config.vsh.yaml

__merge__: /src/api/comp_method.yaml
name: seurat_rpca
label: Seurat RPCA
summary: Integration using Seurat's anchor-based RPCA integration
description: |
  Seurat's Reciprocal PCA (RPCA) integration method represents a faster and more 
  conservative (less correction) approach compared to CCA integration. This method 
  is especially useful for large datasets or datasets with similar biological 
  composition across batches.
  
  The method works by:
  1. Finding highly variable features for each dataset
  2. Running PCA on each dataset
  3. Identifying integration anchors using RPCA
  4. Using anchors to harmonize datasets with more conservative correction
references:
  # Stuart, T., Butler, A., Hoffman, P. et al.
  # Comprehensive Integration of Single-Cell Data.
  # Cell 177, 1888-1902.e21 (2019). https://doi.org/10.1016/j.cell.2019.05.031
  doi: 10.1016/j.cell.2019.05.031
links:
  repository: https://github.com/satijalab/seurat
  documentation: https://satijalab.org/seurat/articles/seurat5_integration.html
info:
  method_types: [embedding]
  preferred_normalization: log_cp10k
arguments:
  - name: --dims
    type: integer
    description: Number of dimensions to use for integration.
    default: 30
  - name: --k_anchor
    type: integer
    description: Number of neighbors to use when picking anchors.
    default: 5
  - name: --k_filter
    type: integer
    description: Number of neighbors to use when filtering anchors.
    default: 200
  - name: --k_score
    type: integer  
    description: Number of neighbors to use when scoring anchors.
    default: 30
resources:
  - type: r_script
    path: script.R
engines:
  - type: docker
    image: openproblems/base_r:1
    setup:
      - type: r
        cran:
          - Seurat
          - SeuratObject
runners:
  - type: executable
  - type: nextflow
    directives:
      label: [lowcpu, highmem, hightime]