From 2d85a7ba1b429134f081dc69a058174a801b544e Mon Sep 17 00:00:00 2001
From: Robrecht Cannoodt <rcannood@gmail.com>
Date: Tue, 3 Sep 2024 06:20:40 +0200
Subject: [PATCH] add singler

---
 src/methods/singler/config.vsh.yaml         | 32 +++++++++++++++
 src/methods/singler/script.R                | 43 +++++++++++++++++++++
 src/workflows/run_benchmark/config.vsh.yaml |  1 +
 src/workflows/run_benchmark/main.nf         |  1 +
 4 files changed, 77 insertions(+)
 create mode 100644 src/methods/singler/config.vsh.yaml
 create mode 100644 src/methods/singler/script.R

diff --git a/src/methods/singler/config.vsh.yaml b/src/methods/singler/config.vsh.yaml
new file mode 100644
index 0000000..082cfca
--- /dev/null
+++ b/src/methods/singler/config.vsh.yaml
@@ -0,0 +1,32 @@
+__merge__: /src/api/comp_method.yaml
+name: "singler"
+label: SingleR
+summary: Reference-Based Single-Cell RNA-Seq Annotation
+description: |
+   Performs unbiased cell type recognition from single-cell RNA sequencing data,
+   by leveraging reference transcriptomic datasets of pure cell types to infer the
+   cell of origin of each single cell independently.
+references:
+  doi:
+    - 10.1038/s41590-018-0276-y
+links:
+  repository: https://www.bioconductor.org/packages/release/bioc/html/SingleR.html
+  documentation: https://www.bioconductor.org/packages/release/bioc/vignettes/SingleR/inst/doc/SingleR.html
+info:
+  preferred_normalization: log_cp10k
+  variants:
+    seurat:
+resources:
+  - type: r_script
+    path: script.R
+engines:
+  - type: docker
+    image: openproblems/base_r:1.0.0
+    setup:
+      - type: r
+        bioc: [SingleR]
+runners:
+  - type: executable
+  - type: nextflow
+    directives: 
+      label: [midtime, highmem, highcpu]
diff --git a/src/methods/singler/script.R b/src/methods/singler/script.R
new file mode 100644
index 0000000..f975eca
--- /dev/null
+++ b/src/methods/singler/script.R
@@ -0,0 +1,43 @@
+cat(">> Loading dependencies\n")
+library(anndata, warn.conflicts = FALSE)
+requireNamespace("SingleR", quietly = TRUE)
+library(Matrix, warn.conflicts = FALSE)
+
+## VIASH START
+par <- list(
+  input_train = "resources_test/task_label_projection/pancreas/train.h5ad",
+  input_test = "resources_test/task_label_projection/pancreas/test.h5ad",
+  output = "output.h5ad"
+)
+meta <- list(
+  name = "seurat_transferdata"
+)
+## VIASH END
+
+cat(">> Load input data\n")
+input_train <- read_h5ad(par$input_train)
+input_test <- read_h5ad(par$input_test)
+
+cat(">> Run method\n")
+pred <- SingleR::SingleR(
+  test = t(input_test$layers[["normalized"]]),
+  ref = t(input_train$layers[["normalized"]]),
+  labels = input_train$obs$label
+)
+
+cat(">> Create output data\n")
+output <- anndata::AnnData(
+  obs = data.frame(
+    row.names = input_test$obs_names,
+    label_pred = pred$labels
+  ),
+  uns = list(
+    method_id = meta$name,
+    dataset_id = input_test$uns[["dataset_id"]],
+    normalization_id = input_test$uns[["normalization_id"]]
+  ),
+  shape = c(input_test$n_obs, 0L)
+)
+
+cat(">> Write output to file\n")
+output$write_h5ad(par$output, compression = "gzip")
diff --git a/src/workflows/run_benchmark/config.vsh.yaml b/src/workflows/run_benchmark/config.vsh.yaml
index d66592f..b291a2d 100644
--- a/src/workflows/run_benchmark/config.vsh.yaml
+++ b/src/workflows/run_benchmark/config.vsh.yaml
@@ -76,6 +76,7 @@ dependencies:
   - name: methods/scanvi
   - name: methods/scanvi_scarches
   - name: methods/seurat_transferdata
+  - name: methods/singler
   - name: methods/xgboost
   - name: metrics/accuracy
   - name: metrics/f1
diff --git a/src/workflows/run_benchmark/main.nf b/src/workflows/run_benchmark/main.nf
index d7245d9..3e3970f 100644
--- a/src/workflows/run_benchmark/main.nf
+++ b/src/workflows/run_benchmark/main.nf
@@ -16,6 +16,7 @@ methods = [
   scanvi,
   scanvi_scarches,
   seurat_transferdata,
+  singler,
   xgboost
 ]