Foundations of probabilistic inference with uncertain evidence

Groen, Frank; Mosleh, Ali

doi:10.1016/j.ijar.2004.09.001

Cited by 32 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The statistical basis for the SLiC method is derived from estimating the probabilistic distance from a measured mass and time pair, M i ϭ (m i , t i ), to the center of a sampling distribution, and then applying Bayes theorem to estimate the likelihood that the point is from that sampling distribution when the results are non-specific [32].…”

Section: Slic Score Calculationmentioning

confidence: 99%

The Utility of Accurate Mass and LC Elution Time Information in the Analysis of Complex Proteomes

Norbeck

Monroe

Adkins

et al. 2005

J. Am. Soc. Mass Spectrom.

View full text Add to dashboard Cite

The combination of mass and normalized elution time (NET) of a peptide identified by liquid chromatography-mass spectrometry (LC-MS) measurements can serve as a unique signature for that peptide. However, the specificity of an LC-MS measurement depends upon the complexity of the proteome (i.e., the number of possible peptides) and the accuracy of the LC-MS measurements. In this work, theoretical tryptic digests of all predicted proteins from the genomes of three organisms of varying complexity were evaluated for specificity. Accuracy of the LC-MS measurement of mass-NET pairs (on a 0 to 1.0 NET scale) was described by bivariate normal sampling distributions centered on the peptide signatures. Measurement accuracy (i.e., mass and NET standard deviations of Ϯ0.1, 1, 5, and 10 ppm, and Ϯ0.01 and 0.05, respectively) was varied to evaluate improvements in process quality. The spatially localized confidence score, a conditional probability of peptide uniqueness, formed the basis for the peptide identification. Application of this approach to organisms with comparatively small proteomes, such as Deinococcus radiodurans, shows that modest mass and elution time accuracies are generally adequate for confidently identifying most peptides. For more complex proteomes, more accurate measurements are required. However, the study suggests that the majority of proteins for even the human proteome should be identifiable with reasonable confidence by using LC-MS measurements with mass accuracies within Ϯ1 ppm and high efficiency separations having elution time measurements within Ϯ0.01

show abstract

Section: Slic Score Calculationmentioning

confidence: 99%

The Utility of Accurate Mass and LC Elution Time Information in the Analysis of Complex Proteomes

Norbeck

Monroe

Adkins

et al. 2005

J. Am. Soc. Mass Spectrom.

View full text Add to dashboard Cite

show abstract

“…The analysis of uncertain data, especially in a Bayesian context, has been the subject of significant literature (for example see [33]). This paper does not seek to replicate or extend previous work.…”

Section: Treatment Of Uncertain Datamentioning

confidence: 99%

Bayesian inference with overlapping data: Reliability estimation of multi-state on-demand continuous life metric systems with uncertain evidence

Jackson

Mosleh

2016

Reliability Engineering & System Safety

Self Cite

View full text Add to dashboard Cite

“…Two modeling approaches are offered for the use of credibility and applicability information in assessing the uncertainty about a single‐valued continuous unknown X given estimates provided by a model. These are: (1) a Bayesian model output adjustment approach where the credibility and applicability of a model are considered as evidence concerning model error; and (2) a weighted likelihood method (WLM), where credibility and applicability measures are used to change the likelihood function (the reader may refer to Groen and Mosleh for a detailed discussion on the WLM).…”

Section: Mathematical Frameworkmentioning

confidence: 99%

Bayesian Treatment of Model Uncertainty for Partially Applicable Models

Droguett

Mosleh

2013

Risk Analysis

Self Cite

View full text Add to dashboard Cite

This article discusses how analyst's or expert's beliefs on the credibility and quality of models can be assessed and incorporated into the uncertainty assessment of an unknown of interest. The proposed methodology is a specialization of the Bayesian framework for the assessment of model uncertainty presented in an earlier paper. This formalism treats models as sources of information in assessing the uncertainty of an unknown, and it allows the use of predictions from multiple models as well as experimental validation data about the models' performances. In this article, the methodology is extended to incorporate additional types of information about the model, namely, subjective information in terms of credibility of the model and its applicability when it is used outside its intended domain of application. An example in the context of fire risk modeling is also provided.

show abstract

Foundations of probabilistic inference with uncertain evidence

Cited by 32 publications

References 20 publications

The Utility of Accurate Mass and LC Elution Time Information in the Analysis of Complex Proteomes

The Utility of Accurate Mass and LC Elution Time Information in the Analysis of Complex Proteomes

Bayesian inference with overlapping data: Reliability estimation of multi-state on-demand continuous life metric systems with uncertain evidence

Bayesian Treatment of Model Uncertainty for Partially Applicable Models

Contact Info

Product

Resources

About