 |
IMPORTANT Installation of GEPAT is complex, and should be carried out by an experienced programmer or system administrator. No setup.exe is provided at the moment. I advise to use eclipse Europa for Java EE developers for obtaining the code and installation. If the server runs in eclipse, export GEPAT as war file if needed. |
ConnectionType: pserver
Host: gepat.cvs.sourceforge.net
Repository path: /cvsroot/gepat
Username: anonymous
No password is required.ensj-39.2.jar Ensj is a java library that provides
convenient access to Ensembl databases.commons-beanutils.jar 1.1commons-collections-3.1.jarcommons-dbcp-1.2.1.jarcommons-digester.jarcommons-fileupload-1.1.1.jarcommons-io-1.1.jarcommons-logging-1.0.4.jarcommons-pool-1.2.jarlog4j-1.2.8.jarjung-1.7.2.jar A Java graph library available at
http://jung.sourceforge.net/colt.jar Needed by jungjsf-api.jarjsf-impl.jarjstl.jarjunit.jarmail.jar Java Mail APIactivation.jar JavaBeans Activation Frameworkmysql-connector-java-3.1.8-bin.jar mySQL JDBCdrmaa.jar For using grid computing |
IMPORTANT The following instructions describe the installation of GEPAT with a mySQL database system and a working directory at C:\GEPAT. If you are using another database or another place for your working directory, please adapt the instructions accordingly. |
core.host
ensembldb.ensembl.org
user anonymousGRANT ALL PRIVILEGES ON *.* TO 'GEPAT'@'localhost'
IDENTIFIED BY 'pass';>
FLUSH PRIVILEGES; CREATE DATABASE users;
USE users; CREATE TABLE users ( user_id VARCHAR(30) NOT NULL ,
firstname VARCHAR(30) , lastname VARCHAR(30) , company VARCHAR(30) ,
address VARCHAR(50) , postalcode VARCHAR(30) , city VARCHAR(30) ,
country VARCHAR(30) , state VARCHAR(30) , telephone VARCHAR(30) , fax
VARCHAR(30) , email TEXT , password TEXT , lastlogin DATE , PRIMARY KEY
(user_id)
); <entry
key="db.izkf.connection">jdbc:mysql://localhost:3306/users</entry>
<entry key="db.izkf.driver">com.mysql.jdbc.Driver</entry>
<entry key="db.izkf.user">GEPAT</entry>
<entry key="db.izkf.passwd">pass</entry>
CREATE DATABASE mapping;
USE mapping;
CREATE TABLE UniGene ( ID INTEGER NOT NULL , UniGene
VARCHAR(20) , PRIMARY KEY (ID)
);
CREATE TABLE KEGG_ID ( GenID INT , KEGG_GenID VARCHAR(20) , PRIMARY KEY
(GenID)
);
CREATE TABLE UniGene_RNA ( ID INTEGER NOT NULL , GenBankACC VARCHAR(20)
NOT NULL , PRIMARY KEY (ID, GenBankACC) , INDEX (ID) , CONSTRAINT
FK_UniGene_RefSeq_1 FOREIGN KEY (ID) REFERENCES UniGene (ID)
);
CREATE TABLE Ensembl_Unigene ( ID INTEGER NOT NULL , Ensembl
VARCHAR(20) NOT NULL , PRIMARY KEY (ID, Ensembl) , INDEX (ID) ,
CONSTRAINT FK_Ensembl_Unigene_1 FOREIGN KEY (ID) REFERENCES UniGene
(ID)
);
CREATE TABLE KEGG_EC ( GenID INT NOT NULL , EC VARCHAR(20) NOT NULL ,
PRIMARY KEY (GenID, EC) , INDEX (GenID) , CONSTRAINT FK_KEGG_EC_1
FOREIGN KEY (GenID) REFERENCES KEGG_ID (GenID)
);
CREATE TABLE KEGG_KO ( GenID INT NOT NULL , KO VARCHAR(20) NOT NULL ,
PRIMARY KEY (GenID, KO) , INDEX (GenID) , CONSTRAINT FK_KEGG_KO_1
FOREIGN KEY (GenID) REFERENCES KEGG_ID (GenID)
);
CREATE TABLE KEGG_Ensembl ( GenID INT NOT NULL , Ensembl VARCHAR(20)
NOT NULL , PRIMARY KEY (GenID, Ensembl) , INDEX (GenID) , CONSTRAINT
FK_KEGG_EC_1_1 FOREIGN KEY (GenID) REFERENCES KEGG_ID (GenID)
);
CREATE TABLE CloneID_UniGene ( CloneID VARCHAR(50) NOT NULL ,
GenBankACC VARCHAR(20) NOT NULL , UniGene INTEGER , PRIMARY KEY
(CloneID, GenBankACC) , INDEX (UniGene) , CONSTRAINT
FK_CloneID_UniGene_1 FOREIGN KEY (UniGene) REFERENCES UniGene (ID)
); <entry
key="db.mapping.connection">jdbc:mysql://localhost:3306/mapping</entry>
<entry key="db.mapping.driver">com.mysql.jdbc.Driver</entry>
<entry key="db.mapping.user">GEPAT</entry>
<entry key="db.mapping.passwd">pass</entry>
de.biozentrum.gepat.util.CreateCloneIDMapping.java
"C:\hs.data"
as argument.CREATE DATABASE kegg;
USE kegg; CREATE TABLE Substrates ( EnzymeID INT , Substrate TEXT
);
CREATE TABLE Products ( EnzymeID INT , Product TEXT
);
CREATE TABLE Cofactors ( EnzymeID INT , Cofactor TEXT
);
CREATE TABLE PathwaysEnzyme ( EnzymeID INT , Pathway TEXT
);
CREATE TABLE Compound ( Entry CHAR(20) , CompoundID INT NOT NULL , Name
TEXT , Formula TEXT , Mass TEXT , PRIMARY KEY (CompoundID)
);
CREATE TABLE PathwaysCompound ( CompoundID INT , Pathway TEXT
);
CREATE TABLE Enzyme ( Entry VARCHAR(20) , EnzymeID INT NOT NULL , Name
TEXT , Class TEXT , Sysname TEXT , Reaction TEXT , PRIMARY KEY
(EnzymeID)
); <entry
key="db.kegg.connection">jdbc:mysql://localhost:3306/kegg</entry>
<entry key="db.kegg.driver">com.mysql.jdbc.Driver</entry>
<entry key="db.kegg.user">GEPAT</entry>
<entry key="db.kegg.passwd">pass</entry>
de.biozentrum.gepat.utilCreateKEGGDB.java"C:\enzyme""C:\compound"de.biozentrum.gepat.CreateKEGGMapping.java"C:\hsa_xrefall.list" <entry
key="path.gepat.keggXML">C:/GEPAT/kegg/xml</entry>
<entry key="path.gepat.keggMap">C:/GEPAT/kegg/map</entry> protein.aliases.v7.0.txt.gzprotein.links.detailed.v7.0.txt.gzCREATE DATABASE interactions;
USE interactions;
CREATE TABLE Interactions (
TaxID INTEGER NOT NULL
, protein1 VARCHAR(20) NOT NULL
, protein2 VARCHAR(20) NOT NULL
, neighborhood INTEGER
, fusion INTEGER
, cooccurence INTEGER
, coexpression INTEGER
, experimental INTEGER
, data_base INTEGER
, textmining INTEGER
, combined_score INTEGER
, PRIMARY KEY (TaxID, protein1, protein2)
);
CREATE TABLE STRING_Mapping (
STRING_Protein VARCHAR(20)
, EnsemblID VARCHAR(20)
);
db.interactions.* entries in the
gepat.properties file to the newly created database:
de.biozentrum.gepat.util.InteractionImporterprotein.aliases.v7.0.txt (including filename)protein.links.detailed.v7.0.txt (including filename)CREATE DATABASE literature;
USE literature;
CREATE TABLE RefSeqLiterature (
Id TEXT
, Pubmed INT
, Authors TEXT
, Title TEXT
, Journal TEXT
);
CREATE TABLE RefSeqSummary (
Id TEXT
, Summary TEXT
);
db.literature.* entries in the
gepat.properties file to the newly generated database:
de.biozentrum.gepat.util.CreateLiteratureDBprotein.gpff (including filename) |
IMPORTANT GEPAT has been tested with R 2.3.1 and the correspondig Bioconductor version. Other versions may also work, but this cannot be guaranteed |
source("http://www.bioconductor.org/getBioC.R")
getBioC()
source("http://www.bioconductor.org/biocLite.R")
biocLite("ctc")
biocLite("convert")
install.packages("impute")
R.* entries in the
gepat.properties file:
<entry key="R.bin">C:/R-2.3.1/bin/R.exe</entry>
<entry key="R.script.dir">C:/GEPAT/src</entry>