Outlier Detection using Projection Quantile Regression for Mass Spectrometry Data with Low Replication

Eo, Soo-Heang; Pak, Daewoo; Choi, Jae Boong; Cho, Hyungjun

doi:10.1186/1756-0500-5-236

Cited by 7 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Outlier detection has been tackled for mass spectrometry by calculating the Mahalanobis distance a distribution gives to all other experimental runs and eliminating those with suspiciously high distances [30] . Another algorithm uses projection and quantile regression to discard values that do not follow the general trend given by the data set [31] , but is computationally intensive for many data points. These methods are useful for removing experimental runs that exhibit high variation, but not for defining outliers within a data set.…”

Section: Discussionmentioning

confidence: 99%

Quantitative Characterization of Cellular Membrane-Receptor Heterogeneity through Statistical and Computational Modeling

Weddell

Imoukhuede

2014

PLoS ONE

View full text Add to dashboard Cite

Cell population heterogeneity can affect cellular response and is a major factor in drug resistance. However, there are few techniques available to represent and explore how heterogeneity is linked to population response. Recent high-throughput genomic, proteomic, and cellomic approaches offer opportunities for profiling heterogeneity on several scales. We have recently examined heterogeneity in vascular endothelial growth factor receptor (VEGFR) membrane localization in endothelial cells. We and others processed the heterogeneous data through ensemble averaging and integrated the data into computational models of anti-angiogenic drug effects in breast cancer. Here we show that additional modeling insight can be gained when cellular heterogeneity is considered. We present comprehensive statistical and computational methods for analyzing cellomic data sets and integrating them into deterministic models. We present a novel method for optimizing the fit of statistical distributions to heterogeneous data sets to preserve important data and exclude outliers. We compare methods of representing heterogeneous data and show methodology can affect model predictions up to 3.9-fold. We find that VEGF levels, a target for tuning angiogenesis, are more sensitive to VEGFR1 cell surface levels than VEGFR2; updating VEGFR1 levels in the tumor model gave a 64% change in free VEGF levels in the blood compartment, whereas updating VEGFR2 levels gave a 17% change. Furthermore, we find that subpopulations of tumor cells and tumor endothelial cells (tEC) expressing high levels of VEGFR (>35,000 VEGFR/cell) negate anti-VEGF treatments. We show that lowering the VEGFR membrane insertion rate for these subpopulations recovers the anti-angiogenic effect of anti-VEGF treatment, revealing new treatment targets for specific tumor cell subpopulations. This novel method of characterizing heterogeneous distributions shows for the first time how different representations of the same data set lead to different predictions of drug efficacy.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantitative Characterization of Cellular Membrane-Receptor Heterogeneity through Statistical and Computational Modeling

Weddell

Imoukhuede

2014

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…M is the difference between the duplicate samples and A is the average of the duplicate samples [30, 31]. Samples that fell outside the lower 25% and upper 25% quantiles of this MA-plot were rejected (Additional file 4).…”

Section: Methodsmentioning

confidence: 99%

Serological markers to measure recent changes in malaria at population level in Cambodia

Kerkhof

Sluydts

Willen

et al. 2016

Malar J

View full text Add to dashboard Cite

BackgroundSerological markers for exposure to different Plasmodium species have recently been used in multiplex immunoassays based on the Luminex technology. However, interpretation of the assay results requires consideration of the half-life of specific antibodies against these markers. Therefore, the aim of the present study was to document the half-life of malaria specific serological makers, as well as assessing the sensitivity of these markers to pick up recent changes in malaria exposure.MethodsA recently developed multiplex immunoassay was used to measure the intensity of antibody (Ab) responses against 19 different Plasmodium specific antigens, covering different human malaria parasites and two vector saliva antigens. Therefore, 8439 blood samples from five cross-sectional surveys in Ratanakiri, Cambodia, were analysed. These involve a random selection from two selected surveys, and an additional set of blood samples of individuals that were randomly re-sampled three, four or five times. A generalized estimating equation model and linear regression models were fitted on log transformed antibody intensity data.ResultsResults showed that most (17/21) Ab-responses are higher in PCR positive than PCR negative individuals. Furthermore, these antibody-responses follow the same upward trend within each age group. Estimation of the half-lives showed differences between serological markers that reflect short- (seasonal) and long-term (year round) transmission trends. Ab levels declined significantly together with a decrease of PCR prevalence in a group of malaria endemic villages.ConclusionFor Plasmodium falciparum, antibodies against LSA3.RE, GLURP and Pf.GLURP.R2 are most likely to be a reflexion of recent (range from 6 to 8 months) exposure in the Mekong Subregion. PvEBP is the only Plasmodium vivax Ag responding reasonably well, in spite of an estimated Ab half-life of more than 1 year. The use of Ab intensity data rather dichotomizing the continuous Ab-titre data (positive vs negative) will lead to an improved approach for serological surveillance.Electronic supplementary materialThe online version of this article (doi:10.1186/s12936-016-1576-z) contains supplementary material, which is available to authorized users.

show abstract

“…Three different algorithms to detect outlying observations in survival data based on censored quantile regression have been proposed [4]: residualbased, boxplot and scoring. The residual-based and boxplot algorithms were developed by modifying existing ones, [2] and [18] respectively, and the scoring algorithm was introduced to provide the outlying magnitude of each point from the distribution of observations and to enable the determination of a threshold by visualizing the scores. Notice that in each run of the algorithm, the 0.5 th conditional quantile, Q(0.50|x i ), must be estimated, and its estimation is not always reliable.…”

Section: Outlier Detection In Censored Quantile Regressionmentioning

confidence: 99%

“…Boxplot algorithm is a modification of the algorithm used by [18] using quantile regression for censored data.…”

Section: Outlier Detection In Censored Quantile Regressionmentioning

confidence: 99%

Consensus outlier detection in survival analysis using the rank product test

Carrasquinha

Veríssimo

Vinga³

2018

Preprint

View full text Add to dashboard Cite

Survival analysis is a well known technique in the medical field. The identification of individuals whose survival time is too short or to long given their profile, assumes great importance for the detection of new prognostic factors. The study of these outlying observations have gained increasing relevancy with the availability of high-throughput molecular and clinical data for large cohorts of patients. Several methods for outlier detection in survival data have been proposed, which include the analysis of the residuals, the measurement of the concordance c-index, and methods based on quantile regression for censored data. However, different results are obtained depending on the type of method used. In order to solve the disparity of results we proposed to apply the Rank Product test. A simulated dataset, and two clinical datasets were used to illustrate our proposed consensus outlier detection method, one from myeloma disease and the other from The Cancer Genome Atlas (TCGA) ovarian cancer. Finally, the Rank Product with multiple testing corrections was performed in order to identify which observations have the highest rank amongst the methods considered. Our results illustrate the potential of this consensus approach for the automated retrieval of outliers and also the identification of biomarkers associated with survival in large datasets.

show abstract

Outlier Detection using Projection Quantile Regression for Mass Spectrometry Data with Low Replication

Cited by 7 publications

References 10 publications

Quantitative Characterization of Cellular Membrane-Receptor Heterogeneity through Statistical and Computational Modeling

Quantitative Characterization of Cellular Membrane-Receptor Heterogeneity through Statistical and Computational Modeling

Serological markers to measure recent changes in malaria at population level in Cambodia

Consensus outlier detection in survival analysis using the rank product test

Contact Info

Product

Resources

About