cheng et al., ,)., There are two ways to represent chemical structures as numeric features which can be processed by machine learning methods. One way is to use molecular descriptors, which can be calculated from chemical structures, physicochemical or topological properties. Currently thousands of continuous and discrete molecular descriptors can be obtained via chemoinformatics toolkits such as PaDEL-Descriptor (Yap, ), OpenBabel (O'Boyle et al., ), CDKit (Steinbeck et al., ), RDKit (Landrum, ), or web servers like E-Dragon (Tetko et al., ), ChemBCPP (Dong et al., ), and ChemDes (Dong et al., ). Using numeric features may result in overfitting when the size of training set is small (Xue et al., ). Hence, feature selection should be done before model building, to reduce the risk of overfitting and enhance the performance of model (Sun et al., )., The other way is to use molecular fingerprints, which represent a molecule as a binary string, such as MACCS, PubChemFP, and KRFP (Klekota and Roth, ). In a molecular fingerprint, lists of substructures or other kinds of patterns are predefined. If a specified pattern presents in a molecule, the corresponding bit in the binary string is set to “1,” otherwise it will be set to “0.” Comparing to molecular descriptors, […]

Pipeline specifications

Software tools PaDEL-descriptor, RDKit, ChemDes
Databases MetaADEDB