# TODO: Add comment # # Author: Korsching Feb 11, 2014 - GPL v3 ############################################################################### #### 14.2.2014 # workflow 1 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # create database db.create.structure(DB.name="brca1x2", DB.path="") # only once, you cannot overwrite # create log on import tasks log.db() # only once, you cannot overwrite # fill and append database import.in.db(import.path.xlsx="/home/korschi/eclipseR/BerndD/data1", DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2") # search for specific position aa <- db.get.all.specific.position(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", position=32900364) # 114 sapply(aa,mode) # some report library(lattice) library(stats) library(plotrix) ab <- data.frame(matrix( c(median(aa[,"Quality"]), mean(aa[,"Quality"]), range(aa[,"Quality"]), sd(aa[,"Quality"]), median(aa[,"Frequency"]), mean(aa[,"Frequency"]), range(aa[,"Frequency"]), sd(aa[,"Frequency"]), median(aa[,"Coverage"]), mean(aa[,"Coverage"]), range(aa[,"Coverage"]), sd(aa[,"Coverage"]), median(aa[,"Reads_Var"]), mean(aa[,"Reads_Var"]), range(aa[,"Reads_Var"]), sd(aa[,"Reads_Var"]), median(aa[,"Balance"]), mean(aa[,"Balance"]), range(aa[,"Balance"]), sd(aa[,"Balance"]) ), 5, 5, byrow=T )) row.names(ab) <- c("Quality","Frequency","Coverage","Reads_Var","Balance") names(ab) <- c("median","mean","min","max","sd") pdf(file=paste(getwd(),"/results1/test.",format(Sys.time(), "%Y%m%d%H%M"),".pdf", sep=""), width=11, height=7, onefile=T, title="test", pointsize=12) par(mfrow=c(2,3)) plot(density(x=aa[,5]), main="Quality") plot(density(x=aa[,6]), main="Frequency") plot(density(x=aa[,7]), main="Coverage") plot(density(x=aa[,8]), main="Reads_Var") plot(density(x=aa[,9]), main="Balance") plot(1:10,1:10, type="n", axes=F, xlab="", ylab="") addtable2plot(x=1,y=5,table=round(ab,2),display.colnames=T,display.rownames=T,vlines=T) dev.off() ### 18.2.2014 # export sample table db.export.sample(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2") ### 20.2.2014 # extract new mutations from group sample.Sample_mutation # import revised and extended base table sample db.overwrite.table.sample(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", data.path.name="/home/korschi/eclipseR/BerndD/data/export.sample.csv") ## extract new mutations from group sample.mutation = 1 or "" -- given the complete group sample.mutation = 0 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") ## windows.size=0 -- exact position result.found.1.mutations.ws0 <- db.get.all.new.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="0", what2="1", window.size=0) #basic set - total number of lines : 10361 #basic set - number of unique positions : 866 #for result set searched in 3241 lines #result set - number of lines : 121 result.found.NA.mutations.ws0 <- db.get.all.new.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="0", what2="-1", window.size=0) #basic set - total number of lines : 10361 #basic set - number of unique positions : 866 #for result set searched in 1796 lines #result set - number of lines : 24 ## windows.size=2 -- relaxed view #result.found.1.mutations.ws2 <- db.get.all.new.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="0", what2="1", window.size=2) #basic set - total number of lines : 10361 #basic set - number of unique positions : 866 #for result set searched in 3241 lines #result set - number of lines : 85 #result.found.NA.mutations.ws2 <- db.get.all.new.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="0", what2="-1", window.size=2) #basic set - total number of lines : 10361 #basic set - number of unique positions : 866 #for result set searched in 1796 lines #result set - number of lines : 19 ### 25.2.2014 # update sample table mutations == "" -> == "-1" db <- dbConnect(dbDriver("SQLite"), dbname="/home/korschi/eclipseR/BerndD/brca1x2") aa <- dbGetQuery(conn=db, "SELECT * FROM sample WHERE mutation=''") nrow(aa) aa <- dbSendQuery(conn=db, paste("UPDATE sample SET mutation=-1 WHERE mutation=''",sep="")) aa <- dbGetQuery(conn=db, "SELECT * FROM sample WHERE mutation=-1") nrow(aa) dbDisconnect(db) # export (version 3) sample and variations table db.export.sample(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2") db.export.variations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2") ### 10.3.2014 ## extract new mutations from group sample.mutation - including: var and frequency source(file="/home/korschi/eclipseR/0functions/var_db/database.R") save.image() get.chr.name(provider="ensembl", db.name="hsapiens_gene_ensembl", gene.symbol="BRCA1") # w/ var aa <- db.get.all.new.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="1", what2="2", chr=17, geneToWork="BRCA1", window.size=0) ab <- db.get.all.new.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="1", what2="2", chr=13, geneToWork="BRCA2", window.size=0) ## create statistics aa <- db.stat.frequency(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="1", chr=17, geneToWork="") #all: 27 - 10361 # "T>A" "G>A" "delC" "insC" "delG" "delT" "delA" "A>G" # "C>A" "T>C" "insG" "insA" "C>T" "insT" "A>C" "G>C" # "G>T" "C>G" "T>G" "A>T" "insTT" "insTC" "insAA" "insTG" # "insTTT" "insGG" "insAT" aa <- db.stat.frequency(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="1", chr=17, geneToWork="BRCA1") # 27 - 4981 aa <- db.stat.frequency(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", what1="1", chr=13, geneToWork="BRCA2") # 27 - 5380 ### 11.3.2014 ## ex- import of database : add mutation flag column in variations db.export.sample(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2") db.export.variations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2") # manual changes in tables, and changes in db functions : db.create.structure(DB.name="brca1x2", DB.path="") db.overwrite.table.sample(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", data.path.name="/home/korschi/eclipseR/BerndD/data/export.sample.txt") # 272 db.overwrite.table.variations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", data.path.name="/home/korschi/eclipseR/BerndD/data/export.variations.txt") # 15398 ### 12.3.2014 # analysis for frequency threshold aa <- db.get.all.specific.position(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", position=41197784) ab <- db.get.all.specific.position(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", position=41246584) ac <- db.get.all.specific.position(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", position=41245671) ad <- db.get.all.specific.position(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", position=32904420) write.table(x=rbind(aa,ab,ac,ad), file="32904420.txt", append=F, quote=F, sep="\t", eol="\n", na="NA", dec=".", row.names=F, col.names=T) ### 27.3.2014 # start from the beginning -- import revised data source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # create database db.create.structure(DB.name="brca1x2", DB.path="") # only once, you cannot overwrite # create log on import tasks rm(protocol.import.mass.db) rm(list.import.data.objects.db) log.db(log.prefix="") # only once, you cannot overwrite # fill and append database import.in.db(import.path.xlsx="/home/korschi/eclipseR/BerndD/data1", log.prefix="d", DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", group.type=0) #export for Bernd db.export.variations(DB.path.name=paste(getwd(),"/brca1x2",sep=""), export.path=paste(getwd(),"/data/export.variations28032014.txt",sep="")) # 13555 rows ### 02.04.2014 - re-import from Bernd db.overwrite.table.variations(DB.path.name="brca1x2", data.path.name="data/export.variations28032014.csv") ### 4.4.2014 - import new entity : kidney stones , 17.4.2014 # start from the beginning source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # create database db.create.structure(DB.name="kidneySt", DB.path="") # only once, you cannot overwrite # create log on import tasks - create different log files log.db(log.prefix="kidneySt.") # fill and append database get.batch.import.number(DB.path.name="/kidneySt") # 1 import.in.db(import.path.xlsx="/data_kidney", log.prefix="kidneySt.", DB.path.name="/kidneySt") # error corrected in sheet 26 : frist column header has to be empty (copy empty cell from good sheet to bad sheet first column) # sil111 001-002-003-007: chr X -> chr 23 # export variants table from new database -- and correct new database table by mutations and chr from old datbase table db.export.sample(DB.path.name="/kidneySt", export.path="/data/export.kidneySt.sample17042014.txt") db.export.variations(DB.path.name="/kidneySt", export.path="/data/export.kidneySt.variations17042014.txt") ### 9.4.2014, 11.4.2014 # start from the beginning -- import revised data #export variations table - add new chromosom col db.export.variations(DB.path.name=paste(getwd(),"/brca1x2",sep=""), export.path=paste(getwd(),"/data/export.variations09042014.txt",sep="")) # 13555 rows #export sample table db.export.sample(DB.path.name=paste(getwd(),"/brca1x2",sep=""), export.path=paste(getwd(),"/data/export.sample09042014.txt",sep="")) # 248 rows # add column in variations # delete database # create database db.create.structure(DB.name="brca1x2", DB.path="") # only once, you cannot overwrite # log remains unaltered # re-import sample db.overwrite.table.sample(DB.path.name="brca1x2", data.path.name="data/export.sample09042014.txt") # re-import variations - with new chromosom col db.overwrite.table.variations(DB.path.name="brca1x2", data.path.name="data/export.variations09042014.txt") # backup db ### import new tables for mutation detection (group.type=1, BRCA: log.prefix="d" default) import.in.db(import.path.xlsx="/home/korschi/eclipseR/BerndD/data_brca12_plus/not_Sanger_tested", log.prefix="d", DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", group.type=1) # now 313-19546 rows # backup db ### statistics stat.14042014 <- db.stat.frequency(DB.path.name="/brca1x2", what1="1", geneToWork=c("BRCA1","BRCA2"), out.path.name="/results1/stat.14042014") #we take group : 0 #total number of lines in group : 13466 #statistics - number of rows : 831 # detect mutations (app. 6 min.) date() mutations.brca1.15042014 <- db.test.on.mutations(DB.path.name="/home/korschi/eclipseR/BerndD/brca1x2", ref1="1", test2="2", geneToWork="BRCA1", stat=NULL, window.size=0, out.path.name="/results1/new.mut") date() #basic set - total number of lines : 13555 #for result set searched in 5991 lines #result set - number of lines : 1133 # get back blocks for test db.get.all.specific.position(DB.path.name="/brca1x2", var.show=T) # check in db state before db.test.on.mutations run db.get.all.specific.position(DB.path.name="/data/brca1x2", what1="1", position=41209053, var=NULL, var.show=F, out.path.name="/results1/block.new.pos") db.get.all.specific.position(DB.path.name="/data/brca1x2", what1="1", position=41256250, var="insT", var.show=F, out.path.name="/results1/block.new.var") db.get.all.specific.position(DB.path.name="/data/brca1x2", what1="1", position=41256250, var=NULL, var.show=F, out.path.name="/results1/block.to.pos") db.get.all.specific.position(DB.path.name="/data/brca1x2", what1="1", position=41209050, var=NULL, var.show=F, out.path.name="/results1/b.5") ### 16.4.2014 # start from the beginning (because of data error - reverse results ) -- import revised data source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # create database w/ new polymorphism column db.create.structure(DB.name="brca1x2", DB.path="") # create database log files log.db(log.prefix="brca1x2.") # what is the first batch number ? get.batch.import.number(DB.path.name="/brca1x2") # 1 # import reference data import.in.db(import.path.xlsx="/data_brca12_plus", log.prefix="brca1x2.", DB.path.name="/brca1x2") #number of files: 32 #number of sheets: 248 #number of rows: 13555 # export variants table from old database db.export.variations(DB.path.name="/data/brca1x2", export.path="/data/export.variations17042014.old.txt") # export variants table from new database -- and correct new database table by mutations and chr from old datbase table db.export.variations(DB.path.name="/brca1x2", export.path="/data/export.variations17042014.new.txt") db.export.sample(DB.path.name="/brca1x2", export.path="/data/export.sample17042014.new.txt") # re-import variants table in new database db.overwrite.table.variations(DB.path.name="/brca1x2", data.path.name="/data/export.variations17042014.new.txt") # export variants table from new database again and send Bernd db.export.variations(DB.path.name="/brca1x2", export.path="/data/export.variations17042014.new2.txt") # import second batch # what is the batch number ? get.batch.import.number(DB.path.name="/brca1x2") # 1 import.in.db(import.path.xlsx="/data_brca12_plus/not_Sanger_tested", log.prefix="brca1x2.", DB.path.name="/brca1x2") ### 23.4.2014 # import in data.frame annd reduce to unique and export again in xlsx source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") log.one(log.prefix="analyse.") import.in.one.df(import.path.xlsx="/data_brca12_plus/not_Sanger_tested/extramenge", log.prefix="analyse.", db.df="test.data01") # nrow(test.data01) # 5991 export.in.one.df(export.path.name.xlsx="/test.data01.a", db.df="test.data01") # #aa <- matrix(cbind(rep(2,20), # c(124,124,124,125,125,125,126,126,126,127,127,127,128,128,128,128,128,128,128,128), # c("A->T","A->T","G->C","A->T","G->C","insA","A->T","A->T","A->T","ins","A->T","del","A->T","A->T","A->T","A->T","ins","A->T","del","A->T"), # stringsAsFactors=F), # 20,3) #export.in.one.df(export.path.name.xlsx="/aa", db.df="aa") #ab <- aa[!duplicated(aa[,c(1,2,3)]), ] #export.in.one.df(export.path.name.xlsx="/ab", db.df="ab") test.data01.b <- test.data01[!duplicated(test.data01[,c("chr","pos","var")]), ] # export.in.one.df(export.path.name.xlsx="/test.data01.b", db.df="test.data01.b") test.data01.c <- how.many.dupli(x=test.data01.b[,c("chr","pos","var")], ref=test.data01[,c("chr","pos","var")]) test.data01.c <- cbind(test.data01.b,test.data01.c[,4,drop=F]) # export.in.one.df(export.path.name.xlsx="/test.data01.c", db.df="test.data01.c") # correct several Excel sheets by adding a chr column & correcting Position->Pos correct.xlsx.01(import.path.xlsx="/data_brca12_plus/tmp1", export.path.xlsx="/data_brca12_plus/tmp2", chr=17) #number of files: 16 #number of sheets: 124 #number of rows: 5632 correct.xlsx.01(import.path.xlsx="/data_brca12_plus/tmp3", export.path.xlsx="/data_brca12_plus/tmp4", chr=13) #number of files: 16 #number of sheets: 124 #number of rows: 7923 #sum : 5632+7923=13555 ### find mutation - test run with SIL132 # copy backup db in main folder and import test data ### test negative import.in.db(import.path.xlsx="/data_brca12_plus/test_mut_neg", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140502") #present group number : 2 #number of files: 2 #number of sheets: 16 #number of rows: 1147 # find mutations test.mutations02 <- db.test.on.mutations(DB.path.name="/brca1x2_20140502", ref1="1", test2="3", geneToWork=c("BRCA1","BRCA2"), stat=NULL, window.size=0, out.path.name="/test.mutations02") #for result set searched in 1147 lines #result set - number of lines : 2 #basic set - total number of lines : 13555 #file output name: /home/korschi/eclipseR/BerndD/test.mutations02.BRCA1_BRCA2.0.2.201405061900.txt # analyse db.get.all.specific.position(DB.path.name="/brca1x2_20140502", what1="", position=41197018, var=NULL, var.show=F, out.path.name="") ### test positive import.in.db(import.path.xlsx="/data_brca12_plus/test_mut_posA", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140502") #present group number : 2 #number of files: 2 #number of sheets: 16 #number of rows: 1147 # find mutations test.mutations03 <- db.test.on.mutations(DB.path.name="/brca1x2_20140502", ref1="1", test2="3", geneToWork=c("BRCA1","BRCA2"), stat=NULL, window.size=0, out.path.name="/test.mutations03") #for result set searched in 1147 lines #result set - number of lines : 6 #basic set - total number of lines : 13555 #file output name: /home/korschi/eclipseR/BerndD/test.mutations03.BRCA1_BRCA2.0.2.201405061856.txt # analyse db.get.all.specific.position(DB.path.name="/brca1x2_20140502", what1="", position=32912189, var=NULL, var.show=F, out.path.name="") ### 02.05.2014 -- import data in a stable database version source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # import data not Sanger tested but mutation free import.in.db(import.path.xlsx="/data_brca12_plus/not_Sanger_tested/nurGute132_139", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140417") # dataset no. 1 # rename & backup database : brca1x2_20140502 # import data mutations_132_139 in a test database import.in.db(import.path.xlsx="/data_brca12_plus/mutations132_139", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140502") # dataset no. 2 # rename & backup database : brca1x2_20140502_mut_test # import data not_Sanger_tested140_155 (only PGM) in a test database import.in.db(import.path.xlsx="/data_brca12_plus/not_Sanger_tested140_155", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140502_mut_test") # dataset no. 3 # rename & backup database : brca1x2_20140502_mut_andNotSanger_test # analysis for no. 2 test.mutations_01vs2 <- db.test.on.mutations(DB.path.name="/brca1x2_20140502_mut_andNotSanger_test", ref1=c("1","2"), test2="3", geneToWork=c("BRCA1","BRCA2"), stat=NULL, window.size=0, out.path.name="/test.mutations_01vs2") #for result set searched in 797 lines #result set - number of lines : 16 #basic set - total number of lines : 16385 #file output name: /home/korschi/eclipseR/BerndD/test.mutations_01vs2.BRCA1_BRCA2.0_1.2.201405061904.txt # analysis for no. 3 test.mutations_01vs3 <- db.test.on.mutations(DB.path.name="/brca1x2_20140502_mut_andNotSanger_test", ref1=c("1","2"), test2="4", geneToWork=c("BRCA1","BRCA2"), stat=NULL, window.size=0, out.path.name="/test.mutations_01vs3") #for result set searched in 3330 lines #result set - number of lines : 66 #basic set - total number of lines : 16385 #file output name: /home/korschi/eclipseR/BerndD/test.mutations_01vs3.BRCA1_BRCA2.0_1.3.201405061908.txt ### 09.05.2014 - developing database source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # insert db column db.insert.column(DB.path.name="/brca1x2_20140502_mut_andNotSanger_test", table.name="variations", col.name="pcranno", data.type="VARCHAR(40)") # import bed files import.bed.info(import.path.bed="/data_brca12_plus/bed_PCR/BRCA1.bed", name.df="pcr.names") import.bed.info(import.path.bed="/data_brca12_plus/bed_PCR/BRCA2.bed", name.df="pcr.names") import.bed.info(import.path.bed="/data_br_8panel/bed_PCR/ATM.bed", name.df="pcr.names") import.bed.info(import.path.bed="/data_br_8panel/bed_PCR/CHEK2.bed", name.df="pcr.names") import.bed.info(import.path.bed="/data_br_8panel/bed_PCR/NBN.bed", name.df="pcr.names") import.bed.info(import.path.bed="/data_br_8panel/bed_PCR/PALB2.bed", name.df="pcr.names") import.bed.info(import.path.bed="/data_br_8panel/bed_PCR/TP53.bed", name.df="pcr.names") # fehlen noch 3 # add pcr annoation to db db.insert.PCR.anno(DB.path.name="/brca1x2_20140502_mut_andNotSanger_test", df.anno="pcr.names") #db.set.nr: 20512 #processed rows: 20512 pcr name exact: 14924 pcr 1:n : 5174 no pcr: 414 # export db.export.variations(DB.path.name="/brca1x2_20140502_mut_andNotSanger_test", export.path="/data/export.BRCA12.variations13052014.txt") ### 13.05.2014 create 8panel database source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") log.db(log.prefix="br8panel.") db.create.structure(DB.name="br8panel", DB.path="") # # do not use at the moment ! import.in.db(import.path.xlsx="/data_br_8panel/PGM146_153", log.prefix="br8panel.", DB.path.name="/br8panel") #present group number : 1 #number of files: 1 #number of sheets: 30 #number of rows: 3516 app. 95-125 rows per sheet import.in.db(import.path.xlsx="/data_br_8panel/Proton149", log.prefix="br8panel.", DB.path.name="/br8panel") #present group number : 2 #number of files: 1 #number of sheets: 32 #number of rows: 18187 app. 500-730 rows per sheet import.in.db(import.path.xlsx="/data_br_8panel/Proton160", log.prefix="br8panel.", DB.path.name="/br8panel") #present group number : 3 #number of files: 1 #number of sheets: 46 #number of rows: 32192 app. 300-824 rows per sheet # sum 53895 # add pcr annoation to db db.insert.PCR.anno(DB.path.name="/br8panel_20140707", df.anno="pcr.names") #db.set.nr: 53895 #processed rows: 53895 pcr name exact: 36623 pcr 1:n : 1895 no pcr: 15377 # export db.export.sample.variations(DB.path.name="/br8panel_20140707", export.path="/data/export.br8panel.variations20140707.txt") ### 20.5.2014 - import new data - test new pcr.name annotation during import source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") # before copy /brca1x2_20140502_mut_andNotSanger_test (with pcr names -> data) # and rename to /brca1x2_20140520 and also copy -> data import.in.db(import.path.xlsx="/data_brca12_plus/sil157_143_158", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140520") #present group number : 4 #number of files: 1 #number of sheets: 34 #number of rows: 2988 # check new pcr anno fn during import - and if successful copy to -> data : ok # test new mutation search fn (16K-lines-db-3k-lines-search: appr. 12min) test.mutations_01vs4 <- db.test.on.mutations(DB.path.name="/brca1x2_20140520", ref1=c("1","2"), test2="5", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=NULL, window.size=0, out.path.name="/test.mutations_01vs4") #for result set searched in 2988 lines #suspected mutation set - number of lines : 2609 #negative observation set - number of lines : 375 #basic set - total number of lines : 16385 #file output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_01vs4.mut.BRCA1_BRCA2.0_1.4.201405201727.txt #file output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_01vs4.neg.BRCA1_BRCA2.0_1.4.201405201727.txt ### 22.5.2014 - export batch 1,2,3 for manual mutation analysis # but export all - easier db.export.sample.variations(DB.path.name="/brca1x2_20140520", export.path="/data/export.brca1x2.variations22052014.txt") ### 16.06.2014 -- again statistics and thersholds source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") stat.all <- db.stat.frequency(DB.path.name="/brca1x2_20140520", batch=NULL, what1="", geneToWork=c("BRCA1","BRCA2"), out.path.name="/stat.all.txt") stat.1.2.3 <- db.stat.frequency(DB.path.name="/brca1x2_20140520", batch=c(1,2,3), what1="", geneToWork=c("BRCA1","BRCA2"), out.path.name="/stat.1.2.3.txt") names(stat.all) hist.plot.simple(x=aa[,6], bin.num=F, bin.size=F, bin.fix=NULL, bin.fix.open=F, norm=F, n.factor=1, curve=F, xlab="", ylab="", xlim=NULL, y.max=NULL, x.at=NULL, y.at=NULL, y.num.format=F, ylog=F, bar.width=1, offset=0, digits=1, col=c("red","green","blue"), cex=1, smooth.f=0, subfolder.filename="/test1", h.title="", s.title=T, add=F) # find mutations test run -- with statistics and >max criteria names(stat.1.2.3) stat.1.2.3[1,] # 15 s pro patient(100 rows) -> 40 pat.: 10 min db.test.on.mutations(DB.path.name="/brca1x2_20140520", ref1=c("1","2","3"), test2="4", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, out.path.name="/test.mutations_123vs4") #test set - processed lines : 3330 #suspected mutation set - number of lines : 135 #negative observation set - number of lines : 3195 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs4.mut.BRCA1_BRCA2.1_2_3.4.201406181505.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs4.neg.BRCA1_BRCA2.1_2_3.4.201406181505.txt db.test.on.mutations(DB.path.name="/brca1x2_20140620", ref1=c("1","2","3"), test2="4", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, out.path.name="/test.mutations_123vs4") #test set - processed lines : 3330 #suspected mutation set - number of lines : 163 #negative observation set - number of lines : 3167 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs4.mut.BRCA1_BRCA2.1_2_3.4.201406201407.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs4.neg.BRCA1_BRCA2.1_2_3.4.201406201407.txt ### 20.06.2014 -- new data import.in.db(import.path.xlsx="/data_brca12_plus/sil156_161", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140620") #present group number : 6 #number of files: 5 #number of sheets: 61 #number of rows: 4700 # db.test.on.mutations(DB.path.name="/brca1x2_20140620", ref1=c("1","2","3"), test2="5", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, out.path.name="/test.mutations_123vs5") #test set - processed lines : 2988 #suspected mutation set - number of lines : 239 #negative observation set - number of lines : 2745 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs5.mut.BRCA1_BRCA2.1_2_3.5.201406201425.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs5.neg.BRCA1_BRCA2.1_2_3.5.201406201425.txt # db.test.on.mutations(DB.path.name="/brca1x2_20140620", ref1=c("1","2","3"), test2="6", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, out.path.name="/test.mutations_123vs6") #test set - processed lines : 4700 #suspected mutation set - number of lines : 449 #negative observation set - number of lines : 4248 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs6.mut.BRCA1_BRCA2.1_2_3.6.201406201451.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs6.neg.BRCA1_BRCA2.1_2_3.6.201406201451.txt ### 07.07.2014 -- br8panel_20140707 - statistics # get gene names aa <- get.unique.genes(DB.path.name="/br8panel_20140707", choose="first") #[1] "NBN" "ATM" "CDH1" "PALB2" "RAD51L3-RFFL" #[6] "TP53" "CHEK2" "RAD51C" "TEX14" ab <- get.unique.genes(DB.path.name="/br8panel_20140707", choose="all") # 4 min / 53000 lines #[1] "" "NBN" "ATM" "NPAT" #[5] "Y_RNA" "C11orf65" "CDH1" "RNA5SP429" #[9] "RP11-354M1.2" "FTLP14" "PALB2" "CTD-2196E14.3" #[13] "RAD51L3-RFFL" "RAD51D" "FNDC8" "TP53" #[17] "CHEK2" "AP001925.1" "RAD51C" "TEX14" #[21] "Vault" "DCTN5" # stat source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") db.stat.frequency(DB.path.name="/br8panel_20140707", batch=NULL, what1="", geneToWork=aa, out.path.name="/stat.br8", workspace.suffix="br8.08072014") #total number of lines in table : 53895 #number of lines in selection : 53895 #statistics - number of rows : 2081 db.stat.frequency(DB.path.name="/br8panel_20140707", batch=c(2,3), what1="", geneToWork=aa, out.path.name="/stat.br8", workspace.suffix="br8.08072014") # 1 min #total number of lines in table : 53895 #number of lines in selection : 50379 #statistics - number of rows : 1988 # NBN.A>C.90946723 hist.plot.simple(x=stat.br8.08072014[,6], bin.num=F, bin.size=F, bin.fix=NULL, bin.fix.open=F, norm=F, n.factor=1, curve=F, xlab="observed counts", ylab="number of events per intervall", xlim=NULL, y.max=NULL, x.at=NULL, y.at=NULL, y.num.format=F, ylog=F, bar.width=1, offset=0, digits=1, col=c("red","green","blue"), cex=1, smooth.f=0, subfolder.filename=NULL, h.title="", s.title=T, add=F) ### 11.07.2014 - import BRCA1/2 data import.in.db(import.path.xlsx="/data_brca12_plus/sil162_163", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140620") #present group number : 7 #number of files: 2 #number of sheets: 22 #number of rows: 1431 43-94 rows per patient db.test.on.mutations(DB.path.name="/brca1x2_20140620", ref1=c("1","2","3"), test2="7", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, stat.freq=NULL, out.path.name="/test.mutations_123vs7", method="brca12") #test set - processed lines : 1431 #suspected mutation set - number of lines : 113 #negative observation set - number of lines : 1318 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs7.mut.BRCA1_BRCA2.1_2_3.7.201407111142.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs7.neg.BRCA1_BRCA2.1_2_3.7.201407111142.txt ### 17.7.2014 - import br8 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() import.in.db(import.path.xlsx="/data_br_8panel/Proton166", log.prefix="br8panel.", DB.path.name="/br8panel_20140707") #present group number : 4 #number of files: 1 #number of sheets: 47 #number of rows: 21120 # create a separate list containing all frequency distributions aa <- date() db.test.dist.basic.dist.frequency(DB.path.name="/br8panel_20140707", batch=4, ref.stat=stat.br8.08072014, ref.freq=freq.br8.08072014, out.path.name="/test.freq.ref.23.4") aa;date() # 3 min #batch: 4 ref.stat: stat.br8.08072014 ref.freq: freq.br8.08072014 #number of lines in batch : 21120 #ref statistics & frequency list : # 19194 (number of observations) #only ref statistics : # 1926 #only frequency list : # 0 #no reference at all : # 0 ### 28.7.2014 - pcr anno br8 , export db , stat br8 batch 2,3,4 , pos/neg list with 10% and no skip >2 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import bed files import.pcr.info(import.path.bed="/data_br_8panel/bed_PCR/10_Gene.bed", name.df="pcr.names.br8", flag=F) # add pcr annoation to db db.insert.PCR.anno(DB.path.name="/br8panel_20140707", df.anno="pcr.names.br8") #db.set.nr: 75015 #processed rows: 75015 pcr name exact: 59618 pcr 1:n : 5193 no pcr: 10204 # export Proton & PGM db.export.sample.variations(DB.path.name="/br8panel_20140707", export.path="/data/export.br8panel_20140707.variations28072014.txt") # stat br8 batch 2,3,4 aa <- get.unique.genes(DB.path.name="/br8panel_20140707", choose="first") #[1] "NBN" "ATM" "CDH1" "PALB2" "RAD51L3-RFFL" #[6] "TP53" "CHEK2" "RAD51C" "TEX14" ab <- get.unique.genes(DB.path.name="/br8panel_20140707", choose="all") #[1] "" "NBN" "ATM" "NPAT" #[5] "Y_RNA" "C11orf65" "CDH1" "RNA5SP429" #[9] "RP11-354M1.2" "FTLP14" "PALB2" "CTD-2196E14.3" #[13] "RAD51L3-RFFL" "RAD51D" "FNDC8" "TP53" #[17] "CHEK2" "AP001925.1" "RAD51C" "TEX14" #[21] "Vault" "DCTN5" aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") db.stat.frequency(DB.path.name="/br8panel_20140707", batch=c(2,3,4), what1="", geneToWork=aa, out.path.name="/stat/stat.br8.2.3.4.28072014", workspace.suffix="br8.2.3.4.28072014") #out path matrix : /home/korschi/eclipseR/BerndD/stat/stat.br8.2.3.4.28072014..201407282353.txt #we take the whole table #SELECT variations.* # FROM sample #INNER JOIN variations #ON sample.sample_id = variations.sample_id #WHERE sample.batch IN (2,3,4) #total number of lines in table : 75015 #number of lines in selection : 71499 #statistics - number of rows : 2321 # pos/neg list with 10% and no skip >2 # import vcf data aa <- date() ab <- import.rs.info(import.path.abs="/home/korschi/Downloads/00all.vcf", in.df=stat.br8.2.3.4.28072014[,c(1,2),drop=F]) aa;date() # 8 min/2321 rows in 61220532 rows dim(ab) ncol(ab) ab <- t(ab) # 843 rows # create stand-alone All.vcf database (text file ~10GB -> database file ~22GB) aa <- date() create.rs.db(import.path.abs="/home/korschi/Downloads/00all.vcf") aa;date() # 10 min - db:00all table:t_00all # pos-neg aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br8panel_20140707", ref1=c("2","3","4"), test2=c("2","3","4"), geneToWork=aa, flagIt=F, stat=stat.br8.2.3.4.28072014, stat.freq=freq.br8.2.3.4.28072014, out.path.name="/test.mutations_234vs234", method="br8simple") ac;date() # ### 27.08.2014 - import BRCA1/2 data import.in.db(import.path.xlsx="/data_brca12_plus/sil168_172", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140620") #present group number : 8 #number of files: 2 #number of sheets: 24 #number of rows: 2000 db.test.on.mutations(DB.path.name="/brca1x2_20140620", ref1=c("1","2","3"), test2="8", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, stat.freq=NULL, out.path.name="/test.mutations_123vs8", method="brca12") # ca. 100 +/-10 pro entry #test set - processed lines : 2000 #suspected mutation set - number of lines : 516 #negative observation set - number of lines : 1484 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs8.mut.geneToWork2.201408271911.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs8.neg.geneToWork2.201408271911.txt ### 28.08.2014 - import BRCA1/2 data import.in.db(import.path.xlsx="/data_brca12_plus/sil182", log.prefix="brca1x2.", DB.path.name="/brca1x2_20140620") #present group number : 9 #number of files: 1 #number of sheets: 6 #number of rows: 816 db.test.on.mutations(DB.path.name="/brca1x2_20140620", ref1=c("1","2","3"), test2="9", geneToWork=c("BRCA1","BRCA2"), flagIt=F, stat=stat.1.2.3, stat.freq=NULL, out.path.name="/test.mutations_123vs9", method="brca12") # ca. 133 pro entry #test set - processed lines : 816 #suspected mutation set - number of lines : 165 #negative observation set - number of lines : 651 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/test.mutations_123vs9.mut.geneToWork2.201408281847.txt #output negative observations: /home/korschi/eclipseR/BerndD/test.mutations_123vs9.neg.geneToWork2.201408281847.txt ### 3.9.2014 - import br8 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() import.in.db(import.path.xlsx="/data_br_8panel/sil182", log.prefix="br8panel.", DB.path.name="/br8panel_20140707") #present group number : 5 #number of files: 1 #number of sheets: 6 #number of rows: 713 aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") db.stat.frequency(DB.path.name="/br8panel_20140707", batch=c(2,3,4,5), what1="", geneToWork=aa, out.path.name="/stat/stat.br8.2bis5.03092014", workspace.suffix="br8.2bis5.03092014") #out path matrix : /home/korschi/eclipseR/BerndD/stat/stat.br8.2bis5.03092014..201409031309.txt #we take the whole table #SELECT variations.* # FROM sample #INNER JOIN variations #ON sample.sample_id = variations.sample_id #WHERE sample.batch IN (2,3,4,5) #total number of lines in table : 75728 #number of lines in selection : 72212 #statistics - number of rows : 2355 # pos-neg aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br8panel_20140707", ref1=c("2","3","4","5"), test2=c("2","3","4","5"), geneToWork=aa, flagIt=F, stat=stat.br8.2bis5.03092014, stat.freq=freq.br8.2bis5.03092014, out.path.name="/test.mutations_2345vs2345", method="br8simple") ac;date() # 16 h ! ### 15.09.2014 - export patients table (unique) and re-import true mutations source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() db.export.sample(DB.path.name="/brca1x2_20140620", export.path="/results1/export.sample_all.txt", unip=F, batch="") db.export.sample(DB.path.name="/brca1x2_20140620", export.path="/results1/export.sample_all_unique.txt", unip=T, batch="") ### 18.09.2014 -- change of strategy : merging of breast 2panel and 8panel to a master database and adding now 4panel data # concept and code in join.db.tables.R # take old database - empty tables and fill with merged data --> sqliteman program # so not execute this line: #db.create.structure(DB.name="br_new", DB.path="") # only once, you cannot overwrite # but create log data.frames log.db(log.prefix="br4x8x2panel.") # only once, you cannot overwrite # fill database (done by sqlite tools) and import new set import.in.db(import.path.xlsx="/data_br_4panel/SIL178.1", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20140918") #present group number : 16 -- ok, last was 15 after merge #number of files: 1 #number of sheets: 30 #number of rows: 1559 ### 7.10.2014 export log files write.table(x=br4x8x2panel.protocol.db, file="br4x8x2panel.protocol.db", append=F, quote=T, sep="\t", dec=".", row.names=T, col.names=T) write.table(x=br8panel.protocol.db, file="br8panel.protocol.db", append=F, quote=T, sep="\t", dec=".", row.names=T, col.names=T) write.table(x=brca1x2.protocol.db, file="brca1x2.protocol.db", append=F, quote=T, sep="\t", dec=".", row.names=T, col.names=T) write.table(x=br4x8x2panel.list.db, file="br4x8x2panel.list.db", append=F, quote=T, sep="\t", dec=".", row.names=T, col.names=T) write.table(x=br8panel.list.db, file="br8panel.list.db", append=F, quote=T, sep="\t", dec=".", row.names=T, col.names=T) write.table(x=brca1x2.list.db, file="brca1x2.list.db", append=F, quote=T, sep="\t", dec=".", row.names=T, col.names=T) # export sample table - to document batch number and to add column with number of genes in the performed analysis db.export.sample(DB.path.name="/br4x8x2panel_20140918", export.path="/0info/br4x8x2panel_batchpanel_20141007.csv", orderby="batch", unip=F, batch="") ### 7.10.2014 brca12 batch 1,2 und 1,2,3 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() aa <- c("BRCA1","BRCA2") db.stat.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(1,2), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.1.2.20141008", workspace.suffix="br4x8x2panel.1.2.20141008") db.stat.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(1,2,3), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.1.2.3.20141008", workspace.suffix="br4x8x2panel.1.2.3.20141008") db.test.dist.basic.dist.frequency(DB.path.name="/br4x8x2panel_20140918", batch=4, ref.stat=stat.br4x8x2panel.1.2.20141008, ref.freq=freq.br4x8x2panel.1.2.20141008, ref.bala=bala.br4x8x2panel.1.2.20141008, out.path.name="/stat/test.freq.ref.12.4") #batch: 4 ref.stat: stat.br4x8x2panel.1.2.20141008 ref.freq: freq.br4x8x2panel.1.2.20141008 ref.bala: bala.br4x8x2panel.1.2.20141008 #number of lines in batch : 3330 #ref statistics & frequency(balance) list : # 3271 (number of observations) #no ref statistics : # 59 db.test.dist.basic.dist.frequency(DB.path.name="/br4x8x2panel_20140918", batch=4, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, ref.bala=bala.br4x8x2panel.1.2.3.20141008, out.path.name="/stat/test.freq.ref.123.4") #batch: 4 ref.stat: stat.br4x8x2panel.1.2.3.20141008 ref.freq: freq.br4x8x2panel.1.2.3.20141008 ref.bala: bala.br4x8x2panel.1.2.3.20141008 #number of lines in batch : 3330 #ref statistics & frequency(balance) list : 3273 (number of observations) #no ref statistics : 57 ### 8.10.2014 4panel source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_4panel/SIL185", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20140918") #present group number : 17 #number of files: 1 #number of sheets: 30 #number of rows: 1331 #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20140918", export.path="/0info/br4x8x2panel_batchpanel_20141009.csv", orderby="batch", unip=F, batch="") # statistics aa <- c("BRCA1","BRCA2","RAD51C","CHEK2") db.stat.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(16,17), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.16.17.20141009", workspace.suffix="br4x8x2panel.16.17.20141009") #total number of lines in table : 111065 #number of lines in selection : 2890 #statistics - number of rows : 206 # test run db.test.dist.basic.dist.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(16,17), ref.stat=stat.br4x8x2panel.16.17.20141009, ref.freq=freq.br4x8x2panel.16.17.20141009, ref.bala=bala.br4x8x2panel.16.17.20141009, out.path.name="/stat/test.freq.ref.16.17x16.17") #batch: 16 17 ref.stat: stat.br4x8x2panel.16.17.20141009 ref.freq: freq.br4x8x2panel.16.17.20141009 ref.bala: bala.br4x8x2panel.16.17.20141009 #number of lines in batch : 2890 #ref statistics & frequency(balance) list : 2890 (number of observations) #no ref statistics : 0 # get all unique gene names get.unique.genes(DB.path.name="/br4x8x2panel_20140918", out.path.name="/0info/unique.gene.names.all.20141009.txt") ## statistics 12,13,14 aa <- c("RAD51C","CHEK2") db.stat.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(12,13,14), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.radcheck.12.13.14.20141010", workspace.suffix="br4x8x2panel.radcheck.12.13.14.20141010") #total number of lines in table : 111065 #number of lines in selection : 71499 #statistics - number of rows : 397 # test run 12,13,14 db.test.dist.basic.dist.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(12,13,14), ref.stat=stat.br4x8x2panel.radcheck.12.13.14.20141010, ref.freq=freq.br4x8x2panel.radcheck.12.13.14.20141010, ref.bala=bala.br4x8x2panel.radcheck.12.13.14.20141010, out.path.name="/stat/test.freq.radcheck.ref.12.13.14x12.13.14") #batch: 12 13 14 ref.stat: stat.br4x8x2panel.radcheck.12.13.14.20141010 ref.freq: freq.br4x8x2panel.radcheck.12.13.14.20141010 ref.bala: bala.br4x8x2panel.radcheck.12.13.14.20141010 #number of lines in batch : 71499 #ref statistics & frequency(balance) list : 12207 (number of observations) #no ref statistics : 59104 #due to -a new event is observed, -not all genes are analysed, -wrong stat table used # pos-neg 1 - fail source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20140918", ref1=c("1","2","3"), test2=c("16","17"), geneToWork=aa, flagIt=F, stat=stat.br4x8x2panel.1.2.3.20141008, stat.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x16.17", method="brca12") ac; date() # 44 min #test set - processed lines : 2890 #suspected mutation set - number of lines : 724 #negative observation set - number of lines : 1681 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x16.17.mut.genes2.201410131646.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x16.17.neg.genes2.201410131646.txt # pos-neg 2 - run aa <- c("RAD51C","CHEK2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20140918", ref1=c("12","13","14"), test2=c("16","17"), geneToWork=aa, flagIt=F, stat=stat.br4x8x2panel.radcheck.12.13.14.20141010, stat.freq=freq.br4x8x2panel.radcheck.12.13.14.20141010, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.radcheck.12.13.14x16.17", method="br8simple") ac; date() # 5 min #test set - processed lines : 2890 #suspected mutation set - number of lines : 224 #negative observation set - number of lines : 2666 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.radcheck.12.13.14x16.17.mut.genes2.201410131747.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.radcheck.12.13.14x16.17.neg.genes2.201410131747.txt ### 14.10.2014 - statistics - test - of color coding in balance 12,13,14 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() aa <- c("RAD51C","CHEK2") db.stat.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(12,13,14), what1="", geneToWork=aa, out.path.name="/stat/stat.br.test.test.RAD51C.CHEK2.12.13.14", workspace.suffix="br4x8x2panel.testtest") #total number of lines in table : 111065 #number of lines in selection : 71499 #statistics - number of rows : 397 ## set flag for SNP (polymorphism) in mutation column set.flags.variations(DB.path.name="/br4x8x2panel_20140918", table.field="mutation", flag.value="3", work.list="/SNPs_der_Gesamtliste_149_160_stat.br8.201407081046.txt") #number of rows processed: 105 #successful: 105 #missed: 0 #total found in database: 2053 ### 30.10.2014 2panel source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_brca12_plus/sil186_193", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20140918") #present group number : 18 #number of files: 7 #number of sheets: 35 #number of rows: 2180 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20140918", ref1=c("1","2","3"), test2=c("18"), geneToWork=aa, flagIt=F, stat=stat.br4x8x2panel.1.2.3.20141008, stat.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x18", method="brca12") ac; date() # 41 min #test set - processed lines : 2180 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 254 #negative observation set - number of lines : 1926 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x18.mut.genes2.201410301031.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x18.neg.genes2.201410301031.txt ### 6.11.2014 10panel -> 2panel ref 1,2,3 & 8panel ref 12,13,14 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL189", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20140918") #present group number : 19 #number of files: 1 #number of sheets: 30 #number of rows: 4812 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20140918", ref1=c("1","2","3"), test2=c("19"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x19", method="brca12") ac; date() # 32 min #test set - processed lines : 4812 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 515 #negative observation set - number of lines : 1232 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x19.mut.genes2.201411061233.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x19.neg.genes2.201411061233.txt ## statistics 12,13,14 aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") db.stat.frequency(DB.path.name="/br4x8x2panel_20140918", batch=c(12,13,14), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.8gene.12.13.14.20141106", workspace.suffix="br4x8x2panel.8gene.12.13.14.20141106") #total number of lines in table : 113245 #number of lines in selection : 71499 #statistics - number of rows : 2321 # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20140918", ref1=c("12","13","14"), test2=c("19"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x19", method="br8simple") ac; date() # 55 min #test set - processed lines : 4812 #suspected mutation set - number of lines : 1447 #negative observation set - number of lines : 3365 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x19.mut.genes8.201411061342.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x19.neg.genes8.201411061342.txt ### 01.12.2014 - 10 genes: 2 algo1 + 8 algo2 : pos neg list ### 2panel ref 1,2,3 & 8panel ref 12,13,14 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL192.2", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20140918") #present group number : 20 #number of files: 1 #number of sheets: 33 #number of rows: 6404 delete.batch.in.db(del.batch=c(20,23), log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20140918") delete.batch.in.db(del.batch=20, log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") import.in.db(import.path.xlsx="/data_br_10panel/SIL192", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 20 #number of files: 1 #number of sheets: 33 #number of rows: 3802 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("20"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x20", method="brca12") ac; date() # 25 min #test set - processed lines : 3858 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 392 #negative observation set - number of lines : 1018 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x20.mut.genes2.201412011820.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x20.neg.genes2.201412011820.txt # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("20"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x20", method="br8simple") ac; date() # 44 min #test set - processed lines : 3858 #suspected mutation set - number of lines : 1300 #negative observation set - number of lines : 2558 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x20.mut.genes8.201412011904.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x20.neg.genes8.201412011904.txt ### 9.12.2014 #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20141201", export.path="/0info/br4x8x2panel_batchpanel_20141209.csv", orderby="batch", unip=F, batch="") get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=20, first=T, out.path.name=NULL) # analysis run - distributions - all proton runs get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=c(12,13,14,16,17,19), first=T, out.path.name=NULL) aa <- c("BRCA1","BRCA2","NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ab <- date() db.stat.frequency(DB.path.name="/br4x8x2panel_20141201", batch=c(12,13,14,16,17,19), sampleID=c(444:457), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.10gene.8a.12.13.14.16.17.19.20141209", workspace.suffix="br4x8x2panel.10gene.8a.12.13.14.16.17.19.20141209") ab; date() # 2 min # nr 80599 #out path matrix : /home/korschi/eclipseR/BerndD/stat/stat.br4x8x2panel.10gene.8a.12.13.14.16.17.19.20141209..201412091702.txt #ba. we take the whole #WHERE sample.batch IN (12,13,14,16,17,19) #OR sample.sample_id IN (444,445,446,447,448,449,450,451,452,453,454,455,456,457) #total number of lines in table : 121859 #number of lines in selection : 80599 #statistics - number of rows : 2731 ### 12.12.2014 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL194", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 21 #number of files: 1 #number of sheets: 26 #number of rows: 5092 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("21"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x21", method="brca12") ac; date() # 6 min #test set - processed lines : 5092 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 576 #negative observation set - number of lines : 1247 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x21.mut.genes2.201412151122.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x21.neg.genes2.201412151122.txt # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("21"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x21", method="br8simple") ac; date() # 9 min #test set - processed lines : 5092 #suspected mutation set - number of lines : 2077 #negative observation set - number of lines : 3015 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x21.mut.genes8.201412151135.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x21.neg.genes8.201412151135.txt ### 16.12.2014 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL198", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 22 #number of files: 1 #number of sheets: 23 #number of rows: 3430 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("22"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x22", method="brca12") ac; date() # 5 min #test set - processed lines : 3430 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 542 #negative observation set - number of lines : 889 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x22.mut.genes2.201412161300.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x22.neg.genes2.201412161300.txt # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("22"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x22", method="br8simple") ac; date() # 5.5 min #test set - processed lines : 3430 #suspected mutation set - number of lines : 1215 #negative observation set - number of lines : 2215 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x22.mut.genes8.201412161314.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x22.neg.genes8.201412161314.txt #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20141201", export.path="/0info/br4x8x2panel_batchpanel_20141216.csv", orderby="batch", unip=F, batch="") get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=21, first=T, out.path.name=NULL) get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=22, first=T, out.path.name=NULL) ### 9.2.2015 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL204", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 23 #number of files: 1 #number of sheets: 17 #number of rows: 34380 # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL206", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 24 #number of files: 1 #number of sheets: 26 #number of rows: 11165 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("23"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x23", method="brca12") ac; date() # 42 min -- nr about 1904-2528 (!) #test set - processed lines : 34380 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 7621 #negative observation set - number of lines : 3188 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x23.mut.genes2.201502091111.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x23.neg.genes2.201502091111.txt ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("24"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x24", method="brca12") ac; date() # 12 min -- nr 399-482 #test set - processed lines : 11165 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 2292 #negative observation set - number of lines : 1872 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x24.mut.genes2.201502091125.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x24.neg.genes2.201502091125.txt # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("23"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x23", method="br8simple") ac; date() # 1h 6 min -- nr 1904-2528 #test set - processed lines : 34380 #suspected mutation set - number of lines : 19143 #negative observation set - number of lines : 15237 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x23.mut.genes8.201502091233.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x23.neg.genes8.201502091233.txt ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("24"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x24", method="br8simple") ac; date() # 19 min -- nr 399-482 #test set - processed lines : 11165 #suspected mutation set - number of lines : 4834 #negative observation set - number of lines : 6331 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x24.mut.genes8.201502091256.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x24.neg.genes8.201502091256.txt #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20141201", export.path="/0info/br4x8x2panel_batchpanel_20150209.csv", orderby="batch", unip=F, batch="") get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=23, first=T, out.path.name=NULL) get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=24, first=T, out.path.name=NULL) ### 13.2.2015 (vgl. 9.12.2014) source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # analysis all PROTON runs so far batch and sampleID (of batch 8) get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=c(12,13,14,16,17,19,22,23,24), first=T, out.path.name=NULL) # not included: "RAD51L3-RFFL" "TEX14" aa <- c("BRCA1","BRCA2","NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ab <- date() db.stat.frequency(DB.path.name="/br4x8x2panel_20141201", batch=c(12,13,14,16,17,19,22,23,24), sampleID=c(444:457), what1="", geneToWork=aa, out.path.name="/stat/stat.br4x8x2panel.10gene.8a.12.13.14.16.17.19.22.23.24.20150213proton", workspace.suffix="br4x8x2panel.10gene.8a.12.13.14.16.17.19.22.23.24.20150213proton") ab; date() # 2 min #out path matrix : /home/korschi/eclipseR/BerndD/stat/stat.br4x8x2panel.10gene.8a.12.13.14.16.17.19.22.23.24.20150213proton..201502131115.txt #ba. we take the whole #SELECT variations.* # FROM sample #INNER JOIN variations #ON sample.sample_id = variations.sample_id #WHERE sample.batch IN (12,13,14,16,17,19,22,23,24) #OR sample.sample_id IN (444,445,446,447,448,449,450,451,452,453,454,455,456,457) #total number of lines in table : 175926 #number of lines in selection : 129574 #statistics - number of rows : 5311 ### 23.2.2015 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL211", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 25 #number of files: 1 #number of sheets: 30 #number of rows: 12985 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("25"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x25", method="brca12") ac; date() # 14 min -- nr 405-479 #test set - processed lines : 12985 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 2402 #negative observation set - number of lines : 2345 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x25.mut.genes2.201502271552.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x25.neg.genes2.201502271552.txt # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("25"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x25", method="br8simple") ac; date() # 22 min -- nr 405-479 #test set - processed lines : 12985 #suspected mutation set - number of lines : 5720 #negative observation set - number of lines : 7265 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x25.mut.genes8.201502271616.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x25.neg.genes8.201502271616.txt #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20141201", export.path="/0info/br4x8x2panel_batchpanel_20150224.csv", orderby="batch", unip=F, batch="") get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=25, first=T, out.path.name=NULL) ### 12.3.2015 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL218", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 26 #number of files: 1 #number of sheets: 30 #number of rows: 37375 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("26"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x26", method="brca12") ac; date() # 36 min -- nr 1167-1364 #test set - processed lines : 37375 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 7455 #negative observation set - number of lines : 4668 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x26.mut.genes2.201503131217.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x26.neg.genes2.201503131217.txt # pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("26"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x26", method="br8simple") ac; date() # 1 h 13 min -- nr 1167-1364 #test set - processed lines : 37375 #suspected mutation set - number of lines : 16488 #negative observation set - number of lines : 20887 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x26.mut.genes8.201503131532.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x26.neg.genes8.201503131532.txt #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20141201", export.path="/0info/br4x8x2panel_batchpanel_20150224.csv", orderby="batch", unip=F, batch="") get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=26, first=T, out.path.name=NULL) ### 27.3.2015 -- test run, new br8adv1 function with all proton runs agains proton reference source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # pos-neg - 8 run - 12,13,14 ref, rule: > 3 (2 old and one new) (br12: 1 old 1 new) aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("16","17","19","22","23","24","25","26"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14xAllProton", method="br8adv1") ac; date() # 4 h 30 min -- nr app.30 - app.2500 #test set - processed lines : 107037 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 31489 #negative observation set - number of lines : 36558 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14xAllProton.mut.genes8.201503271720.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14xAllProton.neg.genes8.201503271720.txt #### test 31.3.-1.4.2015 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() #new br8adv1 function aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("25"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/del.test.test.br12.1.2.3x25", method="br8adv1") ac; date() # del from file space : del.test.test.br12.1.2.3x25 #test set - fetched lines : 12985 # 100 % #test set - gene not in work list - lines : 8238 # 63 % #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 2742 #negative observation set - number of lines : 2005 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/del.test.test.br12.1.2.3x25.mut.genes2.201504011329.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/del.test.test.br12.1.2.3x25.neg.genes2.201504011329.txt # 14 min ### 1.4.2015 - Wiederholung des 27.3.2015 -- test run, new br8adv1 function with all proton runs agains proton reference source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # pos-neg - 8 run - 12,13,14 ref, rule: > 3 (2 old and one new) (br12: 1 old 1 new) aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("16","17","19","22","23","24","25","26"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14xAllProton", method="br8adv1") ac; date() # 5 h -- nr app.30 - app.2500 #test set - fetched lines : 107037 #test set - gene not in work list - lines : 38035 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 34087 #negative observation set - number of lines : 34915 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14xAllProton.mut.genes8.201504011953.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14xAllProton.neg.genes8.201504011953.txt ### 13.4.2015 source(file="/home/korschi/eclipseR/0functions/var_db/database.R") source(file="/home/korschi/eclipseR/0functions/var_db/import.R") save.image() # import new set import.in.db(import.path.xlsx="/data_br_10panel/SIL226", log.prefix="br4x8x2panel.", DB.path.name="/br4x8x2panel_20141201") #present group number : 27 #number of files: 1 #number of sheets: 30 #number of rows: 9384 # pos-neg - 2 run - 1,2,3 ref aa <- c("BRCA1","BRCA2") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("1","2","3"), test2=c("27"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.1.2.3.20141008, ref.freq=freq.br4x8x2panel.1.2.3.20141008, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br12.1.2.3x27", method="brca12") ac; date() # 10 min -- nr 287-401 #test set - fetched lines : 9384 #test set - gene not in work list - lines : 6064 #mutations flagged in the db (as 2 ) : 0 #suspected mutation set - number of lines : 1645 #negative observation set - number of lines : 1675 #reference set - number of lines : 17182 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x27.mut.genes2.201504131518.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br12.1.2.3x27.neg.genes2.201504131518.txt # NEW pos-neg - 8 run - 12,13,14 ref aa <- c("NBN","ATM","CDH1","PALB2","RAD51D","TP53","CHEK2","RAD51C") ac <- date() db.test.on.mutations(DB.path.name="/br4x8x2panel_20141201", ref1=c("12","13","14"), test2=c("27"), geneToWork=aa, flagIt=F, ref.stat=stat.br4x8x2panel.8gene.12.13.14.20141106, ref.freq=freq.br4x8x2panel.8gene.12.13.14.20141106, mcode=1, mcode.in=2, out.path.name="/results1/test.mutations.br8.12.13.14x27", method="br8indel") ac; date() # 8 min -- nr 273-401 (30% schneller) #test set - fetched lines : 9384 #test set - gene not in work list - lines : 3320 #test set - no indel - lines : 617 #test set - no stat (1) - lines : 1226 #test set - no stat (2) - lines : 0 #suspected mutation set - number of lines : 3019 #negative observation set - number of lines : 3045 #reference set - number of lines : 71499 #output suspected mutations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x27.mut.genes8.201504131637.txt #output negative observations: /home/korschi/eclipseR/BerndD/results1/test.mutations.br8.12.13.14x27.neg.genes8.201504131637.txt #### export sample table - to document batch number and to add column with number of genes in the performed analysis #### db.export.sample(DB.path.name="/br4x8x2panel_20141201", export.path="/0info/br4x8x2panel_batchpanel_20150224.csv", orderby="batch", unip=F, batch="") get.unique.genes(DB.path.name="/br4x8x2panel_20141201", batch=26, first=T, out.path.name=NULL)