{"id":15002159,"url":"https://github.com/yunjaechoi/vaemols","last_synced_at":"2025-10-30T08:31:02.692Z","repository":{"id":109913340,"uuid":"163844046","full_name":"YunjaeChoi/vaemols","owner":"YunjaeChoi","description":"Variational Autoencoder for Molecules","archived":false,"fork":false,"pushed_at":"2019-01-02T15:36:51.000Z","size":28523,"stargazers_count":31,"open_issues_count":1,"forks_count":10,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-02T07:21:59.246Z","etag":null,"topics":["molecule","rdkit","tensorflow","variational-autoencoder"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YunjaeChoi.png","metadata":{"files":{"readme":"README.rst","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":"2019-01-02T13:23:34.000Z","updated_at":"2024-08-16T23:07:51.000Z","dependencies_parsed_at":"2023-03-21T09:17:42.132Z","dependency_job_id":null,"html_url":"https://github.com/YunjaeChoi/vaemols","commit_stats":{"total_commits":4,"total_committers":2,"mean_commits":2.0,"dds":0.5,"last_synced_commit":"9d75444cef101dc0be863d64cb34beef0c4d895c"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YunjaeChoi%2Fvaemols","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YunjaeChoi%2Fvaemols/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YunjaeChoi%2Fvaemols/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YunjaeChoi%2Fvaemols/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YunjaeChoi","download_url":"https://codeload.github.com/YunjaeChoi/vaemols/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238945669,"owners_count":19556700,"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":["molecule","rdkit","tensorflow","variational-autoencoder"],"created_at":"2024-09-24T18:34:00.529Z","updated_at":"2025-10-30T08:30:58.117Z","avatar_url":"https://github.com/YunjaeChoi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"Variational Autoencoder for Molecules\n***********************************************\n\nVariational autoencoder for molecules in tensorflow.\n\nDependencies\n============\n\n1. Rdkit\n\n.. code:: shell\n\n    conda install -c rdkit rdkit\n\n2. Tensorflow\n\ncpu-version\n\n.. code:: shell\n\n    pip install tensorflow\n\ngpu-version\n\n.. code:: shell\n\n    pip install tensorflow-gpu\n\n\nPreprocessing\n=============\n\n1. Data\n-------\n\n`ChEBML 24 Database \u003chttps://www.ebi.ac.uk/chembl/downloads\u003e`_\nwas used for SMILES data.\n\nSMILES strings were padded with spaces to max_len(default=120) and strings larger than max_len were discarded. Remaining strings are labeled character by character(max_len labels in one string).\n\n2. preprocess.py\n----------------\n\nDoes the following steps:\n\n1. Downloads `chembl_24_1_chemreps.txt.gz \u003cftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_24_1_chemreps.txt.gz\u003e`_\n\n2. Preprocess SMILES strings\n\n3. Saves processed data into numpy arrays.\n\nNumpy arrays contains training data, testing data, dictionaries for character \u003c-\u003e label(integer) interchange.\n\nTraining\n========\n\n1. Model\n--------\n\nModel consists of CNN encoder and CuDNNGRU decoder and defined in \n`vae.py \u003chttps://github.com/YunjaeChoi/vaemols/blob/master/vaemols/models/vae.py\u003e`_\n\n2. train.py\n-----------\n\nDoes the following steps:\n\n1. Loads preprcessed data\n\n2. trains with fit_generator using DataGenerator\n\n\nNotebooks\n=========\n\nNotebooks are here to help after training is done.\n\n1. `structure_variation.ipynb \u003chttps://github.com/YunjaeChoi/vaemols/blob/master/structure_variation.ipynb\u003e`_\n-------------------------------------------------------------------------------------------------------------\n\nThis notebook helps to get variational structures when given a SMILES string.\n\n2. `visualize_latent_space.ipynb \u003chttps://github.com/YunjaeChoi/vaemols/blob/master/visualize_latent_space.ipynb\u003e`_\n-------------------------------------------------------------------------------------------------------------------\n\nThis notebook helps visualizing learned latent space using a plot or tensorboard.\n\ntensorboard visualization example:\n\n.. image:: https://raw.githubusercontent.com/YunjaeChoi/vaemols/master/doc/image/tensorboard.png\n\n3. `find_top_k_mols_in_latent_space.ipynb \u003chttps://github.com/YunjaeChoi/vaemols/blob/master/find_top_k_mols_in_latent_space.ipynb\u003e`_\n-------------------------------------------------------------------------------------------------------------------------------------\n\nThis notebook helps to get top_k similar molecules measured by euclidean distance in latent space.\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyunjaechoi%2Fvaemols","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyunjaechoi%2Fvaemols","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyunjaechoi%2Fvaemols/lists"}