Build branch main with version main (3c05b79)

Build pipeline: viash-hub.htrnaseq.main-bc45k Source commit: 3c05b7950b Source message: Remove duplicate entries from feature data (#41)
2025-02-17 15:45:09 +00:00
parent 1f84d46798
commit 6468e4a5de
61 changed files with 144 additions and 76 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,3 +1,9 @@
+# htrnaseq v0.5.2
+
+## Bug fixes
+
+* `create_fdata`: remove duplicate entries from feature data (PR #41).
+
 # htrnaseq v0.5.1

 ## Bug fixes
--- a/src/eset/create_fdata/create_fdata.py
+++ b/src/eset/create_fdata/create_fdata.py
@@ -119,10 +119,17 @@ def main(par):
        idx, cols = pd.factorize(column_to_get)
        symbol_values = annotation.reindex(cols, axis=1).to_numpy()[np.arange(len(annotation)), idx]
        annotation["SYMBOL"] = symbol_values
-
-    logger.info("Writing to %s", par["output"])
+    logger.info("Dropping unused columns")
    annotation = annotation.drop(["score", "source", "frame", "feature"], axis=1)
+    logger.info("Looking for duplicate rows and removing them. Starting with %i entries", annotation.shape[0])
+    annotation = annotation.drop_duplicates(keep="first", ignore_index=True)
+    logger.info("After removing duplicates: %i entries", annotation.shape[0])
+    logger.info("Writing to %s", par["output"])
    annotation.to_csv(par["output"], sep="\t", header=True, index=False, na_rep="NA")
+    # Do these checks *after* writing the csv in order to be able to check the data
+    logger.info("Checking for unique gene IDs")
+    if not annotation["gene_id"].is_unique:
+        raise ValueError("Values from the 'gene_id' column are not unique after processing!") 
    logger.info("%s finished", meta['name'])


--- a/src/eset/create_fdata/test.py
+++ b/src/eset/create_fdata/test.py
@@ -3,6 +3,7 @@ import sys
 import pandas as pd
 from pathlib import Path
 from uuid import uuid4
+from shutil import copyfile

 ### VIASH START
 meta = {
@@ -57,5 +58,45 @@ def test_create_fdata(run_component, test_annotation_path, random_path):
    pd.testing.assert_frame_equal(expected, result, check_like=True)


+def test_make_unique(run_component, test_annotation_path, random_path):
+    gtf_with_duplicate_entry_path = random_path("gtf")
+    output_path = random_path("tsv")
+    entry_to_add = (
+        "\n20	ensembl_havana	gene	87250	97094	.	+	.	gene_id " +
+        "\"ENSG00000178591.7\"; gene_version \"7\"; gene_name \"DEFB125\"; " +
+        "gene_source \"ensembl_havana\"; gene_biotype \"protein_coding\";\n"
+    )
+    copyfile(test_annotation_path, gtf_with_duplicate_entry_path)
+    with gtf_with_duplicate_entry_path.open("a") as open_gtf:
+        open_gtf.write(entry_to_add)
+    run_component([
+        "--gtf", gtf_with_duplicate_entry_path,
+        "--output", output_path
+    ])
+    assert output_path.is_file()
+    result = pd.read_csv(output_path, sep="\t", dtype=pd.StringDtype())
+    expected_dict = {
+        "seqname": ["20", "20", "20", "21"],
+        "start": ["87250", "142590", "157454", "297570"],
+        "end": ["97094", "145751", "159163", "300321"],
+        "strand": ["+", "+", "+", "+"],
+        "gene_id": ["ENSG00000178591", "ENSG00000125788",
+                    "ENSG00000088782", "ENSG00000247315"],
+        "gene_version": ["7", "6", "5", "4"],
+        "gene_name": ["DEFB125", "DEFB126", "DEFB127", pd.NA],
+        "gene_source": ["ensembl_havana", "ensembl_havana",
+                        "ensembl_havana", "havana"],
+        "gene_biotype": ["protein_coding", "protein_coding",
+                         "protein_coding", "protein_coding"],
+        "ENSEMBL_with_version": ["ENSG00000178591.7", "ENSG00000125788",
+                                 "ENSG00000088782", "ENSG00000247315"],
+        "ENSEMBL": ["ENSG00000178591", "ENSG00000125788",
+                    "ENSG00000088782", "ENSG00000247315"],
+        "SYMBOL": ["DEFB125", "DEFB126", "DEFB127", pd.NA]
+    }
+    expected = pd.DataFrame.from_dict(expected_dict, dtype=pd.StringDtype())
+    pd.testing.assert_frame_equal(expected, result, check_like=True)
+
+
 if __name__ == '__main__':
    sys.exit(pytest.main([__file__]))
--- a/target/executable/eset/create_eset/.config.vsh.yaml
+++ b/target/executable/eset/create_eset/.config.vsh.yaml
@@ -198,7 +198,7 @@ build_info:
  output: "target/executable/eset/create_eset"
  executable: "target/executable/eset/create_eset/create_eset"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/eset/create_eset/create_eset
+++ b/target/executable/eset/create_eset/create_eset
@@ -477,9 +477,9 @@ RUN Rscript -e 'if (!requireNamespace("remotes", quietly = TRUE)) install.packag

 LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke"
 LABEL org.opencontainers.image.description="Companion container for running component eset create_eset"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:05Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:42Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/eset/create_fdata/.config.vsh.yaml
+++ b/target/executable/eset/create_fdata/.config.vsh.yaml
@@ -177,7 +177,7 @@ build_info:
  output: "target/executable/eset/create_fdata"
  executable: "target/executable/eset/create_fdata/create_fdata"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/eset/create_fdata/create_fdata
+++ b/target/executable/eset/create_fdata/create_fdata
@@ -478,9 +478,9 @@ RUN pip install --upgrade pip && \

 LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke"
 LABEL org.opencontainers.image.description="Companion container for running component eset create_fdata"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:05Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:42Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
@@ -1162,10 +1162,17 @@ def main(par):
        idx, cols = pd.factorize(column_to_get)
        symbol_values = annotation.reindex(cols, axis=1).to_numpy()[np.arange(len(annotation)), idx]
        annotation["SYMBOL"] = symbol_values
-
-    logger.info("Writing to %s", par["output"])
+    logger.info("Dropping unused columns")
    annotation = annotation.drop(["score", "source", "frame", "feature"], axis=1)
+    logger.info("Looking for duplicate rows and removing them. Starting with %i entries", annotation.shape[0])
+    annotation = annotation.drop_duplicates(keep="first", ignore_index=True)
+    logger.info("After removing duplicates: %i entries", annotation.shape[0])
+    logger.info("Writing to %s", par["output"])
    annotation.to_csv(par["output"], sep="\\t", header=True, index=False, na_rep="NA")
+    # Do these checks *after* writing the csv in order to be able to check the data
+    logger.info("Checking for unique gene IDs")
+    if not annotation["gene_id"].is_unique:
+        raise ValueError("Values from the 'gene_id' column are not unique after processing!") 
    logger.info("%s finished", meta['name'])


--- a/target/executable/eset/create_pdata/.config.vsh.yaml
+++ b/target/executable/eset/create_pdata/.config.vsh.yaml
@@ -191,7 +191,7 @@ build_info:
  output: "target/executable/eset/create_pdata"
  executable: "target/executable/eset/create_pdata/create_pdata"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/eset/create_pdata/create_pdata
+++ b/target/executable/eset/create_pdata/create_pdata
@@ -488,9 +488,9 @@ RUN pip install --upgrade pip && \

 LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke"
 LABEL org.opencontainers.image.description="Companion container for running component eset create_pdata"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:05Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:42Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml
+++ b/target/executable/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml
@@ -148,7 +148,7 @@ build_info:
  output: "target/executable/integration_test_components/htrnaseq/check_eset"
  executable: "target/executable/integration_test_components/htrnaseq/check_eset/check_eset"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/integration_test_components/htrnaseq/check_eset/check_eset
+++ b/target/executable/integration_test_components/htrnaseq/check_eset/check_eset
@@ -470,9 +470,9 @@ RUN Rscript -e 'if (!requireNamespace("remotes", quietly = TRUE)) install.packag

 LABEL org.opencontainers.image.authors="Dries Schaumont"
 LABEL org.opencontainers.image.description="Companion container for running component integration_test_components/htrnaseq check_eset"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:05Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:42Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml
+++ b/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml
@@ -158,7 +158,7 @@ build_info:
  output: "target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output"
  executable: "target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output
+++ b/target/executable/integration_test_components/well_demultiplexing/check_cutadapt_output/check_cutadapt_output
@@ -476,9 +476,9 @@ RUN pip install --upgrade pip && \

 LABEL org.opencontainers.image.authors="Dries Schaumont"
 LABEL org.opencontainers.image.description="Companion container for running component integration_test_components/well_demultiplexing check_cutadapt_output"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:05Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:42Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/io/publish_fastqs/.config.vsh.yaml
+++ b/target/executable/io/publish_fastqs/.config.vsh.yaml
@@ -143,7 +143,7 @@ build_info:
  output: "target/executable/io/publish_fastqs"
  executable: "target/executable/io/publish_fastqs/publish_fastqs"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/io/publish_fastqs/publish_fastqs
+++ b/target/executable/io/publish_fastqs/publish_fastqs
@@ -470,9 +470,9 @@ RUN apt-get update && \
  rm -rf /var/lib/apt/lists/*

 LABEL org.opencontainers.image.description="Companion container for running component io publish_fastqs"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:03Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:41Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/io/publish_results/.config.vsh.yaml
+++ b/target/executable/io/publish_results/.config.vsh.yaml
@@ -187,7 +187,7 @@ build_info:
  output: "target/executable/io/publish_results"
  executable: "target/executable/io/publish_results/publish_results"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/io/publish_results/publish_results
+++ b/target/executable/io/publish_results/publish_results
@@ -484,9 +484,9 @@ RUN apt-get update && \
  rm -rf /var/lib/apt/lists/*

 LABEL org.opencontainers.image.description="Companion container for running component io publish_results"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:04Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:41Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/parallel_map/.config.vsh.yaml
+++ b/target/executable/parallel_map/.config.vsh.yaml
@@ -279,7 +279,7 @@ build_info:
  output: "target/executable/parallel_map"
  executable: "target/executable/parallel_map/parallel_map"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/parallel_map/parallel_map
+++ b/target/executable/parallel_map/parallel_map
@@ -540,9 +540,9 @@ ENV STAR_BINARY=STAR
 COPY STAR /usr/local/bin/$STAR_BINARY
 LABEL org.opencontainers.image.authors="Dries Schaumont, Toni Verbeiren"
 LABEL org.opencontainers.image.description="Companion container for running component parallel_map"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:06Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:43Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/report/create_report/.config.vsh.yaml
+++ b/target/executable/report/create_report/.config.vsh.yaml
@@ -201,7 +201,7 @@ build_info:
  output: "target/executable/report/create_report"
  executable: "target/executable/report/create_report/create_report"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/report/create_report/create_report
+++ b/target/executable/report/create_report/create_report
@@ -476,9 +476,9 @@ RUN Rscript -e 'if (!requireNamespace("remotes", quietly = TRUE)) install.packag

 LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke"
 LABEL org.opencontainers.image.description="Companion container for running component report create_report"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:06Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:43Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/stats/combine_star_logs/.config.vsh.yaml
+++ b/target/executable/stats/combine_star_logs/.config.vsh.yaml
@@ -198,7 +198,7 @@ build_info:
  output: "target/executable/stats/combine_star_logs"
  executable: "target/executable/stats/combine_star_logs/combine_star_logs"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/stats/combine_star_logs/combine_star_logs
+++ b/target/executable/stats/combine_star_logs/combine_star_logs
@@ -490,9 +490,9 @@ RUN pip install --upgrade pip && \

 LABEL org.opencontainers.image.authors="Dries Schaumont"
 LABEL org.opencontainers.image.description="Companion container for running component stats combine_star_logs"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:03Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:41Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/stats/generate_pool_statistics/.config.vsh.yaml
+++ b/target/executable/stats/generate_pool_statistics/.config.vsh.yaml
@@ -182,7 +182,7 @@ build_info:
  output: "target/executable/stats/generate_pool_statistics"
  executable: "target/executable/stats/generate_pool_statistics/generate_pool_statistics"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/stats/generate_pool_statistics/generate_pool_statistics
+++ b/target/executable/stats/generate_pool_statistics/generate_pool_statistics
@@ -483,9 +483,9 @@ RUN pip install --upgrade pip && \

 LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke"
 LABEL org.opencontainers.image.description="Companion container for running component stats generate_pool_statistics"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:04Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:41Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/executable/stats/generate_well_statistics/.config.vsh.yaml
+++ b/target/executable/stats/generate_well_statistics/.config.vsh.yaml
@@ -264,7 +264,7 @@ build_info:
  output: "target/executable/stats/generate_well_statistics"
  executable: "target/executable/stats/generate_well_statistics/generate_well_statistics"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/executable/stats/generate_well_statistics/generate_well_statistics
+++ b/target/executable/stats/generate_well_statistics/generate_well_statistics
@@ -520,9 +520,9 @@ RUN pip install --upgrade pip && \

 LABEL org.opencontainers.image.authors="Dries Schaumont, Marijke Van Moerbeke"
 LABEL org.opencontainers.image.description="Companion container for running component stats generate_well_statistics"
-LABEL org.opencontainers.image.created="2025-02-17T07:49:04Z"
+LABEL org.opencontainers.image.created="2025-02-17T14:58:42Z"
 LABEL org.opencontainers.image.source="https://github.com/viash-hub/htrnaseq"
-LABEL org.opencontainers.image.revision="a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+LABEL org.opencontainers.image.revision="3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
 LABEL org.opencontainers.image.version="main"

 VIASHDOCKER
--- a/target/nextflow/eset/create_eset/.config.vsh.yaml
+++ b/target/nextflow/eset/create_eset/.config.vsh.yaml
@@ -198,7 +198,7 @@ build_info:
  output: "target/nextflow/eset/create_eset"
  executable: "target/nextflow/eset/create_eset/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/eset/create_eset/main.nf
+++ b/target/nextflow/eset/create_eset/main.nf
@@ -3072,7 +3072,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/eset/create_eset",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/eset/create_fdata/.config.vsh.yaml
+++ b/target/nextflow/eset/create_fdata/.config.vsh.yaml
@@ -177,7 +177,7 @@ build_info:
  output: "target/nextflow/eset/create_fdata"
  executable: "target/nextflow/eset/create_fdata/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/eset/create_fdata/main.nf
+++ b/target/nextflow/eset/create_fdata/main.nf
@@ -3044,7 +3044,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/eset/create_fdata",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
@@ -3236,10 +3236,17 @@ def main(par):
        idx, cols = pd.factorize(column_to_get)
        symbol_values = annotation.reindex(cols, axis=1).to_numpy()[np.arange(len(annotation)), idx]
        annotation["SYMBOL"] = symbol_values
-
-    logger.info("Writing to %s", par["output"])
+    logger.info("Dropping unused columns")
    annotation = annotation.drop(["score", "source", "frame", "feature"], axis=1)
+    logger.info("Looking for duplicate rows and removing them. Starting with %i entries", annotation.shape[0])
+    annotation = annotation.drop_duplicates(keep="first", ignore_index=True)
+    logger.info("After removing duplicates: %i entries", annotation.shape[0])
+    logger.info("Writing to %s", par["output"])
    annotation.to_csv(par["output"], sep="\\\\t", header=True, index=False, na_rep="NA")
+    # Do these checks *after* writing the csv in order to be able to check the data
+    logger.info("Checking for unique gene IDs")
+    if not annotation["gene_id"].is_unique:
+        raise ValueError("Values from the 'gene_id' column are not unique after processing!") 
    logger.info("%s finished", meta['name'])


--- a/target/nextflow/eset/create_pdata/.config.vsh.yaml
+++ b/target/nextflow/eset/create_pdata/.config.vsh.yaml
@@ -191,7 +191,7 @@ build_info:
  output: "target/nextflow/eset/create_pdata"
  executable: "target/nextflow/eset/create_pdata/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/eset/create_pdata/main.nf
+++ b/target/nextflow/eset/create_pdata/main.nf
@@ -3058,7 +3058,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/eset/create_pdata",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml
+++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/.config.vsh.yaml
@@ -148,7 +148,7 @@ build_info:
  output: "target/nextflow/integration_test_components/htrnaseq/check_eset"
  executable: "target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf
+++ b/target/nextflow/integration_test_components/htrnaseq/check_eset/main.nf
@@ -2997,7 +2997,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/integration_test_components/htrnaseq/check_eset",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml
+++ b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/.config.vsh.yaml
@@ -158,7 +158,7 @@ build_info:
  output: "target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output"
  executable: "target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf
+++ b/target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output/main.nf
@@ -3009,7 +3009,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/integration_test_components/well_demultiplexing/check_cutadapt_output",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/io/publish_fastqs/.config.vsh.yaml
+++ b/target/nextflow/io/publish_fastqs/.config.vsh.yaml
@@ -143,7 +143,7 @@ build_info:
  output: "target/nextflow/io/publish_fastqs"
  executable: "target/nextflow/io/publish_fastqs/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/io/publish_fastqs/main.nf
+++ b/target/nextflow/io/publish_fastqs/main.nf
@@ -2983,7 +2983,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/io/publish_fastqs",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/io/publish_results/.config.vsh.yaml
+++ b/target/nextflow/io/publish_results/.config.vsh.yaml
@@ -187,7 +187,7 @@ build_info:
  output: "target/nextflow/io/publish_results"
  executable: "target/nextflow/io/publish_results/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/io/publish_results/main.nf
+++ b/target/nextflow/io/publish_results/main.nf
@@ -3032,7 +3032,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/io/publish_results",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/parallel_map/.config.vsh.yaml
+++ b/target/nextflow/parallel_map/.config.vsh.yaml
@@ -279,7 +279,7 @@ build_info:
  output: "target/nextflow/parallel_map"
  executable: "target/nextflow/parallel_map/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/parallel_map/main.nf
+++ b/target/nextflow/parallel_map/main.nf
@@ -3144,7 +3144,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/parallel_map",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/report/create_report/.config.vsh.yaml
+++ b/target/nextflow/report/create_report/.config.vsh.yaml
@@ -201,7 +201,7 @@ build_info:
  output: "target/nextflow/report/create_report"
  executable: "target/nextflow/report/create_report/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/report/create_report/main.nf
+++ b/target/nextflow/report/create_report/main.nf
@@ -3077,7 +3077,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/report/create_report",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/stats/combine_star_logs/.config.vsh.yaml
+++ b/target/nextflow/stats/combine_star_logs/.config.vsh.yaml
@@ -198,7 +198,7 @@ build_info:
  output: "target/nextflow/stats/combine_star_logs"
  executable: "target/nextflow/stats/combine_star_logs/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/stats/combine_star_logs/main.nf
+++ b/target/nextflow/stats/combine_star_logs/main.nf
@@ -3060,7 +3060,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/stats/combine_star_logs",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml
+++ b/target/nextflow/stats/generate_pool_statistics/.config.vsh.yaml
@@ -182,7 +182,7 @@ build_info:
  output: "target/nextflow/stats/generate_pool_statistics"
  executable: "target/nextflow/stats/generate_pool_statistics/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/stats/generate_pool_statistics/main.nf
+++ b/target/nextflow/stats/generate_pool_statistics/main.nf
@@ -3044,7 +3044,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/stats/generate_pool_statistics",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml
+++ b/target/nextflow/stats/generate_well_statistics/.config.vsh.yaml
@@ -264,7 +264,7 @@ build_info:
  output: "target/nextflow/stats/generate_well_statistics"
  executable: "target/nextflow/stats/generate_well_statistics/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/stats/generate_well_statistics/main.nf
+++ b/target/nextflow/stats/generate_well_statistics/main.nf
@@ -3139,7 +3139,7 @@ meta = [
    "engine" : "docker|native",
    "output" : "target/nextflow/stats/generate_well_statistics",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/utils/listInputDir/.config.vsh.yaml
+++ b/target/nextflow/utils/listInputDir/.config.vsh.yaml
@@ -165,7 +165,7 @@ build_info:
  output: "target/nextflow/utils/listInputDir"
  executable: "target/nextflow/utils/listInputDir/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/utils/listInputDir/main.nf
+++ b/target/nextflow/utils/listInputDir/main.nf
@@ -3004,7 +3004,7 @@ meta = [
    "engine" : "native|native",
    "output" : "target/nextflow/utils/listInputDir",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/workflows/htrnaseq/.config.vsh.yaml
+++ b/target/nextflow/workflows/htrnaseq/.config.vsh.yaml
@@ -319,7 +319,7 @@ build_info:
  output: "target/nextflow/workflows/htrnaseq"
  executable: "target/nextflow/workflows/htrnaseq/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
  dependencies:
  - "target/nextflow/stats/combine_star_logs"
--- a/target/nextflow/workflows/htrnaseq/main.nf
+++ b/target/nextflow/workflows/htrnaseq/main.nf
@@ -3223,7 +3223,7 @@ meta = [
    "engine" : "native|native",
    "output" : "target/nextflow/workflows/htrnaseq",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/workflows/runner/.config.vsh.yaml
+++ b/target/nextflow/workflows/runner/.config.vsh.yaml
@@ -207,7 +207,7 @@ build_info:
  output: "target/nextflow/workflows/runner"
  executable: "target/nextflow/workflows/runner/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
  dependencies:
  - "target/nextflow/utils/listInputDir"
--- a/target/nextflow/workflows/runner/main.nf
+++ b/target/nextflow/workflows/runner/main.nf
@@ -3069,7 +3069,7 @@ meta = [
    "engine" : "native|native",
    "output" : "target/nextflow/workflows/runner",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml
+++ b/target/nextflow/workflows/well_demultiplex/.config.vsh.yaml
@@ -211,7 +211,7 @@ build_info:
  output: "target/nextflow/workflows/well_demultiplex"
  executable: "target/nextflow/workflows/well_demultiplex/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
  dependencies:
  - "target/dependencies/vsh/vsh/biobox/v0.3.0/nextflow/cutadapt"
--- a/target/nextflow/workflows/well_demultiplex/main.nf
+++ b/target/nextflow/workflows/well_demultiplex/main.nf
@@ -3084,7 +3084,7 @@ meta = [
    "engine" : "native|native",
    "output" : "target/nextflow/workflows/well_demultiplex",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {
--- a/target/nextflow/workflows/well_metadata/.config.vsh.yaml
+++ b/target/nextflow/workflows/well_metadata/.config.vsh.yaml
@@ -209,7 +209,7 @@ build_info:
  output: "target/nextflow/workflows/well_metadata"
  executable: "target/nextflow/workflows/well_metadata/main.nf"
  viash_version: "0.9.0"
-  git_commit: "a0a780a9c1554e0e02de9e05bc88313594a08c6c"
+  git_commit: "3c05b7950b9627acdaa70687e0915d5ee69b6d1b"
  git_remote: "https://github.com/viash-hub/htrnaseq"
 package_config:
  name: "htrnaseq"
--- a/target/nextflow/workflows/well_metadata/main.nf
+++ b/target/nextflow/workflows/well_metadata/main.nf
@@ -3064,7 +3064,7 @@ meta = [
    "engine" : "native|native",
    "output" : "target/nextflow/workflows/well_metadata",
    "viash_version" : "0.9.0",
-    "git_commit" : "a0a780a9c1554e0e02de9e05bc88313594a08c6c",
+    "git_commit" : "3c05b7950b9627acdaa70687e0915d5ee69b6d1b",
    "git_remote" : "https://github.com/viash-hub/htrnaseq"
  },
  "package_config" : {