You are on page 1of 36

Markov Model

Prof.khaled ElBahnasy
Markov Model
Markov Model (Cont.)
Markov Assumption
First Order Markov Assumption
Transition Matrix
Transition Graph
Example 1
Example 2
Example3: Training the Model
Viterbi Algorithm
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Viterbi Algorithm (Cont.)
Forward algorithm
Forward algorithm (Cont.)
Forward algorithm (Cont.)
Forward algorithm (Cont.)
Forward algorithm (Cont.)
Forward algorithm (Cont.)
Forward algorithm (Cont.)
Summary
Remark
Example 3
• A sequence segment of bases A, C, G, T from the human
preproglucagon gene: GTATTAAATCCGTAGTCTGAACTAACTA · ·· ·· ·· ·· ·
• A “Words” – such as ‘CTGAC’ – are suspected to serve some biological
function if they seem to occur often in a segment of the sequence.
• So it is of interest to measure the “ofteness” of the occurrences of a
“word.”
• The following table observes frequencies/proportions of pairs of
consecutive bases from a sequence of 1571 bases:

2nd base
A C G T
1 base
st

A 0.359 0.143 0.167 0.331


C 0.384 0.156 0.023 0.437
G 0.305 0.199 0.150 0.345
T 0.284 0.182 0.177 0.357
overall 0.328 0.167 0.144 0.360
Example 3
By using Markov Model
• Construct the transition state for this data.
• Compute the probability of finding any pair base starting by A
(AA, AC, AG,,………). select one case.
• Compute the probability of finding any triple base starting by T
(TCG, TAC, TGC..…). select one case.
• Compute the probability of ‘CTGAC’ given the first base being
‘C’.
Example 4
Probability of seq, path if all promoter
Probability of seq, path if all background
Probability of seq, path sequence if mixed
?

You might also like