This competition is part of the Developing Fundamental AI Programming Skills for Drug Discovery: Workshop and Coding Challenge conducted by [Gulf Cost Consortium](https://www.gulfcoastconsortia.org/). This part of the challenge is administered by the [Sirimulla lab](http://www.sirimullaresearchgroup.com/).

**Description of problem and Dataset: **

There is currently an urgent need to find effective drugs for treating coronavirus disease 2019 (COVID-19). Here we present a dataset with compound activities for live viral infectivity(cytopathic effect) for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The task is to develop a binary classification model to estimate the cytopathic effect. This application could serve the scientific community when prioritizing compounds for in vitro screening and may ultimately accelerate the identification of novel drug candidates for COVID-19 treatment.


The dataset contains molecules in SMILES format associated with labels active (1) and inactive (0). Participants are required to build binary classification models. Packages like [RDKit](https://www.rdkit.org/docs/), [volsurf](https://www.moldiscovery.com/software/vsplus/),  and [mayachemtools](http://www.mayachemtools.org/) can be used to generate features of the molecules and machine learning packages such as [sciKit-learn](https://scikit-learn.org/stable/) and [Tensorflow](https://www.tensorflow.org/) can be used for building machine learning models. [DeepChem](https://deepchem.io/) is another molecular machine learning package that can be used. 

More information:
KC, G.B., Bocci, G., Verma, S. et al. A machine learning platform to estimate anti-SARS-CoV-2 activities. Nat Mach Intell 3, 527–535 (2021). https://doi.org/10.1038/s42256-021-00335-w


Useful resource
https://www.macinchem.org/blog/files/fe66130c1da3375e46d0512e483eb901-2791.php

## Acknowledgements

We thank NIH/NCATS for making this dataset available.