{"id":13481174,"url":"https://github.com/masashitsubaki/molecularGNN_3Dstructure","last_synced_at":"2025-03-27T11:32:01.000Z","repository":{"id":162894687,"uuid":"174896976","full_name":"masashitsubaki/molecularGNN_3Dstructure","owner":"masashitsubaki","description":"Graph neural network (GNN) for molecular property prediction (3D structure)","archived":false,"fork":false,"pushed_at":"2020-11-28T02:05:35.000Z","size":16506,"stargazers_count":93,"open_issues_count":1,"forks_count":23,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-10-30T14:43:39.663Z","etag":null,"topics":[],"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/masashitsubaki.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}},"created_at":"2019-03-11T00:11:09.000Z","updated_at":"2024-10-02T13:52:45.000Z","dependencies_parsed_at":"2023-06-30T03:45:35.717Z","dependency_job_id":null,"html_url":"https://github.com/masashitsubaki/molecularGNN_3Dstructure","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masashitsubaki%2FmolecularGNN_3Dstructure","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masashitsubaki%2FmolecularGNN_3Dstructure/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masashitsubaki%2FmolecularGNN_3Dstructure/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masashitsubaki%2FmolecularGNN_3Dstructure/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/masashitsubaki","download_url":"https://codeload.github.com/masashitsubaki/molecularGNN_3Dstructure/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245836278,"owners_count":20680345,"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":[],"created_at":"2024-07-31T17:00:49.375Z","updated_at":"2025-03-27T11:31:59.834Z","avatar_url":"https://github.com/masashitsubaki.png","language":"Python","funding_links":[],"categories":["Deep Learning"],"sub_categories":[],"readme":"# Graph neural network (GNN) for molecular property prediction (3D structure)\n\n\n### _**Important: this repository will not be further developed and maintained because we have shown and believe that graph neural networks or graph convolutional networks are incorrect and useless for modeling molecules (see our paper in [NeurIPS 2020](https://proceedings.neurips.cc/paper/2020/hash/1534b76d325a8f591b52d302e7181331-Abstract.html)). Please consider switching to our new and simple machine learning model called [quantum deep field](https://github.com/masashitsubaki/QuantumDeepField_molecule).**_\n\n\nThis code is a simpler version (different from the original paper) of our GNN model and its implementation for \"[Fast and Accurate Molecular Property Prediction: Learning Atomic Interactions and Potentials with Neural Networks (The Journal of Physical Chemistry Letters, 2018)](https://pubs.acs.org/doi/10.1021/acs.jpclett.8b01837)\" in PyTorch.\n\nWe show an example of the learning curve, which uses a subset of the QM9 dataset (the molecular size is less than 14 atoms), as follows.\n\n\u003cdiv align='center'\u003e\n\u003cp\u003e\u003cimg src=\"figures/learning.jpeg\" width='500' /\u003e\u003c/p\u003e\n\u003c/div\u003e\n\nThis result can be completely reproduced by our code and one command (see \"Usage\").\n\n\n## Characteristics of our implementation\n\n- This code is easy-to-use for beginners. The requirement is only PyTorch.\n- Preprocessing a dataset and learning a GNN model can be done by only one command, \"bash train.sh.\"\n- If you prepare another dataset with the same format as seen in the directory, dataset/QM9/data.txt, you can learn a GNN model with your dataset.\n\n\n## Requirements\n\n- PyTorch (of course numpy and scipy)\n\n\n## Usage\n\nWe provide two major scripts in the main directory as follows.\n\n- \"preprocessing.py\" creates tensor data from original text data (see dataset/QM9/data.txt).\n- \"train.py\" trains a GNN model using the preprocessed data to predict a molecular property.\n\nYou can easy to train a GNN model by the following commands.\n\nClone our repository,\n```\ngit clone https://github.com/masashitsubaki/molecularGNN_3Dstructure.git\n```\nchange directory, \n```\ncd molecularGNN_3Dstructure/main\n```\nand run the bash file for training.\n```\nbash train.sh\n```\nAn image of running on google colaboratory is as follows.\n\n\u003cdiv align='center'\u003e\n\u003cp\u003e\u003cimg src=\"figures/train.jpeg\" width='500' /\u003e\u003c/p\u003e\n\u003c/div\u003e\n\nYou can also change the model hyperparameters described in train.sh (e.g., the dimensionality, number of hidden layers, and batch size).\n\n\u003cdiv align='center'\u003e\n\u003cp\u003e\u003cimg src=\"figures/setting.jpeg\" width='500' /\u003e\u003c/p\u003e\n\u003c/div\u003e\n\nTry to learn various GNN models to find your own best model for your dataset!\n\n\n## Learning a GNN with your dataset\n\nIn the dataset directory, we provide a subset of the QM9 dataset (see dataset/QM9/data.txt), which the format is as follows.\n\n\u003cdiv align='center'\u003e\n\u003cp\u003e\u003cimg src=\"figures/data.jpeg\" width='500' /\u003e\u003c/p\u003e\n\u003c/div\u003e\n\nIf you prepare a dataset with the same format (any molecular property can be used!), you can learn a GNN model with your dataset.\n\n\n## How to cite\n\n```\n@article{tsubaki2018fast,\n  title={Fast and Accurate Molecular Property Prediction: Learning Atomic Interactions and Potentials with Neural Networks},\n  author={Tsubaki, Masashi and Mizoguchi, Teruyasu},\n  journal={The journal of physical chemistry letters},\n  volume={9},\n  number={19},\n  pages={5733--5741},\n  year={2018},\n  publisher={ACS Publications}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmasashitsubaki%2FmolecularGNN_3Dstructure","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmasashitsubaki%2FmolecularGNN_3Dstructure","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmasashitsubaki%2FmolecularGNN_3Dstructure/lists"}