Merge pull request sanger-tol#110 from sanger-tol/xml_template

Allow population of either an XML or docx genome note template
reichan1998 · Mar 27, 2024 · 12bff64 · 12bff64
2 parents 659026f + ac7b5ea
commit 12bff64
Show file tree

Hide file tree

Showing 12 changed files with 105 additions and 41 deletions.
diff --git a/.nf-core.yml b/.nf-core.yml
@@ -20,3 +20,4 @@ lint:
   multiqc_config:
     - report_comment
   actions_ci: false
+  template_strings: False
diff --git a/assets/genome_note_template.xml b/assets/genome_note_template.xml
@@ -0,0 +1,34 @@
+<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE article>
+<article>
+    <body>
+        <sec>
+            <title>Species taxonomy</title>
+            <p>{{ TAX_STRING }};
+                <italic>{{ GENUS }}</italic>;
+                <italic>{{ GENUS_SPECIES }}</italic> ($TAXONOMY_AUTHORITY) (NCBI:txid{{ NCBI_TAXID }}) {{ TEST_NOT_REPLACED }}.
+            </p>
+        </sec>
+        <sec>
+            <table>
+                <thead>
+                    <tr>
+                        <th align="center" valign="top">INSDC accession</th>
+                        <th align="center" valign="top">Chromosome</th>
+                        <th align="center" valign="top">Length (Mb)</th>
+                        <th align="center" valign="top">GC%</th>
+                    </tr>
+                </thead>
+                <tbody>
+                    {% for chromosome in CHR_TABLE %}
+                    <tr>
+                        <td align="left" valign="top">{{ chromosome.get('Accession') }}</td>
+                        <td align="center" valign="top">{{ chromosome.get('Chromosome') }}</td>
+                        <td align="center" valign="top">{{ chromosome.get('Length') }}</td>
+                        <td align="center" valign="top">{{ chromosome.get('GC') }}</td>
+                    </tr>
+                    {% endfor %}
+                </tbody>
+            </table>
+        </sec>
+    </body>
+</article>
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
@@ -1,3 +1,3 @@
 sample,datatype,datafile
 ieCloDipt1,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Cloeon_dipterum/genomic_data/ieCloDipt1/pacbio/m64094_200901_101741.ccs.bc1001_BAK8A_OA--bc1001_BAK8A_OA.subsampled.bam
-ieCloDipt1,hic,https://tolit.cog.sanger.ac.uk/test-data/Cloeon_dipterum/analysis/ieCloDipt1.1/read_mapping/hic/GCA_949628265.1.unmasked.hic.ieCloDipt1.subsampled.cram
+ieCloDipt1,hic,https://tolit.cog.sanger.ac.uk/test-data/Cloeon_dipterum/analysis/ieCloDipt1.1/read_mapping/hic/GCA_949628265.1.unmasked.hic.ieCloDipt1.subsampled.cram
diff --git a/bin/populate_genome_note_template.py b/bin/populate_genome_note_template.py
@@ -15,9 +15,10 @@ def parse_args(args=None):
 
     parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
     parser.add_argument("PARAM_FILE", help="Input parameters CSV file.")
-    parser.add_argument("TEMPLATE_FILE", help="Input Genome Note Template Doc file.")
+    parser.add_argument("TEMPLATE_FILE", help="Input Genome Note Template file.")
+    parser.add_argument("TEMPLATE_TYPE", help="Input Genome Note Template file type.")
     parser.add_argument("FILE_OUT", help="Output file.")
-    parser.add_argument("--version", action="version", version="%(prog)s 1.0")
+    parser.add_argument("--version", action="version", version="%(prog)s 1.1")
     return parser.parse_args(args)
 
 
@@ -26,10 +27,14 @@ def make_dir(path):
         os.makedirs(path, exist_ok=True)
 
 
-def write_file(template, file_out):
+def write_file(template, type, file_out):
     out_dir = os.path.dirname(file_out)
     make_dir(out_dir)
-    template.save(os.path.join(out_dir, file_out))
+    if type == "docx":
+        template.save(os.path.join(out_dir, file_out))
+    else:
+        with open(file_out, "w") as fout:
+            fout.write(template)
 
 
 def build_param_list(param_file):
@@ -82,18 +87,25 @@ def build_param_list(param_file):
         return mydict
 
 
-def populate_template(param_file, template_file, file_out):
+def populate_template(param_file, template_file, template_type, file_out):
     myenv = jinja2.Environment(undefined=jinja2.DebugUndefined)
     context = build_param_list(param_file)
-    template = DocxTemplate(template_file)
-    template.render(context, myenv)
+    if template_type == "docx":
+        template = DocxTemplate(template_file)
+        template.render(context, myenv)
+        write_file(template, template_type, file_out)
+    else:
+        with open(template_file, "r") as file:
+            data = file.read()
 
-    write_file(template, file_out)
+        template = myenv.from_string(data)
+        content = template.render(context)
+        write_file(content, template_type, file_out)
 
 
 def main(args=None):
     args = parse_args(args)
-    populate_template(args.PARAM_FILE, args.TEMPLATE_FILE, args.FILE_OUT)
+    populate_template(args.PARAM_FILE, args.TEMPLATE_FILE, args.TEMPLATE_TYPE, args.FILE_OUT)
 
 
 if __name__ == "__main__":

diff --git a/conf/base.config b/conf/base.config
@@ -4,33 +4,6 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    Increasing the number of CPUs often gives diminishing returns, so we increase it
-    following a logarithm curve. Example:
-        - 0 < value <= 1: start + step
-        - 1 < value <= 2: start + 2*step
-        - 2 < value <= 4: start + 3*step
-        - 4 < value <= 8: start + 4*step
-    In order to support re-runs, the step increase may be multiplied by the attempt
-    number prior to calling this function.
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-// Modified logarithm function that doesn't return negative numbers
-def positive_log(value, base) {
-    if (value <= 1) {
-        return 0
-    } else {
-        return Math.log(value)/Math.log(base)
-    }
-}
-
-def log_increase_cpus(start, step, value, base) {
-    return check_max(start + step * (1 + Math.ceil(positive_log(value, base))), 'cpus')
-}
-
-
 process {
 
     errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }

diff --git a/conf/test.config b/conf/test.config
@@ -38,6 +38,7 @@ params {
     // Genome Notes Portal
     write_to_portal  = false
     genome_notes_api = "https://notes-staging.tol.sanger.ac.uk/api/v1"
+    note_template    = "${projectDir}/assets/genome_note_template.xml"
 
     // HiGlass Options
     upload_higlass_data = false

diff --git a/conf/test_full.config b/conf/test_full.config
@@ -38,6 +38,8 @@ params {
     // Genome Notes Portal
     write_to_portal  = false
     genome_notes_api = "https://notes-staging.tol.sanger.ac.uk/api/v1"
+    note_template    = "${projectDir}/assets/genome_note_template.docx"
+
 
     // HiGlass Options
     upload_higlass_data = true

diff --git a/docs/usage.md b/docs/usage.md
@@ -35,6 +35,12 @@ If you wish to run the optional step that writes genome metatdata key value-pair
    --genome_notes_api '[URL for Genome Notes Portal API]'
 ```
 
+If you want to populate a genome notes template file with the key-value pairs generated by this pipeline you will need to pass the path to the template file as the "note_template" parameter. Templates may be either docx or xml format.
+
+```bash
+   --note_template '[URL for Genome Notes Portal API]'
+```
+
 You will also need to set a nextflow secret to store the API key belonging to your user.
 
 ```bash

diff --git a/modules/local/populate_template.nf b/modules/local/populate_template.nf
@@ -11,20 +11,22 @@ process POPULATE_TEMPLATE {
     path(note_template)
 
     output:
-    tuple val(meta), path("*.docx"), emit: genome_note
+    tuple val(meta), path("*.{docx,xml}"), emit: genome_note
     path "versions.yml", emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def prefix = task.ext.prefix ?: meta.id
+    def file_type = note_template.extension
 
     """
     populate_genome_note_template.py \\
         $param_data \\
         $note_template \\
-        ${prefix}.docx
+        ${file_type} \\
+        ${prefix}.${file_type}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/nextflow.config b/nextflow.config
@@ -24,6 +24,7 @@ params {
     // Genome Notes 
     write_to_portal                 = false     
     genome_notes_api                = null
+    note_template                   = null
 
     // HiGlass options
     upload_higlass_data             = false
@@ -280,3 +281,29 @@ def check_max(obj, type) {
         }
     }
 }
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Increasing the number of CPUs often gives diminishing returns, so we increase it
+    following a logarithm curve. Example:
+        - 0 < value <= 1: start + step
+        - 1 < value <= 2: start + 2*step
+        - 2 < value <= 4: start + 3*step
+        - 4 < value <= 8: start + 4*step
+    In order to support re-runs, the step increase may be multiplied by the attempt
+    number prior to calling this function.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+// Modified logarithm function that doesn't return negative numbers
+def positive_log(value, base) {
+    if (value <= 1) {
+        return 0
+    } else {
+        return Math.log(value)/Math.log(base)
+    }
+}
+
+def log_increase_cpus(start, step, value, base) {
+    return check_max(start + step * (1 + Math.ceil(positive_log(value, base))), 'cpus')
+}
diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -83,6 +83,13 @@
                     "description": "URL for Genome Notes Portal API .",
                     "fa_icon": "far fa-file-code"
                 },
+                "note_template": {
+                    "type": "string",
+                    "format": "file-path",
+                    "description": "The path to a genome note template file.",
+                    "help_text": "Set this parameter if you have a genome note template file that you wish to populate. Templates may be docx or xml files",
+                    "fa_icon": "fas fa-folder-open"
+                },
                 "upload_higlass_data": {
                     "type": "boolean",
                     "description": "flag to control if Higlass server should be updated to add new files",

diff --git a/workflows/genomenote.nf b/workflows/genomenote.nf
@@ -25,7 +25,7 @@ if (params.lineage_tax_ids) { ch_lineage_tax_ids = Channel.fromPath(params.linea
 
 // Check optional parameters
 if (params.lineage_db) { ch_lineage_db = Channel.fromPath(params.lineage_db) } else { ch_lineage_db = Channel.empty() }
-
+if (params.note_template) { ch_note_template = Channel.fromPath(params.note_template) } else { ch_note_template = Channel.empty() } 
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -35,7 +35,6 @@ if (params.lineage_db) { ch_lineage_db = Channel.fromPath(params.lineage_db) } e
 
 ch_metdata_input           = Channel.of( metadata_inputs )
 ch_file_list               = Channel.fromPath("$projectDir/assets/genome_metadata_template.csv")
-ch_note_template           = Channel.fromPath("$projectDir/assets/genome_note_template.docx")    
 ch_multiqc_config          = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
 ch_multiqc_custom_config   = params.multiqc_config ? Channel.fromPath( params.multiqc_config, checkIfExists: true ) : Channel.empty()
 ch_multiqc_logo            = params.multiqc_logo   ? Channel.fromPath( params.multiqc_logo, checkIfExists: true ) : Channel.empty()