Patch release PR: 2.5.4

CHANGELOG.md

@@ -3,6 +3,22 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 2.5.4 - [2024-02-12]
+
+### `Added`
+
+### `Changed`
+
+- [#581](https://github.com/nf-core/mag/pull/581) - Added explicit licence text to headers of all custom scripts (reported by @FriederikeHanssen and @maxibor, fix by @jfy133)
+
+### `Fixed`
+
+- [#583](https://github.com/nf-core/mag/pull/583) - Fix GTDB database input when directory supplied (fix by @jfy133)
+
+### `Dependencies`
+
+### `Deprecated`
+
 ## 2.5.3 - [2024-02-05]
 
 ### `Added`

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/2.5.3" target="_blank">nf-core/mag</a>
+  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/2.5.4" target="_blank">nf-core/mag</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/mag/2.5.3/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/mag/2.5.4/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-mag-methods-description":
     order: -1000

bin/combine_tables.py

@@ -1,5 +1,9 @@
 #!/usr/bin/env python
 
+## Originally written by Daniel Straub and Sabrina Krakau and released under the MIT license.
+## See git repository (https://github.com/nf-core/mag) for full license text.
+
+
 import sys
 import argparse
 import os.path
@@ -8,11 +12,25 @@
 
 def parse_args(args=None):
     parser = argparse.ArgumentParser()
-    parser.add_argument("-d", "--depths_summary", required=True, metavar="FILE", help="Bin depths summary file.")
-    parser.add_argument("-b", "--busco_summary", metavar="FILE", help="BUSCO summary file.")
-    parser.add_argument("-c", "--checkm_summary", metavar="FILE", help="CheckM summary file.")
-    parser.add_argument("-q", "--quast_summary", metavar="FILE", help="QUAST BINS summary file.")
-    parser.add_argument("-g", "--gtdbtk_summary", metavar="FILE", help="GTDB-Tk summary file.")
+    parser.add_argument(
+        "-d",
+        "--depths_summary",
+        required=True,
+        metavar="FILE",
+        help="Bin depths summary file.",
+    )
+    parser.add_argument(
+        "-b", "--busco_summary", metavar="FILE", help="BUSCO summary file."
+    )
+    parser.add_argument(
+        "-c", "--checkm_summary", metavar="FILE", help="CheckM summary file."
+    )
+    parser.add_argument(
+        "-q", "--quast_summary", metavar="FILE", help="QUAST BINS summary file."
+    )
+    parser.add_argument(
+        "-g", "--gtdbtk_summary", metavar="FILE", help="GTDB-Tk summary file."
+    )
     parser.add_argument("-a", "--cat_summary", metavar="FILE", help="CAT table file.")
     parser.add_argument(
         "-o",
@@ -45,7 +63,14 @@ def parse_cat_table(cat_table):
         for line in f:
             maxcol = max(maxcol, len(line.split("\t")))
 
-    header = ["bin", "classification", "reason", "lineage", "lineage scores", "full lineage names"]
+    header = [
+        "bin",
+        "classification",
+        "reason",
+        "lineage",
+        "lineage scores",
+        "full lineage names",
+    ]
 
     df = pd.read_table(
         cat_table,
@@ -55,7 +80,11 @@ def parse_cat_table(cat_table):
         skiprows=1,
     )
     # merge all rank columns into a single column
-    df["CAT_rank"] = df.filter(regex="rank_\d+").apply(lambda x: ";".join(x.dropna()), axis=1).str.lstrip()
+    df["CAT_rank"] = (
+        df.filter(regex="rank_\d+")
+        .apply(lambda x: ";".join(x.dropna()), axis=1)
+        .str.lstrip()
+    )
     # remove rank_* columns
     df.drop(df.filter(regex="rank_\d+").columns, axis=1, inplace=True)
 
@@ -65,21 +94,34 @@ def parse_cat_table(cat_table):
 def main(args=None):
     args = parse_args(args)
 
-    if not args.busco_summary and not args.checkm_summary and not args.quast_summary and not args.gtdbtk_summary:
-        sys.exit("No summary specified! Please specify at least BUSCO, CheckM or QUAST summary.")
+    if (
+        not args.busco_summary
+        and not args.checkm_summary
+        and not args.quast_summary
+        and not args.gtdbtk_summary
+    ):
+        sys.exit(
+            "No summary specified! Please specify at least BUSCO, CheckM or QUAST summary."
+        )
 
     # GTDB-Tk can only be run in combination with BUSCO or CheckM
     if args.gtdbtk_summary and not (args.busco_summary or args.checkm_summary):
-        sys.exit("Invalid parameter combination: GTDB-TK summary specified, but no BUSCO or CheckM summary!")
+        sys.exit(
+            "Invalid parameter combination: GTDB-TK summary specified, but no BUSCO or CheckM summary!"
+        )
 
     # handle bin depths
     results = pd.read_csv(args.depths_summary, sep="\t")
-    results.columns = ["Depth " + str(col) if col != "bin" else col for col in results.columns]
+    results.columns = [
+        "Depth " + str(col) if col != "bin" else col for col in results.columns
+    ]
     bins = results["bin"].sort_values().reset_index(drop=True)
 
     if args.busco_summary:
         busco_results = pd.read_csv(args.busco_summary, sep="\t")
-        if not bins.equals(busco_results["GenomeBin"].sort_values().reset_index(drop=True)):
+        if not bins.equals(
+            busco_results["GenomeBin"].sort_values().reset_index(drop=True)
+        ):
             sys.exit("Bins in BUSCO summary do not match bins in bin depths summary!")
         results = pd.merge(
             results, busco_results, left_on="bin", right_on="GenomeBin", how="outer"
@@ -107,7 +149,9 @@ def main(args=None):
         ]
         checkm_results = pd.read_csv(args.checkm_summary, usecols=use_columns, sep="\t")
         checkm_results["Bin Id"] = checkm_results["Bin Id"] + ".fa"
-        if not bins.equals(checkm_results["Bin Id"].sort_values().reset_index(drop=True)):
+        if not bins.equals(
+            checkm_results["Bin Id"].sort_values().reset_index(drop=True)
+        ):
             sys.exit("Bins in CheckM summary do not match bins in bin depths summary!")
         results = pd.merge(
             results, checkm_results, left_on="bin", right_on="Bin Id", how="outer"
@@ -116,7 +160,9 @@ def main(args=None):
 
     if args.quast_summary:
         quast_results = pd.read_csv(args.quast_summary, sep="\t")
-        if not bins.equals(quast_results["Assembly"].sort_values().reset_index(drop=True)):
+        if not bins.equals(
+            quast_results["Assembly"].sort_values().reset_index(drop=True)
+        ):
             sys.exit("Bins in QUAST summary do not match bins in bin depths summary!")
         results = pd.merge(
             results, quast_results, left_on="bin", right_on="Assembly", how="outer"
@@ -134,7 +180,13 @@ def main(args=None):
         cat_results = parse_cat_table(args.cat_summary)
         if len(set(cat_results["bin"].to_list()).difference(set(bins))) > 0:
             sys.exit("Bins in CAT summary do not match bins in bin depths summary!")
-        results = pd.merge(results, cat_results[["bin", "CAT_rank"]], left_on="bin", right_on="bin", how="outer")
+        results = pd.merge(
+            results,
+            cat_results[["bin", "CAT_rank"]],
+            left_on="bin",
+            right_on="bin",
+            how="outer",
+        )
 
     results.to_csv(args.out, sep="\t")
 

bin/domain_classification.R

@@ -1,7 +1,7 @@
 #!/usr/bin/env Rscript
 
-# Written by Jim Downie and released under the MIT license.
-# See git repository (https://github.com/nf-core/mag) for full license text.
+## Written by Jim Downie and released under the MIT license.
+## See git repository (https://github.com/nf-core/mag) for full license text.
 
 library(optparse)
 library(tidyverse)

bin/filter_ssu.py

@@ -1,5 +1,8 @@
 #!/usr/bin/env python
 
+## Originally written by Hadrien Gourlé and released under the MIT license.
+## See git repository (https://github.com/nf-core/mag) for full license text.
+
 from __future__ import print_function
 
 import os
@@ -28,10 +31,16 @@ def filter(args):
 
 
 def main():
-    parser = argparse.ArgumentParser(prog="filter_ssu.py", usage="filter ssu hits from refinem")
+    parser = argparse.ArgumentParser(
+        prog="filter_ssu.py", usage="filter ssu hits from refinem"
+    )
     parser.add_argument("--evalue", help="evalue threshold")
-    parser.add_argument("ssu", metavar="ssu.tsv", help="ssu tsv file generated by refinem")
-    parser.add_argument("output", metavar="output.tsv", default="output.tsv", help="output file name")
+    parser.add_argument(
+        "ssu", metavar="ssu.tsv", help="ssu tsv file generated by refinem"
+    )
+    parser.add_argument(
+        "output", metavar="output.tsv", default="output.tsv", help="output file name"
+    )
     parser.set_defaults(func=filter)
     args = parser.parse_args()
 

bin/get_mag_depths.py

@@ -1,5 +1,8 @@
 #!/usr/bin/env python
 
+## Originally written by Sabrina Krakau and released under the MIT license.
+## See git repository (https://github.com/nf-core/mag) for full license text.
+
 import sys
 import argparse
 import os.path
@@ -14,7 +17,12 @@
 def parse_args(args=None):
     parser = argparse.ArgumentParser()
     parser.add_argument(
-        "-b", "--bins", required=True, nargs="+", metavar="FILE", help="Bins: FASTA containing all contigs."
+        "-b",
+        "--bins",
+        required=True,
+        nargs="+",
+        metavar="FILE",
+        help="Bins: FASTA containing all contigs.",
     )
     parser.add_argument(
         "-d",
@@ -23,9 +31,15 @@ def parse_args(args=None):
         metavar="FILE",
         help="(Compressed) TSV file containing contig depths for each sample: contigName, contigLen, totalAvgDepth, sample1_avgDepth, sample1_var [, sample2_avgDepth, sample2_var, ...].",
     )
-    parser.add_argument("-a", "--assembler", required=True, type=str, help="Assembler name.")
-    parser.add_argument("-i", "--id", required=True, type=str, help="Sample or group id.")
-    parser.add_argument("-m", "--binner", required=True, type=str, help="Binning method.")
+    parser.add_argument(
+        "-a", "--assembler", required=True, type=str, help="Assembler name."
+    )
+    parser.add_argument(
+        "-i", "--id", required=True, type=str, help="Sample or group id."
+    )
+    parser.add_argument(
+        "-m", "--binner", required=True, type=str, help="Binning method."
+    )
     return parser.parse_args(args)
 
 
@@ -56,7 +70,9 @@ def main(args=None):
 
     # Initialize output files
     n_samples = len(sample_names)
-    with open(args.assembler + "-" + args.binner + "-" + args.id + "-binDepths.tsv", "w") as outfile:
+    with open(
+        args.assembler + "-" + args.binner + "-" + args.id + "-binDepths.tsv", "w"
+    ) as outfile:
         print("bin", "\t".join(sample_names), sep="\t", file=outfile)
 
     # for each bin, access contig depths and compute mean bin depth (for all samples)
@@ -77,10 +93,15 @@ def main(args=None):
                         all_depths[sample].append(contig_depths[sample])
 
         binname = os.path.basename(file)
-        with open(args.assembler + "-" + args.binner + "-" + args.id + "-binDepths.tsv", "a") as outfile:
+        with open(
+            args.assembler + "-" + args.binner + "-" + args.id + "-binDepths.tsv", "a"
+        ) as outfile:
             print(
                 binname,
-                "\t".join(str(statistics.median(sample_depths)) for sample_depths in all_depths),
+                "\t".join(
+                    str(statistics.median(sample_depths))
+                    for sample_depths in all_depths
+                ),
                 sep="\t",
                 file=outfile,
             )

bin/get_mag_depths_summary.py

@@ -1,5 +1,8 @@
 #!/usr/bin/env python
 
+## Originally written by Sabrina Krakau and released under the MIT license.
+## See git repository (https://github.com/nf-core/mag) for full license text.
+
 import sys
 import argparse
 import pandas as pd

bin/multiqc_to_custom_tsv.py

@@ -1,5 +1,8 @@
 #!/usr/bin/env python
-# copied from nf-core/viralrecon and adjusted
+
+## Copied from nf-core/viralrecon and adjusted
+## See git repository (https://github.com/nf-core/viralrecon) for full license text.
+
 
 import os
 import sys
@@ -9,9 +12,7 @@
 
 
 def parse_args(args=None):
-    Description = (
-        "Create custom spreadsheet for pertinent MultiQC bowtie 2 metrics generated by the nf-core/mag pipeline."
-    )
+    Description = "Create custom spreadsheet for pertinent MultiQC bowtie 2 metrics generated by the nf-core/mag pipeline."
     Epilog = "Example usage: python multiqc_to_custom_tsv.py"
     parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
     parser.add_argument(
@@ -86,7 +87,9 @@ def metrics_dict_to_file(FileFieldList, MultiQCDataDir, OutFile, se):
     for yamlFile, mappingList in FileFieldList:
         yamlFile = os.path.join(MultiQCDataDir, yamlFile)
         if os.path.exists(yamlFile):
-            MetricsDict = yaml_fields_to_dict(YAMLFile=yamlFile, AppendDict=MetricsDict, FieldMappingList=mappingList)
+            MetricsDict = yaml_fields_to_dict(
+                YAMLFile=yamlFile, AppendDict=MetricsDict, FieldMappingList=mappingList
+            )
             FieldList += [x[0] for x in mappingList]
         else:
             print("WARNING: File does not exist: {}".format(yamlFile))
@@ -96,7 +99,15 @@ def metrics_dict_to_file(FileFieldList, MultiQCDataDir, OutFile, se):
         with open(OutFile, "w") as fout:
             if se:
                 fout.write(
-                    "{}\n".format("\t".join(["Sample", "SE reads not mapped (kept)", "SE reads mapped (discarded)"]))
+                    "{}\n".format(
+                        "\t".join(
+                            [
+                                "Sample",
+                                "SE reads not mapped (kept)",
+                                "SE reads mapped (discarded)",
+                            ]
+                        )
+                    )
                 )
             else:
                 fout.write(
@@ -118,7 +129,10 @@ def metrics_dict_to_file(FileFieldList, MultiQCDataDir, OutFile, se):
                             [
                                 k,
                                 str(MetricsDict[k][FieldList[0]]),
-                                str(MetricsDict[k][FieldList[1]] + MetricsDict[k][FieldList[2]]),
+                                str(
+                                    MetricsDict[k][FieldList[1]]
+                                    + MetricsDict[k][FieldList[2]]
+                                ),
                             ]
                         )
                     )