User:Lindenb/Notebook/UMR915/20100921

20100920        Top        20100922       

Biomongo

started moving biomongo on server 2. the history of the mongo shell is in

  ~/.dbshell

updated families:

var c=db.families.find();
while(c.hasNext())
  {
  var f=c.next();
  var pro= f.project;
  var a=[pro];
  f.project=a;
  db.families.save(f);
  }

re-updated families. Used a DBRef instead of a simple id;

 var c=db.families.find();
 while(c.hasNext())
   {
   var f=c.next();
   var pro= f.project[0];
   delete f.project;
   f.project={"$ref":"projects","$id":pro}; 
   db.families.save(f);
   }

using dbref: http://www.mongodb.org/display/DOCS/Database+References#DatabaseReferences-DBRef

  c=db.families.find(); while(c.hasNext()) { f=c.next(); printjson(f.projectIds[0].fetch()); }
      {
      "_id" : "XXX",
      "label" : "XXXX",
      "description" : "XXXXXXX",
      "creation" : "2010-09-14"
       }
    (...)

Working with trees

insert GO into mongo with File:Go2mongo.xsl and http://archive.geneontology.org/latest-termdb/go_daily-termdb.rdf-xml.gz

  db.go.drop();
 
  term={_id:"GO:0000001",name:"mitochondrion inheritance",synonyms:["mitochondrial inheritance"],definition:"The distribution of mitochondria, including the mitochondrial genome, into daughter cells after mitosis or meiosis, mediated by interactions between mitochondria and the cytoskeleton.",is_a:[{'$ref':'go','$id':'GO:0048308'},{'$ref':'go','$id':'GO:0048311'}]};
  db.go.save(term);
  term={_id:"GO:0000002",name:"mitochondrial genome maintenance",definition:"The maintenance of the structure and integrity of the mitochondrial genome; includes replication and segregation of the mitochondrial chromosome.",is_a:[{'$ref':'go','$id':'GO:0007005'}],dbxrefs:[{database_symbol:"InterPro",reference:"IPR009446"},{database_symbol:"Pfam",reference:"PF06420"}]};
  db.go.save(term);
  term={_id:"GO:0000003",name:"reproduction",synonyms:["GO:0019952","GO:0050876","reproductive physiological process"],definition:"The production by an organism of new individuals that contain some portion of their genetic material inherited from that organism.",is_a:[{'$ref':'go','$id':'GO:0008150'}],dbxrefs:[{database_symbol:"Wikipedia",reference:"Reproduction"}]};
  db.go.save(term);
  term={_id:"GO:0000005",name:"ribosomal chaperone activity",definition:"OBSOLETE. Assists in the correct assembly of ribosomes or ribosomal subunits in vivo, but is not a component of the assembled ribosome when performing its normal biological function.",comments:["This term was made obsolete because it refers to a class of gene products and a biological process rather than a molecular function."],is_a:[{'$ref':'go','$id':'obsolete_molecular_function'}]};
  db.go.save(term);
  term={_id:"GO:0042254",name:"ribosome biogenesis",synonyms:["GO:0007046","ribosomal chaperone activity","ribosome biogenesis and assembly"],definition:"The process of the formation of the constituents of the ribosome subunits, their assembly, and their transport to the sites of protein synthesis.",is_a:[{'$ref':'go','$id':'GO:0022613'}],dbxrefs:[{database_symbol:"InterPro",reference:"IPR001790"},{database_symbol:"InterPro",reference:"IPR004037"},{database_symbol:"InterPro",reference:"IPR007023"},{database_symbol:"InterPro",reference:"IPR012948"},{database_symbol:"SP_KW",reference:"KW-0690"},{database_symbol:"HAMAP",reference:"MF_00554"},{database_symbol:"HAMAP",reference:"MF_00699"},{database_symbol:"HAMAP",reference:"MF_00803"},{database_symbol:"HAMAP",reference:"MF_01852"},{database_symbol:"Pfam",reference:"PF00466"},{database_symbol:"Pfam",reference:"PF04939"},{database_symbol:"Pfam",reference:"PF08142"},{database_symbol:"PROSITE",reference:"PS01082"},{database_symbol:"Wikipedia",reference:"Ribosome_biogenesis"},{database_symbol:"SMART",reference:"SM00785"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR00436"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR01575"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR02729"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR03594"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR03596"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR03597"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR03598"}]};
  db.go.save(term);
  term={_id:"GO:0044183",name:"protein binding involved in protein folding",synonyms:["chaperone activity"],definition:"Interacting selectively and non-covalently with any protein or protein complex (a complex of two or more proteins that may include other nonprotein molecules) that contributes to the process of protein folding.",is_a:[{'$ref':'go','$id':'GO:0005515'}]};
  db.go.save(term);
  term={_id:"GO:0051082",name:"unfolded protein binding",synonyms:["binding unfolded ER proteins","chaperone activity","fimbrium-specific chaperone activity","glycoprotein-specific chaperone activity","histone-specific chaperone activity","ribosomal chaperone activity","tubulin-specific chaperone activity"],definition:"Interacting selectively and non-covalently with an unfolded protein.",is_a:[{'$ref':'go','$id':'GO:0005515'}],dbxrefs:[{database_symbol:"InterPro",reference:"IPR000397"},{database_symbol:"InterPro",reference:"IPR001305"},{database_symbol:"InterPro",reference:"IPR001404"},{database_symbol:"InterPro",reference:"IPR002194"},{database_symbol:"InterPro",reference:"IPR002777"},{database_symbol:"InterPro",reference:"IPR002939"},{database_symbol:"InterPro",reference:"IPR003095"},{database_symbol:"InterPro",reference:"IPR003708"},{database_symbol:"InterPro",reference:"IPR004127"},{database_symbol:"InterPro",reference:"IPR004226"},{database_symbol:"InterPro",reference:"IPR004487"},{database_symbol:"InterPro",reference:"IPR004961"},{database_symbol:"InterPro",reference:"IPR008971"},{database_symbol:"InterPro",reference:"IPR009033"},{database_symbol:"InterPro",reference:"IPR009169"},{database_symbol:"InterPro",reference:"IPR010236"},{database_symbol:"InterPro",reference:"IPR011599"},{database_symbol:"InterPro",reference:"IPR012713"},{database_symbol:"InterPro",reference:"IPR012714"},{database_symbol:"InterPro",reference:"IPR012715"},{database_symbol:"InterPro",reference:"IPR012716"},{database_symbol:"InterPro",reference:"IPR012717"},{database_symbol:"InterPro",reference:"IPR012718"},{database_symbol:"InterPro",reference:"IPR012719"},{database_symbol:"InterPro",reference:"IPR012720"},{database_symbol:"InterPro",reference:"IPR012721"},{database_symbol:"InterPro",reference:"IPR012722"},{database_symbol:"InterPro",reference:"IPR012724"},{database_symbol:"InterPro",reference:"IPR012725"},{database_symbol:"InterPro",reference:"IPR016153"},{database_symbol:"InterPro",reference:"IPR016154"},{database_symbol:"InterPro",reference:"IPR019805"},{database_symbol:"HAMAP",reference:"MF_00117"},{database_symbol:"PROSITE",reference:"MF_00117"},{database_symbol:"HAMAP",reference:"MF_00175"},{database_symbol:"PROSITE",reference:"MF_00175"},{database_symbol:"HAMAP",reference:"MF_00307"},{database_symbol:"PROSITE",reference:"MF_00307"},{database_symbol:"HAMAP",reference:"MF_00308"},{database_symbol:"PROSITE",reference:"MF_00308"},{database_symbol:"PROSITE",reference:"MF_00332"},{database_symbol:"HAMAP",reference:"MF_00505"},{database_symbol:"PROSITE",reference:"MF_00505"},{database_symbol:"HAMAP",reference:"MF_00600"},{database_symbol:"PROSITE",reference:"MF_00679"},{database_symbol:"HAMAP",reference:"MF_00790"},{database_symbol:"PROSITE",reference:"MF_00821"},{database_symbol:"HAMAP",reference:"MF_00822"},{database_symbol:"HAMAP",reference:"MF_01046"},{database_symbol:"HAMAP",reference:"MF_01152"},{database_symbol:"PROSITE",reference:"MF_01152"},{database_symbol:"HAMAP",reference:"MF_01183"},{database_symbol:"ProDom",reference:"PD010430"},{database_symbol:"Pfam",reference:"PF00684"},{database_symbol:"Pfam",reference:"PF01430"},{database_symbol:"Pfam",reference:"PF01556"},{database_symbol:"Pfam",reference:"PF01920"},{database_symbol:"Pfam",reference:"PF02556"},{database_symbol:"Pfam",reference:"PF02970"},{database_symbol:"Pfam",reference:"PF02996"},{database_symbol:"Pfam",reference:"PF03280"},{database_symbol:"PIRSF",reference:"PIRSF002356"},{database_symbol:"PIRSF",reference:"PIRSF002583"},{database_symbol:"PIRSF",reference:"PIRSF005261"},{database_symbol:"PRINTS",reference:"PR00625"},{database_symbol:"PRINTS",reference:"PR01594"},{database_symbol:"PROSITE",reference:"PS00298"},{database_symbol:"PROSITE",reference:"PS00750"},{database_symbol:"PROSITE",reference:"PS00751"},{database_symbol:"PROSITE",reference:"PS00995"},{database_symbol:"PROSITE",reference:"PS51188"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR00074"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR00115"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR00382"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR00809"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR02350"},{database_symbol:"JCVI_TIGRFAMS",reference:"TIGR03142"}]};
  db.go.save(term);
  term={_id:"GO:0000006",name:"high affinity zinc uptake transmembrane transporter activity",definition:"Catalysis of the transfer of a solute or solutes from one side of a membrane to the other according to the reaction: Zn2+(out) = Zn2+(in), probably powered by proton motive force. In high affinity transport the transporter is able to bind the solute even if it is only present at very low concentrations.",is_a:[{'$ref':'go','$id':'GO:0005385'}]};
  db.go.save(term);

useful functions

  var goNodeIsA=  function (childNode, parentId) {
   if (childNode == null) {
       return false;
   }
   if (childNode._id == parentId) {
       return true;
   }
   if (!childNode.is_a) {
       return false;
   }
   for (var i = 0; i < childNode.is_a.length; ++i) {
       if (goNodeIsA(childNode.is_a[i].fetch(), parentId)) {
           return true;
       }
   }
   return false;
 }

var goIsA=function (childId, parentId) {
   return goNodeIsA(db.go.findOne({_id:childId}), parentId);
   }

tests

is GO:0003723 (RNA binding) a descendant of GO:0005488 (binding) ?

 > goIsA("GO:0003723","GO:0005488");                                                               
 true

is GO:0003723 (RNA binding) a descendant of GO:0050355 (triphosphatase activity) ?

> goIsA("GO:0003723","GO:0050355");
false

find all the descendants of 'GO:0005488'

  db.go.find({},{name:1,is_a:1}).forEach(function(term) { if(goIsA(term._id,'GO:0005488')) printjson(term); })

  {
       "_id" : "GO:0080084",
        "name" : "5S rDNA binding",
        "is_a" : [
   {
     "$ref" : "go",
     "$id" : "GO:0000182"
   }
 ]
  }
  {
       "_id" : "GO:0080087",
        "name" : "callose binding",
        "is_a" : [
   {
     "$ref" : "go",
     "$id" : "GO:0030247"
   }
 ]
  }
  {
       "_id" : "GO:0080115",
 "name" : "myosin XI tail binding",
 "is_a" : [
   {
     "$ref" : "go",
     "$id" : "GO:0032029"
   }
 ]
  }
  {
        "_id" : "GO:0090079",
 "name" : "translation regulator activity, nucleic acid binding",
 "is_a" : [
   {
     "$ref" : "go",
     "$id" : "GO:0003676"
   },
   {
     "$ref" : "go",
     "$id" : "GO:0045182"
   }
 ]
  }