[Biojava-l] Emission with duration

[Schreiber, Mark]

Hi -

How difficult would it be to make a markov model that emitted sequence
from a state using a duration distribution. For Example in gene finding
programs the model often loops over the coding state, unfortunately this
means the probability of a certain length of sequence declines
geometrically. In reality the length distribution of genes is a gamma
distribution.

Without looking into the internals, I think you could sample the
duration distribution to tell you how many times to sample the coding
(or other) state. When doing the forward backward viterbi stuff I guess
it would have to score the seqeunce by emission and rather than
factoring in the transition probabilities it would look up the duration
distribution instead.

Now that we have the Integer sub alphabets this may not be too hard (I
hope).

- Mark

Mark Schreiber PhD
Bioinformatics
AgResearch Invermay
PO Box 50034
Mosgiel
New Zealand
 
PH:   +64 3 489 9175
FAX:  +64 3 489 3739

=======================================================================
Attention: The information contained in this message and/or attachments
from AgResearch Limited is intended only for the persons or entities
to which it is addressed and may contain confidential and/or privileged
material. Any review, retransmission, dissemination or other use of, or
taking of any action in reliance upon, this information by persons or
entities other than the intended recipients is prohibited by AgResearch
Limited. If you have received this message in error, please notify the
sender immediately.
=======================================================================