Added a new feature branch 'copo_metadata' to solve issue #115

assets/genome_metadata_template.csv

@@ -6,3 +6,4 @@ ENA,Taxonomy,https://www.ebi.ac.uk/ena/browser/api/xml/TAXONOMY_ID,xml
 NCBI,Assembly,https://api.ncbi.nlm.nih.gov/datasets/v2alpha/genome/accession/ASSEMBLY_ACCESSION/dataset_report?filters.exclude_atypical=false&filters.assembly_version=current&chromosomes=1&chromosomes=2&chromosomes=3&chromosomes=X&chromosomes=Y&chromosomes=M,json
 NCBI,Taxonomy,https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=taxonomy&id=TAXONOMY_ID,xml
 GOAT,Assembly,http://goat.genomehubs.org/api/v2/record?recordId=ASSEMBLY_ACCESSION&result=assembly&taxonomy=ncbi,json
+COPO,Biosample,https://copo-project.org/api/sample/biosampleAccession/BIOSAMPLE_ACCESSION?standard=tol&return_type=json,json

bin/combine_parsed_data.py

@@ -17,6 +17,9 @@
     ("NCBI_ASSEMBLY", "ncbi_assembly_file"),
     ("NCBI_TAXONOMY", "ncbi_taxonomy_file"),
     ("GOAT_ASSEMBLY", "goat_assembly_file"),
+    ("COPO_BIOSAMPLE", "copo_biosample_wgs_file"),
+    ("COPO_BIOSAMPLE_HIC", "copo_biosample_hic_file"),
+    ("COPO_BIOSAMPLE_RNA", "copo_biosample_rna_file"),
 ]
 
 

bin/parse_json_copo_biosample.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python3
+
+import argparse
+import os
+import json
+import sys
+import string
+import numbers
+
+fetch = [
+    ("SPECIMEN_ID", ("SPECIMEN_ID",)),
+    ("biosampleAccession", ("BIOSAMPLE_ACCESSION",)),
+    ("SCIENTIFIC_NAME", ("GENUS_SPECIES",)),
+    ("COMMON_NAME", ("COMMON_NAME",)),
+    ("COLLECTED_BY", ("COLLECTORS",)),
+    ("COLLECTOR_AFFILIATION", ("COLLECTOR_INSTITUTE",)),
+    ("DATE_OF_COLLECTION", ("COLLECTOR_DATE",)),
+    ("DESCRIPTION_OF_COLLECTION_METHOD", ("COLLECTION_METHOD",)),
+    ("COLLECTION_LOCATION", ("COLLECTION_LOCATION",)),
+    ("DECIMAL_LATITUDE", ("LATITUDE",)),
+    ("DECIMAL_LONGITUDE", ("LONGITUDE",)),
+    ("HABITAT", ("HABITAT",)),
+    ("IDENTIFIED_BY", ("IDENTIFIER",)),
+    ("IDENTIFIER_AFFILIATION", ("IDENTIFIER_INSTITUTE",)),
+    ("PRESERVATION_APPROACH", ("PRESERVATION_METHOD",)),
+    ("SYMBIONT", ("SYMBIONT",)),
+    ("TAXON_ID", ("NCBI_TAXID",)),
+    ("ORDER_OR_GROUP", ("ORDER",)),
+    ("FAMILY", ("FAMILY",)),
+    ("GENUS", ("GENUS",)),
+    ("SEX", ("SEX",)),
+    ("LIFESTAGE", ("LIFESTAGE",)),
+    ("ORGANISM_PART", ("ORGANISM_PART",)),
+    ("GAL", ("GAL",)),
+]
+
+
+def parse_args(args=None):
+    Description = "Parse contents of a COPO json file report and pul out meta data required by a genome note."
+    Epilog = "Example usage: python parse_json_copo_biosample.py <FILE_IN> <FILE_OUT>"
+
+    parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
+    parser.add_argument("FILE_IN", help="Input JSON Assembly file.")
+    parser.add_argument("FILE_OUT", help="Output file.")
+    parser.add_argument("--version", action="version", version="%(prog)s 1.0")
+    return parser.parse_args(args)
+
+
+def make_dir(path):
+    if len(path) > 0:
+        os.makedirs(path, exist_ok=True)
+
+
+def print_error(error, context="Line", context_str=""):
+    error_str = "ERROR: Please check json file -> {}".format(error)
+    if context != "":
+        if context_str != "":
+            error_str = "ERROR: Please check json file -> {}\n{}: '{}'".format(
+                error, context.strip(), context_str.strip()
+            )
+        else:
+            error_str = "ERROR: Please check json file -> {}\n{}".format(error, context.strip())
+
+    print(error_str)
+    sys.exit(1)
+
+
+def parse_json(file_in, file_out):
+    biosample_type = "COPO"
+    with open(file_in, "r") as json_file:
+        data = json.load(json_file)
+
+    param_list = []
+    record = data["records"][0]  # Get the single record
+
+    if len(data["records"]) != 1:
+        print_error("More than one record found")
+
+    for f in fetch:
+        param = find_element(record, f[1], index=0)
+        if param is not None:
+            if isinstance(param, numbers.Number):
+                param = str(param)
+            if any(p in string.punctuation for p in param):
+                param = '"' + param + '"'
+            # Prefix parameter name if biosample type is COPO
+            param_name = f[0]
+            if biosample_type == "COPO":
+                param_name = f"{biosample_type}_{param_name}"
+            param_list.append([param_name, param])
+
+    if len(param_list) > 0:
+        out_dir = os.path.dirname(file_out)
+        make_dir(out_dir)
+        with open(file_out, "w") as fout:
+            fout.write(",".join(["#paramName", "paramValue"]) + "\n")
+            for param_pair in param_list:
+                fout.write(",".join(param_pair) + "\n")
+
+    else:
+        print_error("No parameters found!", "File: {}".format(file_in))
+
+
+def find_element(data, fields, index=0):
+    if index < len(fields):
+        key = fields[index]
+        if key in data:
+            sub_data = data[key]
+            if type(sub_data) in [list, dict]:
+                return find_element(sub_data, fields, index + 1)
+            return sub_data
+        else:
+            return None
+    return None
+
+
+def main(args=None):
+    args = parse_args(args)
+    parse_json(args.FILE_IN, args.FILE_OUT)
+
+
+if __name__ == "__main__":
+    sys.exit(main())