1. Protein secondary structure predictions By: Refael Vivanti & Tal Tabakman

2. Rising accuracy of protein secondary structure prediction Burkhard Rost

3. ? Main dogma in biology D.N.A. R.N.A strand of A.A. protein
AGCTCTCTGAGGCTT
UCGAGAGACUCCGAA
AGHTY ?

4. Sequence – structure gap
Today we have much more sequenced proteins than protein’s structures.
The gap is rapidly increasing.
Problem:
Finding protein structure isn’t that simple.
Solution:
A good start : find secondary structure.

5. "ויהי כל הארץ שפה אחת ודברים אחדים" בראשית יא א
"ויהי כל הארץ שפה אחת ודברים אחדים" בראשית יא א
Comparing methods requires same terms and tests.
Secondary structure types:
H - helix
E – β strand
L\C – other.
seq
A A P P L L L L M M M G I M M R R I M
E E E E E C C C C H H H H C C C E E E
pred

6. How to evaluate a prediction?
The Q3 test:
correctly predicted residues
number of residues
Of course, all methods would be tested on the same proteins.

7. Old methods Fasman & Chou (1974) :
First generation – single residue statistics
Fasman & Chou (1974) :
Some residues have particular secondary
structure preference.
Examples: Glu α-Helix
Val β-strand
Second generation – segment statistics
Similar, but also considering adjacent residues.

8. Difficulties Q3 of strands (E) : 28% - 48%.
Bad accuracy - below 66% (Q3 results).
Q3 of strands (E) : 28% - 48%.
Predicted structures were too short.

9. Methods accuracy comparison

10. 3rd generation methods Third generation methods reached 77% accuracy.
They consist of two new ideas:
1. A biological idea –
Using evolutionary information.
2. A technological idea –
Using neural networks.

11. How can evolutionary information help us?
Homologues similar structure
But sequences change up to 85%
Sequence would vary differently - depends on structure

12. How can evolutionary information help us?
Where can we find high sequence conservation?
Some examples:
In defined secondary structures.
In protein core’s segments (more hydrophobic).
In amphipatic helices (cycle of hydrophobic and hydrophilic residues).

13. How can evolutionary information help us?
Predictions based on multiple alignments were made manually.
Problem:
There isn’t any well defined algorithm!
Solution:
Use Neural Networks .

14. Artificial Neural Networks
An attempt to imitate the human brain construction, (assuming this is the way it works).
When do we use it ?
When we can’t solve the problems ourselves!!!

15. Artificial Neural Network
The neural network basic structure :
Big amount of processors –
“neurons”.
Highly connected.
Working together.

16. Artificial Neural Network
What does a neuron do?
Gets “signals” from its neighbours.
Each signal has different weight.
When achieving certain threshold - sends signals.

17. Artificial Neural Network
General structure of ANN :
One input layer.
Some hidden layers.
One output layer.
Our ANN have one-direction flow !

18. Artificial Neural Network
A neuron may be:
NOT gate
gate AND
OR gate
Because this is a complete system, a neural network can compute anything.

19. Artificial Neural Network
Network training and testing :
Test set
Correct
Neural network
Training set
Incorrect
Back - propagation
Training set - inputs for which we know the wanted output.
Back propagation - algorithm for changing neurons pulses
“power”.
Test set - inputs used for final network performance test.

20. Artificial Neural Network
The Network is a ‘black box’:
Even when it succeeds
it’s hard to understand
how.
It’s difficult to conclude
an algorithm from the network
It’s hard to deduce
new scientific principles.

21. Structure of 3rd generation methods
Find homologues using
large data bases.
Create a profile representing
the entire protein family.
Give sequence and profile to ANN.
Output of the ANN:
2nd structure prediction.

22. Structure of 3rd generation methods
The ANN learning process:
Training & testing set:
- Proteins with known sequence & structure.
Training:
- Insert training set to ANN as input.
- Compare output to known structure.
- Back propagation.

23. 3rd generation methods - difficulties
Main problem - unwise selection of training & test
sets for ANN.
First problem – unbalanced training
Overall protein composition:
Helices - 32%
Strands - 21%
Coils – 47%
What will happen if we train the ANN with random segments ?

24. 3rd generation methods - difficulties
Second problem – unwise separation between training
& test proteins
What will happen if homology / correlation exists
between test & training proteins?
over optimism!
Above 80% accuracy in testing.
Third problem – similarity between test proteins.

25. PSI - PRED : 3RD generation method based on the iterated
Protein Secondary Structure Prediction Based on Position – specific Scoring Matrices David T. Jones
PSI - PRED : 3RD generation method based on the iterated
PSI – BLAST algorithm.

26. PSI - BLAST
PSSM - position specific scoring matrix
Sequence
Distant homologues
PSI - BLAST outperforms other algorithms in finding distant
homologues.
PSSM – input for PSI - PRED.

27. PSI - PRED Two ANNs working together. Sequence + PSSM Prediction
ANN’s architecture:
Two ANNs working together.
Sequence + PSSM
1ST ANN
Prediction
2ND ANN
Final
prediction

28. PSI - PRED Step 1: Step 2: 1ST ANN
Create PSSM from sequence - 3 iterations of
PSI – BLAST.
Step 2: 1ST ANN
Sequence + PSSM st ANN’s input.
A D C Q E I L H T S T T W Y V
15 RESIDUES
E/H/C
output: central amino acid
secondary state prediction.
A D C Q E I L H T S T T W Y V

29. PSI - PRED Using PSI - BLAST brings up PSI – BLAST difficulties:
Iteration - extension
of proteins family
Updating PSSM
Inclusion of
non – homologues
“Misleading” PSSM

30. PSI - PRED Step 3: 2nd ANN what’s wrong with that ?
So why do we need a second ANN ?
possible output for 1st ANN:
one-amino-acid helix
doesn’t exist
seq
A A P P L L L L M M M G I M M R R I M
E E E E E C C C C C H C C C C C E E E
pred
what’s wrong with that ?
Solution: ANN that “looks” at the whole context !
Input: output of 1st ANN.
Output: final prediction.

31. PSI - PRED Training : Testing :
10% of proteins were used as “inner” test.
Balanced training.
Testing :
187 proteins, Highly resolved
structure.
PSI – BLAST was used for
removing homologues.
Without structural similarities.

32. PSI - PRED
Jones’s reported results :
Q3 results : 76% - 77%.

33. PSI - PRED Reliability numbers: The way the ANN tells us
how much it is sure about
the assignment.
Used by many methods.
Correlates with accuracy.

34. Performance evaluation
Through 3rd generation methods accuracy
jumped ~10%.
Many 3rd generation methods exist today.
Which method is the best one ?
How to recognize “over-optimism” ?

35. Performance evaluation
CASP - Critical Assessment of Techniques
for Protein Structure Prediction.
EVA – Automatic Evaluation of Automatic Prediction
Servers.

37. Performance evaluation
Conclusion :
PSI-PRED seams to be one of the most reliable
method today.
Reasons :
The widest evolutionary information
(PSI - BLAST profiles).
Strict training & testing criterions for ANN.

38. Improvements The first 3rd generation method PHD: ~72% in Q3.
3rd generation methods best results: ~77% in Q3 .
Sources of improvement :
Larger protein data bases.
PSI – BLAST
PSI – PRED broke through, many followed...

39. Improvements How can we do better than that ?
Through larger data bases (?).
Combination of methods.
Example:
Combining 4 best methods Q3 of ~78% !
Find why certain proteins
predicted poorly.

40. Improvements What is the limit of prediction improvement? than others.
Some regions of proteins are more mobile
than others.
12% of proteins structure is unknown even by
“manual” methods.
The limit of accuracy is 88% !

41. Secondary structure prediction in practice
protein structure
genome analysis
finding structural
switches

42. Finding Structural Switches
young et al:
Prediction of secondary structure
with several methods
Different results + same preferences
Structural switch ???

43. Bibliography Jones DT. Protein secondary structure prediction based on
position specific scoring matrices. J Mol Biol :
Rost B. Rising accuracy of protein secondary structure prediction
'Protein structure determination, analysis, and modeling for
drug discovery‘ (ed. D Chasman), New York: Dekker, pp