ó ,ÍÃIc@s£dZddlZddlZddlZdd„Zddd„ƒYZddd„ƒYZid d 6d d 6d d 6d d6dd6dd6Zddd„ƒYZdS(sÊConnect with a BioSQL database and load Biopython like objects from it. This provides interfaces for loading biological objects from a relational database, and is compatible with the BioSQL standards. iÿÿÿÿNtMySQLdbcKs¨t|ƒ}t|dƒ}|jƒ}|dkr~d|krW|d|d<|d=nd|krÆ|d|d<|d=qÆnHd|kr¢|d|d<|d=nd|krÆ|d|d<|d=n|d krï|jdƒ rïd |d>> from BioSeq import BioSeqDatabase >>> server = BioSeqDatabase.open_database(user = "root", db="minidb") the various options are: driver -> The name of the database driver to use for connecting. The driver should implement the python DB API. By default, the MySQLdb driver is used. user -> the username to connect to the database with. password, passwd -> the password to connect with host -> the hostname of the database database or db -> the name of the database tconnectRtdatabasetdbtpasswordtpasswdtpsycopgtpsycopg2t template1tdbnamet t=(RR(t __import__tgetattrtcopytgettInterfaceErrortjointitemstDBServer(tdrivertkwargstmoduleRtkwtconntitdsn((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt open_databases<                1RcBs}eZd d„Zd„Zd„Zd„Zd„Zd„Zd„Z d d d„Z d„Z d „Z d „Z d „ZRS( cCsI||_|dkr!|j}nt|tj|ƒƒ|_||_dS(N(RtNonet__name__tAdaptortDBUtilst get_dbutilstadaptort module_name(tselfRRR"((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt__init__Ls    cCs|jjd|jjS(Ns(%r)(t __class__RR!R(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt__repr__SscCst|j|ƒS(N(tBioSeqDatabaseR!(R#tname((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt __getitem__UscCs |jjƒS(N(R!tlist_biodatabase_names(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytkeysWscCs!g|jƒD]}||^q S(N(R+(R#tkey((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytvaluesYscCs'g|jƒD]}|||f^q S(N(R+(R#R,((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR[scCs5|jj|ƒ}tj|j|ƒ}|jƒdS(s=Try to remove all references to items in a database. N(R!tfetch_dbid_by_dbnametLoadertDatabaseRemovertremove(R#tdb_nametdb_idtremover((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytremove_database^scCs2d}|jj||||fƒt|j|ƒS(s8Add a new database to the server and return it. sJINSERT INTO biodatabase (name, authority, description) VALUES (%s, %s, %s)(R!texecuteR'(R#R2t authorityt descriptiontsql((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt new_databaseescCs t|dƒ}d}xm|jƒD]_}|jdƒdkr@q"|jdƒdkrXq"|jƒr"||jƒ7}|d7}q"q"W|jdkrª|jjj|ƒn\|jdkró|jd ƒ}x;|d D]}|jjj|ƒqÓWnt d |jƒ‚d S(súLoad a database schema into the given database. This is used to create tables, etc when a database is first created. sql_file should specify the complete path to a file containing SQL entries for building the tables. trbts--it#R RRRt;iÿÿÿÿs&Module %s not supported by the loader.N(RR(R( topent xreadlinestfindtstripR"R!tcursorR6tsplitt ValueError(R#tsql_filet sql_handleR9tlinet sql_partstsql_line((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytload_database_sqlns$  cCs |jjƒS(s0Commits the current transaction to the database.(R!tcommit(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRL•scCs |jjƒS(s$Rolls backs the current transaction.(R!trollback(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRM™scCs |jjƒS(s3Close the connection. No further activity possible.(R!tclose(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRNsN(Rt __module__RR$R&R)R+R-RR5R:RKRLRMRN(((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRKs        '  RcBsÔeZd„Zd„Zed„Zd„Zd„Zd„Zd„Z d„Z d„Z d „Z d „Z d „Zd „Zd „Zd„Zd„Zdd„Zdd„Zd„Zdd„Zdd„ZRS(cCs%||_|jƒ|_||_dS(N(RRCtdbutils(R#RRP((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR$¢s cCs|jj|j|ƒS(N(RPtlast_idRC(R#ttable((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRQ§scCs|jj|j|ƒS(sASet the autocommit mode. True values enable; False value disable.(RPt autocommitR(R#ty((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRSªscCs |jjƒS(s Commits the current transaction.(RRL(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRL®scCs |jjƒS(s$Rolls backs the current transaction.(RRM(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRM²scCs |jjƒS(s3Close the connection. No further activity possible.(RRN(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRN¶scCsJ|jjd|fƒ|jjƒ}|s>td|ƒ‚n|ddS(Ns6select biodatabase_id from biodatabase where name = %ss$Cannot find biodatabase with name %ri(RCR6tfetchalltKeyError(R#R trv((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR.ºs  cCs›d}|g}|r/|d7}|j|ƒn|jj||ƒ|jjƒ}|sjtd|ƒ‚nt|ƒdkrtd|ƒ‚n|ddS(Ns0select bioentry_id from bioentry where name = %ss and biodatabase_id = %ssCannot find display id %ris&More than one entry with display id %ri(tappendRCR6RUt IndexErrortlen(R#tdbidR(R9tfieldsRW((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytfetch_seqid_by_display_idÅs  cCs›d}|g}|r/|d7}|j|ƒn|jj||ƒ|jjƒ}|sjtd|ƒ‚nt|ƒdkrtd|ƒ‚n|ddS(Ns5select bioentry_id from bioentry where accession = %ss and biodatabase_id = %ssCannot find accession %ris%More than one entry with accession %ri(RXRCR6RURYRZ(R#R[R(R9R\RW((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytfetch_seqid_by_accessionÓs  cCs?d}|g}|r/|d7}|j|ƒn|j||ƒS(Ns5select bioentry_id from bioentry where accession = %ss and biodatabase_id = %s(RXtexecute_and_fetch_col0(R#R[R(R9R\((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytfetch_seqids_by_accessionás   c Cs|jdƒ}t|ƒdkr4td|ƒ‚n|d}t|ƒdkr]|d}nd}d}||g}|r•|d7}|j|ƒn|jj||ƒ|jjƒ}|sÐtd |ƒ‚nt|ƒdkrõtd |ƒ‚n|ddS( Nt.isBad version %riit0sFSELECT bioentry_id FROM bioentry WHERE accession = %s AND version = %ss and biodatabase_id = %ssCannot find version %rs#More than one entry with version %r(RDRZRYRXRCR6RU( R#R[R(t acc_versiontacctversionR9R\RW((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytfetch_seqid_by_versionés&    cCsvd}|g}|r/|d7}|j|ƒn|jj||ƒ|jjƒ}|sjtd|ƒ‚n|ddS(Ns6SELECT bioentry_id FROM bioentry WHERE identifier = %ss and biodatabase_id = %ssCannot find display id %ri(RXRCR6RURY(R#R[t identifierR9R\RW((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytfetch_seqid_by_identifiers  cCs |jdƒS(NsSELECT name FROM biodatabase(R_(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR* scCs|jd|fƒS(Ns:SELECT bioentry_id FROM bioentry WHERE biodatabase_id = %s(R_(R#R[((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytlist_bioentry_idsscCs|jd|fƒS(Ns3SELECT name FROM bioentry WHERE biodatabase_id = %s(R_(R#R[((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytlist_bioentry_display_idsscCs|jj||ƒS(sReturn ids given a SQL statement to select for them. This assumes that the given SQL does a SELECT statement that returns a list of items. This parses them out of the 2D list they come as and just returns them in a list. (RCR_(R#R9targs((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt list_any_idsscCsX|jj||pdƒ|jjƒ}t|ƒdksPtdt|ƒƒ‚|dS(NisExpected 1 response, got %di((RCR6RURZtAssertionError(R#R9RkRW((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt execute_one$s(cCs|jj||pdƒdS(s%Just execute an sql command. N((RCR6(R#R9Rk((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR6*scCs+||}|jd|d||fƒdS(Nsaselect SUBSTRING(seq FROM %s FOR %s) from biosequence where bioentry_id = %sii(Rn(R#tseqidtstarttendtlength((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_subseq_as_string/s cCs=|jj||pdƒg|jjƒD]}|d^q)S(Ni((RCR6RU(R#R9Rktfield((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR_6scCs&|jj||pdƒ|jjƒS(N((RCR6RU(R#R9Rk((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytexecute_and_fetchall:sN(RROR$RQtTrueRSRLRMRNR.R]R^R`RfRhR*RiRjRlRRnR6RsR_Ru(((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR¡s*                 Rht primary_idtgiR]t display_idR(R^t accessionRfReR'cBs’eZd„Zd„Zd„Zd„Zd„Zd„Zd„Zd„Z d„Z d „Z d „Z d „Z d „Zd „Zed„ZRS(cCs+||_||_|jj|ƒ|_dS(N(R!R(R.R[(R#R!R(((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR$Is  cCsd|j|jfS(NsBioSeqDatabase(%r, %r)(R!R((R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR&MscCs+|jj|j|ƒ}tj|j|ƒS(skGets a Bio::Seq object by its name Example: seq = db.get_Seq_by_id('ROA1_HUMAN') (R!R]R[tBioSeqt DBSeqRecord(R#R(Ro((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt get_Seq_by_idPscCs+|jj|j|ƒ}tj|j|ƒS(shGets a Bio::Seq object by accession number Example: seq = db.get_Seq_by_acc('X77802') (R!R^R[R{R|(R#R(Ro((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_Seq_by_accYscCs+|jj|j|ƒ}tj|j|ƒS(shGets a Bio::Seq object by version number Example: seq = db.get_Seq_by_ver('X77802.1') (R!RfR[R{R|(R#R(Ro((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_Seq_by_verbscCs>|jj|j|ƒ}g|D]}tj|j|ƒ^qS(stGets a *list* of Bio::Seq objects by accession number Example: seqs = db.get_Seq_by_acc('X77802') (R!R`R[R{R|(R#R(tseqidsRo((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_Seqs_by_acckscCstdƒ‚dS(Nswaiting for Python 2.2's iter(tNotImplementedError(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_PrimarySeq_streamtscCs|jj|jƒS(sArray of all the primary_ids of the sequences in the database. These maybe ids (display style) or accession numbers or something else completely different - they *are not* meaningful outside of this database implementation. (R!RiR[(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_all_primary_ids{scCstj|j|ƒS(N(R{R|R!(R#R,((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR)„scCs |jƒS(N(R„(R#((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR+†scCs!g|jƒD]}||^q S(N(R+(R#R,((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR-ˆscCs'g|jƒD]}|||f^q S(N(R+(R#R,((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyRŠscKs¶t|ƒdkr!tdƒ‚n|jƒd\}}|tkrutdttjƒƒdd!t|ƒfƒ‚nt|}t|j|ƒ}||j|ƒ}t j |j|ƒS(Nis#single key/value parameter expectedis"lookup() expects one of %s, not %riÿÿÿÿ( RZt TypeErrorRt_allowed_lookupstreprR+R R!R[R{R|(R#Rtktvt lookup_namet lookup_funcRo((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytlookups , cCs||S(sçGets a Bio::Seq object by the primary (internal) id. The primary id in these cases has to come from $db->get_all_primary_ids. There is no other way to get (or guess) the primary_ids in a database. ((R#Ro((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytget_Seq_by_primary_id™scCsMtj|j|j|ƒ}d}x%|D]}|d7}|j|ƒq(W|S(s¡Load a set of SeqRecords into the BioSQL database. record_iterator is either a list of SeqRecord objects, or an Iterator object that returns SeqRecord objects (such as the output from the Bio.SeqIO.parse() function), which will be used to populate the database. fetch_NCBI_taxonomy is boolean flag allowing or preventing connection to the taxonomic database on the NCBI server (via Bio.Entrez) to fetch a detailed taxonomy for each SeqRecord. Example: from Bio import SeqIO count = db.load(SeqIO.parse(open(filename), format)) Returns the number of records loaded. ii(R/tDatabaseLoaderR!R[tload_seqrecord(R#trecord_iteratortfetch_NCBI_taxonomyt db_loadert num_recordst cur_record((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pytload¢s   (RROR$R&R}R~RRRƒR„R)R+R-RRŒRtFalseR•(((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyR'Hs        (((( t__doc__R{R/RRRRR†R'(((sˆ/oak/stanford/groups/akundaje/marinovg/programs/biopython-1.50.tar.gz/biopython-1.50/build/lib.linux-x86_64-2.7/BioSQL/BioSeqDatabase.pyt s    9V