Model group Models Authors Contributed by Type Cite as License Tags
Model group Models Authors Contributed by Type Cite as License Tags
Basenji 1 David R. Kelley et al. Ziga Avsec tensorflow https://doi.org/10.1101/gr.227819.117 Apache License v2 RNA expression, Histone modification, DNA accessibility
Basset 1 David R. Kelley et al. Roman Kreuzhuber pytorch https://doi.org/10.1101/gr.200535.115 MIT DNA accessibility
CleTimer 2 Leohnard Wachutka et al. Leohnard Wachutka et al. None Apache License v2 RNA splicing
CpGenie 51 Haoyang Zeng et al. Roman Kreuzhuber custom, keras https://doi.org/10.1093/nar/gkx177 Apache License v2 DNA methylation
DeepBind 927 Babak Alipanahi et al. Johnny Israeli keras https://doi.org/10.1038/nbt.3300 BSD 3-Clause DNA binding
DeepCpG_DNA 5 Christof Angermueller et al. Roman Kreuzhuber keras https://doi.org/10.1186/s13059-017-1189-z
https://doi.org/10.5281/zenodo.1094823
MIT DNA methylation
DeepSEA 2 Jian Zhou et al. Roman Kreuzhuber pytorch https://doi.org/10.1038/nmeth.3547 CC-BY 3.0 Histone modification, DNA binding, DNA accessibility
Divergent421 1 Nancy Xu Nancy Xu keras MIT DNA accessibility
FactorNet 30 Daniel Quang et al. Ziga Avsec keras https://doi.org/10.1101/151274 MIT DNA binding
HAL 1 Alexander B. Rosenberg et al. Jun Cheng et al. None https://doi.org/10.1016/j.cell.2015.09.054 MIT RNA splicing
KipoiSplice 2 Ziga Avsec et al. Ziga Avsec et al. sklearn https://doi.org/10.1101/375345 MIT RNA splicing
MMSplice 10 Jun Cheng et al. Jun Cheng et al. custom, keras MIT RNA splicing
MaxEntScan 2 Gene Yeo et al. Jun Cheng et al. None https://doi.org/10.1089/1066527041410418 MIT RNA splicing
SiSp 1 Stephanie Maria Linker et al. Lara Urban keras https://doi.org/10.1101/328138 MIT RNA splicing
deepTarget 1 Byunghan Lee et al. Ziga Avsec None https://arxiv.org/pdf/1603.09123.pdf GPL-v3 RNA binding
extended_coda 1 Pang Wei Koh et al. Johnny Israeli keras https://doi.org/10.1093/bioinformatics/btx243 MIT Histone modification
labranchor 1 Joseph M. Paggi et al. Jun Cheng keras https://doi.org/10.1101/185868 CC BY-NC 4.0 RNA splicing
lsgkm-SVM 322 Dongwon Lee Roman Kreuzhuber None https://doi.org/10.1093/bioinformatics/btw142 MIT
pwm_HOCOMOCO 600 Ivan V. Kulakovskiy et al. Ziga Avsec keras https://doi.org/10.1093/nar/gkv1249 MIT DNA binding
rbp_eclip 112 Žiga Avsec et al. Žiga Avsec keras https://doi.org/10.1093/bioinformatics/btx727 MIT RNA binding

Kipoi models

CircleCI

This repository hosts predictive models for genomics and serves as a model source for Kipoi. Each folder containing the following files is considered to be a single model:

├── dataloader.py     # implements the dataloader
├── dataloader.yaml   # describes the dataloader
├── dataloader_files/      #/ files required by the dataloader
│   └── ...
├── model.yaml        # describes the model
├── model_files/           #/ files required by the model (like weights.h5 and arch.json)
│   └── ...
└── example_files/         #/ small example files used to test the model
    └── ...

Folders named *_files are tracked by Git Large File Storage (LFS). New models are added by simply submitting a pull-request to https://github.com/kipoi/models.

Contributing models

1. Install Kipoi

  1. Install git-lfs
  2. Install kipoi
    • pip install kipoi
  3. Run kipoi ls (this will checkout the kipoi/models repo to ~/.kipoi/models)

2. Add the model

  1. cd ~/.kipoi/models
  2. Write the model: Create a new folder <my new model> containing all the required files
    • Option 1: Copy the existing model: cp -R <existing model> <my new model> & edit the copied files
    • Option 2: Run kipoi init, answer the questions & edit the created files
    • Option 3: mkdir <my new model> & write all the files from scratch
  3. Test the model
    • Step 1: kipoi test ~/.kipoi/models/my_new_model
    • Step 2: kipoi test-source kipoi --all -k my_new_model
  4. Commit your changes
    • cd ~/.kipoi/models && git commit -m "Added <my new model>"

3. Submit the pull-request

  1. Fork the https://github.com/kipoi/models repo on github (click on the Fork button)
  2. Add your fork as a git remote to ~/.kipoi/models
    • cd ~/.kipoi/models && git remote add fork https://github.com/<username>/models.git
  3. Push to your fork
    • git push fork master
  4. Submit a pull-request (click the New pull request button on your github fork - https://github.com/<username>/models>)

See docs/contributing getting started and docs/tutorials/contributing/models for more information.

Using models (to predict, score variants, build new models)

To explore available models, visit http://kipoi.org/models. See kipoi/README.md and docs/using getting started for more information on how to programatically access the models from this repository using CLI, python or R.

Configuring local storage location

This model source (https://github.com/kipoi/models) is included in the Kipoi config file (~/.kipoi/config.yaml) by default:

# ~/.kipoi/config.yaml
model_sources:
    kipoi:
        type: git-lfs
        remote_url: [email protected]:kipoi/models.git
        local_path: ~/.kipoi/models/

If you wish to keep the models stored elsewhere, edit the local_path accordingly.