feat: add script to get organisms and genomes from ncbi api (#159) (#160

)

README.md

@@ -32,3 +32,11 @@ python3 ./files/build-genomes-files.py
 
 The environment can be deactivated by running `deactivate`, and re-activated by running `source ./venv/bin/activate`
 again.
+
+## Building data files from the NCBI API
+
+Using the Python environment described above, run the script:
+
+```shell
+python3 ./files/build-files-from-ncbi.py
+```

files/build-files-from-ncbi.py

@@ -0,0 +1,81 @@
+from urllib.parse import quote as url_quote
+import pandas as pd
+import requests
+
+TAXA_URL = "https://docs.google.com/spreadsheets/d/1Gg9sw2Qw765tOx2To53XkTAn-RAMiBtqYrfItlLXXrc/gviz/tq?tqx=out:csv&sheet=Sheet1.csv"
+
+TAXONOMY_URL = "https://api.ncbi.nlm.nih.gov/datasets/v2/taxonomy/dataset_report"
+
+ASSEMBLIES_URL = "https://hgdownload.soe.ucsc.edu/hubs/BRC/assemblyList.json"
+
+ORGANISMS_OUTPUT_PATH = "files/source/organisms-from-ncbi.tsv"
+GENOMES_OUTPUT_PATH = "files/source/genomes-from-ncbi.tsv"
+
+def build_taxonomy_request_body(taxa):
+  return {"taxons": taxa, "children": False, "ranks": ["genus"]}
+
+def get_organism_row(organism_taxonomy):
+  return {
+    "taxon": organism_taxonomy["current_scientific_name"]["name"],
+    "taxonomyId": organism_taxonomy["tax_id"],
+    "assemblyCount": next(count["count"] for count in organism_taxonomy["counts"] if count["type"] == "COUNT_TYPE_ASSEMBLY"),
+  }
+
+def get_organisms_df(taxa):
+  return pd.DataFrame([get_organism_row(organism_info["taxonomy"]) for organism_info in requests.post(TAXONOMY_URL, json=build_taxonomy_request_body(taxa)).json()["reports"]])
+
+def get_tax_ids(organisms_df):
+  return list(organisms_df["taxonomyId"])
+
+def build_genomes_url(tax_ids):
+  return f"https://api.ncbi.nlm.nih.gov/datasets/v2/genome/taxon/{url_quote(",".join([str(id) for id in tax_ids]))}/dataset_report?filters.assembly_source=refseq&filters.has_annotation=true&filters.exclude_paired_reports=true&filters.exclude_atypical=true&filters.assembly_level=scaffold&filters.assembly_level=chromosome&filters.assembly_level=complete_genome"
+
+def get_genome_row(genome_info):
+  refseq_category = genome_info["assembly_info"].get("refseq_category")
+  return {
+    "taxon": genome_info["organism"]["organism_name"],
+    "taxonomyId": genome_info["organism"]["tax_id"],
+    "accession": genome_info["accession"],
+    "isRef": refseq_category == "reference genome",
+    "level": genome_info["assembly_info"]["assembly_level"],
+    "chromosomeCount": genome_info["assembly_stats"].get("total_number_of_chromosomes"),
+    "length": genome_info["assembly_stats"]["total_sequence_length"],
+    "scaffoldCount": genome_info["assembly_stats"]["number_of_scaffolds"],
+    "scaffoldN50": genome_info["assembly_stats"]["scaffold_n50"],
+    "scaffoldL50": genome_info["assembly_stats"]["scaffold_l50"],
+    "coverage": genome_info["assembly_stats"].get("genome_coverage"),
+    "gcPercent": genome_info["assembly_stats"]["gc_percent"],
+    "annotationStatus": genome_info["annotation_info"].get("status"),
+    "pairedAccession": genome_info["paired_accession"],
+  }
+
+def get_genomes_df(tax_ids):
+  return pd.DataFrame(data=[get_genome_row(genome_info) for genome_info in requests.get(build_genomes_url(tax_ids)).json()["reports"]])
+
+def build_files():
+  print("Building files")
+
+  taxa_df = pd.read_csv(TAXA_URL, keep_default_na=False)
+
+  organisms_source_df = get_organisms_df(list(taxa_df["Name"]))
+
+  organisms_df = organisms_source_df.merge(taxa_df[["TaxId", "CustomTags"]], how="left", left_on="taxonomyId", right_on="TaxId").drop(columns=["TaxId"])
+
+  organisms_df.to_csv(ORGANISMS_OUTPUT_PATH, index=False, sep="\t")
+
+  print(f"Wrote to {ORGANISMS_OUTPUT_PATH}")
+
+  genomes_source_df = get_genomes_df(get_tax_ids(organisms_df))
+  assemblies_df = pd.DataFrame(requests.get(ASSEMBLIES_URL).json()["data"])[["ucscBrowser", "genBank", "refSeq"]]
+
+  gen_bank_merge_df = genomes_source_df.merge(assemblies_df, how="left", left_on="pairedAccession", right_on="genBank")
+  ref_seq_merge_df = genomes_source_df.merge(assemblies_df, how="left", left_on="accession", right_on="refSeq")
+
+  genomes_df = gen_bank_merge_df.combine_first(ref_seq_merge_df)
+
+  genomes_df.to_csv(GENOMES_OUTPUT_PATH, index=False, sep="\t")
+
+  print(f"Wrote to {GENOMES_OUTPUT_PATH}")
+
+if __name__ == "__main__":
+  build_files()

files/source/genomes-from-ncbi.tsv

@@ -0,0 +1,21 @@
+taxon	taxonomyId	accession	isRef	level	chromosomeCount	length	scaffoldCount	scaffoldN50	scaffoldL50	coverage	gcPercent	annotationStatus	pairedAccession	ucscBrowser	genBank	refSeq
+Mycobacterium tuberculosis H37Rv	83332	GCF_000195955.2	True	Complete Genome	1.0	4411532	1	4411532	1		65.5		GCA_000195955.2			
+Plasmodium falciparum 3D7	36329	GCF_000002765.6	True	Complete Genome	14.0	23292622	14	1687656	5	100.0x	19.5	Full annotation	GCA_000002765.3	https://genome.ucsc.edu/h/GCF_000002765.5	GCA_000002765.3	GCF_000002765.5
+Leishmania major strain Friedlin	347515	GCF_000002725.2	True	Complete Genome	36.0	32855089	36	1091540	11		59.5	Full annotation	GCA_000002725.2	https://genome.ucsc.edu/h/GCF_000002725.2	GCA_000002725.2	GCF_000002725.2
+Plasmodium yoelii	5861	GCF_900002385.2	True	Complete Genome	14.0	23043114	14	2046250	5	100.0x	21.5	Full annotation	GCA_900002385.2	https://genome.ucsc.edu/h/GCF_900002385.2	GCA_900002385.2	GCF_900002385.2
+Coccidioides posadasii str. Silveira	443226	GCF_018416015.2	True	Complete Genome	9.0	28193268	9	8079863	2	475.0x	46.5	Full annotation	GCA_018416015.2	https://genome.ucsc.edu/h/GCA_018416015.2	GCA_018416015.2	GCF_018416015.1
+Plasmodium vinckei vinckei	54757	GCF_900681995.1	True	Complete Genome	14.0	18338688	14	1692345	5	155.0x	23.0	Full annotation	GCA_900681995.1	https://genome.ucsc.edu/h/GCF_900681995.1	GCA_900681995.1	GCF_900681995.1
+Leishmania donovani	5661	GCF_000227135.1	True	Chromosome	36.0	32444968	36	1024085	11		59.5	Full annotation	GCA_000227135.2	https://genome.ucsc.edu/h/GCF_000227135.1	GCA_000227135.2	GCF_000227135.1
+Toxoplasma gondii ME49	508771	GCF_000006565.2	True	Chromosome	14.0	65633124	2276	4973582	6	26.5x	52.5		GCA_000006565.2	https://genome.ucsc.edu/h/GCF_000006565.2	GCA_000006565.2	GCF_000006565.2
+Trypanosoma brucei brucei TREU927	185431	GCF_000002445.2	True	Chromosome	11.0	26075494	12	2481190	4		46.5	Full annotation	GCA_000002445.1	https://genome.ucsc.edu/h/GCF_000002445.2	GCA_000002445.1	GCF_000002445.2
+Anopheles gambiae	7165	GCF_943734735.2	True	Chromosome	3.0	264451381	190	99149756	2	54.0x	44.5	Full annotation	GCA_943734735.2	https://genome.ucsc.edu/h/GCF_943734735.2	GCA_943734735.2	GCF_943734735.2
+Plasmodium vivax	5855	GCF_000002415.2	True	Chromosome	14.0	27007701	2747	1678596	6		42.5	Full annotation	GCA_000002415.2	https://genome.ucsc.edu/h/GCF_000002415.2	GCA_000002415.2	GCF_000002415.2
+Culex pipiens pallens	42434	GCF_016801865.2	True	Chromosome	3.0	566339288	289	186194774	2	250.0x	37.0	Full annotation	GCA_016801865.2			
+Leishmania braziliensis MHOM/BR/75/M2904	420245	GCF_000002845.2	True	Chromosome	35.0	32068771	138	992961	11		58.0		GCA_000002845.2	https://genome.ucsc.edu/h/GCF_000002845.2	GCA_000002845.2	GCF_000002845.2
+Trypanosoma cruzi	5693	GCF_000209065.1	True	Scaffold		89937456	29495	88624	212		51.5	Full annotation	GCA_000209065.1	https://genome.ucsc.edu/h/GCF_000209065.1	GCA_000209065.1	GCF_000209065.1
+Coccidioides immitis RS	246410	GCF_000149335.2	True	Scaffold		28947925	6	4323945	3		46.0	Full annotation	GCA_000149335.2	https://genome.ucsc.edu/h/GCF_000149335.2	GCA_000149335.2	GCF_000149335.2
+Mycobacterium tuberculosis H37Rv	83332	GCF_000277735.2	False	Complete Genome	1.0	4411709	1	4411709	1		65.5		GCA_000277735.2			
+Severe acute respiratory syndrome coronavirus 2	2697049	GCF_009858895.2	False	Complete Genome	1.0	29903	1	29903	1		38.0		GCA_009858895.3			
+Monkeypox virus	10244	GCF_000857045.1	False	Complete Genome	1.0	196858	1	196858	1		33.0		GCA_000857045.1			
+Mycobacterium tuberculosis	1773	GCF_030566675.1	False	Complete Genome	1.0	4516435	1	4516435	1	20.0x	65.5		GCA_030566675.1			
+Mycobacterium tuberculosis	1773	GCF_963525475.1	False	Complete Genome	1.0	4469156	1	4469156	1	100.0x	65.5		GCA_963525475.1			

files/source/organisms-from-ncbi.tsv

@@ -0,0 +1,18 @@
+taxon	taxonomyId	assemblyCount	CustomTags
+Anopheles gambiae	7165	7	VEuPathDb
+Coccidioides immitis	5501	5	
+Coccidioides posadasii	199306	13	
+Culex pipiens	7175	5	VEuPathDb
+Leishmania braziliensis	5660	11	VEuPathDb
+Leishmania donovani	5661	12	VEuPathDb
+Leishmania major	5664	7	VEuPathDb
+Monkeypox virus	10244	6911	Virus
+Mycobacterium tuberculosis	1773	7823	Bact
+Plasmodium falciparum	5833	67	VEuPathDb
+Plasmodium vinckei	5860	10	VEuPathDb
+Plasmodium vivax	5855	19	VEuPathDb
+Plasmodium yoelii	5861	15	VEuPathDb
+Severe acute respiratory syndrome coronavirus 2	2697049	92	Virus
+Toxoplasma gondii	5811	29	VEuPathDb
+Trypanosoma brucei	5691	5	VEuPathDb
+Trypanosoma cruzi	5693	45	VEuPathDb