{ "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" ], "tag": [ "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_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "src_xref_key" }, { "type": "string", "label": "src_xref_id" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "start_aa" }, { "type": "string", "label": "end_aa" }, { "type": "string", "label": "site_seq" } ], [ "O14672-1", "37", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "37", "37", "Tyr", "Tyr", "Y" ], [ "O14672-1", "37", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "37", "37", "Tyr", "Tyr", "Y" ], [ "P35318-1", "125", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "125", "125", "Tyr", "Tyr", "Y" ], [ "P35318-1", "125", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "125", "125", "Tyr", "Tyr", "Y" ], [ "P35318-1", "125", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "125", "125", "Tyr", "Tyr", "Y" ], [ "P05067-1", "378", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "378", "378", "Tyr", "Tyr", "Y" ], [ "P05067-1", "378", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "378", "378", "Tyr", "Tyr", "Y" ], [ "O75752-1", "226", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "226", "226", "Tyr", "Tyr", "Y" ], [ "O75752-1", "226", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "226", "226", "Tyr", "Tyr", "Y" ], [ "O75752-1", "226", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "226", "226", "Tyr", "Tyr", "Y" ], [ "O43286-1", "65", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "65", "65", "Tyr", "Tyr", "Y" ], [ "O43286-1", "65", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "65", "65", "Tyr", "Tyr", "Y" ], [ "Q76M96-1", "415", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "415", "415", "Tyr", "Tyr", "Y" ], [ "Q76M96-1", "415", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "415", "415", "Tyr", "Tyr", "Y" ], [ "Q76M96-1", "415", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "415", "415", "Tyr", "Tyr", "Y" ], [ "P16070-1", "412", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "412", "412", "Tyr", "Tyr", "Y" ], [ "P16070-1", "412", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "412", "412", "Tyr", "Tyr", "Y" ], [ "P16070-1", "412", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "412", "412", "Tyr", "Tyr", "Y" ], [ "P16070-1", "560", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "560", "560", "Tyr", "Tyr", "Y" ], [ "P16070-1", "560", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "560", "560", "Tyr", "Tyr", "Y" ], [ "P16070-1", "560", "Tyr", "", "O-linked", "protein_xref_pubmed", "23399548", "protein_xref_glygen_ds", "GLY_000268", "560", "560", "Tyr", "Tyr", "Y" ], [ "P16070-1", "560", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "560", "560", "Tyr", "Tyr", "Y" ], [ "P16070-1", "564", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "564", "564", "Tyr", "Tyr", "Y" ], [ "P16070-1", "564", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "564", "564", "Tyr", "Tyr", "Y" ], [ "P32970-1", "74", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "74", "74", "Tyr", "Tyr", "Y" ], [ "P32970-1", "74", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "74", "74", "Tyr", "Tyr", "Y" ], [ "P32970-1", "74", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "74", "74", "Tyr", "Tyr", "Y" ], [ "P29279-1", "182", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "182", "182", "Tyr", "Tyr", "Y" ], [ "P29279-1", "182", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "182", "182", "Tyr", "Tyr", "Y" ], [ "O94907-1", "68", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "68", "68", "Tyr", "Tyr", "Y" ], [ "O94907-1", "68", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "68", "68", "Tyr", "Tyr", "Y" ], [ "O94907-1", "68", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "68", "68", "Tyr", "Tyr", "Y" ], [ "O94907-1", "168", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "168", "168", "Tyr", "Tyr", "Y" ], [ "O94907-1", "168", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "168", "168", "Tyr", "Tyr", "Y" ], [ "O94907-1", "179", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "179", "179", "Tyr", "Tyr", "Y" ], [ "O94907-1", "179", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "179", "179", "Tyr", "Tyr", "Y" ], [ "Q16610-1", "43", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "43", "43", "Tyr", "Tyr", "Y" ], [ "Q16610-1", "43", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "43", "43", "Tyr", "Tyr", "Y" ], [ "Q16610-1", "43", "Tyr", "", "O-linked", "protein_xref_pubmed", "23399548", "protein_xref_glygen_ds", "GLY_000268", "43", "43", "Tyr", "Tyr", "Y" ], [ "Q16610-1", "43", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "43", "43", "Tyr", "Tyr", "Y" ], [ "Q9UHF1-1", "49", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "49", "49", "Tyr", "Tyr", "Y" ], [ "Q9UHF1-1", "49", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "49", "49", "Tyr", "Tyr", "Y" ], [ "Q96DB9-1", "51", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "51", "51", "Tyr", "Tyr", "Y" ], [ "Q96DB9-1", "51", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "51", "51", "Tyr", "Tyr", "Y" ], [ "Q99988-1", "60", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "60", "60", "Tyr", "Tyr", "Y" ], [ "Q99988-1", "60", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "60", "60", "Tyr", "Tyr", "Y" ], [ "P06865-1", "227", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "227", "227", "Tyr", "Tyr", "Y" ], [ "P06865-1", "227", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "227", "227", "Tyr", "Tyr", "Y" ], [ "P06865-1", "227", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "227", "227", "Tyr", "Tyr", "Y" ], [ "P98160-1", "52", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "52", "52", "Tyr", "Tyr", "Y" ], [ "P98160-1", "52", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "52", "52", "Tyr", "Tyr", "Y" ], [ "P28300-1", "129", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "129", "129", "Tyr", "Tyr", "Y" ], [ "P28300-1", "129", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "129", "129", "Tyr", "Tyr", "Y" ], [ "P28300-1", "129", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "129", "129", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "372", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "372", "372", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "372", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "372", "372", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "372", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "372", "372", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "523", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "523", "523", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "523", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "523", "523", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "551", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "551", "551", "Tyr", "Tyr", "Y" ], [ "Q86X29-1", "551", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "551", "551", "Tyr", "Tyr", "Y" ], [ "Q9NS15-1", "986", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "986", "986", "Tyr", "Tyr", "Y" ], [ "Q9NS15-1", "986", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "986", "986", "Tyr", "Tyr", "Y" ], [ "Q9UKM7-1", "248", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "248", "248", "Tyr", "Tyr", "Y" ], [ "Q9UKM7-1", "248", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "248", "248", "Tyr", "Tyr", "Y" ], [ "Q9H8J5-1", "198", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "198", "198", "Tyr", "Tyr", "Y" ], [ "Q9H8J5-1", "198", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "198", "198", "Tyr", "Tyr", "Y" ], [ "P14543-1", "326", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "326", "326", "Tyr", "Tyr", "Y" ], [ "P14543-1", "326", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "326", "326", "Tyr", "Tyr", "Y" ], [ "P14543-1", "326", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "326", "326", "Tyr", "Tyr", "Y" ], [ "P42857-1", "144", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "144", "144", "Tyr", "Tyr", "Y" ], [ "P42857-1", "144", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "144", "144", "Tyr", "Tyr", "Y" ], [ "P42857-1", "150", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "150", "150", "Tyr", "Tyr", "Y" ], [ "P42857-1", "150", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "150", "150", "Tyr", "Tyr", "Y" ], [ "P42857-1", "150", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "150", "150", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "50", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "50", "50", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "50", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "50", "50", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "50", "Tyr", "", "O-linked", "protein_xref_pubmed", "23399548", "protein_xref_glygen_ds", "GLY_000268", "50", "50", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "50", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "50", "50", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "51", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "51", "51", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "51", "Tyr", "", "O-linked", "protein_xref_pubmed", "23584533", "protein_xref_glygen_ds", "GLY_000268", "51", "51", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "51", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "51", "51", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "54", "Tyr", "", "O-linked", "protein_xref_glygen_ds", "GLY_000268", "protein_xref_glygen_ds", "GLY_000268", "54", "54", "Tyr", "Tyr", "Y" ], [ "Q02818-1", "54", "Tyr", "", "O-linked", "protein_xref_pubmed", "25813380", "protein_xref_glygen_ds", "GLY_000268", "54", "54", "Tyr", "Tyr", "Y" ] ] }, "readme": "Name\n - Human Tyr O-Linked Glycosylation Sites\n\nVersion\n - v-2.4.1\n\nCreated on\n - 2019-09-06T14:06:38.994596\n\nModified on\n - 2022-09-26T09:04:47.907359\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - \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/glygener/glygen-backend-integration/blob/master/dataset-maker/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/ln2releases/data/v-2.4.1/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_tyr_o_linked.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv\n Name: human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\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: \"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: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"1\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"4\"\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"1\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"40\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"40\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv" }