Presentation on theme: "Two bioinformatics applications of dynamic Bayesian networks"— Presentation transcript:
1Two bioinformatics applications of dynamic Bayesian networks William Stafford NobleDepartment of Genome SciencesDepartment of Computer Science and EngineeringUniversity of Washington
2Outline Segmenting genomic data Matching peptides to mass spectra Background: DNA, chromatin and DNase ISimple solutionWaveletsHierarchical modelMatching peptides to mass spectraBackground: tandem mass spectrometryModeling peptide fragmentation
3The human genome in vivo Chromatin FiberGene ‘domains’NucleusTrans-factor complexDnaseIHypersensitive SiteGenesGenomicDNAPackaged into Chromatin
6A simple hidden Markov model very^OpenchromatinClosedchromatinEach state contains a single Gaussian.The model has six parameters (two transitions, two means, two standard deviations).The parameters are initialized randomly and trained in an unsupervised fashion via expectation-maximization.EM is re-started 100 times, and we select the parameters that yield the highest likelihood.The original data set is then segmented using either Viterbi or posterior decoding.
8A problem, and two solutions Problem: We are interested in phenomena occurring at multiple scales.Solution #1: Perform a wavelet smooth prior to HMM analysis.Solution #2: Build a more complex probability model.
13Change point model Four-state model: major DNase hypersensitive site (DHS),minor DHS,intermediate sensitivity region, andinsensitive region.Continuous mixture of Gaussians at each state.Gamma distribution of lengths within each region.
21Future directions Many types of genomic data Phylogenetic conservation scoresVarious histone modificationsReplication timing, etc.Perform segmentions in multiple dimensions simultaneously.Assign statistical significance to observed segments.
22Shotgun proteomics Training PSMs Test PSMs Trained Model Evaluation ProbabilityModelPSM = peptide-spectrum match
24Bayesian networkWe model peptide fragmentation using a Bayesian network.Nodes represent random variables, and edges represent conditional dependencies.Each node stores a conditional probability table (CPT) giving Pr(node|parents).Is b-ionobserved?b-ionintensity1.000.00no b-ion observed0.750.25b-ion observedintensity > 50%intensity < 50%
25Ion series modeled in a Markov chain Is b-ionobserved?Is b-ionobserved?Is b-ionobserved?Is b-ionobserved?Is b-ionobserved?b-ionintensityb-ionintensityb-ionintensityb-ionintensityb-ionintensity~ PepHMM (Han et al., 2005).
26A more realistic model Is b-ion observed? b-ion intensity N-term AA C-term AAIs iondetectable?Fractionalm/zIs protonmobile?
31An incorrect identification Bayes net: HQDETQDALNALDLLTNEKSEQUEST: LRPGAELLEGAHVGNFVEMKThis peptide does not appear in E. coli, the organism from which this protein sample was derived.Blue = b and y, green = a, red = ammonia loss, magenta = water loss, sienna = +2
32Co-eluting peptides SEQUEST: AFPEAVLFIHPLDAK Bayes net: DVFVHFSALQGNQFKSEQUEST: AFPEAVLFIHPLDAKBlue = b and y, green = a, red = ammonia loss, magenta = water loss, sienna = +2
33Future directionsBuild a single Bayesian network that includes all ion types.Produce more descriptive outputs from the Bayesian network for input to the classifier.Add more biophysical details to the model: chromatography retention time, a better mass-to-charge estimate, etc.Generate a better (larger, more accurate) gold standard data set.
34Acknowledgments DNase I hypersensitivity Wavelet analysis: Bob Thurman John StamatoyannopoulosPete SaboScott Kuehnmany others in the Stam labWavelet analysis: Bob ThurmanChange point modelCharles LawrenceHeng LianWilliam ThompsonMass spectrometryAaron KlammerJeff BilmesSheila ReynoldsMichael MacCoss