Hi I am looking for some pointers towards machine learning approaches that have been used so far in predicting "origins of replication" and would it be worthwhile going at this problem because of the tremendous data that has been made available by Next generation sequencing. And if not what makes this problem so intractable in vertebrates.
thanks
You may want to check out this interesting recent paper:
"Genetic Variation in Human DNA Replication Timing" Cell (2014)
They used variation in read coverage from whole-genome sequencing in the 1000 Genomes Project to infer replication origin locations. After that, they found replication origin differences among individuals that were attributable to genotype.
Actually I went through this paper.
And I was thinking if roadmap epigenomics data could be utilized to add on to above approach in Human. I am not sure if it's an intractable idea/ even worth trying from a machine learning perspective. Thus just wanted to think out loud!
Log in to answer this question.
