{"id":19540612,"url":"https://github.com/kbhalajiyadav/lipophilicity_model","last_synced_at":"2026-04-16T18:45:31.536Z","repository":{"id":261825425,"uuid":"885446260","full_name":"kbhalajiyadav/lipophilicity_model","owner":"kbhalajiyadav","description":"This project trains a Morgan Fingerprint model to predict lipophilicity.","archived":false,"fork":false,"pushed_at":"2024-11-08T17:09:41.000Z","size":90,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-08T18:35:23.141Z","etag":null,"topics":["maccs-fingerprint","mlpregressor","morgan-fingerprints","nn","rdkit","rdkit-chem","rmse-score","sklearn","smiles"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kbhalajiyadav.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-08T15:47:13.000Z","updated_at":"2024-11-08T17:09:45.000Z","dependencies_parsed_at":"2024-11-08T17:24:02.821Z","dependency_job_id":"4af7fde6-8180-42a3-a8e6-713d91f587bd","html_url":"https://github.com/kbhalajiyadav/lipophilicity_model","commit_stats":null,"previous_names":["kbhalajiyadav/lipophilicity_model"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbhalajiyadav%2Flipophilicity_model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbhalajiyadav%2Flipophilicity_model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbhalajiyadav%2Flipophilicity_model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kbhalajiyadav%2Flipophilicity_model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kbhalajiyadav","download_url":"https://codeload.github.com/kbhalajiyadav/lipophilicity_model/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240795007,"owners_count":19858725,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["maccs-fingerprint","mlpregressor","morgan-fingerprints","nn","rdkit","rdkit-chem","rmse-score","sklearn","smiles"],"created_at":"2024-11-11T03:05:09.493Z","updated_at":"2026-04-16T18:45:26.511Z","avatar_url":"https://github.com/kbhalajiyadav.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Lipophilicity Model with Morgan Fingerprints\n\nThis repository contains a Python package and script to train a model predicting lipophilicity based on Morgan fingerprints of molecular SMILES representations. The model uses an MLP regressor and evaluates its performance using Root Mean Squared Error (RMSE) on test data.\n\n## Contents\n- **src/train_model.py**: Script for loading data, generating fingerprints, training the model, and saving evaluation results.\n- **data/Lipophilicity.csv**: Data file.\n- **config.json**: Model hyperparameters specification.\n- **environment.yml**: Conda environment file listing dependencies.\n- **results.txt**: Output file that stores the model's RMSE, the conda environment used, and key hyperparameters.\n\n## Installation\n\n1. **Clone the repository**:\n   ```bash\n   git clone https://github.com/kbhalajiyadav/lipophilicity_model.git\n   cd lipophilicity_model\n   ```\n\n2. **Set up the environment**:\n   Create a new Conda environment using the `environment.yml` file:\n   ```bash\n   conda env create -f environment.yml\n   conda activate molecule_modeling  # Replace with your actual environment name\n   ```\n\n### Usage\n\nYou can specify model hyperparameters either through a JSON configuration file or by using command-line arguments.\n\n#### Running the Script\n\nTo run the model training script with a JSON configuration file:\n```bash\npython src/train_model.py --config config.json\n```\n\n#### Specifying Hyperparameters Directly in the Command Line\n\nIf you prefer, you can specify hyperparameters directly on the command line. For example:\n```bash\npython src/train_model.py --hidden_layer_sizes 100,50 --alpha 0.01\n```\n\n#### Using Both JSON and Command-Line Arguments\n\nWhen both are used, command-line arguments will override values from the JSON file:\n```bash\npython src/train_model.py --config config.json --alpha 0.01\n```\n\n#### Config File Example\n\nCreate a JSON configuration file like this in the main directory:\n```json\n{\n   \"hidden_layer_sizes\": [100, 100],\n   \"alpha\": 0.001\n}\n```\n\n### Output\n\nThe script will save:\n- The RMSE for the test set,\n- The name of the active conda environment, and\n- Hyperparameter settings\n\n...to `results.txt` in the main directory.\n\n\n- **Arguments**:\n  - `--hidden_layer_sizes`: Specifies the architecture of the neural network.\n  - `--alpha`: Sets the regularization strength of the model.\n\nAfter execution, the script will output the test set RMSE, current environment, and hyperparameters to `results.txt`.\n\n## License\n\nThis project is licensed under the Apache-2.0 License.\n\n--\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkbhalajiyadav%2Flipophilicity_model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkbhalajiyadav%2Flipophilicity_model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkbhalajiyadav%2Flipophilicity_model/lists"}