theochem / b3db Goto Github PK
View Code? Open in Web Editor NEWA large benchmark dataset, Blood-Brain Barrier Database (B3DB), complied from 50 published resources.
License: Creative Commons Zero v1.0 Universal
A large benchmark dataset, Blood-Brain Barrier Database (B3DB), complied from 50 published resources.
License: Creative Commons Zero v1.0 Universal
There are some nan strings in the final data and should be removed.
Add About and keywords in Github.
The molecule 847 - 3-methylhexane (SMILES C=C([CH]CC)CC) is problematic as there is a carbon atom with unusual valence and the SMILES does not match SMILES for 3-methylhexane. This should be https://pubchem.ncbi.nlm.nih.gov/compound/11507.
Credit goes to Dr. Andrea Mauri from Alvascience.
A license for this database is required.
Problem Statement: Having a simple, no-nonsense queried database of antivirals that are BBB permeable or not?
Preliminary Approach: @fwmeng88 's upcoming computational model to be applied to a comprehensive list of antivirals taken up from https://www.viprbrc.org/brc/home.spg?decorator=vipr and then building a simple database to show the BBB permeability.
Outcomes: Since I don't see similar results after an initial literature review, this represents a low hanging fruit, which might be useful to the community. It is good to have data on antiviral BBB permeability for training future models. Though people can grab a list of antiviral SMILES from PubChem, and run them through SwissADME for BBB permeability data, and a visual inspection through EggPlot: https://chemistry-europe.onlinelibrary.wiley.com/doi/10.1002/cmdc.201600182. This effort might compare the two models, helping find outliers from the SwissADME data.
I hope this is interesting enough to spend some time, and develop it together. Happy to stay in the loop, and chat.
Hi, I would like to know whether the molecules with categorical labels are experimentally determined or computationally predicted. Thank you
There are more molecules with BBB permeability information that should be added in the next release. @fwmeng88
We should add the extra molecules from B3cls to B3DB when we finish that work.
Hi,
I've noticed that there's a smiles_result column in the regression dataset, which is not present in the classification dataset.
What exactly is this, is this the cleaned up SMILES or something else? If it is, why is it not present in the classification dataset?
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.