I am new to using R and i have to use the Viterbi algorithm to calculate the hidden states. the problem is the program is not reading my transition probailities correctly. below is all the information i have

b) Use zero order Markov models defined for sequence1_A2 and sequence2_A2 and apply Viterbi algorithm to find the most likely path for sequence CGCGTTCATTCAATG in frame 1 only (45 pts)

Assume:

Initial transition probabilities

a_0c= a_0n.5

a_nn= a_nc.5

a_cc.55 a_cn= 0.45

where, a_ijis transition probability, c- coding, n-non-coding. the second probaility (on the right is for non coding)

cn

P(A)= 281/.204P(A)= 107/.195

P(T)/.144P(T)/.186

P(G)/.354P(G)/.333

P(C)/.298 P(C)/.284

below is the script i use and the result i get in R:

# Initialise HMM > hmm = initHMM(c("C","N"), c("A","T","G","C"), transProbs=matrix(c(.20,.14,.34,.29),2), + emissionProbs=matrix(c(.19,.18,.33,.28),2)) > > > print(hmm) $States [1] "C" "N" $Symbols [1] "A" "T" "G" "C" $startProbs C N 0.5 0.5 $transProbs to from C N C 0.20 0.34 N 0.14 0.29 $emissionProbs symbols states A T G C C 0.19 0.33 0.19 0.33 N 0.18 0.28 0.18 0.28 > # Sequence of observations > observations = c("C","G","C","G","T","T","C","A","T","T","C","A","A","T","G") > # Calculate Viterbi path > viterbi = viterbi(hmm,observations) > print(viterbi) [1] "C" "N" "N" "N" "N" "N" "N" "N" "N" "N" "N" "N" "N" "N" "N"