{ "bcoid": "GLY_000268", "title": "Human Tyr O-Linked Glycosylation Sites", "description": "The Human Tyr O-Linked Glycosylation Sites dataset contains human [taxid:9606] UniProtKB accessions that ...", "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "O14672-1...", "37..." ], [ "O14672-1...", "37..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_key" } ], [ "O14672-1", "37", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "O14672-1", "37", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P35318-1", "125", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P35318-1", "125", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P35318-1", "125", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P05067-1", "378", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P05067-1", "378", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "O75752-1", "226", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "O75752-1", "226", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "O75752-1", "226", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "O43286-1", "65", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "O43286-1", "65", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q76M96-1", "415", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q76M96-1", "415", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "Q76M96-1", "415", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P16070-1", "412", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P16070-1", "412", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P16070-1", "412", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P16070-1", "560", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P16070-1", "560", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P16070-1", "560", "Tyr", "", "o-linked", "23399548", "protein_xref_pubmed" ], [ "P16070-1", "560", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P16070-1", "564", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P16070-1", "564", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P32970-1", "74", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P32970-1", "74", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P32970-1", "74", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P29279-1", "182", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P29279-1", "182", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "O94907-1", "68", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "O94907-1", "68", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "O94907-1", "68", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "O94907-1", "168", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "O94907-1", "168", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "O94907-1", "179", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "O94907-1", "179", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q16610-1", "43", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q16610-1", "43", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "Q16610-1", "43", "Tyr", "", "o-linked", "23399548", "protein_xref_pubmed" ], [ "Q16610-1", "43", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q9UHF1-1", "49", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q9UHF1-1", "49", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q96DB9-1", "51", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q96DB9-1", "51", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q99988-1", "60", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q99988-1", "60", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P06865-1", "227", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P06865-1", "227", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P06865-1", "227", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P98160-1", "52", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P98160-1", "52", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P28300-1", "129", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P28300-1", "129", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P28300-1", "129", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q86X29-1", "372", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q86X29-1", "372", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "Q86X29-1", "372", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q86X29-1", "523", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q86X29-1", "523", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q86X29-1", "551", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q86X29-1", "551", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q9NS15-1", "986", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q9NS15-1", "986", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q9UKM7-1", "248", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q9UKM7-1", "248", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q9H8J5-1", "198", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q9H8J5-1", "198", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P14543-1", "326", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P14543-1", "326", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P14543-1", "326", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P42857-1", "144", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P42857-1", "144", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "P42857-1", "150", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "P42857-1", "150", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "P42857-1", "150", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q02818-1", "50", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q02818-1", "50", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "Q02818-1", "50", "Tyr", "", "o-linked", "23399548", "protein_xref_pubmed" ], [ "Q02818-1", "50", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q02818-1", "51", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q02818-1", "51", "Tyr", "", "o-linked", "23584533", "protein_xref_pubmed" ], [ "Q02818-1", "51", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ], [ "Q02818-1", "54", "Tyr", "", "o-linked", "GLYDS000268", "protein_xref_glygen_ds" ], [ "Q02818-1", "54", "Tyr", "", "o-linked", "25813380", "protein_xref_pubmed" ] ] }, "readme": "Name\n - Human Tyr O-Linked Glycosylation Sites\n\nVersion\n - 1.5.27\n\nCreated on\n - 2019-09-06T14:06:38.994596\n\nModified on\n - 2020-04-10T11:45:58.303524\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Human Tyr O-Linked Glycosylation Sites dataset contains human [taxid:9606] UniProtKB accessions that are Tyr O-Linked Glycosylated. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. If you use this dataset please provide proper attribution to GlyGen\n\nDescription Domain\n Keywords\n - tyrosine\n - o-linked glycosylation\n - glycosylation sites\n\n Pipeline Steps\n - Step-1: The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position of glycosylation against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries.\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: human_proteoform_glycosylation_sites_tyr_o_linked.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_tyr_o_linked.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv\n Name: human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"31\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"40\"\n Name: \"xref_id\"\n Description: \"\"\n Unique Values: \"4\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"1\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"1\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"1\"\n Name: \"xref_key\"\n Description: \"\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv" }