Pasar al contenido principal

STATISTICAL METHODS AND APPLICATIONS IN HIGH-DIMENSIONAL DATA ANALYSIS AND EXPERIMENTAL DESIGN

RYC-2015-18544

•
Nombre agencia financiadora Ministerio de Ciencia e Innovación
Acrónimo agencia financiadora MICINN
Programa Programa Estatal de Promoción del Talento y su Empleabilidad en I+D+i
Subprograma Subprograma Estatal de Incorporación
Convocatoria Ramón y Cajal
Año convocatoria 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Investigación, Desarrollo e Innovación
Centro beneficiario UNIVERSITAT POMPEU FABRA CCT
Identificador persistente http://dx.doi.org/10.13039/501100004837

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Pushing the analytical limits: new insights into complex mixtures using mass spectra segments of constant ultrahigh resolving power

  • Palacio Lozano, Diana Catalina
  • Gavard, Remy
  • Arenas Diaz, Juan P.
  • Thomas, Mary J.
  • Stranz, David D.
  • Mejía-Ospino, Enrique
  • Guzman, Alexander
  • Spencer, Simon E.F.
  • Rossell, David
  • Barrow, Mark P.
A new strategy has been developed for characterization of the most challenging complex mixtures to date, using a combination of custom-designed experiments and a new data pre-processing algorithm. In contrast to traditional methods, the approach enables operation of Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) with constant ultrahigh resolution at hitherto inaccessible levels (approximately 3 million FWHM, independent of m/z). The approach, referred to as OCULAR, makes it possible to analyze samples that were previously too complex, even for high field FT-ICR MS instrumentation. Previous FT-ICR MS studies have typically spanned a broad mass range with decreasing resolving power (inversely proportional to m/z) or have used a single, very narrow m/z range to produce data of enhanced resolving power; both methods are of limited effectiveness for complex mixtures spanning a broad mass range, however. To illustrate the enhanced performance due to OCULAR, we show how a record number of unique molecular formulae (244 779 elemental compositions) can be assigned in a single, non-distillable petroleum fraction without the aid of chromatography or dissociation (MS/MS) experiments. The method is equally applicable to other areas of research, can be used with both high field and low field FT-ICR MS instruments to enhance their performance, and represents a step-change in the ability to analyze highly complex samples., This work was supported by a Newton Fund award (reference number 275910721), Research Agreement No. 5211770 UIS-ICP, and COLCIENCIAS (project No. FP44842-039-2015). Juan P. Arenas thanks COLCIENCIAS for the Scholarship. Rémy Gavard and Mary Thomas thank EPSRC for a PhD studentship through the EPSRC Centre for Doctoral Training in Molecular Analytical Science (grant number EP/L015307/1). David Rossell was partially supported by Ramon y Cajal Fellowship RYC-2015-18544 from Ministerio de Economia y Competitividad (Government of Spain) and by a "Ayudas Fundacion BBVA a Equipos de Investigacion Cientifica en Big Data 2017" award from the BBVA Foundation.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

KairosMS: a new solution for the processing of hyphenated ultrahigh resolution mass spectrometry data

  • Gavard, Remy
  • Jones, Hugh E.
  • Palacio Lozano, Diana Catalina
  • Thomas, Mary J.
  • Rossell, David
  • Spencer, Simon E.F.
  • Barrow, Mark P.
The use of hyphenated Fourier transform mass spectrometry (FTMS) methods affords additional information about complex chemical mixtures. Coeluted components can be resolved thanks to the ultrahigh resolving power, which also allows extracted ion chromatograms (EICs) to be used for the observation of isomers. As such data sets can be large and data analyses laborious, improved tools are needed for data analyses and extraction of key information. The typical workflow for this type of data is based upon manually dividing the total ion chromatogram (TIC) into several windows of usually equal retention time, averaging the signal of each window to create a single mass spectrum, extracting a peak list, performing the compositional assignments, visualizing the results, and repeating the process for each window. Through removal of the need to manually divide a data set into many time windows and analyze each one, a time-consuming workflow has been significantly simplified. An environmental sample from the oil sands region of Alberta, Canada, and dissolved organic matter samples from the Suwannee River Fulvic Acid (SRFA) and marine waters (Marine DOM) were used as a test bed for the new method. A complete solution named KairosMS was developed in the R language utilizing the Tidyverse packages and Shiny for the user interface. KairosMS imports raw data from common file types, processes it, and exports a mass list for compositional assignments. KairosMS then incorporates those assignments for analysis and visualization. The present method increases the computational speed while reducing the manual work of the analysis when compared to other current methods. The algorithm subsequently incorporates the assignments into the processed data set, generating a series of interactive plots, EICs for individual components or entire compound classes, and can export raw data or graphics for off-line use. Using the example of petroleum related data, it is then visualized according to heteroatom class, carbon number, double bond equivalents, and retention time. The algorithm also gives the ability to screen for isomeric contributions and to follow homologous series or compound classes, instead of individual components, as a function of time.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Concentration of posterior model probabilities and normalized L0 criteria

  • Rossell Ribera, David
We study frequentist properties of Bayesian and L0 model selection, with a focus on (potentially non-linear) high-dimensional regression. We propose a construction to study how posterior probabilities and normalized L0 criteria concentrate on the (Kullback-Leibler) optimal model and other subsets of the model space. When such concentration occurs, one also bounds the frequentist probabilities of selecting the correct model, type I and type II errors. These results hold generally, and help validate the use of posterior probabilities and L0 criteria to control frequentist error probabilities associated to model selection and hypothesis tests. Regarding regression, we help understand the effect of the sparsity imposed by the prior or the L0 penalty, and of problem characteristics such as the sample size, signal-to-noise, dimension and true sparsity. A particular finding is that one may use less sparse formulations than would be asymptotically optimal, but still attain consistency and often also significantly better finite-sample performance. We also prove new results related to misspecifying the mean or covariance structures, and give tighter rates for certain non-local priors than currently available., DR was partially funded by the Europa Excelencia grant EUR2020-112096, NIH grant R01 CA158113-01, Ramón y Cajal Fellowship RYC-2015-18544, Plan Estatal PGC2018-101643-B-I00 and Ayudas Fundación BBVA a equipos de investigación científica en Big Data 2017.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

General Bayesian loss function selection and the use of improper models

  • Jewson, Jack
  • Rossell Ribera, David
Statisticians often face the choice between using probability models or a paradigm defined by minimising a loss function. Both approaches are useful and, if the loss can be re-cast into a proper probability model, there are many tools to decide which model or loss is more appropriate for the observed data, in the sense of explaining the data's nature. However, when the loss leads to an improper model, there are no principled ways to guide this choice. We address this task by combining the Hyvärinen score, which naturally targets infinitesimal relative probabilities, and general Bayesian updating, which provides a unifying framework for inference on losses and models. Specifically we propose the ℋ-score, a general Bayesian selection criterion and prove that it consistently selects the (possibly improper) model closest to the data-generating truth in Fisher's divergence. We also prove that an associated ℋ-posterior consistently learns optimal hyper-parameters featuring in loss functions, including a challenging tempering parameter in generalised Bayesian inference. As salient examples, we consider robust regression and non-parametric density estimation where popular loss functions define improper models for the data and hence cannot be dealt with using standard model selection tools. These examples illustrate advantages in robustness-efficiency trade-offs and enable Bayesian inference for kernel density estimation, opening a new avenue for Bayesian non-parametrics., Jack Jewson and David Rossell were partially funded by the Ayudas Fundación BBVA a Equipos de Investigación Cientifica 2017 and Proyectos de Investigación Científica en Matemáticas 2021, and Government of Spain's Plan Nacional PGC2018-101643-B-I00 grants. David Rossell was also partially funded by the Europa Excelencia grant EUR2020-112096 and Ramón y Cajal Fellowship RYC-2015-18544.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Dependence in elliptical partial correlation graphs

  • Rossell Ribera, David
  • Zwiernik, Piotr
The Gaussian model equips strong properties that facilitate studying and interpreting graphical models. Specifically it reduces conditional independence and the study of positive association to determining partial correlations and their signs. When Gaussianity does not hold partial correlation graphs are a useful relaxation of graphical models, but it is not clear what information they contain (besides the obvious lack of linear association). We study elliptical and transelliptical distributions as middleground between the Gaussian and other families that are more flexible but either do not embed strong properties or do not lead to simple interpretation. We characterize the meaning of zero partial correlations in elliptical and elliptical copula models and show that they retain much of the dependence structure from the Gaussian case. Regarding positive dependence, we prove impossibility results to learn certain positive (trans)elliptical graphical models, including that an elliptical distribution that is multivariate totally positive of order two for all dimensions must be essentially Gaussian. We then show how to interpret positive partial correlations as a relaxation, and obtain important properties related to faithfulness and Simpson’s paradox. We illustrate the transelliptical model potential to study tail dependence in S&P500 data, and of positivity to improve regularized inference., DR and PZ were supported from the Spanish Government grants (RYC-2015-18544, RYC2017-22544, PGC2018-101643-B-I00), and Ayudas Fundación BBVA a Equipos de Investigación Cientifica 2017. DR was partially supported by NIH grant R01 CA158113-01 and Europa Excelencia EUR2020-112096.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

KairosMS: a new solution for the processing of hyphenated ultrahigh resolution mass spectrometry data

  • Gavard, Remy
  • Jones, Hugh E.
  • Palacio Lozano, Diana Catalina
  • Thomas, Mary J.
  • Rossell, David
  • Spencer, Simon E.F.
  • Barrow, Mark P.
The use of hyphenated Fourier transform mass spectrometry (FTMS) methods affords additional information about complex chemical mixtures. Coeluted components can be resolved thanks to the ultrahigh resolving power, which also allows extracted ion chromatograms (EICs) to be used for the observation of isomers. As such data sets can be large and data analyses laborious, improved tools are needed for data analyses and extraction of key information. The typical workflow for this type of data is based upon manually dividing the total ion chromatogram (TIC) into several windows of usually equal retention time, averaging the signal of each window to create a single mass spectrum, extracting a peak list, performing the compositional assignments, visualizing the results, and repeating the process for each window. Through removal of the need to manually divide a data set into many time windows and analyze each one, a time-consuming workflow has been significantly simplified. An environmental sample from the oil sands region of Alberta, Canada, and dissolved organic matter samples from the Suwannee River Fulvic Acid (SRFA) and marine waters (Marine DOM) were used as a test bed for the new method. A complete solution named KairosMS was developed in the R language utilizing the Tidyverse packages and Shiny for the user interface. KairosMS imports raw data from common file types, processes it, and exports a mass list for compositional assignments. KairosMS then incorporates those assignments for analysis and visualization. The present method increases the computational speed while reducing the manual work of the analysis when compared to other current methods. The algorithm subsequently incorporates the assignments into the processed data set, generating a series of interactive plots, EICs for individual components or entire compound classes, and can export raw data or graphics for off-line use. Using the example of petroleum related data, it is then visualized according to heteroatom class, carbon number, double bond equivalents, and retention time. The algorithm also gives the ability to screen for isomeric contributions and to follow homologous series or compound classes, instead of individual components, as a function of time.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Pushing the analytical limits: new insights into complex mixtures using mass spectra segments of constant ultrahigh resolving power

  • Palacio Lozano, Diana Catalina
  • Gavard, Remy
  • Arenas Diaz, Juan P.
  • Thomas, Mary J.
  • Stranz, David D.
  • Mejía-Ospino, Enrique
  • Guzman, Alexander
  • Spencer, Simon E.F.
  • Rossell, David
  • Barrow, Mark P.
A new strategy has been developed for characterization of the most challenging complex mixtures to date, using a combination of custom-designed experiments and a new data pre-processing algorithm. In contrast to traditional methods, the approach enables operation of Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) with constant ultrahigh resolution at hitherto inaccessible levels (approximately 3 million FWHM, independent of m/z). The approach, referred to as OCULAR, makes it possible to analyze samples that were previously too complex, even for high field FT-ICR MS instrumentation. Previous FT-ICR MS studies have typically spanned a broad mass range with decreasing resolving power (inversely proportional to m/z) or have used a single, very narrow m/z range to produce data of enhanced resolving power; both methods are of limited effectiveness for complex mixtures spanning a broad mass range, however. To illustrate the enhanced performance due to OCULAR, we show how a record number of unique molecular formulae (244 779 elemental compositions) can be assigned in a single, non-distillable petroleum fraction without the aid of chromatography or dissociation (MS/MS) experiments. The method is equally applicable to other areas of research, can be used with both high field and low field FT-ICR MS instruments to enhance their performance, and represents a step-change in the ability to analyze highly complex samples., This work was supported by a Newton Fund award (reference number 275910721), Research Agreement No. 5211770 UIS-ICP, and COLCIENCIAS (project No. FP44842-039-2015). Juan P. Arenas thanks COLCIENCIAS for the Scholarship. Rémy Gavard and Mary Thomas thank EPSRC for a PhD studentship through the EPSRC Centre for Doctoral Training in Molecular Analytical Science (grant number EP/L015307/1). David Rossell was partially supported by Ramon y Cajal Fellowship RYC-2015-18544 from Ministerio de Economia y Competitividad (Government of Spain) and by a "Ayudas Fundacion BBVA a Equipos de Investigacion Cientifica en Big Data 2017" award from the BBVA Foundation.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Concentration of posterior model probabilities and normalized L0 criteria

  • Rossell Ribera, David
We study frequentist properties of Bayesian and L0 model selection, with a focus on (potentially non-linear) high-dimensional regression. We propose a construction to study how posterior probabilities and normalized L0 criteria concentrate on the (Kullback-Leibler) optimal model and other subsets of the model space. When such concentration occurs, one also bounds the frequentist probabilities of selecting the correct model, type I and type II errors. These results hold generally, and help validate the use of posterior probabilities and L0 criteria to control frequentist error probabilities associated to model selection and hypothesis tests. Regarding regression, we help understand the effect of the sparsity imposed by the prior or the L0 penalty, and of problem characteristics such as the sample size, signal-to-noise, dimension and true sparsity. A particular finding is that one may use less sparse formulations than would be asymptotically optimal, but still attain consistency and often also significantly better finite-sample performance. We also prove new results related to misspecifying the mean or covariance structures, and give tighter rates for certain non-local priors than currently available., DR was partially funded by the Europa Excelencia grant EUR2020-112096, NIH grant R01 CA158113-01, Ramón y Cajal Fellowship RYC-2015-18544, Plan Estatal PGC2018-101643-B-I00 and Ayudas Fundación BBVA a equipos de investigación científica en Big Data 2017.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Dependence in elliptical partial correlation graphs

  • Rossell Ribera, David
  • Zwiernik, Piotr
The Gaussian model equips strong properties that facilitate studying and interpreting graphical models. Specifically it reduces conditional independence and the study of positive association to determining partial correlations and their signs. When Gaussianity does not hold partial correlation graphs are a useful relaxation of graphical models, but it is not clear what information they contain (besides the obvious lack of linear association). We study elliptical and transelliptical distributions as middleground between the Gaussian and other families that are more flexible but either do not embed strong properties or do not lead to simple interpretation. We characterize the meaning of zero partial correlations in elliptical and elliptical copula models and show that they retain much of the dependence structure from the Gaussian case. Regarding positive dependence, we prove impossibility results to learn certain positive (trans)elliptical graphical models, including that an elliptical distribution that is multivariate totally positive of order two for all dimensions must be essentially Gaussian. We then show how to interpret positive partial correlations as a relaxation, and obtain important properties related to faithfulness and Simpson’s paradox. We illustrate the transelliptical model potential to study tail dependence in S&P500 data, and of positivity to improve regularized inference., DR and PZ were supported from the Spanish Government grants (RYC-2015-18544, RYC2017-22544, PGC2018-101643-B-I00), and Ayudas Fundación BBVA a Equipos de Investigación Cientifica 2017. DR was partially supported by NIH grant R01 CA158113-01 and Europa Excelencia EUR2020-112096.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

General Bayesian loss function selection and the use of improper models

  • Jewson, Jack
  • Rossell Ribera, David
Statisticians often face the choice between using probability models or a paradigm defined by minimising a loss function. Both approaches are useful and, if the loss can be re-cast into a proper probability model, there are many tools to decide which model or loss is more appropriate for the observed data, in the sense of explaining the data's nature. However, when the loss leads to an improper model, there are no principled ways to guide this choice. We address this task by combining the Hyvärinen score, which naturally targets infinitesimal relative probabilities, and general Bayesian updating, which provides a unifying framework for inference on losses and models. Specifically we propose the ℋ-score, a general Bayesian selection criterion and prove that it consistently selects the (possibly improper) model closest to the data-generating truth in Fisher's divergence. We also prove that an associated ℋ-posterior consistently learns optimal hyper-parameters featuring in loss functions, including a challenging tempering parameter in generalised Bayesian inference. As salient examples, we consider robust regression and non-parametric density estimation where popular loss functions define improper models for the data and hence cannot be dealt with using standard model selection tools. These examples illustrate advantages in robustness-efficiency trade-offs and enable Bayesian inference for kernel density estimation, opening a new avenue for Bayesian non-parametrics., Jack Jewson and David Rossell were partially funded by the Ayudas Fundación BBVA a Equipos de Investigación Cientifica 2017 and Proyectos de Investigación Científica en Matemáticas 2021, and Government of Spain's Plan Nacional PGC2018-101643-B-I00 grants. David Rossell was also partially funded by the Europa Excelencia grant EUR2020-112096 and Ramón y Cajal Fellowship RYC-2015-18544.