Merge branch 'master' into fix_dedupfailsonmatchinginstances

This commit is contained in:
Claudio Atzori 2023-10-02 11:28:16 +02:00
commit fa692b3629
6 changed files with 94 additions and 28 deletions

1
.gitignore vendored
View File

@ -26,3 +26,4 @@ spark-warehouse
/**/*.log /**/*.log
/**/.factorypath /**/.factorypath
/**/.scalafmt.conf /**/.scalafmt.conf
/.java-version

View File

@ -81,7 +81,7 @@ case class SparkModel(conf: DedupConfig) {
MapDocumentUtil.truncateList( MapDocumentUtil.truncateList(
MapDocumentUtil.getJPathList(fdef.getPath, documentContext, fdef.getType), MapDocumentUtil.getJPathList(fdef.getPath, documentContext, fdef.getType),
fdef.getSize fdef.getSize
).toArray ).asScala
case Type.StringConcat => case Type.StringConcat =>
val jpaths = CONCAT_REGEX.split(fdef.getPath) val jpaths = CONCAT_REGEX.split(fdef.getPath)

View File

@ -222,7 +222,7 @@ object BioDBToOAF {
def uniprotToOAF(input: String): List[Oaf] = { def uniprotToOAF(input: String): List[Oaf] = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json = parse(input) lazy val json = parse(input)
val pid = (json \ "pid").extract[String] val pid = (json \ "pid").extract[String].trim()
val d = new Dataset val d = new Dataset

View File

@ -1,15 +1,44 @@
{"pdb": "1CW0", "title": "crystal structure analysis of very short patch repair (vsr) endonuclease in complex with a duplex dna", "authors": ["S.E.Tsutakawa", "H.Jingami", "K.Morikawa"], "doi": "10.1016/S0092-8674(00)81550-0", "pmid": "10612397"} {"classification": "Signaling protein", "pdb": "5NM4", "deposition_date": "2017-04-05", "title": "A2a adenosine receptor room-temperature structure determined by serial Femtosecond crystallography", "Keywords": ["Oom-temperature", " serial crystallography", " signaling protein"], "authors": ["T.weinert", "R.cheng", "D.james", "D.gashi", "P.nogly", "K.jaeger", "M.hennig", "", "J.standfuss"], "pmid": "28912485", "doi": "10.1038/S41467-017-00630-4"}
{"pdb": "2CWW", "title": "crystal structure of thermus thermophilus ttha1280, a putative sam- dependent rna methyltransferase, in complex with s-adenosyl-l- homocysteine", "authors": ["A.A.Pioszak", "K.Murayama", "N.Nakagawa", "A.Ebihara", "S.Kuramitsu", "M.Shirouzu", "S.Yokoyama", "Riken Structural Genomics/proteomics Initiative (Rsgi)"], "doi": "10.1107/S1744309105029842", "pmid": "16511182"} {"classification": "Oxidoreductase/oxidoreductase inhibitor", "pdb": "4KN3", "deposition_date": "2013-05-08", "title": "Structure of the y34ns91g double mutant of dehaloperoxidase from Amphitrite ornata with 2,4,6-trichlorophenol", "Keywords": ["Lobin", " oxygen storage", " peroxidase", " oxidoreductase", " oxidoreductase-", "Oxidoreductase inhibitor complex"], "authors": ["C.wang", "L.lovelace", "L.lebioda"], "pmid": "23952341", "doi": "10.1021/BI400627W"}
{"pdb": "6CWE", "title": "structure of alpha-gsa[8,6p] bound by cd1d and in complex with the va14vb8.2 tcr", "authors": ["J.Wang", "D.Zajonc"], "doi": null, "pmid": null} {"classification": "Transport protein", "pdb": "8HKM", "deposition_date": "2022-11-27", "title": "Ion channel", "Keywords": ["On channel", " transport protein"], "authors": ["D.h.jiang", "J.t.zhang"], "pmid": "37494189", "doi": "10.1016/J.CELREP.2023.112858"}
{"pdb": "5CWS", "title": "crystal structure of the intact chaetomium thermophilum nsp1-nup49- nup57 channel nucleoporin heterotrimer bound to its nic96 nuclear pore complex attachment site", "authors": ["C.J.Bley", "S.Petrovic", "M.Paduch", "V.Lu", "A.A.Kossiakoff", "A.Hoelz"], "doi": "10.1126/SCIENCE.AAC9176", "pmid": "26316600"} {"classification": "Signaling protein", "pdb": "6JT1", "deposition_date": "2019-04-08", "title": "Structure of human soluble guanylate cyclase in the heme oxidised State", "Keywords": ["Oluble guanylate cyclase", " signaling protein"], "authors": ["L.chen", "Y.kang", "R.liu", "J.-x.wu"], "pmid": "31514202", "doi": "10.1038/S41586-019-1584-6"}
{"pdb": "5CWE", "title": "structure of cyp107l2 from streptomyces avermitilis with lauric acid", "authors": ["T.-V.Pham", "S.-H.Han", "J.-H.Kim", "D.-H.Kim", "L.-W.Kang"], "doi": null, "pmid": null} {"classification": "Immune system", "pdb": "7OW6", "deposition_date": "2021-06-16", "title": "Crystal structure of a tcr in complex with hla-a*11:01 bound to kras G12d peptide (vvvgadgvgk)", "Keywords": ["La", " kras", " tcr", " immune system"], "authors": ["V.karuppiah", "R.a.robinson"], "doi": "10.1038/S41467-022-32811-1"}
{"pdb": "7CW4", "title": "acetyl-coa acetyltransferase from bacillus cereus atcc 14579", "authors": ["J.Hong", "K.J.Kim"], "doi": "10.1016/J.BBRC.2020.09.048", "pmid": "32972748"} {"classification": "Biosynthetic protein", "pdb": "5EQ8", "deposition_date": "2015-11-12", "title": "Crystal structure of medicago truncatula histidinol-phosphate Phosphatase (mthpp) in complex with l-histidinol", "Keywords": ["Istidine biosynthesis", " metabolic pathways", " dimer", " plant", "", "Biosynthetic protein"], "authors": ["M.ruszkowski", "Z.dauter"], "pmid": "26994138", "doi": "10.1074/JBC.M115.708727"}
{"pdb": "2CWP", "title": "crystal structure of metrs related protein from pyrococcus horikoshii", "authors": ["K.Murayama", "M.Kato-Murayama", "M.Shirouzu", "S.Yokoyama", "Riken StructuralGenomics/proteomics Initiative (Rsgi)"], "doi": null, "pmid": null} {"classification": "De novo protein", "pdb": "8CWA", "deposition_date": "2022-05-18", "title": "Solution nmr structure of 8-residue rosetta-designed cyclic peptide D8.21 in cdcl3 with cis/trans switching (tc conformation, 53%)", "Keywords": ["Yclic peptide", " non natural amino acids", " cis/trans", " switch peptides", "", "De novo design", "Membrane permeability", "De novo protein"], "authors": ["T.a.ramelot", "R.tejero", "G.t.montelione"], "pmid": "36041435", "doi": "10.1016/J.CELL.2022.07.019"}
{"pdb": "2CW7", "title": "crystal structure of intein homing endonuclease ii", "authors": ["H.Matsumura", "H.Takahashi", "T.Inoue", "H.Hashimoto", "M.Nishioka", "S.Fujiwara", "M.Takagi", "T.Imanaka", "Y.Kai"], "doi": "10.1002/PROT.20858", "pmid": "16493661"} {"classification": "Hydrolase", "pdb": "3R6M", "deposition_date": "2011-03-21", "title": "Crystal structure of vibrio parahaemolyticus yeaz", "Keywords": ["Ctin/hsp70 nucleotide-binding fold", " bacterial resuscitation", " viable", "But non-culturable state", "Resuscitation promoting factor", "Ygjd", "", "Yjee", "Vibrio parahaemolyticus", "Hydrolase"], "authors": ["A.roujeinikova", "I.aydin"], "pmid": "21858042", "doi": "10.1371/JOURNAL.PONE.0023245"}
{"pdb": "1CWU", "title": "brassica napus enoyl acp reductase a138g mutant complexed with nad+ and thienodiazaborine", "authors": ["A.Roujeinikova", "J.B.Rafferty", "D.W.Rice"], "doi": "10.1074/JBC.274.43.30811", "pmid": "10521472"} {"classification": "Hydrolase", "pdb": "2W5J", "deposition_date": "2008-12-10", "title": "Structure of the c14-rotor ring of the proton translocating Chloroplast atp synthase", "Keywords": ["Ydrolase", " chloroplast", " atp synthase", " lipid-binding", " cf(0)", " membrane", "", "Transport", "Formylation", "Energy transduction", "Hydrogen ion transport", "", "Ion transport", "Transmembrane", "Membrane protein"], "authors": ["M.vollmar", "D.schlieper", "M.winn", "C.buechner", "G.groth"], "pmid": "19423706", "doi": "10.1074/JBC.M109.006916"}
{"pdb": "3CWN", "title": "escherichia coli transaldolase b mutant f178y", "authors": ["T.Sandalova", "G.Schneider", "A.Samland"], "doi": "10.1074/JBC.M803184200", "pmid": "18687684"} {"classification": "De novo protein", "pdb": "4GLU", "deposition_date": "2012-08-14", "title": "Crystal structure of the mirror image form of vegf-a", "Keywords": ["-protein", " covalent dimer", " cysteine knot protein", " growth factor", " de", "Novo protein"], "authors": ["K.mandal", "M.uppalapati", "D.ault-riche", "J.kenney", "J.lowitz", "S.sidhu", "", "S.b.h.kent"], "pmid": "22927390", "doi": "10.1073/PNAS.1210483109"}
{"pdb": "1CWL", "title": "human cyclophilin a complexed with 4 4-hydroxy-meleu cyclosporin", "authors": ["V.Mikol", "J.Kallen", "P.Taylor", "M.D.Walkinshaw"], "doi": "10.1006/JMBI.1998.2108", "pmid": "9769216"} {"classification": "Hydrolase/hydrolase inhibitor", "pdb": "3WYL", "deposition_date": "2014-09-01", "title": "Crystal structure of the catalytic domain of pde10a complexed with 5- Methoxy-3-(1-phenyl-1h-pyrazol-5-yl)-1-(3-(trifluoromethyl)phenyl) Pyridazin-4(1h)-one", "Keywords": ["Ydrolase-hydrolase inhibitor complex"], "authors": ["H.oki", "Y.hayano"], "pmid": "25384088", "doi": "10.1021/JM5013648"}
{"pdb": "3CW2", "title": "crystal structure of the intact archaeal translation initiation factor 2 from sulfolobus solfataricus .", "authors": ["E.A.Stolboushkina", "S.V.Nikonov", "A.D.Nikulin", "U.Blaesi", "D.J.Manstein", "R.V.Fedorov", "M.B.Garber", "O.S.Nikonov"], "doi": "10.1016/J.JMB.2008.07.039", "pmid": "18675278"} {"classification": "Isomerase", "pdb": "5BOR", "deposition_date": "2015-05-27", "title": "Structure of acetobacter aceti pure-s57c, sulfonate form", "Keywords": ["Cidophile", " pure", " purine biosynthesis", " isomerase"], "authors": ["K.l.sullivan", "T.j.kappock"]}
{"pdb": "3CW9", "title": "4-chlorobenzoyl-coa ligase/synthetase in the thioester-forming conformation, bound to 4-chlorophenacyl-coa", "authors": ["A.S.Reger", "J.Cao", "R.Wu", "D.Dunaway-Mariano", "A.M.Gulick"], "doi": "10.1021/BI800696Y", "pmid": "18620418"} {"classification": "Hydrolase", "pdb": "1X0C", "deposition_date": "2005-03-17", "title": "Improved crystal structure of isopullulanase from aspergillus niger Atcc 9642", "Keywords": ["Ullulan", " glycoside hydrolase family 49", " glycoprotein", " hydrolase"], "authors": ["M.mizuno", "T.tonozuka", "A.yamamura", "Y.miyasaka", "H.akeboshi", "S.kamitori", "", "A.nishikawa", "Y.sakano"], "pmid": "18155243", "doi": "10.1016/J.JMB.2007.11.098"}
{"pdb": "3CWU", "title": "crystal structure of an alka host/guest complex 2'-fluoro-2'-deoxy-1, n6-ethenoadenine:thymine base pair", "authors": ["B.R.Bowman", "S.Lee", "S.Wang", "G.L.Verdine"], "doi": "10.1016/J.STR.2008.04.012", "pmid": "18682218"} {"classification": "Oxidoreductase", "pdb": "7CUP", "deposition_date": "2020-08-23", "title": "Structure of 2,5-dihydroxypridine dioxygenase from pseudomonas putida Kt2440", "Keywords": ["On-heme dioxygenase", " oxidoreductase"], "authors": ["G.q.liu", "H.z.tang"]}
{"pdb": "5CWF", "title": "crystal structure of de novo designed helical repeat protein dhr8", "authors": ["G.Bhabha", "D.C.Ekiert"], "doi": "10.1038/NATURE16162", "pmid": "26675729"} {"classification": "Ligase", "pdb": "1VCN", "deposition_date": "2004-03-10", "title": "Crystal structure of t.th. hb8 ctp synthetase complex with sulfate Anion", "Keywords": ["Etramer", " riken structural genomics/proteomics initiative", " rsgi", "", "Structural genomics", "Ligase"], "authors": ["M.goto", "Riken structural genomics/proteomics initiative (rsgi)"], "pmid": "15296735", "doi": "10.1016/J.STR.2004.05.013"}
{"classification": "Transferase/transferase inhibitor", "pdb": "6C9V", "deposition_date": "2018-01-28", "title": "Mycobacterium tuberculosis adenosine kinase bound to (2r,3s,4r,5r)-2- (hydroxymethyl)-5-(6-(4-phenylpiperazin-1-yl)-9h-purin-9-yl) Tetrahydrofuran-3,4-diol", "Keywords": ["Ucleoside analog", " complex", " inhibitor", " structural genomics", " psi-2", "", "Protein structure initiative", "Tb structural genomics consortium", "", "Tbsgc", "Transferase-transferase inhibitor complex"], "authors": ["R.a.crespo", "Tb structural genomics consortium (tbsgc)"], "pmid": "31002508", "doi": "10.1021/ACS.JMEDCHEM.9B00020"}
{"classification": "De novo protein", "pdb": "4LPY", "deposition_date": "2013-07-16", "title": "Crystal structure of tencon variant g10", "Keywords": ["Ibronectin type iii fold", " alternate scaffold", " de novo protein"], "authors": ["A.teplyakov", "G.obmolova", "G.l.gilliland"], "pmid": "24375666", "doi": "10.1002/PROT.24502"}
{"classification": "Isomerase", "pdb": "2Y88", "deposition_date": "2011-02-03", "title": "Crystal structure of mycobacterium tuberculosis phosphoribosyl Isomerase (variant d11n) with bound prfar", "Keywords": ["Romatic amino acid biosynthesis", " isomerase", " tim-barrel", " histidine", "Biosynthesis", "Tryptophan biosynthesis"], "authors": ["J.kuper", "A.v.due", "A.geerlof", "M.wilmanns"], "pmid": "21321225", "doi": "10.1073/PNAS.1015996108"}
{"classification": "Unknown function", "pdb": "1SR0", "deposition_date": "2004-03-22", "title": "Crystal structure of signalling protein from sheep(sps-40) at 3.0a Resolution using crystal grown in the presence of polysaccharides", "Keywords": ["Ignalling protein", " involution", " unknown function"], "authors": ["D.b.srivastava", "A.s.ethayathulla", "N.singh", "J.kumar", "S.sharma", "T.p.singh"]}
{"classification": "Dna binding protein", "pdb": "3RH2", "deposition_date": "2011-04-11", "title": "Crystal structure of a tetr-like transcriptional regulator (sama_0099) From shewanella amazonensis sb2b at 2.42 a resolution", "Keywords": ["Na/rna-binding 3-helical bundle", " structural genomics", " joint center", "For structural genomics", "Jcsg", "Protein structure initiative", "Psi-", "Biology", "Dna binding protein"], "authors": ["Joint center for structural genomics (jcsg)"]}
{"classification": "Transferase", "pdb": "2WK5", "deposition_date": "2009-06-05", "title": "Structural features of native human thymidine phosphorylase And in complex with 5-iodouracil", "Keywords": ["Lycosyltransferase", " developmental protein", " angiogenesis", "", "5-iodouracil", "Growth factor", "Enzyme kinetics", "", "Differentiation", "Disease mutation", "Thymidine", "Phosphorylase", "Chemotaxis", "Transferase", "Mutagenesis", "", "Polymorphism"], "authors": ["E.mitsiki", "A.c.papageorgiou", "S.iyer", "N.thiyagarajan", "S.h.prior", "", "D.sleep", "C.finnis", "K.r.acharya"], "pmid": "19555658", "doi": "10.1016/J.BBRC.2009.06.104"}
{"classification": "Hydrolase", "pdb": "3P9Y", "deposition_date": "2010-10-18", "title": "Crystal structure of the drosophila melanogaster ssu72-pctd complex", "Keywords": ["Hosphatase", " cis proline", " lmw ptp-like fold", " rna polymerase ii ctd", "", "Hydrolase"], "authors": ["J.w.werner-allen", "P.zhou"], "pmid": "21159777", "doi": "10.1074/JBC.M110.197129"}
{"classification": "Recombination/dna", "pdb": "6OEO", "deposition_date": "2019-03-27", "title": "Cryo-em structure of mouse rag1/2 nfc complex (dna1)", "Keywords": ["(d)j recombination", " dna transposition", " rag", " scid", " recombination", "", "Recombination-dna complex"], "authors": ["X.chen", "Y.cui", "Z.h.zhou", "W.yang", "M.gellert"], "pmid": "32015552", "doi": "10.1038/S41594-019-0363-2"}
{"classification": "Hydrolase", "pdb": "4ECA", "deposition_date": "1997-02-21", "title": "Asparaginase from e. coli, mutant t89v with covalently bound aspartate", "Keywords": ["Ydrolase", " acyl-enzyme intermediate", " threonine amidohydrolase"], "authors": ["G.j.palm", "J.lubkowski", "A.wlodawer"], "pmid": "8706862", "doi": "10.1016/0014-5793(96)00660-6"}
{"classification": "Transcription/protein binding", "pdb": "3UVX", "deposition_date": "2011-11-30", "title": "Crystal structure of the first bromodomain of human brd4 in complex With a diacetylated histone 4 peptide (h4k12ack16ac)", "Keywords": ["Romodomain", " bromodomain containing protein 4", " cap", " hunk1", " mcap", "", "Mitotic chromosome associated protein", "Peptide complex", "Structural", "Genomics consortium", "Sgc", "Transcription-protein binding complex"], "authors": ["P.filippakopoulos", "S.picaud", "T.keates", "E.ugochukwu", "F.von delft", "", "C.h.arrowsmith", "A.m.edwards", "J.weigelt", "C.bountra", "S.knapp", "Structural", "Genomics consortium (sgc)"], "pmid": "22464331", "doi": "10.1016/J.CELL.2012.02.013"}
{"classification": "Membrane protein", "pdb": "1TLZ", "deposition_date": "2004-06-10", "title": "Tsx structure complexed with uridine", "Keywords": ["Ucleoside transporter", " beta barrel", " uridine", " membrane", "Protein"], "authors": ["J.ye", "B.van den berg"], "pmid": "15272310", "doi": "10.1038/SJ.EMBOJ.7600330"}
{"classification": "Dna binding protein", "pdb": "7AZD", "deposition_date": "2020-11-16", "title": "Dna polymerase sliding clamp from escherichia coli with peptide 20 Bound", "Keywords": ["Ntibacterial drug", " dna binding protein"], "authors": ["C.monsarrat", "G.compain", "C.andre", "I.martiel", "S.engilberge", "V.olieric", "", "P.wolff", "K.brillet", "M.landolfo", "C.silva da veiga", "J.wagner", "G.guichard", "", "D.y.burnouf"], "pmid": "34806883", "doi": "10.1021/ACS.JMEDCHEM.1C00918"}
{"classification": "Transferase", "pdb": "5N3K", "deposition_date": "2017-02-08", "title": "Camp-dependent protein kinase a from cricetulus griseus in complex With fragment like molecule o-guanidino-l-homoserine", "Keywords": ["Ragment", " complex", " transferase", " serine threonine kinase", " camp", "", "Kinase", "Pka"], "authors": ["C.siefker", "A.heine", "G.klebe"]}
{"classification": "Biosynthetic protein", "pdb": "8H52", "deposition_date": "2022-10-11", "title": "Crystal structure of helicobacter pylori carboxyspermidine Dehydrogenase in complex with nadp", "Keywords": ["Arboxyspermidine dehydrogenase", " biosynthetic protein"], "authors": ["K.y.ko", "S.c.park", "S.y.cho", "S.i.yoon"], "pmid": "36283333", "doi": "10.1016/J.BBRC.2022.10.049"}
{"classification": "Metal binding protein", "pdb": "6DYC", "deposition_date": "2018-07-01", "title": "Co(ii)-bound structure of the engineered cyt cb562 variant, ch3", "Keywords": ["Esigned protein", " 4-helix bundle", " electron transport", " metal binding", "Protein"], "authors": ["F.a.tezcan", "J.rittle"], "pmid": "30778140", "doi": "10.1038/S41557-019-0218-9"}
{"classification": "Protein fibril", "pdb": "6A6B", "deposition_date": "2018-06-27", "title": "Cryo-em structure of alpha-synuclein fiber", "Keywords": ["Lpha-syn fiber", " parkinson disease", " protein fibril"], "authors": ["Y.w.li", "C.y.zhao", "F.luo", "Z.liu", "X.gui", "Z.luo", "X.zhang", "D.li", "C.liu", "X.li"], "pmid": "30065316", "doi": "10.1038/S41422-018-0075-X"}
{"classification": "Dna", "pdb": "7D5E", "deposition_date": "2020-09-25", "title": "Left-handed g-quadruplex containing two bulges", "Keywords": ["-quadruplex", " bulge", " dna", " left-handed"], "authors": ["P.das", "A.maity", "K.h.ngo", "F.r.winnerdy", "B.bakalar", "Y.mechulam", "E.schmitt", "", "A.t.phan"], "pmid": "33503265", "doi": "10.1093/NAR/GKAA1259"}
{"classification": "Transferase", "pdb": "3RSY", "deposition_date": "2011-05-02", "title": "Cellobiose phosphorylase from cellulomonas uda in complex with sulfate And glycerol", "Keywords": ["H94", " alpha barrel", " cellobiose phosphorylase", " disaccharide", "Phosphorylase", "Transferase"], "authors": ["A.van hoorebeke", "J.stout", "W.soetaert", "J.van beeumen", "T.desmet", "S.savvides"]}
{"classification": "Oxidoreductase", "pdb": "7MCI", "deposition_date": "2021-04-02", "title": "Mofe protein from azotobacter vinelandii with a sulfur-replenished Cofactor", "Keywords": ["Zotobacter vinelandii", " mofe-protein", " nitrogenase", " oxidoreductase"], "authors": ["W.kang", "C.lee", "Y.hu", "M.w.ribbe"], "doi": "10.1038/S41929-022-00782-7"}
{"classification": "Dna", "pdb": "1XUW", "deposition_date": "2004-10-26", "title": "Structural rationalization of a large difference in rna affinity Despite a small difference in chemistry between two 2'-o-modified Nucleic acid analogs", "Keywords": ["Na mimetic methylcarbamate amide analog", " dna"], "authors": ["R.pattanayek", "L.sethaphong", "C.pan", "M.prhavc", "T.p.prakash", "M.manoharan", "", "M.egli"], "pmid": "15547979", "doi": "10.1021/JA044637K"}
{"classification": "Lyase", "pdb": "7C0D", "deposition_date": "2020-05-01", "title": "Crystal structure of azospirillum brasilense l-2-keto-3-deoxyarabonate Dehydratase (hydroxypyruvate-bound form)", "Keywords": ["-2-keto-3-deoxyarabonate dehydratase", " lyase"], "authors": ["Y.watanabe", "S.watanabe"], "pmid": "32697085", "doi": "10.1021/ACS.BIOCHEM.0C00515"}
{"classification": "Signaling protein", "pdb": "5LYK", "deposition_date": "2016-09-28", "title": "Crystal structure of intracellular b30.2 domain of btn3a1 bound to Citrate", "Keywords": ["30.2", " butyrophilin", " signaling protein"], "authors": ["F.mohammed", "A.t.baker", "M.salim", "B.e.willcox"], "pmid": "28862425", "doi": "10.1021/ACSCHEMBIO.7B00694"}
{"classification": "Toxin", "pdb": "4IZL", "deposition_date": "2013-01-30", "title": "Structure of the n248a mutant of the panton-valentine leucocidin s Component from staphylococcus aureus", "Keywords": ["I-component leucotoxin", " staphylococcus aureus", " s component", "Leucocidin", "Beta-barrel pore forming toxin", "Toxin"], "authors": ["L.maveyraud", "B.j.laventie", "G.prevost", "L.mourey"], "pmid": "24643034", "doi": "10.1371/JOURNAL.PONE.0092094"}
{"classification": "Dna", "pdb": "6F3C", "deposition_date": "2017-11-28", "title": "The cytotoxic [pt(h2bapbpy)] platinum complex interacting with the Cgtacg hexamer", "Keywords": ["Rug-dna complex", " four-way junction", " dna"], "authors": ["M.ferraroni", "C.bazzicalupi", "P.gratteri", "F.papi"], "pmid": "31046177", "doi": "10.1002/ANIE.201814532"}
{"classification": "Signaling protein/inhibitor", "pdb": "4L5M", "deposition_date": "2013-06-11", "title": "Complexe of arno sec7 domain with the protein-protein interaction Inhibitor n-(4-hydroxy-2,6-dimethylphenyl)benzenesulfonamide at ph6.5", "Keywords": ["Ec-7domain", " signaling protein-inhibitor complex"], "authors": ["F.hoh", "J.rouhana"], "pmid": "24112024", "doi": "10.1021/JM4009357"}
{"classification": "Signaling protein", "pdb": "5I6J", "deposition_date": "2016-02-16", "title": "Crystal structure of srgap2 f-barx", "Keywords": ["Rgap2", " f-bar", " fx", " signaling protein"], "authors": ["M.sporny", "J.guez-haddad", "M.n.isupov", "Y.opatowsky"], "pmid": "28333212", "doi": "10.1093/MOLBEV/MSX094"}
{"classification": "Metal binding protein", "pdb": "1Q80", "deposition_date": "2003-08-20", "title": "Solution structure and dynamics of nereis sarcoplasmic calcium binding Protein", "Keywords": ["Ll-alpha", " metal binding protein"], "authors": ["G.rabah", "R.popescu", "J.a.cox", "Y.engelborghs", "C.t.craescu"], "pmid": "15819893", "doi": "10.1111/J.1742-4658.2005.04629.X"}
{"classification": "Transferase", "pdb": "1TW1", "deposition_date": "2004-06-30", "title": "Beta-1,4-galactosyltransferase mutant met344his (m344h-gal-t1) complex With udp-galactose and magnesium", "Keywords": ["Et344his mutation; closed conformation; mn binding", " transferase"], "authors": ["B.ramakrishnan", "E.boeggeman", "P.k.qasba"], "pmid": "15449940", "doi": "10.1021/BI049007+"}
{"classification": "Rna", "pdb": "2PN4", "deposition_date": "2007-04-23", "title": "Crystal structure of hepatitis c virus ires subdomain iia", "Keywords": ["Cv", " ires", " subdoamin iia", " rna", " strontium", " hepatitis"], "authors": ["Q.zhao", "Q.han", "C.r.kissinger", "P.a.thompson"], "pmid": "18391410", "doi": "10.1107/S0907444908002011"}

View File

@ -1,6 +1,36 @@
{"pid": "Q6GZX4", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 41."}], "title": "Putative transcription factor 001R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]} {"pid": " Q6GZX4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 43"}], "title": "Putative transcription factor 001R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": "Q6GZX3", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 42."}], "title": "Uncharacterized protein 002L;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]} {"pid": " Q6GZX3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 45"}], "title": "Uncharacterized protein 002L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": "Q197F8", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 27."}], "title": "Uncharacterized protein 002R;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]} {"pid": " Q197F8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 29"}], "title": "Uncharacterized protein 002R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": "Q197F7", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 23."}], "title": "Uncharacterized protein 003L;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]} {"pid": " Q197F7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 23"}], "title": "Uncharacterized protein 003L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": "Q6GZX2", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 36."}], "title": "Uncharacterized protein 3R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]} {"pid": " Q6GZX2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 3R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": "Q6GZX1", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 34."}], "title": "Uncharacterized protein 004R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]} {"pid": " Q6GZX1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 38"}], "title": "Uncharacterized protein 004R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197F5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 005L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZX0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 47"}], "title": "Uncharacterized protein 005R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q91G88", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-06-28", "date_info": "entry version 53"}], "title": "Putative KilA-N domain-containing protein 006L", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
{"pid": " Q6GZW9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 34"}], "title": "Uncharacterized protein 006R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 32"}], "title": "Uncharacterized protein 007R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197F3", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 007R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q197F2", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 22"}], "title": "Uncharacterized protein 008L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZW6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 67"}], "title": "Putative helicase 009L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q91G85", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 38"}], "title": "Uncharacterized protein 009R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
{"pid": " Q6GZW5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 010R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197E9", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 011L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZW4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 011R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 012L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197E7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 37"}], "title": "Uncharacterized protein IIV3-013L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZW2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 30"}], "title": "Uncharacterized protein 013R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 014R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 50"}], "title": "Uncharacterized protein 015R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 017L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV7", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 018L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 87"}], "title": "Putative serine/threonine-protein kinase 019R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 40"}], "title": "Uncharacterized protein 020R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 021L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197D8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-12-14", "date_info": "entry version 35"}], "title": "Transmembrane protein 022L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZV2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 023R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197D7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 25"}], "title": "Uncharacterized protein 023R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZV1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 024R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197D5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 24"}], "title": "Uncharacterized protein 025R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q91G70", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 026R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
{"pid": " Q6GZU9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 49"}], "title": "Uncharacterized protein 027R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZU8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 55"}], "title": "Uncharacterized protein 028R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}

View File

@ -2,7 +2,9 @@
package eu.dnetlib.dhp.broker.oa.util; package eu.dnetlib.dhp.broker.oa.util;
import java.io.IOException; import java.io.IOException;
import java.nio.charset.StandardCharsets;
import org.apache.commons.io.IOUtils;
import org.apache.spark.sql.Row; import org.apache.spark.sql.Row;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
@ -27,10 +29,14 @@ public class TrustUtils {
static { static {
mapper = new ObjectMapper(); mapper = new ObjectMapper();
try { try {
dedupConfig = mapper dedupConfig = DedupConfig
.readValue( .load(
DedupConfig.class.getResourceAsStream("/eu/dnetlib/dhp/broker/oa/dedupConfig/dedupConfig.json"), IOUtils
DedupConfig.class); .toString(
DedupConfig.class
.getResourceAsStream("/eu/dnetlib/dhp/broker/oa/dedupConfig/dedupConfig.json"),
StandardCharsets.UTF_8));
deduper = new SparkDeduper(dedupConfig); deduper = new SparkDeduper(dedupConfig);
} catch (final IOException e) { } catch (final IOException e) {
log.error("Error loading dedupConfig, e"); log.error("Error loading dedupConfig, e");
@ -57,7 +63,7 @@ public class TrustUtils {
return TrustUtils.rescale(score, threshold); return TrustUtils.rescale(score, threshold);
} catch (final Exception e) { } catch (final Exception e) {
log.error("Error computing score between results", e); log.error("Error computing score between results", e);
return BrokerConstants.MIN_TRUST; throw new RuntimeException(e);
} }
} }