data(SeqListSCOPe)
head(SeqListSCOPe)
SeqListSCOPe[1]
nchar(SeqListSCOPe[1])
summary(sapply(SeqListSCOPe, nchar))
data(HydroScore)
MySeqScoreList <- lapply(SeqListSCOPe, FUN=CharSequence2ScoreSequence, HydroScore)
head(MySeqScoreList)
AA <- automatic_analysis(sequences=MySeqScoreList, model='iid')
AA[[1]]
# the p-value of the first 10 sequences
sapply(AA, function(x){x$`p-value`})[1:10]
# the 20th smallest p-values
sort(sapply(AA, function(x){x$`p-value`}))[1:20]
which(sapply(AA, function(x){x$`p-value`})<0.05)
table(sapply(AA, function(x){x$`method`}))
# The maximum sequence length equals 404 so it here normal that the exact method is used for
# all the 606 sequences of the data base
# Score distribution learned on the data set
scoreSequences2probabilityVector(MySeqScoreList)
Run the code above in your browser using DataLab