add cycombine no controls

CHANGELOG.md

@@ -25,6 +25,8 @@
 
 * Added `metrics/n_inconsistent_peaks` + some new helper functions (PR #31)
 
+* Added `methods/cycombine_nocontrol` (PR #35).
+
 ## MAJOR CHANGES
 
 * Updated file schema (PR #18): 

src/methods/cycombine_nocontrols/config.vsh.yaml

@@ -0,0 +1,41 @@
+__merge__: ../../api/comp_method.yaml
+
+name: cycombine_nocontrols
+label: cyCombine (no-controls)
+summary: "cyCombine perform batch correction by using self-organizing maps and ComBat."
+description: |
+  cyCombine perform batch integration by first using self-organizing maps (SOM) to 
+  group similar cells, then applies a ComBat-based method to correct batch effects within 
+  each group of similar cells. 
+
+  Here, we run cyCombine without control samples (replicates in cyCombine terminology).
+references:
+  doi: 
+    - 10.1038/s41467-022-29383-5
+links:
+  documentation: https://biosurf.org/cyCombine.html
+  repository: https://github.com/biosurf/cyCombine
+
+resources:
+  # The script of your component (required)
+  - type: r_script
+    path: script.R
+  # Additional resources your script needs (optional)
+  # - type: file
+  #   path: weights.pt
+
+engines:
+  - type: docker
+    image: openproblems/base_r:1.0.0
+    # Add custom dependencies here (optional). For more information, see
+    # https://viash.io/reference/config/engines/docker/#setup .
+    setup:
+      - type: r
+        bioc: [sva]
+        github: [biosurf/cyCombine]
+
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [midtime,midmem,midcpu]

src/methods/cycombine_nocontrols/script.R

@@ -0,0 +1,61 @@
+library(anndata)
+requireNamespace("cyCombine", quietly = TRUE)
+
+## VIASH START
+par <- list(
+  input = "resources_test/task_cyto_batch_integration/starter_file/unintegrated_censored.h5ad",
+  output = "resources_test/task_cyto_batch_integration/starter_file/output.h5ad"
+)
+meta <- list(name = "cycombine")
+## VIASH END
+
+cat("Reading input files\n")
+input_adata <- anndata::read_h5ad(par[["input"]])
+
+cat("Preparing input Anndata and df\n")
+
+adata_to_correct <- input_adata[, input_adata$var$to_correct]
+
+markers_to_correct <- input_adata$var_names[input_adata$var$to_correct]
+
+df_to_correct <- as.data.frame(
+  adata_to_correct$layers[["preprocessed"]],
+  check.names=FALSE
+)
+df_to_correct$batch <- adata_to_correct$obs$batch
+df_to_correct$sample <- adata_to_correct$obs$sample
+
+cat("Run cyCombine\n")
+df_corrected <- cyCombine::batch_correct(
+  df = df_to_correct,
+  seed = 42,
+  markers = markers_to_correct
+)
+
+cat("Preparing output Anndata\n")
+df_not_corrected <- as.data.frame(
+  input_adata[, !input_adata$var$to_correct]$layers[["preprocessed"]]
+)
+
+df_output <- cbind(
+  df_corrected[, markers_to_correct],
+  df_not_corrected
+)
+
+# reorder column to match input_adata
+df_output <- df_output[, input_adata$var_names]
+
+output <- anndata::AnnData(
+  obs = input_adata$obs[, integer(0)],
+  var = input_adata$var[colnames(df_output), integer(0)],
+  layers = list(integrated = df_output),
+  uns = list(
+    dataset_id = input_adata$uns$dataset_id,
+    method_id = meta$name,
+    parameters = list()
+  )
+)
+
+cat("Write output AnnData to file\n")
+
+output$write_h5ad(par[["output"]], compression = "gzip")

src/workflows/run_benchmark/config.vsh.yaml

@@ -71,6 +71,7 @@ dependencies:
   - name: methods/harmonypy
   - name: methods/limma_remove_batch_effect
   - name: methods/combat
+  - name: methods/cycombine_nocontrols
   - name: metrics/emd
   - name: metrics/n_inconsistent_peaks
 

src/workflows/run_benchmark/main.nf

@@ -14,7 +14,8 @@ methods = [
   limma_remove_batch_effect,
   no_integration,
   perfect_integration,
-  combat
+  combat,
+  cycombine_nocontrols
 ]
 
 // construct list of metrics