TOWARDS A PROBABILISTIC RECOGNITION CODE FOR PROTEIN-DNA INTERACTIONS
Lists
Only you see this
Abstract
We are investigating the rules that govern protein-DNA interactions, using a statistical mechanics based formalism that is related to the Boltzmann Machine of the neural net literature. Our approach is data-driven, in which probabilistic algorithms are used to model protein-DNA interactions, given SELEX and phage data as input. Under the ''one-to-one'' model for interactions (i.e. one amino acid contacts one base), we can successfully identify the wild-type binding sites of EGR and MIG protein families. The predictions using our method are the same or better than that of methods existing in the literature, however our methodology offers the potential to capitalize in quantitative detail on more data as it becomes available.
BibTeX
@inproceedings{benos2000towards,
author = {Panayiotis V. Benos},
title = {{TOWARDS A PROBABILISTIC RECOGNITION CODE FOR PROTEIN-DNA INTERACTIONS}},
booktitle = {University},
year = {2000},
}Loading related content...