Bayesian matching of unlabeled marked point sets using random fields, with an application to molecular alignment

  title={Bayesian matching of unlabeled marked point sets using random fields, with an application to molecular alignment},
  author={Irina Czogiel and Ian L. Dryden and Christopher J. Brignell},
  journal={The Annals of Applied Statistics},
Statistical methodology is proposed for comparing unlabeled marked point sets, with an application to aligning steroid molecules in chemoinformatics. Methods from statistical shape analysis are combined with techniques for predicting random fields in spatial statistics in order to define a suitable measure of similarity between two marked point sets. Bayesian modeling of the predicted field overlap between pairs of point sets is proposed, and posterior inference of the alignment is carried out… 

Figures and Tables from this paper

Matching markers and unlabeled configurations in protein gels

The methodology is successfully used to automatically locate and remove a grossly misallocated marker within the given data set.

Bayesian comparison of protein structures using partial Procrustes distance

This paper provides a Bayesian model to alignprotein structures, by considering the effect of both local and global geometric information of protein structures, which is much more efficient than previous approaches.

MAD‐Bayes matching and alignment for labelled and unlabelled configurations

Inference based on the models like those in Green and Mardia (2006) and Fallaize et al. (2014), using MAD-Bayes, nicely bridge the gap between Bayesian and optimisation approaches to inferring matching and alignme t.

Probabilistic Model for Robust Affine and Non-Rigid Point Set Matching

In this work, we propose a combinative strategy based on regression and clustering for solving point set matching problems under a Bayesian framework, in which the regression estimates the

Bayesian Registration of Functions and Curves

This work focuses on two applications involving the classification of mo use vertebrae shape outlines and the alignment of mass spectrometry data in proteomics, represented using the recently introduced quare root velocity function, which enables a warping invariant elastic distance to be calculated in a straightforward manner.

Bayesian alignment of proteins via Delaunay tetrahedralization

This method uses Delaunay tetrahedralization to add a priori structural information of protein in the Bayesian methodology and shows advantages over competing methods in achieving a global alignment of proteins, accelerating the convergence rate and improving the parameter estimates.

Fibre optic sensing of ageing railway infrastructure enhanced with statistical shape analysis

Developing early-warning sensor-based maintenance systems for ageing railway infrastructure, such as masonry arch bridges, can be a challenging task due to the difficulty of identifying

Fibre optic sensing of ageing railway infrastructure enhanced with statistical shape analysis

A new method of applying statistical modelling and machine learning to enhance the interpretation of fibre optic sensing data, and, therefore, improve deterioration monitoring of railway infrastructure.



Statistical Analysis of Unlabeled Point Sets: Comparing Molecules in Chemoinformatics

Application of Bayesian methodology to a set of steroid molecules illustrates its potential utility involving the comparison of molecules in chemoinformatics and bioinformatics.

Bayesian alignment using hierarchical models, with applications in protein bioinformatics

This paper introduces hierarchical models for shape analysis tasks, in which the points in the configurations are either unlabelled or have at most a partial labelling constraining the matching, and in which some points may only appear in one of the configurations.

Bayesian matching of unlabelled point sets using Procrustes and configuration models

An improvement to the existing Procrustes algorithm is proposed which improves convergence rates, using occasional large jumps in the burn-in period and a connection between the two models is made using a Laplace approximation.

Alignment of Multiple Configurations Using Hierarchical Models

The two-configuration matching approach of Green and Mardia (2006) is extended to the multiple configuration setting, based on the introduction of a set of hidden locations underlying the observed configuration points, resulting in a simplified formulation of the model.

Random fields of multivariate test statistics, with applications to shape analysis

Our data are random fields of multivariate Gaussian observations, and we fit a multivariate linear model with common design matrix at each point. We are interested in detecting those points where

Fast Bayesian Shape Matching Using Geometric Algorithms

A Bayesian approach to comparison of geometric shapes with applications to classication of the molecular structures of proteins is presented, and computationally approximation algorithms based on a geometric hashing algorithm which is suitable for fully Bayesian shape matching against large databases are explored.

Structure-activity relationships from molecular similarity matrices.

The results show that data matrices derived from molecular similarity calculations can provide the basis for rapid elucidation of both qualitative and quantitative structure-activity relationships.

Hierarchical Grouping to Optimize an Objective Function

Abstract A procedure for forming hierarchical groups of mutually exclusive subsets, each of which has members that are maximally similar with respect to specified characteristics, is suggested for

An Approach to Statistical Spatial-Temporal Modeling of Meteorological Fields

Abstract In this article we develop a random field model for the mean temperature over the region in the northern United States covering eastern Montana through the Dakotas and northern Nebraska up