Hierarchically-coupled hidden Markov models for learning kinetic rates from single-molecule data

Jan-Willem Meent, Jonathan Bronson, Frank Wood, Ruben Gonzalez Jr., Chris Wiggins
; Proceedings of the 30th International Conference on Machine Learning, PMLR 28(2):361-369, 2013.

Abstract

We address the problem of analyzing sets of noisy time-varying signals that all report on the same process but confound straightforward analyses due to complex inter-signal heterogeneities and measurement artifacts. In particular we consider single-molecule experiments which indirectly measure the distinct steps in a biomolecular process via observations of noisy time-dependent signals such as a fluorescence intensity or bead position. Straightforward hidden Markov model (HMM) analyses attempt to characterize such processes in terms of a set of conformational states, the transitions that can occur between these states, and the associated rates at which those transitions occur; but require ad-hoc post-processing steps to combine multiple signals. Here we develop a hierarchically coupled HMM that allows experimentalists to deal with inter-signal variability in a principled and automatic way. Our approach is a generalized expectation maximization hyperparameter point estimation procedure with variational Bayes at the level of individual time series that learns an single interpretable representation of the overall data generating process.

Cite this Paper


BibTeX
@InProceedings{pmlr-v28-willemvandemeent13, title = {Hierarchically-coupled hidden {M}arkov models for learning kinetic rates from single-molecule data}, author = {Jan-Willem Meent and Jonathan Bronson and Frank Wood and Ruben Gonzalez Jr. and Chris Wiggins}, pages = {361--369}, year = {2013}, editor = {Sanjoy Dasgupta and David McAllester}, volume = {28}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/willemvandemeent13.pdf}, url = {http://proceedings.mlr.press/v28/willemvandemeent13.html}, abstract = {We address the problem of analyzing sets of noisy time-varying signals that all report on the same process but confound straightforward analyses due to complex inter-signal heterogeneities and measurement artifacts. In particular we consider single-molecule experiments which indirectly measure the distinct steps in a biomolecular process via observations of noisy time-dependent signals such as a fluorescence intensity or bead position. Straightforward hidden Markov model (HMM) analyses attempt to characterize such processes in terms of a set of conformational states, the transitions that can occur between these states, and the associated rates at which those transitions occur; but require ad-hoc post-processing steps to combine multiple signals. Here we develop a hierarchically coupled HMM that allows experimentalists to deal with inter-signal variability in a principled and automatic way. Our approach is a generalized expectation maximization hyperparameter point estimation procedure with variational Bayes at the level of individual time series that learns an single interpretable representation of the overall data generating process.} }
Endnote
%0 Conference Paper %T Hierarchically-coupled hidden Markov models for learning kinetic rates from single-molecule data %A Jan-Willem Meent %A Jonathan Bronson %A Frank Wood %A Ruben Gonzalez Jr. %A Chris Wiggins %B Proceedings of the 30th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2013 %E Sanjoy Dasgupta %E David McAllester %F pmlr-v28-willemvandemeent13 %I PMLR %J Proceedings of Machine Learning Research %P 361--369 %U http://proceedings.mlr.press %V 28 %N 2 %W PMLR %X We address the problem of analyzing sets of noisy time-varying signals that all report on the same process but confound straightforward analyses due to complex inter-signal heterogeneities and measurement artifacts. In particular we consider single-molecule experiments which indirectly measure the distinct steps in a biomolecular process via observations of noisy time-dependent signals such as a fluorescence intensity or bead position. Straightforward hidden Markov model (HMM) analyses attempt to characterize such processes in terms of a set of conformational states, the transitions that can occur between these states, and the associated rates at which those transitions occur; but require ad-hoc post-processing steps to combine multiple signals. Here we develop a hierarchically coupled HMM that allows experimentalists to deal with inter-signal variability in a principled and automatic way. Our approach is a generalized expectation maximization hyperparameter point estimation procedure with variational Bayes at the level of individual time series that learns an single interpretable representation of the overall data generating process.
RIS
TY - CPAPER TI - Hierarchically-coupled hidden Markov models for learning kinetic rates from single-molecule data AU - Jan-Willem Meent AU - Jonathan Bronson AU - Frank Wood AU - Ruben Gonzalez Jr. AU - Chris Wiggins BT - Proceedings of the 30th International Conference on Machine Learning PY - 2013/02/13 DA - 2013/02/13 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-willemvandemeent13 PB - PMLR SP - 361 DP - PMLR EP - 369 L1 - http://proceedings.mlr.press/v28/willemvandemeent13.pdf UR - http://proceedings.mlr.press/v28/willemvandemeent13.html AB - We address the problem of analyzing sets of noisy time-varying signals that all report on the same process but confound straightforward analyses due to complex inter-signal heterogeneities and measurement artifacts. In particular we consider single-molecule experiments which indirectly measure the distinct steps in a biomolecular process via observations of noisy time-dependent signals such as a fluorescence intensity or bead position. Straightforward hidden Markov model (HMM) analyses attempt to characterize such processes in terms of a set of conformational states, the transitions that can occur between these states, and the associated rates at which those transitions occur; but require ad-hoc post-processing steps to combine multiple signals. Here we develop a hierarchically coupled HMM that allows experimentalists to deal with inter-signal variability in a principled and automatic way. Our approach is a generalized expectation maximization hyperparameter point estimation procedure with variational Bayes at the level of individual time series that learns an single interpretable representation of the overall data generating process. ER -
APA
Meent, J., Bronson, J., Wood, F., Gonzalez Jr., R. & Wiggins, C.. (2013). Hierarchically-coupled hidden Markov models for learning kinetic rates from single-molecule data. Proceedings of the 30th International Conference on Machine Learning, in PMLR 28(2):361-369

Related Material