Mercurial > repos > maciek > spamr_vet_tools
changeset 0:4d244352ec4c draft
Initial commit: added Python scripts and XML configurations.
| author | maciek |
|---|---|
| date | Mon, 17 Feb 2025 09:57:10 +0000 |
| parents | |
| children | e57a908b9d3d |
| files | spamr_vet_tools/1_quality_script_fastp_bracken.py spamr_vet_tools/1_quality_script_fastp_bracken.xml spamr_vet_tools/2_quast_get_fasta.py spamr_vet_tools/2_quast_get_fasta.xml spamr_vet_tools/3_MLST_AMRFINDER_STARAMR.py spamr_vet_tools/3_mlst_amr_staramr.xml |
| diffstat | 6 files changed, 512 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/spamr_vet_tools/1_quality_script_fastp_bracken.py Mon Feb 17 09:57:10 2025 +0000 @@ -0,0 +1,123 @@ +import json +import csv +import sys +import os + +def extract_software_data(json_data, software_name): + """ + Usage: python script.py input.json + For "bracken", add a "contamination" column where the value is "pass" + if fraction_total_reads > 0.6, otherwise "fail". + For "fastp", include only specific columns. + """ + # Ensure json_data is a dictionary + if isinstance(json_data, list): + json_data = next((entry for entry in json_data if "analysis_software_name" in entry and entry["analysis_software_name"] == software_name), None) + + if not isinstance(json_data, dict): + print(f"Invalid JSON format for {software_name} extraction.") + return + + results = json_data.get("results", []) + extracted_data = [] + headers = [] # Use list to collect headers to maintain order + output_csv_file = f"{software_name}_output.csv" + + # Define specific columns for "fastp" + fastp_columns = [ + "summary_sequencing", + "summary_before_filtering_total_reads", + "summary_before_filtering_total_bases", + "summary_before_filtering_q20_bases", + "summary_before_filtering_q30_bases", + "summary_before_filtering_q20_rate", + "summary_before_filtering_q30_rate", + "summary_before_filtering_read1_mean_length", + "summary_before_filtering_read2_mean_length", + "summary_before_filtering_gc_content", + "summary_after_filtering_total_reads", + "summary_after_filtering_total_bases", + "summary_after_filtering_q20_bases", + "summary_after_filtering_q30_bases", + "summary_after_filtering_q20_rate", + "summary_after_filtering_q30_rate", + "summary_after_filtering_read1_mean_length", + "summary_after_filtering_read2_mean_length", + "summary_after_filtering_gc_content", + "filtering_result_passed_filter_reads", + "filtering_result_low_quality_reads", + "filtering_result_too_many_N_reads", + "filtering_result_too_short_reads", + "filtering_result_too_long_reads", + "duplication_rate", + "insert_size_peak", + ] + + for entry in results: + if "content" in entry and isinstance(entry["content"], list): + for content_item in entry["content"]: + row_data = {} + if software_name == "fastp": + for key, value in content_item.items(): + if isinstance(value, dict): + for sub_key, sub_value in value.items(): + if isinstance(sub_value, dict): + for sub_sub_key, sub_sub_value in sub_value.items(): + column_name = f"{key}_{sub_key}_{sub_sub_key}" + if column_name in fastp_columns: + row_data[column_name] = sub_sub_value + if column_name not in headers: + headers.append(column_name) + else: + column_name = f"{key}_{sub_key}" + if column_name in fastp_columns: + row_data[column_name] = sub_value + if column_name not in headers: + headers.append(column_name) + else: + if key in fastp_columns: + row_data[key] = value + if key not in headers: + headers.append(key) + elif software_name == "bracken": + for key, value in content_item.items(): + if isinstance(value, dict): + for sub_key, sub_value in value.items(): + column_name = f"{key}_{sub_key}" + row_data[column_name] = sub_value + if column_name not in headers: + headers.append(column_name) + else: + row_data[key] = value + if key not in headers: + headers.append(key) + + # Add contamination column for "bracken" + fraction_total_reads = row_data.get("fraction_total_reads", 0) + row_data["contamination"] = "pass" if float(fraction_total_reads) > 0.6 else "fail" + if "contamination" not in headers: + headers.append("contamination") + + extracted_data.append(row_data) + + with open(output_csv_file, "w", newline="", encoding="utf-8") as f: + writer = csv.DictWriter(f, fieldnames=headers) + writer.writeheader() + writer.writerows(extracted_data) + + print(f"File CSV generato con successo: {output_csv_file}") + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python script.py input.json") + sys.exit(1) + + input_json_file = sys.argv[1] + + try: + with open(input_json_file, "r", encoding="utf-8") as file: + json_data = json.load(file) + extract_software_data(json_data, "fastp") + extract_software_data(json_data, "bracken") + except Exception as e: + print(f"Error processing file: {e}")
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/spamr_vet_tools/1_quality_script_fastp_bracken.xml Mon Feb 17 09:57:10 2025 +0000 @@ -0,0 +1,42 @@ +<tool id="quality_script_fastp_bracken" + name="Quality Control FastP Bracken" + version="0.1.0+galaxy0" + python_template_version="3.5" + profile="21.05"> + + <description>Quality control using FastP and Bracken</description> + + <requirements> + <requirement type="package">python</requirement> + </requirements> + + <command detect_errors="exit_code"> + <![CDATA[ + python 1_quality_script_fastp_bracken.py --input $json_input --output wynik.csv + ]]> + </command> + + <inputs> + <param name="json_input" type="data" format="json" label="Input JSON Data"/> + </inputs> + + <outputs> + <data name="output_file" format="csv" from_work_dir="wynik.csv" label="FastP-Bracken Summary Report"/> + </outputs> + + <help>< - A tool for fast and efficient quality control. +- [Bracken](https://github.com/jenniferlu717/Bracken) - A tool for accurate species abundance estimation. + +For support, please contact the tool maintainers. + ]]></help> + +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/spamr_vet_tools/2_quast_get_fasta.py Mon Feb 17 09:57:10 2025 +0000 @@ -0,0 +1,134 @@ +import json +import csv +import sys +import os + +def extract_software_data(json_data, software_name): + """ + + Usage: python script.py input.json + For "quast", include specific columns and calculate a Filter_N50 based on "N50". + Added extract_contigs_to_fasta to get fasta file from shovill + """ + # Ensure json_data is a dictionary + if isinstance(json_data, list): + json_data = next((entry for entry in json_data if "analysis_software_name" in entry and entry["analysis_software_name"] == software_name), None) + + if not isinstance(json_data, dict): + print(f"Invalid JSON format for {software_name} extraction.") + return + + results = json_data.get("results", []) + extracted_data = [] + headers = [ + "Assembly", + "contigs_(>=_0_bp)", + "contigs_(>=_1000_bp)", + "Total_length_(>=_0_bp)", + "Total_length_(>=_1000_bp)", + "contigs", + "Largest_contig", + "Total_length", + "GC", + "N50", + "Filter_N50", + "N90", + "auN", + "L50", + "L90", + "total_reads", + "left", + "right", + "Mapped", + "Properly_paired", + "Avg._coverage_depth", + "Coverage_>=_1x", + "N's_per_100_kbp" + ] + output_csv_file = f"{software_name}_output.csv" + + for entry in results: + if "content" in entry and isinstance(entry["content"], list): + for content_item in entry["content"]: + n50 = content_item.get("N50", "") + try: + n50_value = float(n50) if n50 else 0 + filter_n50 = "pass" if n50_value > 20000 else "fail" + except ValueError: + filter_n50 = "fail" # If the value is non-numeric, consider it as "fail" + + extracted_data.append({ + "Assembly": content_item.get("Assembly", ""), + "contigs_(>=_0_bp)": content_item.get("contigs_(>=_0_bp)", ""), + "contigs_(>=_1000_bp)": content_item.get("contigs_(>=_1000_bp)", ""), + "Total_length_(>=_0_bp)": content_item.get("Total_length_(>=_0_bp)", ""), + "Total_length_(>=_1000_bp)": content_item.get("Total_length_(>=_1000_bp)", ""), + "contigs": content_item.get("contigs", ""), + "Largest_contig": content_item.get("Largest_contig", ""), + "Total_length": content_item.get("Total_length", ""), + "GC": content_item.get("GC", ""), + "N50": content_item.get("N50", ""), + "Filter_N50": filter_n50, + "N90": content_item.get("N90", ""), + "auN": content_item.get("auN", ""), + "L50": content_item.get("L50", ""), + "L90": content_item.get("L90", ""), + "total_reads": content_item.get("total_reads", ""), + "left": content_item.get("left", ""), + "right": content_item.get("right", ""), + "Mapped": content_item.get("Mapped", ""), + "Properly_paired": content_item.get("Properly_paired", ""), + "Avg._coverage_depth": content_item.get("Avg._coverage_depth", ""), + "Coverage_>=_1x": content_item.get("Coverage_>=_1x", ""), + "N's_per_100_kbp": content_item.get("N's_per_100_kbp", "") + }) + + with open(output_csv_file, "w", newline="", encoding="utf-8") as f: + writer = csv.DictWriter(f, fieldnames=headers) + writer.writeheader() + writer.writerows(extracted_data) + + print(f"CSV file successfully generated: {output_csv_file}") + +def extract_contigs_to_fasta(json_data): + """ + Extract contigs information from "shovill" and save it as a FASTA file. + """ + if isinstance(json_data, list): + json_data = next((entry for entry in json_data if "analysis_software_name" in entry and entry["analysis_software_name"] == "shovill"), None) + + if not isinstance(json_data, dict): + print("Invalid JSON format for shovill extraction.") + return + + results = json_data.get("results", []) + output_fasta_file = "shovill_contigs.fasta" + + with open(output_fasta_file, "w", encoding="utf-8") as f: + for entry in results: + if "content" in entry and isinstance(entry["content"], list): + for content_item in entry["content"]: + name = content_item.get("name", "unknown") + length = content_item.get("length", "unknown") + coverage = content_item.get("coverage", "unknown") + sequence = content_item.get("sequence", "") + + header = f">{name}_{length}_{coverage}" + f.write(f"{header}\n{sequence}\n") + + print(f"FASTA file successfully generated: {output_fasta_file}") + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python script.py input.json") + sys.exit(1) + + input_json_file = sys.argv[1] + + try: + with open(input_json_file, "r", encoding="utf-8") as file: + json_data = json.load(file) + extract_software_data(json_data, "quast") + extract_contigs_to_fasta(json_data) + except Exception as e: + print(f"Error processing file: {e}")
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/spamr_vet_tools/2_quast_get_fasta.xml Mon Feb 17 09:57:10 2025 +0000 @@ -0,0 +1,68 @@ +<tool id="quast_get_fasta" + name="QUAST Analysis and FASTA Generator" + version="0.1.0+galaxy0" + python_template_version="3.5" + profile="21.05"> + + <description>Extracts QUAST metrics and generates FASTA files from JSON input.</description> + + <requirements> + <requirement type="package">python</requirement> + </requirements> + + <command detect_errors="exit_code"> + <![CDATA[ + python 2_quast_get_fasta.py --input $json_input + ]]> + </command> + + <inputs> + <param name="json_input" type="data" format="json" label="Input JSON File" + help="Provide a JSON file containing QUAST and Shovill results."/> + </inputs> + + <outputs> + <data name="csv_output" format="csv" from_work_dir="quast_output.csv" + label="QUAST Summary (CSV)"/> + <data name="fasta_output" format="fasta" from_work_dir="shovill_contigs.fasta" + label="Shovill Contigs (FASTA)"/> + </outputs> + + <tests> + <test> + <param name="json_input" value="example_input.json"/> + <output name="csv_output" file="expected_output.csv" compare="diff"/> + <output name="fasta_output" file="expected_output.fasta" compare="diff"/> + </test> + </tests> + + <help><![CDATA[ +QUAST Analysis and FASTA Generator +================================== + +This tool extracts key statistics from **QUAST** and generates a **FASTA** file containing assembled contigs from **Shovill**. + +Usage Instructions +------------------ +1. Upload or provide a **JSON file** containing **QUAST** and **Shovill** results. +2. The tool will: + - Extract **assembly metrics** from QUAST and save them as a CSV. + - Convert **contigs from Shovill** into a FASTA file. +3. The outputs will be: + - `quast_output.csv` (QUAST summary metrics) + - `shovill_contigs.fasta` (FASTA file with contigs) + +Outputs +------- +- **CSV File:** Contains QUAST summary metrics such as `N50`, `GC content`, `total length`, `L50`, and other key assembly statistics. +- **FASTA File:** Extracts contigs from **Shovill**, formatting them properly for downstream analysis. + +References +---------- +- `QUAST <http://bioinf.spbau.ru/quast>`_ - Quality assessment tool for genome assemblies. +- `Shovill <https://github.com/tseemann/shovill>`_ - A tool for rapid bacterial genome assembly using SPAdes. + +For questions or issues, please contact the tool maintainers. + ]]></help> + +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/spamr_vet_tools/3_MLST_AMRFINDER_STARAMR.py Mon Feb 17 09:57:10 2025 +0000 @@ -0,0 +1,73 @@ +import json +import csv +import sys + +def generate_csv_from_json(json_data): + """ + + Usage: python script.py input.json + Parse the JSON and generate CSV files based on the analysis_software_name Abricate, AMRfinder plus and STARamr. + Additionally, extract and process the 'mlst_file' content into its own CSV. + """ + for entry in json_data: + analysis_software = entry.get("analysis_software_name", "unknown") + results = entry.get("results", []) + + if results: + csv_file = f"{analysis_software}_output.csv" + extracted_data = [] + headers = [] + + for result in results: + if result.get("name") == "mlst_file": + mlst_file_path = "mlst.csv" + mlst_content = result.get("content", []) + mlst_headers = ["Isolate ID", "Scheme", "Sequence Type", "Locus"] + + # Write the MLST CSV file + if mlst_content: + with open(mlst_file_path, "w", newline="", encoding="utf-8") as f: + writer = csv.DictWriter(f, fieldnames=mlst_headers) + writer.writeheader() + for row in mlst_content: + writer.writerow({ + "Isolate ID": row.get("Isolate ID", ""), + "Scheme": row.get("Scheme", ""), + "Sequence Type": row.get("Sequence Type", ""), + "Locus": "; ".join(row.get("Locus", [])) + }) + + print(f"MLST CSV file successfully generated: {mlst_file_path}") + + if "content" in result and isinstance(result["content"], list): + for content_item in result["content"]: + extracted_data.append(content_item) + for key in content_item.keys(): + if key not in headers: + headers.append(key) # Maintain the original order of the JSON keys + + # Write the CSV file if there is data + if extracted_data: + with open(csv_file, "w", newline="", encoding="utf-8") as f: + writer = csv.DictWriter(f, fieldnames=headers) + writer.writeheader() + for row in extracted_data: + writer.writerow({key: row.get(key, "") for key in headers}) + + print(f"CSV file successfully generated: {csv_file}") + else: + print(f"No content found for {analysis_software}.") + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python script.py input.json") + sys.exit(1) + + input_json_file = sys.argv[1] + + try: + with open(input_json_file, "r", encoding="utf-8") as file: + json_data = json.load(file) + generate_csv_from_json(json_data) + except Exception as e: + print(f"Error processing file: {e}")
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/spamr_vet_tools/3_mlst_amr_staramr.xml Mon Feb 17 09:57:10 2025 +0000 @@ -0,0 +1,72 @@ +<tool id="mlst_amr_staramr" + name="MLST, AMRfinder, and STARamr Analysis" + version="0.1.0+galaxy0" + python_template_version="3.5" + profile="21.05"> + + <description>Extracts MLST, AMRfinder Plus, and STARamr results from JSON input.</description> + + <requirements> + <requirement type="package">python</requirement> + </requirements> + + <command detect_errors="exit_code"> + <![CDATA[ + python 3_mlst_amr_staramr.py --input $json_input + ]]> + </command> + + <inputs> + <param name="json_input" type="data" format="json" label="Input JSON File" + help="Provide a JSON file containing MLST, AMRfinder Plus, and STARamr results."/> + </inputs> + + <outputs> + <data name="mlst_csv" format="csv" from_work_dir="mlst.csv" + label="MLST Summary (CSV)"/> + <data name="amr_csv" format="csv" from_work_dir="AMRfinderPlus_output.csv" + label="AMRfinder Plus Results (CSV)"/> + <data name="staramr_csv" format="csv" from_work_dir="STARamr_output.csv" + label="STARamr Results (CSV)"/> + </outputs> + + <tests> + <test> + <param name="json_input" value="example_input.json"/> + <output name="mlst_csv" file="expected_mlst.csv" compare="diff"/> + <output name="amr_csv" file="expected_amr.csv" compare="diff"/> + <output name="staramr_csv" file="expected_staramr.csv" compare="diff"/> + </test> + </tests> + + <help><![CDATA[ +MLST, AMRfinder, and STARamr Analysis +===================================== + +This tool extracts MLST, AMRfinder Plus, and STARamr results from JSON input and converts them into CSV format. + +Usage Instructions +------------------ +1. Provide a **JSON file** containing **MLST, AMRfinder Plus, and STARamr** results. +2. The tool will process the data and generate: + - `mlst.csv`: MLST typing results. + - `AMRfinderPlus_output.csv`: Results from **AMRfinder Plus**. + - `STARamr_output.csv`: Results from **STARamr**. + +Outputs +------- +- **MLST CSV File:** Contains MLST typing information, including sequence type and scheme. +- **AMRfinder Plus CSV File:** Lists detected antimicrobial resistance genes. +- **STARamr CSV File:** Includes resistance profiles and sequence typing. + +References +---------- +- `MLST <https://pubmlst.org/>`_ - Multi-locus sequence typing database. +- `AMRfinder Plus <https://www.ncbi.nlm.nih.gov/pathogens/antimicrobial-resistance/AMRFinder/>`_ - Antimicrobial resistance gene detection. +- `STARamr <https://github.com/phac-nml/staramr>`_ - Salmonella sequence typing and resistance analysis. + +For questions or issues, please contact the tool maintainers. + ]]></help> + +</tool> +