Project list

1
Project list

• Peptide MHC binding predictions using position
  specific scoring matrices including pseudo counts
  and sequences weighting techniques
• Peptide MHC binding predictions using artificial
  neural networks with different sequence encoding
  schemes
• Gibbs sampler approach to the prediction of MHC
  class II binding motifs
• Improved protein sequence alignment using
  sequence profiles
• Improved sequence alignments using position
  specific gap penalties
• Improved protein template identification using
  hidden Markov models (HMMER)
• Chemo-informatics using Support Vector Machines

2
PSSM

• Peptide MHC binding predictions using position
  specific scoring matrices including pseudo counts
  and sequences weighting techniques
• Compare methods for sequence weighting
• Clustering vs heuristics
• Benchmark (Peters et al 2006) covering 20 MHC
  molecules, compare to best other methods

3
NN

• Peptide MHC binding predictions using artificial
  neural networks with different sequence encoding
  schemes
• Benchmark (Peters et al 2006) covering 20 MHC
  molecules, compare to best other methods
• Compare sequence encoding schemes

4
Gibbs sampler

• Gibbs sampler approach to the prediction of MHC
  class II binding motifs
• Develop Gibbs sampler to prediction of MHC class
  II binding motifs
• Benchmark Nielsen et al 2007 covering 14 HLA-DR
  alleles

5
Sequence alignment - 1

• Improved protein sequence alignment using
  sequence profiles
• Develop sequence profile alignment scoring scheme
  to improve sequence alignment

6
Sequence alignment - 2

• Improved protein sequence alignment using using
  position specific gap penalties
• Develop scheme for position specific gap
  penalties to improve sequence alignment
• Gap penalties in the core of a protein should be
  higher than gap penalties in loops

7
Hidden Markov models

• Improved protein template identification using
  hidden Markov models (HMMER)
• Train profile HMM to remote protein fold
  recognition
• Use the Hmmer program to construct profile HMM
  for selected set of proteins from the CASP8
  competition
• Use Hmmer model to identify PDB templates for
  hmology modeling for CASP8 targets

8
Support vector machines

• Chemo-informatics using Support Vector Machines