ouroboros / data /annotation-examples.json
REXWind's picture
Publish the Ouroboros scientific showcase to CladeTeam
03677d0 verified
Raw History Blame Contribute Delete
22.1 kB
{
"source": {
"filename": "type_with_data_clean.json",
"sha256": "cce9148caa567b7c2700016d21d0cdf99d953e90ac84280e0bbef7e6aaf683da",
"records": 545334,
"keyCountsMatchSuppliedCSV": true
},
"selection": "One concise illustrative record per key; source annotation text is unchanged. Not a representative performance sample.",
"examples": {
"similarity": {
"id": "A5IKJ0",
"text": "Belongs to the MurCDEF family.",
"annotations": [
"Belongs to the MurCDEF family."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/A5IKJ0/entry",
"recordIndex0": 352690,
"sequenceLength": 457,
"sequenceSha256": "f36b7898727dfaaa5bca0a414dc20beeb05bf222e0e2a0633dd2eeac576e38ef"
},
"function": {
"id": "Q48154",
"text": "Catalyzes the NADPH-dependent reduction of D-ribulose 5-phosphate to D-ribitol 5-phosphate and the further reaction of D-ribitol 5-phosphate with CTP to form CDP-ribitol.",
"annotations": [
"Catalyzes the NADPH-dependent reduction of D-ribulose 5-phosphate to D-ribitol 5-phosphate and the further reaction of D-ribitol 5-phosphate with CTP to form CDP-ribitol."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q48154/entry",
"recordIndex0": 893,
"sequenceLength": 474,
"sequenceSha256": "ddbf6c9b14dbec5651ddf47b09a6df7d27c1cacc444a23c3e7d39614f805af8a"
},
"subunit": {
"id": "B9LSR7",
"text": "Part of the 50S ribosomal subunit. Forms a cluster with proteins L3 and L24e, part of which may contact the 16S rRNA in 2 intersubunit bridges.",
"annotations": [
"Part of the 50S ribosomal subunit. Forms a cluster with proteins L3 and L24e, part of which may contact the 16S rRNA in 2 intersubunit bridges."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/B9LSR7/entry",
"recordIndex0": 145290,
"sequenceLength": 132,
"sequenceSha256": "2add064280b6dff0da6452219b4e40bee3ffabdf4e7624d4fec746cfa9f6f2df"
},
"catalytic activity": {
"id": "A5IKJ0",
"text": "ATP + L-alanine + UDP-N-acetyl-alpha-D-muramate = ADP + H(+) + phosphate + UDP-N-acetyl-alpha-D-muramoyl-L-alanine",
"annotations": [
"ATP + L-alanine + UDP-N-acetyl-alpha-D-muramate = ADP + H(+) + phosphate + UDP-N-acetyl-alpha-D-muramoyl-L-alanine"
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/A5IKJ0/entry",
"recordIndex0": 352690,
"sequenceLength": 457,
"sequenceSha256": "f36b7898727dfaaa5bca0a414dc20beeb05bf222e0e2a0633dd2eeac576e38ef"
},
"pathway": {
"id": "A5IKJ0",
"text": "Cell wall biogenesis; peptidoglycan biosynthesis.",
"annotations": [
"Cell wall biogenesis; peptidoglycan biosynthesis."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/A5IKJ0/entry",
"recordIndex0": 352690,
"sequenceLength": 457,
"sequenceSha256": "f36b7898727dfaaa5bca0a414dc20beeb05bf222e0e2a0633dd2eeac576e38ef"
},
"cofactor": {
"id": "Q9HD60",
"text": "Binds 2 magnesium ions per subunit. They probably participate in the reaction catalyzed by the enzyme. May bind an additional third magnesium ion after substrate binding.",
"annotations": [
"Binds 2 magnesium ions per subunit. They probably participate in the reaction catalyzed by the enzyme. May bind an additional third magnesium ion after substrate binding."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q9HD60/entry",
"recordIndex0": 12053,
"sequenceLength": 1186,
"sequenceSha256": "b64767e98e6e5e1c2a82135261c13c6ca5952863d25100a51648d043f27f4d43"
},
"tissue specificity": {
"id": "Q63151",
"text": "Predominantly expressed in the brain, and to a much lesser extent, in lung, adrenal gland, kidney, small intestine, and adipose tissue but not detected in heart or liver.",
"annotations": [
"Predominantly expressed in the brain, and to a much lesser extent, in lung, adrenal gland, kidney, small intestine, and adipose tissue but not detected in heart or liver."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q63151/entry",
"recordIndex0": 905,
"sequenceLength": 720,
"sequenceSha256": "9c87e82bc81938a07f7ea66f25eb129c8fa7fe08c8a0c3e07b92d611a28f2c5a"
},
"domain": {
"id": "P25234",
"text": "Residue Phe-302, localized near active sites, is a bulky residue that modulates substrate specificity and especially act as steric hindrances for triacylglycerol binding.",
"annotations": [
"Residue Phe-302, localized near active sites, is a bulky residue that modulates substrate specificity and especially act as steric hindrances for triacylglycerol binding."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/P25234/entry",
"recordIndex0": 23161,
"sequenceLength": 305,
"sequenceSha256": "c6f3407c6a0b7fb0b4f993734add49be7029707d66cd04c3e175d3fa2c674f6b"
},
"subcellular location": {
"id": "Q9R271",
"text": "Membrane-associated in synaptosomes. Localized diffusely in the cytoplasm before nerve growth factor (NGF) stimulation. Recruited to late endosomes after NGF stimulation.",
"annotations": [
"Membrane-associated in synaptosomes. Localized diffusely in the cytoplasm before nerve growth factor (NGF) stimulation. Recruited to late endosomes after NGF stimulation."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q9R271/entry",
"recordIndex0": 22734,
"sequenceLength": 1277,
"sequenceSha256": "c2e75e04f31ad375fca7360ee2ccfdb453f3e05d4721dfc9c8602e569a1ff03f"
},
"PTM": {
"id": "P05322",
"text": "Methylation at Lys-5 is linked to gene activation. Methylation at Lys-10 is linked to gene repression (By similarity). Acetylation is generally linked to gene activation.",
"annotations": [
"Methylation at Lys-5 is linked to gene activation. Methylation at Lys-10 is linked to gene repression (By similarity).",
"Acetylation is generally linked to gene activation."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/P05322/entry",
"recordIndex0": 16595,
"sequenceLength": 136,
"sequenceSha256": "bd22f8c297fe940fc58666ffa4b7243bb3c9275f4e2e0440d852e253b57872c6"
},
"miscellaneous": {
"id": "P29153",
"text": "The N-terminal region like those of many plant virus capsid proteins is highly basic. It has been suggested that these regions may be involved in protein-RNA interaction.",
"annotations": [
"The N-terminal region like those of many plant virus capsid proteins is highly basic. It has been suggested that these regions may be involved in protein-RNA interaction."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/P29153/entry",
"recordIndex0": 5192,
"sequenceLength": 189,
"sequenceSha256": "7382df4af3c7ed084e7a136ceda0ca32b0f29505d3b83635920228344e10b044"
},
"induction": {
"id": "P02764",
"text": "Alpha-1-AGP is synthesized in the liver, the synthesis being controlled by glucocorticoids, interleukin-1 and interleukin-6, it increases 5- to 50-fold upon inflammation.",
"annotations": [
"Alpha-1-AGP is synthesized in the liver, the synthesis being controlled by glucocorticoids, interleukin-1 and interleukin-6, it increases 5- to 50-fold upon inflammation."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/P02764/entry",
"recordIndex0": 259,
"sequenceLength": 205,
"sequenceSha256": "5a25f6a2edcd26ad6d56ef4ce98143f13513edfa0fb4b5f496367ab47ef9a1b4"
},
"disruption phenotype": {
"id": "D4GU63",
"text": "Impaired formation of the tetrasaccharide present at 'Asn-532' of S-layer glycoprotein Csg. No effect on 'Asn-47' and 'Asn-117' glycosylation of S-layer glycoprotein Csg.",
"annotations": [
"Impaired formation of the tetrasaccharide present at 'Asn-532' of S-layer glycoprotein Csg. No effect on 'Asn-47' and 'Asn-117' glycosylation of S-layer glycoprotein Csg."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/D4GU63/entry",
"recordIndex0": 1209,
"sequenceLength": 307,
"sequenceSha256": "3c97891c656da825b839f4e533f665c1cbf388dc613aa552b31733cf3426055f"
},
"activity regulation": {
"id": "Q9PRW2",
"text": "Inhibited by PMSF, bovine aprotinin (APR), soybean trypsin inhibitor (STI), and high temperature (85 degrees Celsius). Is not inhibited by EDTA, and beta-mercaptoethanol.",
"annotations": [
"Inhibited by PMSF, bovine aprotinin (APR), soybean trypsin inhibitor (STI), and high temperature (85 degrees Celsius). Is not inhibited by EDTA, and beta-mercaptoethanol."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q9PRW2/entry",
"recordIndex0": 51019,
"sequenceLength": 15,
"sequenceSha256": "4a3dc17571719b236d082190f5d5dcedd7a18b35203862f6c958e8b5459410b4"
},
"developmental stage": {
"id": "Q5AQU1",
"text": "Barely detectable in asexual spores (conidia), disappears after germination, and starts to accumulate 10 hours after spore inoculation, throughout growth and conidiation.",
"annotations": [
"Barely detectable in asexual spores (conidia), disappears after germination, and starts to accumulate 10 hours after spore inoculation, throughout growth and conidiation."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q5AQU1/entry",
"recordIndex0": 5340,
"sequenceLength": 722,
"sequenceSha256": "54459fc16f64b669443d735b63b98c3eca9775eaabda3b5358367c740cdf089b"
},
"sequence caution": {
"id": "Q6ZT03",
"text": "Contaminating sequence. Potential poly-A sequence. Wrong choice of CDS. The sequence differs from that shown in N-terminus because it seems to be derived from a pre-mRNA.",
"annotations": [
"Contaminating sequence. Potential poly-A sequence.",
"Wrong choice of CDS.",
"The sequence differs from that shown in N-terminus because it seems to be derived from a pre-mRNA."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q6ZT03/entry",
"recordIndex0": 284393,
"sequenceLength": 1969,
"sequenceSha256": "1df32f185072c6756c822797e2257ac20663585bb0eccc215c8c936270adbd81"
},
"caution": {
"id": "Q4J8U7",
"text": "It is uncertain whether Met-1 is the initiator. Was originally thought to originate from S.solfataricus strain P1, but the culture was contaminated with S.acidocaldarius.",
"annotations": [
"It is uncertain whether Met-1 is the initiator.",
"Was originally thought to originate from S.solfataricus strain P1, but the culture was contaminated with S.acidocaldarius."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q4J8U7/entry",
"recordIndex0": 13937,
"sequenceLength": 369,
"sequenceSha256": "5d7da99cc2b44fa0127ce22823fd1ad033a408516b20e4a27bdca1eb1424b283"
},
"biophysicochemical properties": {
"id": "Q7KZ19",
"text": "kcat is 3.7 min(-1) with 5alpha-cholest-7-en-3beta-ol (lathosterol) as substrate. kcat is 2.2 min(-1) with cholesta-5,7-dien-3beta-ol (7-dehydrocholesterol) as substrate.",
"annotations": [
"kcat is 3.7 min(-1) with 5alpha-cholest-7-en-3beta-ol (lathosterol) as substrate. kcat is 2.2 min(-1) with cholesta-5,7-dien-3beta-ol (7-dehydrocholesterol) as substrate."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q7KZ19/entry",
"recordIndex0": 62252,
"sequenceLength": 504,
"sequenceSha256": "996cc0bbc33f589266ba536b8442741ee686816dbceb0611f32ace76144f001a"
},
"disease": {
"id": "Q8N226",
"text": "A chromosomal aberration involving ZFTA is found in 3 chondroid lipomas. Translocation t(11;16)(q13;p13) with ZFTA produces a ZFTA-MRTFB fusion protein (PubMed:20607705).",
"annotations": [
"A chromosomal aberration involving ZFTA is found in 3 chondroid lipomas. Translocation t(11;16)(q13;p13) with ZFTA produces a ZFTA-MRTFB fusion protein (PubMed:20607705)."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q8N226/entry",
"recordIndex0": 79569,
"sequenceLength": 1088,
"sequenceSha256": "66e17a021f0f20009f55903ad146eb48bfa8619b3fde87a7fc423979d52e1ca8"
},
"alternative products": {
"id": "P0DTD1",
"text": "Normal translation results in Replicase polyprotein 1a. Ribosomal frameshifting at the end of this protein occurs at low frequency and produces Replicase polyprotein 1ab.",
"annotations": [
"Normal translation results in Replicase polyprotein 1a. Ribosomal frameshifting at the end of this protein occurs at low frequency and produces Replicase polyprotein 1ab."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/P0DTD1/entry",
"recordIndex0": 361250,
"sequenceLength": 7096,
"sequenceSha256": "edbd5d8a5deb16bfd31ff3029c7897b816b752cb26cd0dcf23d089dcdd841586"
},
"online information": {
"id": "Q89883",
"text": "Icosahedral capsid structure complexed with antiviral compound SCH 38057 Icosahedral capsid structure complexed with antiviral compound SDZ 35-682 Icosahedral capsid structure",
"annotations": [
"Icosahedral capsid structure complexed with antiviral compound SCH 38057",
"Icosahedral capsid structure complexed with antiviral compound SDZ 35-682",
"Icosahedral capsid structure"
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q89883/entry",
"recordIndex0": 522169,
"sequenceLength": 2179,
"sequenceSha256": "25169e5632ca15db8145c824b10bfa4671122060cb7176aba7168fd200638ae3"
},
"biotechnology": {
"id": "P14004",
"text": "Non-allergenic peptides identified from the mapped major conformational IgE epitope-containing areas could be used for the engineering of house dust mite allergy vaccine.",
"annotations": [
"Non-allergenic peptides identified from the mapped major conformational IgE epitope-containing areas could be used for the engineering of house dust mite allergy vaccine."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/P14004/entry",
"recordIndex0": 111144,
"sequenceLength": 132,
"sequenceSha256": "48b1b45d243dbcbd966c154c6e89ee82bd340e01c864d75328d95dd76eb6449b"
},
"polymorphism": {
"id": "Q3SYF2",
"text": "Numerous size polymorphism are present in KRTAP4 gene family, which are mainly due to variations in the sequence encoding cysteine-rich repeat segments (PubMed:15955084).",
"annotations": [
"Numerous size polymorphism are present in KRTAP4 gene family, which are mainly due to variations in the sequence encoding cysteine-rich repeat segments (PubMed:15955084)."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q3SYF2/entry",
"recordIndex0": 20898,
"sequenceLength": 146,
"sequenceSha256": "59ad989df2f8b79d296e5eda3c9b9ba74fc4f30c6ad7f9877683a304f1d9ca1a"
},
"mass spectrometry": {
"id": "Q8K1F5",
"text": "With 1 acetyl and 2 phosphate groups. With 1 acetyl and 3 phosphate groups. With 1 acetyl, 1 methyl and 2 phosphate groups. With 1 acetyl, 1 methyl and 3 phosphate groups.",
"annotations": [
"With 1 acetyl and 2 phosphate groups.",
"With 1 acetyl and 3 phosphate groups.",
"With 1 acetyl, 1 methyl and 2 phosphate groups.",
"With 1 acetyl, 1 methyl and 3 phosphate groups."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q8K1F5/entry",
"recordIndex0": 235893,
"sequenceLength": 107,
"sequenceSha256": "438a391ce36655ab6a96c1ddd501e7dccbdb5f87dcc169aa82856cc4e65363b8"
},
"allergen": {
"id": "Q9TRH5",
"text": "Causes an allergic reaction in human. Has six major and 3 minor IgE-binding regions and 5 major and 1 minor IgG-binding regions. Is a cause of cow's milk allergy (CMA).",
"annotations": [
"Causes an allergic reaction in human. Has six major and 3 minor IgE-binding regions and 5 major and 1 minor IgG-binding regions. Is a cause of cow's milk allergy (CMA)."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q9TRH5/entry",
"recordIndex0": 5303,
"sequenceLength": 214,
"sequenceSha256": "da494c1d90823ddbb367e374bf85b90da470d18064c0676dbe2a59a0751c0507"
},
"toxic dose": {
"id": "Q8AXY1",
"text": "LD(50) is 25 mg/kg by intraperitoneal injection into mice. LD(50) is 7.5 mg/kg by intravenous injection into mice. LD(50) is 0.5 mg/kg by intracerebroventricular injection.",
"annotations": [
"LD(50) is 25 mg/kg by intraperitoneal injection into mice.",
"LD(50) is 7.5 mg/kg by intravenous injection into mice.",
"LD(50) is 0.5 mg/kg by intracerebroventricular injection."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q8AXY1/entry",
"recordIndex0": 247161,
"sequenceLength": 138,
"sequenceSha256": "c5e4c2aab09bfc6bbe8d550ba3b50a154643a20a94d0f51375a925d950e6f18b"
},
"RNA editing": {
"id": "B0L3A2",
"text": "The nonsense codon (UGA) at position 14 is modified to a sense codon (UGI), which is the equivalent of UGG. ADAR is responsible of FBXW7-AS1 expression and RNA-editing.",
"annotations": [
"The nonsense codon (UGA) at position 14 is modified to a sense codon (UGI), which is the equivalent of UGG. ADAR is responsible of FBXW7-AS1 expression and RNA-editing."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/B0L3A2/entry",
"recordIndex0": 64327,
"sequenceLength": 85,
"sequenceSha256": "741e248a9af7f9d135140a923a9af36521c01f7bacafc6dbcdea7d44801f4a9a"
},
"pharmaceutical": {
"id": "Q53ZV4",
"text": "Available under the name Actimmune (Genentech). Used for reducing the frequency and severity of serious infections associated with chronic granulomatous disease (CGD).",
"annotations": [
"Available under the name Actimmune (Genentech). Used for reducing the frequency and severity of serious infections associated with chronic granulomatous disease (CGD)."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/Q53ZV4/entry",
"recordIndex0": 73732,
"sequenceLength": 166,
"sequenceSha256": "62f4843c60cbed2b811412deaf7c7932eb8da01c0646c400fa694004491f67de"
},
"interaction": {
"id": "A5YVF1",
"text": "Accumulates in inclusion bodies in the cell periphery. May interact with the ER network from the perinuclear region out to the cell periphery (By similarity).",
"annotations": [
"Accumulates in inclusion bodies in the cell periphery. May interact with the ER network from the perinuclear region out to the cell periphery (By similarity)."
],
"source": "Supplied Swiss-Prot dataset 路 original annotation",
"origin": "project-dataset",
"url": "https://www.uniprot.org/uniprotkb/A5YVF1/entry",
"recordIndex0": 534464,
"sequenceLength": 633,
"sequenceSha256": "41fdf1a183e94dd502ccd9de09bba4100acbb08f85e4d5feaacd38e639b3f0d6"
}
}
}