Neural Networks for Protein Structure Prediction Brown, JMB 1999OutlineWhat is Protein Structure?PowerPoint PresentationSlide 5Protein StructureWhat is “secondary structure”?Slide 8Slide 9Secondary structure predictionA survey of structure predictionSlide 12Slide 13What’s multiple alignment doing here ?Slide 15Slide 16The PSI-PRED algorithmGeneration of sequence profileThe sequence profile looks like thisPreparing for the second stepIntro to Neural nets (the second and third steps of PSIPRED)Artificial Neural NetworkSlide 23Layered ArchitectureSlide 25What a unit (neuron) doesWeights, bias and transfer functionSlide 28Where’s the algorithm?Back to PSIPRED …Step 2Slide 32Step 3Test of performanceCross-validationNeural Networks for Protein Structure PredictionBrown, JMB 1999CS 498 SSSaurabh SinhaOutline•Goal is to predict “secondary structure” of a protein from its sequence•Artificial Neural Network used for this task•Evaluation of prediction accuracyWhat is Protein Structure?http://academic.brooklyn.cuny.edu/biology/bio4fv/page/3d_prot.htmhttp://matcmadison.edu/biotech/resources/proteins/labManual/images/220_04_114.pngProtein Structure•An amino acid sequence “folds” into a complex 3-D structure•Finding out this 3-D structure is a crucial and challenging task•Experimental methods (e.g., X-ray crystallography) are very tedious•Computational predictions are a possibility, but very difficultWhat is “secondary structure”?http://www.wiley.com/college/pratt/0471393878/student/structure/secondary_structure/secondary_structure.gif“Strand” “Helix”http://www.npaci.edu/features/00/Mar/protein.jpg“Strand”“Helix”Secondary structure prediction•Well, the whole 3-D “tertiary” protein structure may be hard to predict from sequence•But can we at least predict the secondary structural elements such as “strand”, “helix” or “coil”?•This is what this paper does•.. and so do many other papers (it is a hard problem !)A survey of structure prediction•The most reliable technique is “comparative modeling”–Find a protein P whose amino acid sequence is very similar to your “target” protein T–Hope that this other protein P does have a known structure–Predict a similar structure similar to that of P, after carefully considering how the sequences of P and T differA survey of structure prediction•Comparative modeling fails if we don’t have a suitable homologous “template” protein P for our protein T•“Ab initio” tertiary methods attempt to predict the structure without using a protein structure–Incorporate basic physical and chemical principles into the structure calculation–Gets very hairy, and highly computationally intensive•The other option is prediction of secondary structure only (i.e., making the goal more modest)–These may be used to provide constraints for tertiary structure predictionSecondary structure prediction•Early methods were based on stereochemical principles•Later methods realized that we can do better if we use not only the one sequence T (our sequence), but also a family of “related sequences”•Search for sequences similar to T, build a multiple alignment of these, and predict secondary structure from the multiple alignment of sequenceWhat’s multiple alignment doing here ?•Most conserved regions of a protein sequence are either functionally important or buried in the protein “core”•More variable regions are usually on surface of the protein, –there are few constraints on what type of amino acids have to be here (apart from bias towards hydrophilic residues)•Multiple alignment tells us which portions are conserved and which are nothttp://bio.nagaokaut.ac.jp/~mbp-lab/img/hpc.pnghydrophobic coreWhat’s multiple alignment doing here ?•Therefore, by looking at multiple alignment, we could predict which residues are in the core of the protein and which are on the surface (“solvent accessibility”)•Secondary structure then predicted by comparing the accessibility patterns associated with helices, strands etc.•This approach (Benner & Gerloff) mostly manual•Today’s paper suggest an automated methodThe PSI-PRED algorithm•Given an amino-acid sequence, predict secondary structure elements in the protein •Three stages:1. Generation of a sequence profile (the “multiple alignment” step)2. Prediction of an initial secondary structure (the neural network step)3. Filtering of the predicted structure (another neural network step)Generation of sequence profile•A BLAST-like program called “PSI-BLAST” used for this step•We saw BLAST earlier -- it is a fast way to find high scoring local alignments•PSI-BLAST is an iterative approach–an initial scan of a protein database using the target sequence T–align all matching sequences to construct a “sequence profile”–scan the database using this new profile•Can also pick out and align distantly related protein sequences for our target sequence TThe sequence profile looks like this• Has 20 x M numbers• The numbers are log likelihood of each residue at each positionPreparing for the second step•Feed the sequence profile to an artificial neural network•But before feeding, do a simply “scaling” to bring the numbers to 0-1 scale€ x →11+ e−xIntro to Neural nets (the second and third steps of PSIPRED)Artificial Neural Network•Supervised learning algorithm•Training examples. Each example has a label –“class” of the example, e.g., “positive” or “negative”–“helix”, “strand”, or “coil”•Learns how to predict the class of an exampleArtificial Neural Network•Directed graph•Nodes or “units” or “neurons”•Edges between units•Each edge has a weight (not known a priori)Layered ArchitectureInput here is a four-dimensional vector. Each dimension goesinto one input unithttp://www.akri.org/cognition/images/annet2.gifLayered Architecturehttp://www.geocomputation.org/2000/GC016/GC016_01.GIF(units)What a unit (neuron) does•Unit i receives a total input xi from the units connected to it, and produces an output yi = fi(xi) where fi() is the “transfer function” of unit i€ xi= wijyj+ wij ∈N −{i}∑yi= fi(xi) = fiwijyj+ wij ∈N −{i}∑ ⎛ ⎝ ⎜ ⎜ ⎞ ⎠ ⎟ ⎟wi is called the “bias” of the unitWeights, bias and transfer functionUnit takes n inputsEach input edge has weight wiBias bOutput aTransfer function f()Linear, Sigmoidal, or
View Full Document
Unlocking...