R/create_probab.R

In bgafun: BGAfun A method to identify specifity determining residues in protein families

"create_probab" <-
function(){
  ## This will return the transition probability matrix needed to calculate the pseudocounts
  
q_A<-c(0.0215,0.0023,0.0019,0.0022,0.0016,0.0019,0.003,0.0058,0.0011,0.0032,0.0044,0.0033,0.0013,0.0016,0.0022,0.0063,0.0037,0.0004,0.0013,0.0051)
q_R<-c(0.0023,0.0178,0.002,0.0016,0.0004,0.0025,0.0027,0.0017,0.0012,0.0012,0.0024,0.0062,0.0008,0.0009,0.001,0.0023,0.0018,0.0003,0.0009,0.0016)
q_N<-c(0.0019,0.002,0.0141,0.0037,0.0004,0.0015,0.0022,0.0029,0.0014,0.001,0.0014,0.0024,0.0005,0.0008,0.0009,0.0031,0.0022,0.0002,0.0007,0.0012)
q_D<-c(0.0022,0.0016,0.0037,0.0213,0.0004,0.0016,0.0049,0.0025,0.001,0.0012,0.0015,0.0024,0.0005,0.0008,0.0012,0.0028,0.0019,0.0002,0.0006,0.0013)
q_C<-c(0.0016,0.0004,0.0004,0.0004,0.0119,0.0003,0.0004,0.0008,0.0002,0.0011,0.0016,0.0005,0.0004,0.0005,0.0004,0.001,0.0009,0.0001,0.0003,0.0014)
q_Q<-c(0.0019,0.0025,0.0015,0.0016,0.0003,0.0073,0.0035,0.0014,0.001,0.0009,0.0016,0.0031,0.0007,0.0005,0.0008,0.0019,0.0014,0.0002,0.0007,0.0012)
q_E<-c(0.003,0.0027,0.0022,0.0049,0.0004,0.0035,0.0161,0.0019,0.0014,0.0012,0.002,0.0041,0.0007,0.0009,0.0014,0.003,0.002,0.0003,0.0009,0.0017)
q_G<-c(0.0058,0.0017,0.0029,0.0025,0.0008,0.0014,0.0019,0.0378,0.001,0.0014,0.0021,0.0025,0.0007,0.0012,0.0014,0.0038,0.0022,0.0004,0.0008,0.0018)
q_H<-c(0.0011,0.0012,0.0014,0.001,0.0002,0.001,0.0014,0.001,0.0093,0.0006,0.001,0.0012,0.0004,0.0008,0.0005,0.0011,0.0007,0.0002,0.0015,0.0006)
q_I<-c(0.0032,0.0012,0.001,0.0012,0.0011,0.0009,0.0012,0.0014,0.0006,0.0184,0.0114,0.0016,0.0025,0.003,0.001,0.0017,0.0027,0.0004,0.0014,0.012)
q_L<-c(0.0044,0.0024,0.0014,0.0015,0.0016,0.0016,0.002,0.0021,0.001,0.0114,0.0371,0.0025,0.0049,0.0054,0.0014,0.0024,0.0033,0.0007,0.0022,0.0095)
q_K<-c(0.0033,0.0062,0.0024,0.0024,0.0005,0.0031,0.0041,0.0025,0.0012,0.0016,0.0025,0.0161,0.0009,0.0009,0.0016,0.0031,0.0023,0.0003,0.001,0.0019)
q_M<-c(0.0013,0.0008,0.0005,0.0005,0.0004,0.0007,0.0007,0.0007,0.0004,0.0025,0.0049,0.0009,0.004,0.0012,0.0004,0.0009,0.001,0.0002,0.0006,0.0023)
q_F<-c(0.0016,0.0009,0.0008,0.0008,0.0005,0.0005,0.0009,0.0012,0.0008,0.003,0.0054,0.0009,0.0012,0.0183,0.0005,0.0012,0.0012,0.0008,0.0042,0.0026)
q_P<-c(0.0022,0.001,0.0009,0.0012,0.0004,0.0008,0.0014,0.0014,0.0005,0.001,0.0014,0.0016,0.0004,0.0005,0.0191,0.0017,0.0014,0.0001,0.0005,0.0012)
q_S<-c(0.0063,0.0023,0.0031,0.0028,0.001,0.0019,0.003,0.0038,0.0011,0.0017,0.0024,0.0031,0.0009,0.0012,0.0017,0.0126,0.0047,0.0003,0.001,0.0024)
q_T<-c(0.0037,0.0018,0.0022,0.0019,0.0009,0.0014,0.002,0.0022,0.0007,0.0027,0.0033,0.0023,0.001,0.0012,0.0014,0.0047,0.0125,0.0003,0.0009,0.0036)
q_W<-c(0.0004,0.0003,0.0002,0.0002,0.0001,0.0002,0.0003,0.0004,0.0002,0.0004,0.0007,0.0003,0.0002,0.0008,0.0001,0.0003,0.0003,0.0065,0.0009,0.0004)
q_Y<-c(0.0013,0.0009,0.0007,0.0006,0.0003,0.0007,0.0009,0.0008,0.0015,0.0014,0.0022,0.001,0.0006,0.0042,0.0005,0.001,0.0009,0.0009,0.0102,0.0015)
q_V<-c(0.0051,0.0016,0.0012,0.0013,0.0014,0.0012,0.0017,0.0018,0.0006,0.012,0.0095,0.0019,0.0023,0.0026,0.0012,0.0024,0.0036,0.0004,0.0015,0.0196)

probab<-c(q_A,q_R,q_N,q_D,q_C,q_Q,q_E,q_G,q_H,q_I,q_L,q_K,q_M,q_F,q_P,q_S,q_T,q_W,q_Y,q_V)
dim(probab)<-c(20,20)
probab<-as.data.frame(probab)
rownames(probab) <- c("A",  "R",  "N",  "D",  "C",  "Q",  "E",  "G", "H",  "I",  "L",  "K",  "M",  "F",  "P",  "S",  "T",  "W",  "Y",  "V")
colnames(probab) <- c("A",  "R",  "N",  "D",  "C",  "Q",  "E",  "G", "H",  "I",  "L",  "K",  "M",  "F",  "P",  "S",  "T",  "W",  "Y",  "V")


 return(probab)

 }