CISC 841 Bioinformatics

1
CISC 841 Bioinformatics Combining HMMs with
SVMs
2
HMM gradients

• Fisher Score ltXgt ?? log P(XH, ?)
• The gradient of a sequence X with respect to a
  given model is computed using the
  forward-backward algorithm.
• Each dimension corresponds to one parameter of
  the model.
• The feature space is tailored to the sequences
  from which the model was trained.

3
SVM-Fisher discrimination

• A probabilistic hidden Markov model ? is
  trained from some example
• sequences x1 x2 x3 xN
• Usually probability model P(xi?) (or function
  of P(xi?)) is used as a measure of
• sequence-model membership, and a threshold is
  used on this measure
• to decide membership.
• The Fisher vector is a vector of gradients of
  P(xi?) (or gradients of function of P(xi?))
• w.r.t the parameters of the model.
• Uxi ?? P(xi?)
• One can take the training example sequences
  (positive set) and other sequences that are
• known to be non-members (negative set), and
  transform them into Fisher vectors.
• A Support Vector Machine (SVM) can be trained
  using the positive and negative
• Fisher vectors, and can be used to classify
  other sequences.

4
Application Protein remote homology detection
5
SVM-Pairwise method
Positive train
Negative train
Protein non-homologs
Protein homologs
1
Positive pairwise score vectors
Negative pairwise score vectors
Testing data
Target protein of unknown function
2
3
Support vector machine
Binary classification
6
Experiment known protein families
Jaakkola, Diekhans and Haussler 1999
7
Sample family sizes
8
A measure of sensitivity and specificity
5
6
ROC 1
ROC 0.67
ROC 0
ROC receiver operating characteristic score is
the normalized area under a curve the plots true
positives as a function of false positives
9
Application Discriminating signal peptide from
transmembrane proteins
10

Feature selection

• We expect gradients w.r.t transition parameters
• to be better discrimination features
• We look for those transitions that
• are differentially used by TM
• proteins and SP proteins
• - transform each signal peptide sequence (1275)
• into a Fisher vector w.r.t transition
  parameters
• and find the resultant vector
• - transform each TM sequence into a Fisher
• vector w.r.t transition parameters and find
• the resultant vector
• - compare the two resultant vectors

11
Gradients of P(sx)

• In pattern recognition problems, we are
  interested in P(sx,?) rather than P(x?)
• Usx ?? log P(sx,?) ?? log P(s, x?) - ??
  log P(x?)

12

Classification experiment

• 10-fold cross validation experiment using
• - positive set (247 TM proteins)
• - negative set (1275 signal peptide containing
  proteins)
• SVM-light package is used.

13
Discrimination results

• Results
• A third (68) more SP proteins that were
  incorrectly classified as TM
• TM proteins are identified correctly.

14
Application Protein-Protein Interaction
Prediction
15
Interaction Profile Hidden Markov Model (ipHMM)
Fredrich et al (2006)
16

• Knowledge transfer
• Build ipHMM from proteins whose structural
  information is available.
• Align the sequences of proteins whose
  structural information is
• not available to the model.

Likelihood Score Vector
ltLSai, A, LSai, B, LSbj,A, LSbj, Bgt
Fisher Score Vector
U (x) ?? logP(x?)
Uij Ej(i) / ej(i) ? k Ej(k)
17
(No Transcript)
18
(No Transcript)
19
Data set Fredrich et al (2006) 2018 proteins
in 36 domain families
20
Conclusions

• Structural information at binding sites enhances
  protein-protein interaction prediction.
• Interaction profile HMM can transfer structural
  information
• Fisher scores extracted from domain profiles
  further enhance protein-protein interaction
  prediction for proteins with no available
  structural information.