Premium
Data Requirements of Reverse‐Engineering Algorithms
Author(s) -
JUST WINFRIED
Publication year - 2007
Publication title -
annals of the new york academy of sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.712
H-Index - 248
eISSN - 1749-6632
pISSN - 0077-8923
DOI - 10.1196/annals.1407.008
Subject(s) - computer science , underdetermined system , reverse engineering , dimension (graph theory) , algorithm , set (abstract data type) , protocol (science) , data set , quality (philosophy) , data mining , theoretical computer science , artificial intelligence , mathematics , medicine , philosophy , alternative medicine , epistemology , pathology , pure mathematics , programming language
: Data Sets used in reverse engineering of biochemical networks contain usually relatively few high‐dimensional data points, which makes the problem in general vastly underdetermined. It is therefore important to estimate the probability that a given algorithm will return a model of acceptable quality when run on a data set of small size but high dimension. We propose a mathematical framework for investigating such questions. We then demonstrate that without assuming any prior biological knowledge, in general no theoretical distinction between the performance of different algorithms can be made. We also give an example of how expected algorithm performance can in principle be altered by utilizing certain features of the data collection protocol. We conclude with some examples of theorems that were proven within the proposed framework.