Non-Homogeneous Hidden Markov Model Qingyuan Liu Introduction (Why - PowerPoint PPT Presentation

Non-Homogeneous Hidden Markov Model Qingyuan Liu

Introduction (Why Homogeneous HMM) • Classify new sequences into new family • Add related sequences into MSA • Compute MSA for groups of related sequence

Introduction (Building a HMM) • Seed sequences for HMM building • Ultra-large multiple sequence alignment using Phylogeny-aware Profiles (UPP) • Parameter – Emission Probability – Transition Probability

Background (Long Indels) • HMM can not deal with long indels. • Example: 10 consecutive residue loss • Assume 0.5 for each deletion transition probability • 0.5 10 is extremely small

Significance • Cause: Emission probability is fixed • Do HMM non-homogeneously instead – Emission probability is not fixed – Different parameters for different cases

Project • Literature review for how to build a nonhomogeneous HMM. • Propose ideas for how to build an non-homogeneous HMM for MSA • Literature review for other possible MSA methods to deal with long indels • Combined tree- and profile-based alignment • Simulation based approach • Group-to-group sequence alignment

Literature: • Sarkar, Abhra, Anindya Bhadra, and Bani K. Mallick. "Nonparametric Bayesian Approaches to Non-homogeneous Hidden Markov Models.” (n.d.): n. pag. 8 May 2012. Web. 4 Apr. 2017. • Ghavidel, Fatemeh Zamanzad, Jargen Claesen, and Tomasz Burzykowski. "A Nonhomogeneous Hidden Markov Model for Gene Mapping Based on Next- Generation Sequencing Data." Journal of Computational Biology 22.2 (2015): 178-88. Web. • Grzegorczyk, Marco. "A Non-homogeneous Dynamic Bayesian Network with a Hidden Markov Model Dependency Structure among the Temporal Data Points." Machine Learning 102.2 (2015): 155-207. Web. • Gowri-Shankar, V., & Rattray, M. (2007). A Reversible Jump Method for Bayesian Phylogenetic Inference with a Nonhomogeneous Substitution Model. Molecular Biology and Evolution,24 (6), 1286-1299. doi:10.1093/molbev/ msm046. • Aalen, O., & Johansen, S. (1978). An Empirical Transition Matrix for Non- Homogeneous Markov Chains Based on Censored Observations. Scandinavian Journal of Statistics, 5 (3), 141-150. Retrieved from http://www.jstor.org/stable/ 4615704

Literature: • Vassiliou, P. G. (1997). The evolution of the theory of non ‐ homogeneous Markov systems. Applied Stochastic Models and Data Analysis,13 (34), 159-176. doi:10.1002/(sici)1099-0747(199709/12)13:3/4<159::aid-asm309>3.3.co;2-h • Loytynoja, A., & Goldman, N. (2008). A model of evolution and structure for multiple sequence alignment. Philosophical Transactions of the Royal Society B: Biological Sciences,363 (1512), 3913-3919. doi:10.1098/rstb.2008.0170 • Karin, E. L., Rabin, A., Ashkenazy, H., Shkedy, D., Avram, O., Cartwright, R. A., & Pupko, T. (2015). Inferring Indel Parameters using a Simulation-based Approach. Genome Biology and Evolution,7 (12), 3226-3238. doi:10.1093/gbe/ evv212 • Yamada, S., Gotoh, O., & Yamana, H. (2006). BMC Bioinformatics,7 (1), 524. doi:10.1186/1471-2105-7-524

Non-Homogeneous Hidden Markov Model Qingyuan Liu Introduction (Why - PowerPoint PPT Presentation

Non-Homogeneous Hidden Markov Model Qingyuan Liu Introduction (Why Homogeneous HMM) Classify new sequences into new family Add related sequences into MSA Compute MSA for groups of related sequence Introduction (Building a HMM)

Hidden Markov Models Pratik Lahiri Introduction A hidden Markov model (HMM) is a

Hidden Markov Model (HMM) Sensor Markov assumption: P ( E t | X 0: t , E 1: t 1 ) = P ( E t | X

Multivariate Hidden Markov model An application to study correlations among cryptocurrency

A C Standard model has 1-1 correspondence between symbols and states, P(A | T) thus P ( x i

The Hidden Markov The Hidden Markov Model (HMM) Model (HMM) 1 Lecture Outline Lecture Outline

Non-Homogeneous Hidden Markov Chain Models for Wavelet-Based Hyperspectral Image Processing

Hidden Markov Models Markov Model (Finite State Machine with Probs) Modeling a sequence of

Hidden Markov Models Training Selecting model parameters What we know The terminology and

Lecture 9: Hidden Markov Model Kai-Wei Chang CS @ University of Virginia kw@kwchang.net Couse

Markov Models Kunsch, H.R., State Space and Hidden Markov Models . ETH- Zurich, Zurich;

1 X 1 X 2 X 3 Ghostbusters HMM Chain Rule and HMMs E 1 E 2 E 3 P(X 1 ) = uniform 1/9 1/9

Hidden Markov Models (HMM) Many slides from Michael Collins and HMMs Overview I The Tagging

Hidden Markov Model, Kalman Filter and A Unifying View Mu Li April 16, 2013 Outline Hidden

Markov chains and Hidden Markov Models 9000 Markov chains and HMMs We will discuss: Markov

Tagging Problems, and Hidden Markov Models Michael Collins, Columbia University Overview The

1 Real HMM Examples Real HMM Examples Speech recognition HMMs: Machine translation HMMs:

Non-Parametric Inference of Transition Probabilities Based on Aalen-Johansen Integral Estimators

Community Employment (CE) Sponsor Briefing Pack j Appreciation The Department would like to

Welcome 1 Martin Conway Engagement and Participation Officer VoiCeS Northumberland

ThinkForward Daniel Gray Childrens Partnership Board, January 2017 ThinkForward was founded

Further development of transfer and exposure models and application to scenarios Activities

rt ts r rs rt

WELCOME THE UNIVERSITY OFUTAH Planning, Design & Construction Forum May 9th,2019

Process Intensification in Small Scale Pharmaceutical Production Aleksandar Mitic Prof. Krist V.

Non-Homogeneous Hidden Markov Model Qingyuan Liu Introduction (Why - PowerPoint PPT Presentation

Non-Homogeneous Hidden Markov Model Qingyuan Liu Introduction (Why Homogeneous HMM) Classify new sequences into new family Add related sequences into MSA Compute MSA for groups of related sequence Introduction (Building a HMM)

Hidden Markov Models Pratik Lahiri Introduction A hidden Markov model (HMM) is a

Hidden Markov Model (HMM) Sensor Markov assumption: P ( E t | X 0: t , E 1: t 1 ) = P ( E t | X

Multivariate Hidden Markov model An application to study correlations among cryptocurrency

A C Standard model has 1-1 correspondence between symbols and states, P(A | T) thus P ( x i

The Hidden Markov The Hidden Markov Model (HMM) Model (HMM) 1 Lecture Outline Lecture Outline

Non-Homogeneous Hidden Markov Chain Models for Wavelet-Based Hyperspectral Image Processing

Hidden Markov Models Markov Model (Finite State Machine with Probs) Modeling a sequence of

Hidden Markov Models Training Selecting model parameters What we know The terminology and

Lecture 9: Hidden Markov Model Kai-Wei Chang CS @ University of Virginia kw@kwchang.net Couse

Markov Models Kunsch, H.R., State Space and Hidden Markov Models . ETH- Zurich, Zurich;

1 X 1 X 2 X 3 Ghostbusters HMM Chain Rule and HMMs E 1 E 2 E 3 P(X 1 ) = uniform 1/9 1/9

Hidden Markov Models (HMM) Many slides from Michael Collins and HMMs Overview I The Tagging

Hidden Markov Model, Kalman Filter and A Unifying View Mu Li April 16, 2013 Outline Hidden

Markov chains and Hidden Markov Models 9000 Markov chains and HMMs We will discuss: Markov

Tagging Problems, and Hidden Markov Models Michael Collins, Columbia University Overview The

1 Real HMM Examples Real HMM Examples Speech recognition HMMs: Machine translation HMMs:

Non-Parametric Inference of Transition Probabilities Based on Aalen-Johansen Integral Estimators

Community Employment (CE) Sponsor Briefing Pack j Appreciation The Department would like to

Welcome 1 Martin Conway Engagement and Participation Officer VoiCeS Northumberland

ThinkForward Daniel Gray Childrens Partnership Board, January 2017 ThinkForward was founded

Further development of transfer and exposure models and application to scenarios Activities

rt ts r rs rt

WELCOME THE UNIVERSITY OFUTAH Planning, Design &amp; Construction Forum May 9th,2019

Process Intensification in Small Scale Pharmaceutical Production Aleksandar Mitic Prof. Krist V.

WELCOME THE UNIVERSITY OFUTAH Planning, Design & Construction Forum May 9th,2019