BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning Methods for the Detection and Prediction of Trans
 membrane Beta-Barrel Proteins in Prokariotes - Dr Piero Fariselli\, Biocom
 puting Group and Department of Computer Science\, University of Bologna
DTSTART:20121017T131500Z
DTEND:20121017T141500Z
UID:TALK39279@talks.cam.ac.uk
CONTACT:Stephen Clark
DESCRIPTION:Among the proteins found in Prokaryotes\, Transmembrane Beta-B
 arrels (TMBBs) are particularly relevant\, since they play key roles in se
 veral cell functions. As their name indicates\, they cross the lipid bilay
 er with β-barrel structures. TMBBs are presently found in the outer membr
 anes of Gram-negative bacteria and of mitochondria and chloroplasts. Loop 
 exposure outside the bacterial cell membranes makes TMBBs important target
 s for vaccine or drug therapies. In genomes\, they are not highly represen
 ted and are difficult to identify with experimental approaches. Actually\,
  the classical\nmethods have a very high rate of false positive assignment
 s. Here we present two methods that have been developed to discriminate TM
 BBs from other types of proteins and to predict the TMBB topology. TMBB\nd
 etection is based on N-to-1 Extreme Learning Machines that significantly o
 utperforms previous methods achieving a Matthews correlation coefficient o
 f 0.82\, a probability of correct pre-diction of 0.92\nand a sensitivity o
 f 0.73. For the topology prediction\, we introduce a Grammatical-Restraine
 d Hidden Conditional Random Fields (GRHCRFs) as an extension of Hidden Con
 ditional Random Fields (HCRFs).\nGRHCRFs while preserving the discriminati
 ve character of HCRFs\, can assign labels in agreement with the production
  rules of a defined grammar. We show that in the task of predicting TMBB t
 opology GRHCRFs\nperform better than CRF and HMM models of the same comple
 xity.\n \nReferences: - Fariselli P.\, Savojardo C.\, Martelli P.L.\, Casa
 dio R.\, "Grammatical-Restrained Hidden Conditional Random Fields for Bioi
 nformatics Applications"\, Algorithms for Molecular Biology 2009\,\n4:13. 
 \n\n- Savojardo C.\, Fariselli P.\, Casadio R.\, "Improving the detection 
 of transmembrane β-barrel chains with N-to-1 Extreme Learning Machines"\,
  Bioinformatics (2011) 27 (22): 3123-3128.\n
LOCATION:Lecture Theatre 1\, Computer Laboratory
END:VEVENT
END:VCALENDAR