{
  "fetched_at": "2026-10-20T06:21:34Z",
  "source_url": "https://www.kaggle.com/competitions/ai-drug-discovery/data",
  "pages": [
    {
      "name": "data-description",
      "content": "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. \n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Important columns\n\n*   `SMILES_stand` - SMILES strings\n*   `Label` - Acitivity labels. 1 if active, 0 otherwise.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "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/).\n\n**Description of problem and Dataset: **\n\nThere 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.\n\n\nThe 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. \n\nMore information:\nKC, 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\n\n\nUseful resource\nhttps://www.macinchem.org/blog/files/fe66130c1da3375e46d0512e483eb901-2791.php\n\n## Acknowledgements\n\nWe thank NIH/NCATS for making this dataset available.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:\n\n$$F1 = 2 \\frac{p \\cdot r}{p + r} \\ where\\ p = \\frac{tp}{tp+fp},\\ r = \\frac{tp}{tp+fn}$$\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\nSubmission Format\n\n## Submission Format\n\nFor every SMILES in the `SMILES_stand` column of `sample-submission.csv`, the `Label` column should contain the predicted activity (1 for active and 0 for inactive) label.\n\n\nThe file should contain a header and have the following format:\n```\nSMILES_stand,Label\nCOc1cc(Nc2nc3c(s2)CCCC3c2ccc(F)cc2)ccc1-n1cnc(C)c1,1\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Rules are simple. \n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}