{"id":20893207,"url":"https://github.com/keiserlab/exceiver","last_synced_at":"2025-05-12T22:32:30.359Z","repository":{"id":62384660,"uuid":"543763968","full_name":"keiserlab/exceiver","owner":"keiserlab","description":null,"archived":false,"fork":false,"pushed_at":"2023-06-06T15:08:09.000Z","size":4101,"stargazers_count":11,"open_issues_count":1,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-03T03:26:59.396Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/keiserlab.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}},"created_at":"2022-09-30T19:43:48.000Z","updated_at":"2023-12-08T08:00:18.000Z","dependencies_parsed_at":"2023-02-12T05:00:42.146Z","dependency_job_id":null,"html_url":"https://github.com/keiserlab/exceiver","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/keiserlab%2Fexceiver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keiserlab%2Fexceiver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keiserlab%2Fexceiver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keiserlab%2Fexceiver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/keiserlab","download_url":"https://codeload.github.com/keiserlab/exceiver/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225156956,"owners_count":17429701,"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":"2024-11-18T10:14:59.369Z","updated_at":"2024-11-18T10:14:59.461Z","avatar_url":"https://github.com/keiserlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# exceiver\n\n[![arXiv](https://img.shields.io/badge/arXiv-2210.14330-b31b1b.svg)](https://arxiv.org/abs/2210.14330)\n\nA pretrained single cell gene expression language model.\n\n## install\n\n1. clone this repository: `git clone git@github.com:keiserlab/exceiver.git`\n2. install lightweight packaging tool: `conda install flit`\n3. install this repo in a new environment: `flit install -s`\n\n## usage\n\nsee `notebooks/example.ipynb` for loading pretrained models:\n\n```\nfrom exceiver.models import Exceiver\n\nmodel = Exceiver.load_from_checkpoint(\"../pretrained_models/exceiver/pretrained_TS_exceiver.ckpt\")\n```\n\n## preprocessing\n\n1. downlaod the Tabula Sapiens dataset [from figshare](https://figshare.com/articles/dataset/Tabula_Sapiens_release_1_0/14267219), specifically `TabulaSapiens.h5ad.zip` (careful this link will likely begin download: https://figshare.com/ndownloader/files/34702114)\n2. run `scripts/preprocess.py`:\n\n```\npython preprocess.py --ts_path /path/to/download/TabulaSapiens.h5ad\n                     --out_path /path/to/prepocessed/TabulaSapiens\n```\n\n## training\n\n`pytorch_lightning` makes distributed training easy and CLI access to a host of hyperparameters by running `scripts/train.py`:\n\n```\npython train.py --name MODELNAME \n                --data_path /path/to/prepocessed/TabulaSapiens \n                --logs path/to/model/logs\n                --frac 0.15 \n                --num_layers 1 \n                --nhead 4 \n                --query_len 128 \n                --batch_size 64 \n                --min_epochs 5 \n                --max_epochs 10 \n                --strategy ddp \n                --gpus 0,1,2,3 \n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeiserlab%2Fexceiver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkeiserlab%2Fexceiver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeiserlab%2Fexceiver/lists"}