Knowledge base of Conditional Random Field (CRF)

Much like a Markov random field, a CRF is an undirected graphical model in which each vertex represents a random variable whose distribution is to be inferred, and each edge represents a dependency between two random variables. (From Wikipedia)

Introduction and Resources#

Google search#

• bioinformatics conditional random field: 13,800
• bioinformatics hidden markov model: 297,000

Tutorials#

• Sutton and McCallum: An Introduction to Conditional Random Fields for Relational Learning
• Hanna M. Wallach: Conditional Random Fields: An Introduction
• Roman Klinger and Katrin Tomanek Classical Probabilistic Models and Conditional Random Fields

Resources#

• Wikipedia: http://en.wikipedia.org/wiki/Conditional_random_field
• Hanna Wallach: http://www.inference.phy.cam.ac.uk/hmw26/crf/
• Gabor Melli: A knowledge base

References#

• J. Lafferty, A. McCallum, and F. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In the proceedings of International Conference on Machine Learning (ICML), pp. 282-289, 2001.
• F. Sha and F. Pereira. Shallow parsing with conditional random fields. In the proceedings of Human Language Technology/North American chapter of the Association for Computational Linguistics annual meeting (HLT/NAACL), 2003.

CRF in Bioinformatics#

Gene predictioin#

• A. Culotta, D. Kulp, A. McCallum. Gene Prediction with Condtinal Random Fields. Technical Report, University of Massachusetts, 2005
• Gross SS, Do CB, Batzoglou S. CONTRAST: de novo gene prediction using a semi-Markov conditional random field. In BCATS 2005 Symposium Proceedings, pp. 82, 2005.
• Jade P. Vinson, David DeCaprio, Matthew D. Pearson, Stacey Luoma, James E. Galagan. Comparative Gene Prediction using Conditional Random Fields. NIPS, 2006.
• Gross SS, Do CB, Batzoglou S. De novo gene prediction using a semi-Markov conditional random field. RECOMB, 2006.
• Matthew K. Doherty. Gene Prediction with Conditional Random Fields. Master Thesis, Massachusetts Institute of Technology, 2007.
• David DeCaprio, Jade P. Vinson, Matthew D. Pearson, Philip Montgomery, Matthew Doherty, and James E. Galagan. Conrad: Gene prediction using conditional random fields. Genome Research, 17(9), pp. 1389-1398, 2007.
• A. Bernal, K. Crammer, A. Hatzigeorgiou, F. Pereira. Global discriminative learning for higher-accuracy computational gene prediction. PLoS Comput Biol, 2007, 3, e54
• Samuel S. Gross, Chuong B. Do, Marina Sirota, and Serafim Batzoglou. CONTRAST: a discriminative, phylogeny-free approach to multiple informant de novo gene prediction. Genome Biology, 8(12):R269, 2007.

SNP array analysis#

• Ling-Yun Wu, Xiaobo Zhou, Fuhai Li, Xiaorong Yang, Chung-Che Chang, Stephen T.C. Wong. Conditional random pattern algorithm for LOH inference and segmentation. Bioinformatics, Vol. 25, No. 1, 61-67, 2009. (PubMed: 18974074)

Classification#

• Chang-Tsun Li, Yinyin Yuan and Roland Wilson. An unsupervised conditional random fields approach for clustering gene expression time series. Bioinformatics, 24(21), pp. 2467-2473, 2008.
• Zafer Barutcuoglu, Edoardo M. Airoldi, Vanessa Dumeaux, Robert E. Schapire and Olga G. Troyanskaya. Aneuploidy Prediction and Tumor Classification with Heterogeneous Hidden Conditional Random Fields. Bioinformatics, doi:10.1093/bioinformatics/btn585, December 2008.

RNA structure#

• Kengo Sato and Yasubumi Sakakibara. RNA secondary structural alignment with conditional random fields. Bioinformatics, 21, pp. ii237–242, 2005.

Protein structure#

• Yan Liu, Jaime Carbonell, Peter Weigele, and Vanathi Gopalakrishnan. Segmentation conditional random fields (SCRFs): A new approach for protein fold recognition. In ACM International conference on Research in Computational Molecular Biology (RECOMB05), 2005.
• Yan Liu, Jaime Carbonell, Peter Weigele, Vanathi Gopalakrishnan. Protein Fold Recognition Using Segmentation Conditional Random Fields (SCRFs). Journal of Computational Biology, 13(2), pp. 394-406, 2006.
• Ming-Hui Li, Lei Lin , Xiao-Long Wang and Tao Liu. Protein-protein interaction site prediction based on conditional random fields. Bioinformatics, 23(5), pp. 597-604, 2007.
• Lixiao Wang and Uwe H. Sauer. OnD-CRF: predicting order and disorder in proteins conditional random fields. Bioinformatics, 24(11), pp.1401-1402, 2008.
• Thanh Hai Dang, Koenraad Van Leemput, Alain Verschoren and Kris Laukens. Prediction of kinase-specific phosphorylation sites using conditional random fields. Bioinformatics, 24(24), pp. 2857-2864, 2008.

Networks#

• Qiang Huang, Ling-Yun Wu, Xiang-Sun Zhang. An Efficient Network Querying Method Based on Conditional Random Fields. Bioinformatics, Vol. 27, No. 22, 3173-3178, 2011.

Software#

FlexCRFs: Flexible Conditional Random Fields#

• http://flexcrfs.sourceforge.net
• FlexCRFs is a conditional random field toolkit for segmenting and labeling sequence data written in C/C++ using STL library. It was implemented based on the theoretic model presented in (Lafferty et al. 2001) and (Sha and Pereira 2003).

Kevin Murphy's CRF Toolbox#

• http://www.cs.ubc.ca/~murphyk/Software/CRF/crf.html
• Conditional random fields (chains, trees and general graphs; includes BP code).

Sunita Sarawagi's CRF package#

• http://crf.sourceforge.net
• The CRF package is a java implementation of Conditional Random Fields for sequential labeling developed by Sunita Sarawagi of IIT Bombay.

CRF++: Yet Another CRF toolkit#

• http://crfpp.sourceforge.net
• CRF++ is a simple, customizable, and open source implementation of Conditional Random Fields (CRFs) for segmenting/labeling sequential data.

Pocket CRF#

• http://sourceforge.net/projects/pocket-crf-1/
• Pocket CRF is a modified version of CRF++, it maintains the simplicity of CRF++ and is able to use high order features.

UGM#

• http://www.cs.ubc.ca/~schmidtm/Software/UGM.html
• UGM is a Matlab toolbox for probabilistic undirected graphical models