{
  "fetched_at": "2026-10-19T15:30:15Z",
  "source_url": "https://www.kaggle.com/competitions/drug-design-challenge/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Dataset \nTo achieve the objective explained in the previous section, a machine learning model should be trained to be used for virtual screening of chemical libraries such as ZINC, CHEMBLE. \nThe present dataset includes the human ErbB1 target and an IC50 activity (enzyme inhibition parameter). The dataset contains 6953 molecules divided into 5215 molecules for training and 1738 for testing. Each molecule is represented using 1416 molecular descriptors. \nIn this challenge, the following column is targeted:\n\n1.\tRegression target (pIC50_nM): continuous target which should be predicted using regression modeling. Here, the R^2 should be used as a performance measure. \n\nIt is preferable that the work be done in an ipython notebook (Google collab could be considered as runtime). Moreover, all data science phases should be considered (Exploratory analysis, preprocessing, visualizations, modeling, model evaluation).\n\n## Useful links\n●\t[The half maximal inhibitory concentration (IC50)](https://en.wikipedia.org/wiki/IC50#:~:text=IC50%20is%20a%20quantitative,cell%2C%20cell%20receptor%20or%20microorganism.)\n●\t[Quantitative structure–activity relationship models (QSAR)](https://en.wikipedia.org/wiki/Quantitative_structure%E2%80%93activity_relationship)\n●\t[ErbB1](https://www.cancer.gov/publications/dictionaries/cancer-terms/def/erbb1)\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Drug design challenge \nThe Physical Chemistry and Biology of Materials laboratory (LCBM) was created in 2020 with the aim of:\n1.\tContribute to the development of industry (pharmaceutical, energy, agri-food, etc.) in Algeria through the development of new drugs, nano-based smart cards, and food supplements.\n2.\tDevelop and optimize industrial processes in the various sectors (energy, pharmaceuticals and agriculture and foods).\n3.\tDevelop and exploit patents in the field of drug design technologies and nanotechnology.\n4.\tCreate a communication space bringing together the various actors in the fields of Chemistry, Physics, Biology, Computer sciences, mathematics, and other disciplines.\n\nThe laboratory includes four research teams. The research team that created this challenge is the following: Simulation and Modeling of Materials and Biomaterials\nAmong the activities of this team is the study of the structure of molecules and biomolecules by molecular modeling, in particular structure/ligand-based drug design methods which will make it possible to determine structures with determined biological activity (cancer, diabetes, HIV-1).\n \n## Context\nCancer is one of the leading causes of global mortality according to the World Health Organization. The traditional methods of combating this health problem are chemotherapy, radiation therapy and surgery. Currently, the development of anticancer drugs is undergoing a methodological change thanks to artificial intelligence and data science. \nThe main objective of this challenge is the identification of the molecules responsible for the inhibition of the ErbB1. The ErbB1 protein is involved in cell signaling pathways that control cell division and survival. Sometimes, mutations (changes) in genes cause ErbB1 proteins to be produced higher than the normal, which causes cancer cells to divide more rapidly. Drugs that block ErbB1 proteins are used in the treatment of some types of cancer. \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Since the latter problem is a Regression problem, the evaluation metric used is R squared (R^2)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Please stick to the rules of the competition, and be HONEST !\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}