Computational aspects of DNA mixture analysis

Therese Graversen; Steffen L. Lauritzen

doi:10.1007/s11222-014-9451-7

Computational aspects of DNA mixture analysis

15 Citations (Scopus)

Abstract

Statistical analysis of DNA mixtures for forensic identification is known to pose computational challenges due to the enormous state space of possible DNA profiles. We describe a general method for computing the expectation of a product of discrete random variables using auxiliary variables and probability propagation in a Bayesian network. We propose a Bayesian network representation for genotypes, allowing computations to be performed locally involving only a few alleles at each step. Exploiting appropriate auxiliary variables in combination with this representation allows efficient computation of the likelihood function and prediction of genotypes of unknown contributors. Importantly, we exploit the computational structure to introduce a novel set of diagnostic tools for assessing the adequacy of the model for describing a particular dataset.

Original language	English
Journal	Statistics and Computing
Volume	25
Issue number	3
Pages (from-to)	527-541
Number of pages	15
ISSN	0960-3174
DOIs	https://doi.org/10.1007/s11222-014-9451-7
Publication status	Published - 2015
Externally published	Yes

Access to Document

10.1007/s11222-014-9451-7

Cite this

@article{960217216dc74c3197702a38d3172c62,

title = "Computational aspects of DNA mixture analysis",

abstract = "Statistical analysis of DNA mixtures for forensic identification is known to pose computational challenges due to the enormous state space of possible DNA profiles. We describe a general method for computing the expectation of a product of discrete random variables using auxiliary variables and probability propagation in a Bayesian network. We propose a Bayesian network representation for genotypes, allowing computations to be performed locally involving only a few alleles at each step. Exploiting appropriate auxiliary variables in combination with this representation allows efficient computation of the likelihood function and prediction of genotypes of unknown contributors. Importantly, we exploit the computational structure to introduce a novel set of diagnostic tools for assessing the adequacy of the model for describing a particular dataset.",

author = "Therese Graversen and Lauritzen, {Steffen L.}",

year = "2015",

doi = "10.1007/s11222-014-9451-7",

language = "English",

volume = "25",

pages = "527--541",

journal = "Statistics and Computing",

issn = "0960-3174",

publisher = "Springer",

number = "3",

}

TY - JOUR

T1 - Computational aspects of DNA mixture analysis

AU - Graversen, Therese

AU - Lauritzen, Steffen L.

PY - 2015

Y1 - 2015

N2 - Statistical analysis of DNA mixtures for forensic identification is known to pose computational challenges due to the enormous state space of possible DNA profiles. We describe a general method for computing the expectation of a product of discrete random variables using auxiliary variables and probability propagation in a Bayesian network. We propose a Bayesian network representation for genotypes, allowing computations to be performed locally involving only a few alleles at each step. Exploiting appropriate auxiliary variables in combination with this representation allows efficient computation of the likelihood function and prediction of genotypes of unknown contributors. Importantly, we exploit the computational structure to introduce a novel set of diagnostic tools for assessing the adequacy of the model for describing a particular dataset.

AB - Statistical analysis of DNA mixtures for forensic identification is known to pose computational challenges due to the enormous state space of possible DNA profiles. We describe a general method for computing the expectation of a product of discrete random variables using auxiliary variables and probability propagation in a Bayesian network. We propose a Bayesian network representation for genotypes, allowing computations to be performed locally involving only a few alleles at each step. Exploiting appropriate auxiliary variables in combination with this representation allows efficient computation of the likelihood function and prediction of genotypes of unknown contributors. Importantly, we exploit the computational structure to introduce a novel set of diagnostic tools for assessing the adequacy of the model for describing a particular dataset.

U2 - 10.1007/s11222-014-9451-7

DO - 10.1007/s11222-014-9451-7

M3 - Journal article

SN - 0960-3174

VL - 25

SP - 527

EP - 541

JO - Statistics and Computing

JF - Statistics and Computing

IS - 3

ER -

Computational aspects of DNA mixture analysis

Abstract

Access to Document

Fingerprint

Cite this