It is really useful to have two sites of metabolism tools available that use contrasting methodologies, FAME 2 using curated dataset of experimentally determined metabolism data to build a machine learning model using simple descriptors. In contrast SMARTCyp uses precomputed activation energies from density functional theory (DFT) calculations of model compounds.
I previously wrote a script displaying the [results of a SMARTCyp calculation in a webview. The first part of the script imports the smartcyp.jar, however with each update I was finding issues so I thought it might be better to simply treat SMARTCyp as a command line application and use subprocess to access it.
Using a similar script we can also access FAME2
FAME DOI is a collection of random forest models trained on a comprehensive and highly diverse data set of 20,000 small molecules annotated with their experimentally determined sites of metabolism taken from multiple species (rat, dog and human) designed to predict sites of metabolism. FAME 2 DOI builds on this work to improve accuracy ,in addition FAME 2 uses a slightly modified version of the visualization developed by Patrik Rydberg and implemented in SMARTCyp using ChemDoodle Web Components.
The Medicines for Malaria Venture have an interesting page in which they are accumulating a list of computational tools and guides describing the use of the tools to address key issues within the drug discovery process.
Tools were chosen to address common needs expressed by medicinal and computational chemists working in the not-for-profit area. Recognising that this is a global effort, we have selected software packages on the basis of being free for all users.
The guides are either text descriptions or webcasts showing the tool in action. To date they include DataWarrior, KNIME, YASARA, ChEMBL and PK Tool.