diff blast_annotations_processor.xml @ 0:a3989edf0a4a draft

planemo upload for repository https://github.com/Onnodg/Naturalis_NLOOR/tree/main/NLOOR_scripts/process_annotations_tool commit c944fd5685f295acba06679e85b67973c173b137
author onnodg
date Tue, 14 Oct 2025 09:08:30 +0000
parents
children 2acf82433aa4
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/blast_annotations_processor.xml	Tue Oct 14 09:08:30 2025 +0000
@@ -0,0 +1,202 @@
+<tool id="blast_annotation_processor" name="BLAST Annotation Processor" version="1.0.0">
+    <description>Process BLAST annotation results with taxonomic analysis</description>
+
+    <requirements>
+        <requirement type="package" version="3.12.3">python</requirement>
+        <requirement type="package" version="3.10.6">matplotlib</requirement>
+        <requirement type="package" version="2.3.2">pandas</requirement>
+        <requirement type="package" version="2.3.2">numpy</requirement>
+        <requirement type="package" version="3.1.5">openpyxl</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+python '$__tool_directory__/blast_annotations_processor.py'
+            --input-anno '$input_anno'
+            --input-unanno '$input_unanno'
+
+            #if $outputs and 'eval_plot' in $outputs
+                --eval-plot '$eval_plot'
+            #end if
+
+            #if $outputs and 'taxa_output' in $outputs
+                --taxa-output '$taxa_output'
+            #end if
+
+            #if $outputs and 'circle_data' in $outputs
+                --circle-data '$circle_data'
+            #end if
+
+            #if $outputs and 'header_anno' in $outputs
+                --header-anno '$header_anno'
+            #end if
+
+            #if $outputs and 'anno_stats' in $outputs
+                --anno-stats '$anno_stats'
+            #end if
+
+            --uncertain-threshold $advanced.uncertain_threshold
+            --eval-threshold $advanced.eval_threshold
+            #if $advanced.use_counts
+                --use-counts
+            #end if
+    ]]></command>
+
+    <inputs>
+        <!-- Required Input Files -->
+        <param name="input_anno" type="data" format="tabular"
+               label="Annotated BLAST output file"
+               help="Tabular BLAST output with taxonomic annotations"/>
+
+        <param name="input_unanno" type="data" format="fasta"
+               label="Original unannotated sequences"
+               help="FASTA file with original sequences before BLAST annotation"/>
+
+        <!-- Output Selection -->
+        <param name="outputs" type="select" multiple="true" display="checkboxes"
+               label="Select outputs to generate" help="Choose which analysis outputs to create">
+            <option value="eval_plot">E-value distribution plot</option>
+            <option value="taxa_output">Taxonomic report (Kraken2-like format)</option>
+            <option value="circle_data">Circular taxonomic datafile</option>
+            <option value="header_anno">Header annotations table</option>
+            <option value="anno_stats">Annotation statistics</option>
+        </param>
+
+        <!-- Processing Parameters -->
+        <section name="advanced" title="Advanced Parameters" expanded="false">
+            <param name="uncertain_threshold" type="float" value="0.9" min="0.0" max="1.0"
+                   label="Uncertain threshold"
+                   help="Threshold for resolving taxonomic conflicts (0.0-1.0). If one taxon represents more than this fraction of reads, it will be used instead of 'Uncertain taxa'"/>
+
+            <param name="eval_threshold" type="float" value="1e-10" min="0"
+                   label="E-value threshold"
+                   help="Maximum E-value to consider for annotations. Results with higher E-values will be filtered out"/>
+
+            <param name="use_counts" type="boolean" checked="true"
+                   label="Use read counts in circular diagrams"
+                   help="If checked, circular diagrams will reflect read abundance. If unchecked, only unique taxa are counted"/>
+        </section>
+    </inputs>
+
+    <outputs>
+        <!-- E-value Plot -->
+        <data name="eval_plot" format="png" label="E-value distribution plot on ${on_string}">
+            <filter>outputs and 'eval_plot' in outputs</filter>
+        </data>
+    
+        <!-- Taxa Output Report -->
+        <data name="taxa_output" format="txt" label="Taxonomic report on ${on_string}">
+            <filter>outputs and 'taxa_output' in outputs</filter>
+        </data>
+
+        <!-- Circular Taxonomy Diagram -->
+        <data name="circle_data" format="txt" label="Circular taxonomic data on ${on_string}">
+            <filter>outputs and 'circle_data' in outputs</filter>
+        </data>
+
+        <!-- Header Annotations -->
+        <data name="header_anno" format="xlsx" label="Header annotations on ${on_string}">
+            <filter>outputs and 'header_anno' in outputs</filter>
+        </data>
+
+        <!-- Annotation Statistics -->
+        <data name="anno_stats" format="txt" label="Annotation statistics on ${on_string}">
+            <filter>outputs and 'anno_stats' in outputs</filter>
+        </data>
+    </outputs>
+
+    <tests>
+        <test expect_num_outputs="5">
+            <param name="input_anno" value="input_test_curated_labels.tabular"/>
+            <param name="input_unanno" value="input_test_curated.fasta"/>
+            <param name="outputs" value="eval_plot,taxa_output,circle_data,header_anno,anno_stats"/>
+            <output name="taxa_output" file="output_taxa_output.txt"/>
+            <output name="eval_plot" file="output_eval.png" compare="sim_size"/>
+            <output name="header_anno" file="header_anno_excel.xlsx" decompress="true"/>
+            <output name="anno_stats" file="output_anno_out.txt"/>
+            <output name="circle_data" file="output_circle_data.txt"/>
+            <section name="advanced">
+               <param name="uncertain_threshold" value="0.9"/>
+               <param name="eval_threshold" value="1e-10"/>
+               <param name="use_counts" value="True"/>
+            </section>
+        </test>
+        <test expect_num_outputs="5">
+            <param name="input_anno" value="galaxy_input_genbank.fa.tabular"/>
+            <param name="input_unanno" value="galaxy_input_pre.fasta"/>
+            <param name="outputs" value="eval_plot,taxa_output,circle_data,header_anno,anno_stats"/>
+            <output name="taxa_output" file="output_genbank_taxa_output.txt"/>
+            <output name="eval_plot" file="output_genbank_eval.png" compare="sim_size"/>
+            <output name="header_anno" file="output_genbank_header_anno.xlsx" decompress="true"/>
+            <output name="anno_stats" file="output_genbank_anno_out.txt"/>
+            <output name="circle_data" file="output_genbank_circle_data.txt"/>
+        </test>
+        <test expect_num_outputs="3">
+            <param name="input_anno" value="galaxy_input_genbank.fa.tabular"/>
+            <param name="input_unanno" value="galaxy_input_pre.fasta"/>
+            <param name="outputs" value="circle_data,header_anno,anno_stats"/>
+            <output name="header_anno" file="output_advanced_header_anno.xlsx" decompress="true"/>
+            <output name="anno_stats" file="output_advanced_anno_out.txt"/>
+            <output name="circle_data" file="advanced_circle_data.txt"/>
+            <section name="advanced">
+               <param name="uncertain_threshold" value="0.8"/>
+               <param name="eval_threshold" value="1e-8"/>
+               <param name="use_counts" value="True"/>
+            </section>
+        </test>
+
+    </tests>
+
+    <help><![CDATA[
+**BLAST Annotation Processor**
+
+This tool processes BLAST annotation results and generates various quality control and visualization outputs.
+
+**Inputs:**
+
+- **Annotated BLAST output**: Tabular BLAST output file with taxonomic annotations. Expected format is standard BLAST tabular output with taxonomic information in the last column.
+
+- **Original unannotated sequences**: FASTA file containing the original sequences that were used for BLAST search. This is used to calculate annotation statistics.
+
+**Outputs:**
+
+- **E-value distribution plot**: Visualization showing the distribution of E-values across all annotated sequences.
+
+- **Taxonomic report**: Kraken2-like format report showing taxonomic composition with read counts and percentages. Includes information about uncertain taxonomic assignments.
+
+- **Circular taxonomic data**: Json data to generate a circular sunburst-style diagram showing taxonomic composition across all taxonomic levels (Kingdom -> Species).
+
+- **Header annotations table**: Excel workbook listing each sequence header with its taxonomic assignment and E-value.
+
+- **Annotation statistics**: Summary statistics about annotation success rates and sequence counts.
+
+**Parameters:**
+
+- **Uncertain threshold**: When multiple conflicting taxonomic assignments exist for a sequence, this threshold determines whether to use the most common assignment (if it exceeds the threshold) or mark it as "Uncertain taxa".
+
+- **E-value threshold**: Sequences with E-values higher than this threshold are filtered out from the analysis.
+
+- **Use read counts**: Determines whether circular data reflects the abundance of reads (checked) or just count unique taxonomic assignments (unchecked).
+#Query ID	#Subject	#Subject accession	#Subject Taxonomy ID	#Identity percentage
+	#Coverage	#evalue	#bitscore	#Source	#Taxonomy
+**Expected Input Format:**
+
+The annotated BLAST file should be in tabular format with at least 7 columns:
+1. Query ID
+2. Subject ID
+3. Subject accession
+4. Subject Taxonomy ID
+5. Identity percentage
+6. Coverage
+7. Evalue
+8. Bitscore
+9. Source
+10. Taxonomy
+
+**Note:** This tool processes files that have been deduplicated and contain read count information in the sequence headers in the format: `sequence_name(count_number)`.
+
+**Credits**
+Authors = Onno de Gorter, 2025.
+Based on a script by Nick Kortleven, translated, modified and wrapped by Onno de Gorter,
+Developed for the New light on old remedies project, a PhD research by Anja Fischer
+    ]]></help>
+</tool>
\ No newline at end of file