feat: added wrapper for MOFA2

.gitattributes

@@ -0,0 +1,2 @@
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true

bio/mofa2/environment.yaml

@@ -0,0 +1,10 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - bioconductor-mofa2 =1.16.0
+  - r-base =4.4.3
+  - r-arrow =22.0.0
+  - mofapy2 =0.7.2
+  - python =3.14.2

bio/mofa2/meta.yaml

@@ -0,0 +1,26 @@
+name: mofa2
+description: |
+  Train a model on a multi-omic data set with default options.
+url: https://www.bioconductor.org/packages/release/bioc/html/MOFA2.html
+authors:
+  - Simon Sack
+input:
+  - |
+    A parquet file in tidy format containing data with the headers: `sample, feature, view, group (optional), value`
+
+    `sample`: The name of the sample
+
+    `feature`: The name of the observed feature
+
+    `group` (optional, advanced): Discouraged for beginners. The aim of the multi-group framework is not to capture differential changes in mean levels between the groups (as for example when doing differential RNA expression). The goal is to compare the sources of variability that drive each group.
+
+    `value`: The observed value
+
+    `view`: The view the observed feature is grouped into
+output:
+  - An HDF5-file with the trained model.
+notes: |
+  In the params, set `scale_group` and/or `scale_views` to `TRUE`, if your groups/views
+  have different ranges/variances. This scales them to unit variance.
+  Defaults to `FALSE` if no params are given.
+  For all other training variables, this wrapper uses the default values.

bio/mofa2/test/Snakefile

@@ -0,0 +1,12 @@
+rule mofa2:
+    input:
+        "{data}.parquet",
+    output:
+        "{data}.hdf5",
+    log:
+        "log/{data}.log",
+    params:
+        scale_groups=False,  # set to TRUE if groups have different ranges/variances
+        scale_views=False,  # set to TRUE if views have different ranges/variances
+    wrapper:
+        "master/bio/mofa2"

bio/mofa2/wrapper.R

@@ -0,0 +1,53 @@
+#!/bin/R
+
+# load libraries
+library(MOFA2)
+library(arrow)
+
+# connect to conda environment
+conda_prefix <- Sys.getenv("CONDA_PREFIX")
+reticulate::use_condaenv(conda_prefix)
+
+# if log file is provided, write log to that file
+if (length(snakemake@log) > 0) {
+  log <- file(snakemake@log[[1]], open = "wt")
+  sink(log)
+  sink(log, type = "message")
+}
+
+# load long.data frame from parquet file with following headers:
+# `sample, feature, view, group (optional), value`
+
+# cast input path as character to avoid errors
+path <- as.character(snakemake@input[[1]])
+
+df <- read_parquet(path)
+
+mofa_object <- create_mofa(df)
+
+data_opts <- get_default_data_options(mofa_object)
+model_opts <- get_default_model_options(mofa_object)
+train_opts <- get_default_training_options(mofa_object)
+
+# model params: scale_groups, scale_views
+if ("scale_groups" %in% names(snakemake@params)) {
+  data_opts$scale_groups <- snakemake@params[["scale_groups"]]
+}
+
+if ("scale_views" %in% names(snakemake@params)) {
+  data_opts$scale_views <- snakemake@params[["scale_views"]]
+}
+
+# create MOFA-object
+mofa_object <- prepare_mofa(
+  object = mofa_object,
+  data_options = data_opts,
+  model_options = model_opts,
+  training_options = train_opts
+)
+
+# train the MOFA model and write the result to `outfile`
+run_mofa(
+  mofa_object,
+  snakemake@output[[1]]
+)

test_wrappers.py

@@ -107,7 +107,6 @@ def _run(wrapper, cmd, check_log=None, compare_results_with_expected=None):
                 f"file://{tmp_test_subdir}/",
             ]
 
-
         if CONTAINERIZED:
             # run snakemake in container
             cmd = [
@@ -129,9 +128,7 @@ def _run(wrapper, cmd, check_log=None, compare_results_with_expected=None):
                         with open(generated) as genf, open(expected) as expf:
                             gen_lines = genf.readlines()
                             exp_lines = expf.readlines()
-                        diff = "".join(
-                            difflib.Differ().compare(gen_lines, exp_lines)
-                        )
+                        diff = "".join(difflib.Differ().compare(gen_lines, exp_lines))
                         raise ValueError(
                             f"Unexpected results: {generated} != {expected}."
                             f"Diff:\n{diff}"
@@ -271,9 +268,19 @@ def test_agat(run):
 def test_alignoth(run):
     run(
         "bio/alignoth",
-        ["snakemake", "--cores", "1", "--use-conda", "-F", "out/json_plot.vl.json", "out/plot.html", "output-dir/"],
+        [
+            "snakemake",
+            "--cores",
+            "1",
+            "--use-conda",
+            "-F",
+            "out/json_plot.vl.json",
+            "out/plot.html",
+            "output-dir/",
+        ],
     )
 
+
 def test_alignoth_report_meta(run):
     run(
         "meta/bio/alignoth_report",
@@ -7166,6 +7173,11 @@ def test_orthanq(run):
         ],
     )
 
+
+def test_mofa2(run):
+    run("bio/mofa2", ["snakemake", "--cores", "1", "data.hdf5", "--use-conda", "-F"])
+
+
 def test_go_yq(run):
     run(
         "utils/go-yq",