Super-search query targeting various record types
==================================================
A) Record sets for each record type are retrieved matching query
for each record type.
- Each record, no matter what record type, has an associated
protein identifier.
- For protein/enzyme/glycoprotein record types, the UniProtKB cannonical accession
is the protein identifier.
- For site record types, the protein identifier is the UniProtKB
cannonical accession of the protein in which the site is located.
- For glycan record types, the protein identifier is the UniProtKB
cannonical accession of the glycoprotein glycosylated by the glycan.
B) A record from each set found in (A) is removed if its associated
protein identifier is not found in all other sets. This is done to
ensure maintain the relationship in the returned records.
{
"glycan": {
"$and": [
{"species.common_name": {"$eq": "Human"}},
{"motifs.name": {"$regex": "Polysialic", "$options": "i"}},
{"mass": {"$gte": 2100}}
]
},
"protein": {
"$and":[
{"expression_tissue.tissue.name":{"$regex": "lung", "$options": "i"}},
{"expression_tissue.present":{"$regex": "yes", "$options": "i"}},
{"expression_disease.significant":{"$regex": "yes", "$options": "i"}},
{"expression_disease.disease.recommended_name.name":{"$regex": "lung", "$options": "i"}}
]
},
"site": {
"$and":[
{"snv":{"$gt":[]}},
{"snv.disease":{"$gt":[]}},
{"glycosylation":{"$gt":[]}},
{"glycosylation.glytoucan_ac":{"$ne":""}},
{
"$or":[
{"species.taxid":{"$eq":9606}},
{"species.name":{"$regex": "homo", "$options": "i"}},
{"species.common_name":{"$regex": "human", "$options": "i"}}
]
}
]
}
}
Search result summary for each record type
========================================================
{
"glycan": {
"result_count": 4,
"list_id": "423013ba9df97f7d5efe85b01c845d71"
},
"protein": {
"result_count": 2,
"list_id": "5452790865b5f5c695f2c1d4b726c1df"
},
"site": {
"result_count": 6,
"list_id": "d5d9ccf0463ef9f796f093056fc840b4"
}
},
Search results associated for each record type
========================================================
{
"glycan": [
{
"glycoprotein": "P02768-1; P29965-1; P19835-1; P02743-1",
"mass_pme": 2769.39,
"inchi_key": {},
"publication": "7841792; 11676606; 11738084; ... ",
"classification": "N-glycan/complex",
"glycoct": "RES 1b:b-dglc-HEX-1:5 2s:n-acetyl ... ",
"number_enzymes": 11,
"number_proteins": 4,
"composition": "neuac (2); hexnac (4); hex (5)",
"glycam": "",
"enzyme": "Q9DBE8-1; P26572-1; P15535-1; ... ",
"number_monosaccharides": 11,
"mass": 2222.78,
"motifs": "GGM.000034; GGM.000001; GGM.000052",
"inchi": "",
"wurcs": "WURCS=2.0/5,11,10/[a2122h-1b_1-5_2*NCC/3=O] ... ",
"glytoucan_ac": "G53276NK",
"hit_score": 0,
"iupac": "alpha-D-NeupAc-(2->?)-beta-D-Galp-(1->4)-beta- ... "
},
{
"glycoprotein": "P00742-1; P00742-1",
"mass_pme": 2857.45,
"inchi_key": {},
"publication": "7620335",
"classification": "N-glycan/complex",
"glycoct": "RES 1b:b-dglc-HEX-1:5 2s:n-acetyl ... ",
"number_enzymes": 14,
"number_proteins": 1,
"composition": "neuac (1); hexnac (5); hex (6)",
"glycam": "",
"enzyme": "Q9Z2Y2-1; P27808-1; Q10469-1; P15535-1; ... ",
"number_monosaccharides": 12,
"mass": 2296.82,
"motifs": "GGM.000001; GGM.000052; GGM.000034",
"inchi": "",
"wurcs": "WURCS=2.0/5,12,11/[a2122h-1b_1-5_2*NCC/3=O] ... ",
"glytoucan_ac": "G46568MX",
"hit_score": 0,
"iupac": "alpha-D-NeupAc-(2->?)-beta-D-Galp-(1->4)- ... "
},
{
"glycoprotein": "P00742-1; P00742-1",
"mass_pme": 2857.45,
"inchi_key": {},
"publication": "7620335",
"classification": "N-glycan/complex",
"glycoct": "RES 1b:b-dglc-HEX-1:5 2s:n-acetyl ... ",
"number_enzymes": 14,
"number_proteins": 1,
"composition": "hexnac (5); neuac (1); hex (6)",
"glycam": "",
"enzyme": "P27808-1; Q9D306-1; Q10469-1; P15535-1; ... ",
"number_monosaccharides": 12,
"mass": 2296.82,
"motifs": "GGM.000001; GGM.000034; GGM.000052",
"inchi": "",
"wurcs": "WURCS=2.0/5,12,11/[a2122h-1b_1-5_2*NCC/3=O] ... ",
"glytoucan_ac": "G49478NM",
"hit_score": 0,
"iupac": "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2) ... "
},
{
"glycoprotein": "P00742-1; P00742-1",
"mass_pme": 2857.45,
"inchi_key": {},
"publication": "7620335",
"classification": "N-glycan/complex",
"glycoct": "RES 1b:b-dglc-HEX-1:5 2s:n-acetyl ... ",
"number_enzymes": 14,
"number_proteins": 1,
"composition": "hex (6); neuac (1); hexnac (5)",
"glycam": "",
"enzyme": "O60909-1; Q9H553-1; Q9UBM8-1; Q9Z2Y2-1; ... ",
"number_monosaccharides": 12,
"mass": 2296.82,
"motifs": "GGM.000034; GGM.000052; GGM.000001",
"inchi": "",
"wurcs": "WURCS=2.0/5,12,11/[a2122h-1b_1-5_2* ... ",
"glytoucan_ac": "G73073LQ",
"hit_score": 0,
"iupac": "beta-D-Galp-(1->4)-beta-D-GlcpNAc-(1->2) ... "
}
],
"protein": [
{
"function": "A high CRP/Alb ratio at POD 14 was an ... ",
"uniprot_canonical_ac": "P02768-1",
"publication_count": 65,
"reported_o_glycosites_with_glycan": 11,
"protein_name": "Serum albumin",
"protein_names_uniprotkb": "Serum albumin",
"gene_names_refseq": "HSA; PRO0883; PRO0903; PRO1341; ALB",
"refseq_ac": "NP_000468.1",
"protein_names_refseq": "serum albumin; serum albumin preproprotein",
"disease": "hyperthyroxinemia, familial dysalbuminemic ... ",
"reported_n_glycosites": 0,
"mass": 69367.0,
"refseq_name": "serum albumin preproprotein",
"reported_n_glycosites_with_glycan": 3,
"reported_o_glycosites": 0,
"predicted_glycosites": 1,
"tax_id": 9606,
"organism": "Homo sapiens",
"pathway": "Scavenging of heme from plasma (R-HSA-2168880); ... ",
"gene_name": "ALB",
"gene_names_uniprotkb": "ALB; PRO1341; PRO2619; GIG20; ... ",
},
{
"function": "Factor Xa is a vitamin K-dependent glycoprotein that ... ",
"uniprot_canonical_ac": "P00742-1",
"publication_count": 45,
"reported_o_glycosites_with_glycan": 13,
"protein_name": "Coagulation factor X",
"protein_names_uniprotkb": "Coagulation factor X; 3.4.21.6; ... ",
"gene_names_refseq": "F10; FX; FXA",
"refseq_ac": "NP_000495.1",
"protein_names_refseq": "coagulation factor X isoform 1 ... ",
"disease": "factor X deficiency (Disease Ontology:DOID:2222)",
"reported_n_glycosites": 2,
"mass": 54732.0,
"refseq_name": "coagulation factor X isoform 1 preproprotein",
"reported_n_glycosites_with_glycan": 81,
"reported_o_glycosites": 2,
"predicted_glycosites": 0,
"tax_id": 9606,
"organism": "Homo sapiens",
"pathway": "Gamma-carboxylation of protein ... ",
"gene_name": "F10",
"gene_names_uniprotkb": "F10"
}
],
"site": [
{
"uniprot_canonical_ac": "P02768-1",
"modifier_url": "",
"start_pos": 443,
"modification": "O-linked glycosylation",
"modification_type": "glycosylation",
"end_pos": 443,
"disease": [],
"modifier_id": "G43417UB",
"evidence": [
{
"url": "http://unicarbkb.org/proteinsummary/P02768/annotated",
"id": "P02768",
"database": "UniCarbKB"
},
{
"url": "https://www.ncbi.nlm.nih.gov/pubmed/30459171",
"id": "30459171",
"database": "PubMed"
}
]
},
{
"uniprot_canonical_ac": "P02768-1",
"modifier_url": "",
"start_pos": 443,
"modification": "",
"modification_type": "phosphorylation",
"end_pos": 443,
"disease": [],
"modifier_id": "",
"evidence": [
{
"url": "https://www.ncbi.nlm.nih.gov/pubmed/19690332",
"id": "19690332",
"database": "PubMed"
}
]
},
{
"uniprot_canonical_ac": "P02768-1",
"modifier_url": "",
"start_pos": 443,
"modification": "",
"modification_type": "phosphorylation",
"end_pos": 443,
"disease": [],
"modifier_id": "",
"evidence": [
{
"url": "https://www.uniprot.org/uniprot/P02768",
"id": "P02768",
"database": "UniProtKB"
}
]
},
{
"uniprot_canonical_ac": "P02768-1",
"modifier_url": "",
"start_pos": 443,
"modification": "S -> P",
"modification_type": "snv",
"end_pos": 443,
"disease": [
{
"url": "http://disease-ontology.org/term/DOID:363",
"id": "DOID:363",
"resource": "Disease Ontology",
"description": "A female reproductive organ cancer that is located_in the uterus.",
"name": "uterine cancer"
}
],
"modifier_id": "",
"evidence": [
{
"url": "https://hive.biochemistry.gwu.edu/biomuta/proteinview/P02768",
"id": "P02768",
"database": "BioMuta"
}
]
},
{
"uniprot_canonical_ac": "P00742-1",
"modifier_url": "",
"start_pos": 190,
"modification": "O-linked glycosylation",
"modification_type": "glycosylation",
"end_pos": 190,
"disease": [],
"modifier_id": "G43417UB",
"evidence": [
{
"url": "http://unicarbkb.org/proteinsummary/P00742/annotated",
"id": "P00742",
"database": "UniCarbKB"
},
{
"url": "https://www.ncbi.nlm.nih.gov/pubmed/22171320",
"id": "22171320",
"database": "PubMed"
}
]
},
{
"uniprot_canonical_ac": "P00742-1",
"modifier_url": "",
"start_pos": 190,
"modification": "S -> R",
"modification_type": "snv",
"end_pos": 190,
"disease": [
{
"url": "http://disease-ontology.org/term/DOID:1324",
"id": "DOID:1324",
"resource": "Disease Ontology",
"description": "A respiratory system cancer that is located_in the lung.",
"name": "lung cancer"
}
],
"modifier_id": "",
"evidence": [
{
"url": "https://hive.biochemistry.gwu.edu/biomuta/proteinview/P00742",
"id": "P00742",
"database": "BioMuta"
}
]
}
]
}
}
|