{
  "fetched_at": "2026-10-19T15:19:16Z",
  "source_url": "https://www.kaggle.com/competitions/covid-19-bioinformatics-drug-target-challenge/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The datasets to be used in this Challenge have been generated and curated by researchers at the\nBrookhaven National Laboratory (BNL) in collaboration with other DOE (Department of Energy)\nNational Laboratories who have joined forces to combat the COVID-19 pandemics. The provided\ndatasets contain the docking scores of molecules (i.e., drug candidates) on SARS-CoV-2 protein\ntargets. Drug candidates are represented in SMILES strings and selected from known drug\ndatabases such as ENAMINE [1], ZINC [2] and DrugBank [3]. All SMILES strings have been\ncanonicalized. The COVID-19 protein targets were provided by researchers at Argonne National\nLaboratory (ANL). The Docking scores were obtained from Autodock 4.2 [4] and then collected\nand organized into a CSV file, where rows represent molecules and columns represent different\ndocking targets.\nThe whole dataset includes docking scores of 300,457 molecules on 18 different COVID-19\nrelated protein docking targets. Part of this data will be provided for training and initial validation.\nThe rest will be held out for evaluating the performance of the models trained by the participants.\nThe training/validation dataset will include the SMILES string representing 270,000 molecules\nand their docking scores against different targets. In the test set, only the SMILES strings will be\nprovided for 30,457 molecules without their docking scores. The participants will need to train\ntheir own model that can be used for accurate prediction of the docking scores of these\nmolecules on different targets. The dataset can be obtained from the github repo [5] created for\nthe Challenge: https://github.com/BC3D/BC3D_2021\n\n# References & Resources\n\n1. https://enamine.net/compound-libraries/diversity-libraries\n\n2. https://zinc.docking.org/\n\n3. https://go.drugbank.com/releases/latest\n\n4. The original docking score data used for creation of the training/testing/validation datasets have been obtained from AutoDock. Further information regarding AutoDock can be found at the following URL: http://autodock.scripps.edu/\n\n5. https://github.com/BC3D/BC3D_2021",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# ***Email Competition Organizers***\n\nIf you haven't done so already, send an email to the organizing team (Bobak Mortazavi (bobakm@tamu.edu), Ryan King (kingrc15@tamu.edu), Subhamoy Mandal (s.mandal@ieee.org) and Tayo Obafemi-Ajayi (tayoobafemiajayi@missouristate.edu)) for information about the next step.\n\n# Challenge Description\n\nThe traditional drug discovery process is expensive and time-consuming. Accelerating this\nprocess a significant challenge, for which taking a ML/AI-based pre-screening approach could\nassist us with high-throughput virtual pre-screening of huge amount of drug candidates to\nidentify highly potent candidates for experimental testing and further validation.\n\n# Goal\n\nThe goal of this challenge is to build effective ML/AI-based surrogate models that can accurately\npredict the docking scores of candidate drug molecules on SARS-CoV-2 protein targets.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# Evaluation\n\nThe participants should submit the docking scores for the molecules in the test set predicted by\ntheir trained model. CSV format (same as the training/validation dataset provided to the\nparticipants) should be used for submitting the predicted scores. The predicted scores will be\ncompared with the ground truth docking scores, based on which the model accuracy will be\nassessed in terms of the averaged mean absolute error (MAE) over all the targets.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# Submission Requirements\n\n- **In order to accept the award for a top place submission, participants must purchase a registration ticket for BHI (https://bhi.embs.org/2023/) and attend the conference. Participants who do not wish to attend the conference are still free to enter their submission but will not be considered for conference awards**",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Submission",
      "content": "# Submission Requirements\n\n- **In order to accept the award for a top place submission, participants must purchase a registration ticket for BHI (https://bhi.embs.org/2023/) and attend the conference. Participants who do not wish to attend the conference are still free to enter their submission but will not be considered for conference awards**\n\n# What to Submit\n\n- Submit a report (recommended length: 4 pages) that contains\n- Technical description of your method\n- Evaluation results of how accurately your trained model was able to fit the docking scores in the training data. Report MAE.\n- URL to your GitHub repo, where your code can be accessed and the prediction results can be reproduced.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}