README.md

metadata

title: Drug Classifier
emoji: 🏢
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.19.2
app_file: app.py
pinned: false

Drug discovery efforts typically involve several years of research and development along with substantial financial investment to comb through tens of thousands, if not millions, of potential new drug molecules. Along the path to being approved as a new drug, most potential new drugs are discarded for any number of reasons, such as possible toxicity, poor bioavailability, lack of efficacy, etc. The goal of this project is to create a drug molecule classifier that quickly identifies potential drug molecules as either “drug-like” or not “drug-like” to increase the speed and efficiency of drug discovery and development. Molecules that receive the label “drug-like” can receive further resources and investigation while not wasting time and resources on molecules deemed not “drug-like”.

Barbara Zdrazil, Eloy Felix, Fiona Hunter, Emma J Manners, James Blackshaw, Sybilla Corbett, Marleen de Veij, Harris Ioannidis, David Mendez Lopez, Juan F Mosquera, Maria Paula Magarinos, Nicolas Bosc, Ricardo Arcila, Tevfik Kizilören, Anna Gaulton, A Patrícia Bento, Melissa F Adasme, Peter Monecke, Gregory A Landrum, Andrew R Leach, The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods, Nucleic Acids Research, Volume 52, Issue D1, 5 January 2024, Pages D1180–D1192, https://doi.org/10.1093/nar/gkad1004

RDKit was invaluable to this project as well.

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference