daisybio/domainsplit is a bioinformatics pipeline that ...
This directory contains a Nextflow pipeline that downloads and processes all required public databases (3did, UniProt, Negatome, STRING, Pfam, pfam2go) to generate the domainsplit.sqlite3 database of domain-domain interactions, then splits it into train/validation/test partitions using several leakage-reduction strategies.
Note
If you are new to Nextflow and nf-core, please refer to this page on how to set-up Nextflow. Make sure to test your setup with -profile test before running the workflow on actual data.
Now, you can run the pipeline using:
nextflow run daisybio/domainsplit \
-profile <docker/singularity/.../institute> \
--outdir <OUTDIR>Warning
Please provide pipeline parameters via the CLI or Nextflow -params-file option. Custom config files including those provided by the -c Nextflow option can be used to provide any configuration except for parameters; see docs.
The main output is the SQLite database file domainsplit.sqlite3 in the results directory, plus per-method, per-split databases under results/split_databases/<method>/<split>.sqlite3.
- Each process in
main.nfis commented for clarity. - Some processes require external scripts (e.g.,
mysql2sqlitefor 3did conversion). - You may need to adjust paths or URLs as needed.
Some processes require secrets passed via environment variables. Copy .env.example to .env and fill in your values — the .env file is gitignored.
| Variable | Required | Description |
|---|---|---|
HF_TOKEN |
Yes (ESM embeddings) | HuggingFace access token for downloading ESM model weights. Obtain at https://huggingface.co/settings/tokens. |
On a SLURM cluster, export the variable in your job script or pass it as a Nextflow secret:
nextflow secrets set HF_TOKEN <your_token>daisybio/domainsplit was originally written by Konstantin Pelz, Christian Romberg, Chiara Thomas.
We thank the following people for their extensive assistance in the development of this pipeline:
If you would like to contribute to this pipeline, please see the contributing guidelines.
An extensive list of references for the tools used by the pipeline can be found in the CITATIONS.md file.
This pipeline uses code and infrastructure developed and maintained by the nf-core community, reused here under the MIT license.
The nf-core framework for community-curated bioinformatics pipelines.
Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.
Nat Biotechnol. 2020 Feb 13. doi: 10.1038/s41587-020-0439-x.