{"id":13593050,"url":"https://github.com/trungnt13/sisua","last_synced_at":"2025-04-14T22:14:53.582Z","repository":{"id":57467940,"uuid":"157284192","full_name":"trungnt13/sisua","owner":"trungnt13","description":"SemI-SUpervised generative Autoencoder models for single cell data ","archived":false,"fork":false,"pushed_at":"2021-03-30T10:29:08.000Z","size":3400,"stargazers_count":18,"open_issues_count":1,"forks_count":4,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-14T22:14:45.864Z","etag":null,"topics":["bayesian-inference","deep-learning","semi-supervised-learning","single-cell","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/trungnt13.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}},"created_at":"2018-11-12T22:10:24.000Z","updated_at":"2024-03-24T10:12:31.000Z","dependencies_parsed_at":"2022-09-19T08:20:18.808Z","dependency_job_id":null,"html_url":"https://github.com/trungnt13/sisua","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trungnt13%2Fsisua","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trungnt13%2Fsisua/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trungnt13%2Fsisua/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trungnt13%2Fsisua/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/trungnt13","download_url":"https://codeload.github.com/trungnt13/sisua/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248968917,"owners_count":21191162,"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":["bayesian-inference","deep-learning","semi-supervised-learning","single-cell","variational-autoencoder"],"created_at":"2024-08-01T16:01:16.093Z","updated_at":"2025-04-14T22:14:53.565Z","avatar_url":"https://github.com/trungnt13.png","language":"Jupyter Notebook","funding_links":[],"categories":["Software packages"],"sub_categories":["RNA-seq","Multi-assay data integration"],"readme":"SISUA\n=====\n\n|SISUA_design|\n\n.. |SISUA_design| image:: https://drive.google.com/uc?export=view\u0026id=1PvvG61_Rgbv_rqT6sCeb1XB6CtdiCMXX\n  :width: 405\n  :height: 249\n\n\nSemi-supervised Single-cell modeling:\n\n* Free software: MIT license\n* Documentation: https://github.com/trungnt13/sisua/tree/master/docs.\n\nReference:\n\n* Trung Ngo Trong, Roger Kramer, Juha Mehtonen, Gerardo González, Ville Hautamäki, Merja Heinäniemi. **\"SISUA: SemI-SUpervised Generative Autoencoder for Single Cell Data\"**, ICML Workshop on Computational Biology, 2019. `[pdf]`__\n\n.. __: https://doi.org/10.1101/631382\n\n\nInstallation\n************\n\nYou only need ``Python 3.6``, the stable version of SISUA installed via pip:\n\n  ``pip install sisua``\n\nInstall the nightly version on github:\n\n  ``pip install git+https://github.com/trungnt13/sisua@master``\n\nFor developers, we create a conda environment for SISUA contribution `sisua_env`__\n\n  ``conda env create -f=sisua_env.yml``\n\n.. __: https://github.com/trungnt13/sisua/blob/master/sisua_env.yml\n\nGetting started\n***************\n\na. The basics:\n    * `Datasets description`__\n    * `Models specification`\n    * `Basic API and work-flow`__\nb. Single-cell analysis:\n    * `Latent space`\n    * `Imputation of genes expression`\n    * `Prediction of protein markers`\nc. Advanced technical topics:\n    * `Probabilistic embedding`__\n    * `Hierarchical modeling` (*coming soon*)\n    * `Causal analysis` (*coming soon*)\n    * `Cross datasets analysis` (*coming soon*)\nd. Benchmarks:\n    * `Scalability test`__\n    * `Fine-tuning networks`\n    * `Data normalization`\n\n.. __: https://github.com/trungnt13/sisua/blob/master/docs/dataset_description.md\n.. __: https://github.com/trungnt13/sisua/blob/master/tutorials/basics.py\n.. __: https://github.com/trungnt13/sisua/blob/master/tutorials/probabilistic_embedding.py\n.. __: https://github.com/trungnt13/sisua/blob/master/tests/scalability.py\n\nRoadmap\n*******\n\n1. [x] Multi-OMICs single-cell dataset (`link`__)\n2. [x] Disentanglement VAE for multi-OMICs data (`link`__)\n3. [x] New model: FactorVAE, BetaVAE, MIxture Semi-supervised Autoencoder (MISA)  (`link`__)\n4. [ ] Better imputation via hierarchical latents model.\n5. [ ] Release SISUA 2\n\n.. __: https://github.com/trungnt13/sisua/blob/master/sisua/data/single_cell_dataset.py\n.. __: https://github.com/trungnt13/sisua/blob/master/sisua/models/fvae.py\n.. __: https://github.com/trungnt13/sisua/blob/master/sisua/models/vae.py\n\nToolkits\n********\n\nWe provide binary toolkits for *fast and efficient* analyzing single-cell datasets:\n\n* `sisua-train`__: train single-cell modeling algorithms, support training multiple systems in parallel.\n* `sisua-analyze`__: evaluate, compare, and interpret trained model.\n* `sisua-embed`__: probabilistic embedding for semi-supervised training.\n* `sisua-data`__: *coming soon*\n\n\n.. __: https://github.com/trungnt13/sisua/blob/master/bin/README.rst\n.. __: https://github.com/trungnt13/sisua/blob/master/bin/README.rst\n.. __: https://github.com/trungnt13/sisua/blob/master/bin/README.rst\n.. __: https://github.com/trungnt13/sisua/blob/master/bin/README.rst\n\nSome important arguments:\n\n-model\n            name of function declared in models__\n\n            - ``scvi``: single-cell Variational Inference model\n            - ``dca``: Deep Count Autoencoder\n            - ``vae``: single-cell Variational Autoencoder\n            - ``movae``: SISUA\n-ds\n            name of dataset declared in data__.\n\n            Description of all predefined datasets is in docs__.\n\n            Some good datasets for practicing:\n\n            - ``pbmc8k_ly``\n            - ``cortex``\n            - ``pbmcecc_ly``\n            - ``pbmcscvi``\n            - ``pbmcscvae``\n\n.. __: https://github.com/trungnt13/sisua/tree/master/sisua/models\n.. __: https://github.com/trungnt13/sisua/tree/master/sisua/data\n.. __: https://github.com/trungnt13/sisua/blob/master/docs/dataset_description.md\n\nConfiguration\n*************\n\nBy default, the data will be saved at your home folder at ``~/bio_data``,\nand the experiments' outputs will be stored at ``~/bio_log``\n\nYou can customize these two paths using the environment variables:\n\n* For storing downloaded and preprocessed data: ``SISUA_DATA``\n* For the experiments: ``SISUA_EXP``\n\nFor example:\n\n.. code-block:: python\n\n  import os\n  os.environ['SISUA_DATA'] = '/tmp/bio_data'\n  os.environ['SISUA_EXP'] = '/tmp/bio_log'\n\n  from sisua.data import EXP_DIR, DATA_DIR\n\n  print(DATA_DIR) # /tmp/bio_data\n  print(EXP_DIR)  # /tmp/bio_log\n\nor you could set the variables in advance:\n\n.. code-block:: bash\n\n  export SISUA_DATA=/tmp/bio_data\n  export SISUA_EXP=/tmp/bio_log\n  python sisua/train.py\n  # or using the provided toolkit: sisua-train\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrungnt13%2Fsisua","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrungnt13%2Fsisua","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrungnt13%2Fsisua/lists"}