@inproceedings{442f8aa85c984faea3d8f0aaad700f30,
title = "Statistical Compression of Protein Folding Patterns for Inference of Recurrent Substructural Themes",
abstract = "Computational analyses of the growing corpus of three-dimensional (3D) structures of proteins have revealed a limited set of recurrent substructural themes, termed super-secondary structures. Knowledge of super-secondary structures is important for the study of protein evolution and for the modeling of proteins with unknown structures. Characterizing a comprehensive dictionary of these super-secondary structures has been an unanswered computational challenge in protein structural studies. This paper presents an unsupervised method for learning such a comprehensive dictionary using the statistical framework of lossless compression on a database comprised of concise geometric representations of protein 3D folding patterns. The best dictionary is defined as the one that yields the most compression of the database. Here we describe the inference methodology and the statistical models used to estimate the encoding lengths. An interactive website for this dictionary is available at http://lcb.infotech.monash.edu.au/proteinConcepts/scop100/dictionary.HTML.",
author = "Ramanan Subramanian and Lloyd Allison and Stuckey, {Peter J.} and Banda, {Maria Garcia De La} and David Abramson and Lesk, {Arthur M.} and Konagurthu, {Arun S.}",
note = "Funding Information: Funding from Australian Research Council (DP150100894) Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 Data Compression Conference, DCC 2017 ; Conference date: 04-04-2017 Through 07-04-2017",
year = "2017",
month = may,
day = "8",
doi = "10.1109/DCC.2017.46",
language = "English (US)",
series = "Data Compression Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "340--349",
editor = "Ali Bilgin and Joan Serra-Sagrista and Marcellin, {Michael W.} and Storer, {James A.}",
booktitle = "Proceedings - DCC 2017, 2017 Data Compression Conference",
address = "United States",
}