1. CSCE555 Bioinformatics Lecture 18 Protein Bioinforamtics and Protein Secondary Structure Prediction Meeting: MW 4:00PM-5:15PM SWGN2A21 Instructor: Dr. Jianjun Hu Course page: http://www.scigen.org/csce555 University of South Carolina Department of Computer Science and Engineering 2008 www.cse.sc.edu. www.cse.sc.edu

2. Outline Understanding Protein Structures Protein bioinformatics: what and why? Protein Secondary Structure Prediction: problem & algorithm Summary

3. Proteins Large organic compounds made of amino acids functions Proteins play a crucial role in virtually all biological processes with a broad range of functions. structure The activity of an enzyme or the function of a protein is governed by the three-dimensional structure

4. How Proteins Are Generated folding

5. Protein Bioinformatics Analysis and prediction of protein structures (Structural Bioinformatics) ◦ Protein Design: design a sequence that will fold into a designated structure Assist experimental biology in assigning functions or suggesting functional hypotheses for all known proteins.

6. DNARNA cDNA ESTs UniGene phenotype Genomic DNA Databases Protein sequence databases protein Protein structure databases transcriptiontranslation Gene expression database Protein Bioinformatics

7. TOP 10 Most Wanted solutions in protein bioinformatics 1. Protein sequence alignment 2. Predicting protein features from sequence 3. Function prediction 4. Protein structure prediction 5. Membrane proteins 6. Functional site identification 7. Protein-protein interaction 8. Protein-small molecule interaction (Docking) 9. Protein design 10. Protein engineering

8. Why Protein Bioinformatics? Function =  interactions Disease Mechanism, Gene regulation, Drug design…

9. Relevance of Protein Structure in the Post-Genome Era sequence structure function medicine

10. Protein Structure Example Beta Sheet HelixLoop 2 chains

11. Proteins Structure is Hierarchical Single peptide chain Multiple peptide chains Local Folding Long-range Folding Multi-meric organization Sequence

12. How to Obtain Protein Structures Experimental methods (>50,000)  X-ray crystallography or NMR (Nuclear magnetic resonance) spectrometry  limitation: protein size, require crystallized proteins  Difficult to get crystallized for membrane proteins Computational methods (predictive methods)  2-D structure (secondary structure)  3-D structure (tertiary structure)  CASP competition: Critical Assessment of Techniques for Protein Structure Prediction

13. Protein Structure Prediction Problem Given the amino acid sequence of a protein, what’s its shape in three- dimensional space? ◦ Sequence → secondary structure → 3D structure → function

14. Why Prediction Needed? The functions of a protein is determined by its structure. Experimental methods to determine protein structure are time-consuming and expensive. Big gap between the available protein sequences and structures.

15. Growth of Protein Sequences and Structures Data from http://www.dna.affrc.go.jp 50,000 as 2008 30000*X species

16. What determines structures: Inter-atomic Forces Covalent bond (short range, very strong) ◦ Binds atoms into molecules / macromolecules Hydrogen bond (short range, strong) ◦ Binds two polar groups (hydrogen + electronegative atom) Disulfide bond / bridge (short range, very strong) ◦ Covalent bond between sulfhydryl (sulfur + hydrogen) groups Hydrophobic / hydrophillic interaction (weak) ◦ Hydrogen bonding w/ H2O in solution Van der Waal’s interaction (very weak) ◦ Nonspecific electrostatic attractive force Electrostatic forces: ◦ oppositely charged side chains form salt bridges

17. Secondary Structure Predication (2D) For each residues in a protein structure, three possible states: a (a-helix), ß (ß-strand), t (others). amino acid sequence Secondary structure sequence Currently the accuracy of secondary structure methods is nearly 80-82% (2006). Theoretical uplimit is 90% due to uncertainty 10% in real proteins Secondary structure prediction can provide useful information to improve other sequence and structure analysis methods, such as sequence alignment and 3-D modeling. http://bioinf.cs.ucl.ac.uk/psipred/psiform.html

18. PSSP: Protein Secondary Structure Prediction Three Generations Based on statistical information of single amino acids Based on local amino acid interaction (segments). Typically a segment containes 11-21 aminoacids Based on evolutionary information of the homology sequences

19. Formulate PSSP as a machine learning classification problem Using a sliding window to move along the amino acid sequence ◦ Each window denotes an instance ◦ Each amino acid inside the window denotes an attribute ◦ The known secondary structure of the central amino acid is the class label

20. How to generalize protein secondary prediction as a machine learning problem? A set of “examples” are generated from sequence with known secondary structures Examples form a training set Build a neural network classifier Apply the classifier to a sequence with unknown secondary structure

21. Introduction to Neural Network What is an Artificial Neural Network? ◦ An extremely simplified model of the brain  Essentially a function approximator  Transforms inputs into outputs to the best of its ability

22. How do Neural Network Work? A neuron (perceptron) is a single layer NN The output of a neuron is a function of the weighted sum of the inputs plus a bias

23. Activation Function Binary active function ◦ f(x)=1 if x>=0 ◦ f(x)=0 otherwise The most common sigmoid function used is the logistic function ◦ f(x) = 1/(1 + e -x )

24. Multi-Layer Feedforward NN Example XOR problem (nonlinear classification capable)

25. Where Do The Weights Come From? The weights in a neural network are the most important factor in determining its function Training is the act of presenting the network with some sample data and modifying the weights to better approximate the desired function (class labels) ◦ Supervised Training  Supplies the neural network with inputs and the desired outputs  Response of the network to the inputs is measured  The weights are modified to reduce the difference between the actual and desired outputs

26. Training in Perceptron Neural Net Training a perceptron: Find the weights W that minimizes the error function: P: number of training data X i : training vectors F(W.X i ): output of the perceptron t(X i ) : target value for X i Use steepest descent: - compute gradient: - update weight vector: - iterate (e: learning rate)

27. Back-propagation algorithm For Mult-layer NN, the errors of hidden layers are not known Searches for weight values that minimize the total error of the network over the set of training examples ◦ Forward pass: Compute the outputs of all units in the network, and the error of the output layers. ◦ Backward pass: The network error is backpropogated for updating the weights (credit assignment problem).

28. 9/12/2015 Copyright G. A. Tagliarini, PhD 28 Feedforward Network Training by Backpropagation: Process Summary Select an architecture Randomly initialize weights While error is too large ◦ Select training pattern and feedforward to find actual network output ◦ Calculate errors and backpropagate error signals ◦ Adjust weights Evaluate performance using the test set

29. NN for Protein Secondary Structure Prediction 0

30. How to Encode Each Amino Acid? 20 bit binary sequence 10000000000000000000-----A 01000000000000000000-----R 00100000000000000000-----N … 00000000000000000001-----V

31. Evaluation of Performance: Accuracy(Q3) ALHEASGPSVILFGSDVTVPPASNAEQAK hhhhhooooeeeeoooeeeooooohhhhh ohhhooooeeeeoooooeeeooohhhhhh Amino acid sequence Actual Secondary Structure Q3=22/29=76% Q3 for random prediction is 33% Secondary structure assignment in real proteins is uncertain to about 10%; Therefore, a “perfect” prediction would have Q3=90%.

32. Performances(CASP) CASPYEAR # of Targets Group CASP11994663% Rost and Sander CASP219962470% Rost CASP319981875%Jones CASP420002880%Jones

33. Summary Protein bioinformatics is a very important area with many interesting problems Computational methods can have big impact in medicine and molecular biology Secondary protein structure prediction algorithms are very strong

34. Slides Acknowledgements Jinbo Xu University of Waterloo Xingquan Zhu

35. Why predict structure: Can Label Proteins by Dominant Structure Protein classification, Structural Blasting

36. Amino Acids Side chain Each amino acid is identified by its side chain, which determines the properties of this amino acid.

37. Side Chain Properties The amino acids names are colored according to their type: positively charged, negatively charged, polar but not charged, aliphatic (nonpolar), and aromatic. Amino acids that are essential to mammals are marked with an asterisk (*). hydrophobicV, L, I, M, F HydrophilicN, E, Q, H, K, R, D In-betweenG, A, S, T, Y, W, C, P Positively chargedR, H, L Negatively chargedD, E Polar but not chargedN, Q, S, T nonpolarA, G, I, L, M, P, V AromaticF, W, Y Hydrophobic amino acids stay inside of a protein, while Hydrophilic ones tend to stay in the exterior of a protein. Oppositely charged amino acids can form salt bridge. Polar amino acids can participate hydrogen bonding

38. Alpha Helix Examples

39. Beta Sheet Examples Parallel beta sheet Anti-parallel beta sheet

40. 9/12/2015 Copyright G. A. Tagliarini, PhD 40 Calculate Outputs For Each Neuron Based On The Pattern The output from neuron j for pattern p is O pj where and k ranges over the input indices and W jk is the weight on the connection from input k to neuron j FeedforwardInputs Outputs

41. 9/12/2015 Copyright G. A. Tagliarini, PhD 41 Calculate The Error Signal For Each Output Neuron The output neuron error signal  pj is given by  pj =(T pj -O pj ) O pj (1-O pj ) T pj is the target value of output neuron j for pattern p O pj is the actual output value of output neuron j for pattern p

42. 9/12/2015 Copyright G. A. Tagliarini, PhD 42 Calculate The Error Signal For Each Hidden Neuron The hidden neuron error signal  pj is given by where  pk is the error signal of a post- synaptic neuron k and W kj is the weight of the connection from hidden neuron j to the post-synaptic neuron k