New pipeline: nf-core/immunodesign #124
Description
Pipeline title/name
immunodesign
Keywords
anybody, CDR
What is it about?
An end-to-end Nextflow pipeline for antibody CDR redesign, structural validation, humanization, and developability scoring. This would be the first nf-core pipeline dedicated to structure-guided antibody optimization, bridging computational protein design and therapeutic antibody development.
Please provide a schematic diagram of the proposed pipeline
Input: Antibody structure files (PDB) and/or paired VH/VL sequences
Steps:
CDR Redesign — AntiFold: Redesigns CDR sequences via inverse folding conditioned on the antibody backbone structure. Generates diverse sequence candidates while preserving structural context.
Structural Validation — ABodyBuilder2: Refolds designed sequences to verify structural integrity of candidates and filters structurally implausible designs.
Humanization — BioPhi Sapiens: Humanizes antibody sequences using a deep learning model trained on human immune repertoires, reducing potential immunogenicity.
Humanness Scoring / Developability — OASis: Scores humanness by searching 9-mer peptides against the Observed Antibody Space (OAS) database, providing a quantitative developability metric.
Output: Ranked, humanized antibody candidates with structural validation metrics and OASis humanness scores; MultiQC summary report.
What would a minimal first release of this pipeline include?
- Accept a PDB structure file as input
- Run AntiFold → ABodyBuilder2 → BioPhi Sapiens → OASis in sequence
- Output ranked, humanized candidates with scores
- A MultiQC summary report of key metrics across all steps
- A working test profile with a small example PDB so anyone can run it out of the box
I confirm my proposed pipeline will follow nf-core guidelines. Most importantly, my pipeline will:
- be built with Nextflow.
- pass nf-core lint tests and use standardized parameters.
- be community-owned and developed within the nf-core organization.
- open source under the MIT license with proper credits and acknowledgments.
- have a descriptive, all lowercase, and without punctuation name.
- use the nf-core pipeline template and predominantly use official nf-core modules.
- focus on a specific data/analysis type with appropriate scope.
- have properly maintained documentation.
- be bundled using versioned Docker/Singularity containers.
Why do we need a new pipeline?
No existing overlap: There is currently no nf-core pipeline for structure-guided antibody CDR optimization or humanization.
Community need: Therapeutic antibody development is a major application area in both academia and industry; a standardized pipeline would benefit many groups.
Reproducibility gap: The tools listed above are all publicly available but have no shared orchestration layer — users must install and run them individually, making reproducibility difficult.
Who would be interested?
- Structural bioinformatics & protein engineering labs
- Immunology groups working on therapeutic antibodies
- Biotech/pharma computational antibody design teams
- Groups already using AntiFold or ABodyBuilder2 independently who would benefit from the full orchestrated workflow
What has been done so far
This pipeline is planned as a hackathon project and an initial working prototype will be developed collaboratively during the event.
URL to existing work (if applicable)
No response
Are there any similar existing nf-core pipelines?
No response