This is a test version of Biostars. For the public version, visit https://www.biostars.org.
Biological Explanation Of Sequence Based Features : Dipeptides

I am wondering, if there is any biological explanation of dipeptides or k-mers ?! what chemo-physical properties they potentially have and how one can interpret them ? For example, if in a protein property prediction, the model comes up with a list of dipeptides, as a predictive features, what they really mean ?!

Also, I have the same question regarding CTD (Composition, Transition and Distribution) of amino acids introduced by this paper

sequence prediction feature

1 answer

They don't have biological relevance per se, except that biological sequences carry information and they are ways to break down that information to achieve things computationally - like using kmers to align, bin or assemble DNA sequences.

Of course each amino acid has certain chemical properties, so dipeptides also have certain properties.

As far as the paper goes, I wouldn't pay too much attention to 17 year old papers on protein folding - I'm not an expert, but I am pretty sure the field is in a totally different place.

Since it is always interesting to come up with an biological story about the computational investigation results, may I ask you, to elaborate a little bit more about, how one can get more insight about the ultimate property of proteins with respect to kmers/dipeptides ?

I am asking about biological explanation of Dipeptides :)

Log in to answer this question.