Jesper Løve Hinrich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jesper Løve Hinrich has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Morten Mørup
Department of Applied Mathematics and Computer Science, Technical University of Denmark
11 shared publications - Kristoffer Hougaard Madsen
Technical University of Denmark
7 shared publications - Søren Føns Nielsen
Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark
3 shared publications - Mikkel Nørgaard Schmidt
Department of Applied Mathematics and Computer Science Department of Applied Mathematics and Computer Science Technical University of Denmark Technical University of Denmark
2 shared publications - Aidee Paulina de la Mata
Department of Chemistry, University of Alberta
1 shared publication - Beatriz Quintanilla-Casas
Departament de Nutrició, Ciències de l’Alimentació i Gastronomia, Campus De l’Alimentació de Torribera, Facultat de Farmàcia i Ciències de l’Alimentació, Universitat de Barcelona, 08921 Santa Coloma de Gramenet, Spain
1 shared publication
Latest Publications
- 5 October 2026
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 98 (41) , 29417-29432
Multiway Modeling of 2D NMR Spectra for Enhanced Chemical Characterization of Complex Mixtures
One-dimensional (1D) proton nuclear magnetic resonance (NMR) spectroscopy is widely used for complex mixture analysis because of its high reproducibility, minimal sample preparation, and inherent quantitative capabilities. However, 1D NMR remains constrained by three interrelated limitations: signal overlap among compounds, chemical-shift variability of the same compounds across samples, and masking of low signal-to-noise features by neighboring high-intensity resonances. Two-dimensional (2D) NMR spectroscopy can reduce these limitations by dispersing spectral information over a second dimension and providing additional structural information. Yet its broader implementation in large-scale studies remains limited by a major data-processing bottleneck: the analysis of multisample, high-dimensional 2D NMR data sets. When acquired across multiple samples, 2D NMR spectra form three-way tensors that contain richer chemical information than conventional 1D data sets but are not readily handled by standard NMR data analysis workflows. In this paper, we discuss how localized 2D spectral alignment combined with tensor decomposition and shift-tolerant multilinear modeling, including PARAFAC, PARAFAC2, and shift-invariant approaches, can recover overlapped, shifted, and low-intensity signals from complex 2D NMR spectra. These workflows hold considerable promise for advancing NMR-based complex mixture analysis by expanding metabolite coverage, improving deconvolution of elusive signals, and enabling more reliable quantification of low-abundance biomarkers in large-scale studies.
- 5 October 2026
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 98 (41) , 29417-29432
Multiway Modeling of 2D NMR Spectra for Enhanced Chemical Characterization of Complex Mixtures
One-dimensional (1D) proton nuclear magnetic resonance (NMR) spectroscopy is widely used for complex mixture analysis because of its high reproducibility, minimal sample preparation, and inherent quantitative capabilities. However, 1D NMR remains constrained by three interrelated limitations: signal overlap among compounds, chemical-shift variability of the same compounds across samples, and masking of low signal-to-noise features by neighboring high-intensity resonances. Two-dimensional (2D) NMR spectroscopy can reduce these limitations by dispersing spectral information over a second dimension and providing additional structural information. Yet its broader implementation in large-scale studies remains limited by a major data-processing bottleneck: the analysis of multisample, high-dimensional 2D NMR data sets. When acquired across multiple samples, 2D NMR spectra form three-way tensors that contain richer chemical information than conventional 1D data sets but are not readily handled by standard NMR data analysis workflows. In this paper, we discuss how localized 2D spectral alignment combined with tensor decomposition and shift-tolerant multilinear modeling, including PARAFAC, PARAFAC2, and shift-invariant approaches, can recover overlapped, shifted, and low-intensity signals from complex 2D NMR spectra. These workflows hold considerable promise for advancing NMR-based complex mixture analysis by expanding metabolite coverage, improving deconvolution of elusive signals, and enabling more reliable quantification of low-abundance biomarkers in large-scale studies.
- Open Access
Probabilistic PARAFAC2
The Parallel Factor Analysis 2 (PARAFAC2) is a multimodal factor analysis model suitable for analyzing multi-way data when one of the modes has incomparable observation units, for example, because of differences in signal sampling or batch sizes. A fully probabilistic treatment of the PARAFAC2 is desirable to improve robustness to noise and provide a principled approach for determining the number of factors, but challenging because direct model fitting requires that factor loadings be decomposed into a shared matrix specifying how the components are consistently co-expressed across samples and sample-specific orthogonality-constrained component profiles. We develop two probabilistic formulations of the PARAFAC2 model along with variational Bayesian procedures for inference: In the first approach, the mean values of the factor loadings are orthogonal leading to closed form variational updates, and in the second, the factor loadings themselves are orthogonal using a matrix Von Mises–Fisher distribution. We contrast our probabilistic formulations to the conventional direct fitting algorithm based on maximum likelihood on synthetic data and real fluorescence spectroscopy and gas chromatography–mass spectrometry data showing that the probabilistic formulations are more robust to noise and model order misspecification. The probabilistic PARAFAC2, thus, forms a promising framework for modeling multi-way data accounting for uncertainty.
Open AccessProbabilistic PARAFAC2
The Parallel Factor Analysis 2 (PARAFAC2) is a multimodal factor analysis model suitable for analyzing multi-way data when one of the modes has incomparable observation units, for example, because of differences in signal sampling or batch sizes. A fully probabilistic treatment of the PARAFAC2 is desirable to improve robustness to noise and provide a principled approach for determining the number of factors, but challenging because direct model fitting requires that factor loadings be decomposed into a shared matrix specifying how the components are consistently co-expressed across samples and sample-specific orthogonality-constrained component profiles. We develop two probabilistic formulations of the PARAFAC2 model along with variational Bayesian procedures for inference: In the first approach, the mean values of the factor loadings are orthogonal leading to closed form variational updates, and in the second, the factor loadings themselves are orthogonal using a matrix Von Mises–Fisher distribution. We contrast our probabilistic formulations to the conventional direct fitting algorithm based on maximum likelihood on synthetic data and real fluorescence spectroscopy and gas chromatography–mass spectrometry data showing that the probabilistic formulations are more robust to noise and model order misspecification. The probabilistic PARAFAC2, thus, forms a promising framework for modeling multi-way data accounting for uncertainty.
- 9 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computing in Science & Engineering
- Vol. 26 (4) , 24-34
Probabilistic Block Term Decomposition for the Modeling of Higher Order Arrays
Tensors are ubiquitous in science and engineering and tensor factorization approaches have become important tools. This paper explores the use of Bayesian modeling in the context of tensor factorization and presents a probabilistic extension of the so-called Block-Term Decomposition (BTD) model and show how it can interpolate between two common decomposition models - the Canonical Polyadic Decomposition (CPD) and the Tucker decomposition. This probabilistic extension is obtained by applying Bayesian inference to the BTD model, allowing for uncertainty quantification, robustness to corruption by noise and model miss-specification. The novelty of this model is its applicability to N th -order tensors, incorporating mode specific orthogonality within each block, and priors that penalizing complexity of the core arrays. On synthetic and two real datasets, we highlight the benefits of probabilistic tensor factorization considering the BTD, demonstrating that the probabilistic BTD can successfully quantify multi-linear structures and is robust to noise.
- 9 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computing in Science & Engineering
- Vol. 26 (4) , 24-34
Probabilistic Block Term Decomposition for the Modeling of Higher Order Arrays
Tensors are ubiquitous in science and engineering and tensor factorization approaches have become important tools. This paper explores the use of Bayesian modeling in the context of tensor factorization and presents a probabilistic extension of the so-called Block-Term Decomposition (BTD) model and show how it can interpolate between two common decomposition models - the Canonical Polyadic Decomposition (CPD) and the Tucker decomposition. This probabilistic extension is obtained by applying Bayesian inference to the BTD model, allowing for uncertainty quantification, robustness to corruption by noise and model miss-specification. The novelty of this model is its applicability to N th -order tensors, incorporating mode specific orthogonality within each block, and priors that penalizing complexity of the core arrays. On synthetic and two real datasets, we highlight the benefits of probabilistic tensor factorization considering the BTD, demonstrating that the probabilistic BTD can successfully quantify multi-linear structures and is robust to noise.
- 1 February 2023
- Published by Elsevier in Analytica Chimica Acta
- Vol. 1249, 340909
PARAFAC2×N: Coupled decomposition of multi-modal data with drift in N modes
- 1 February 2023
- Published by Elsevier in Analytica Chimica Acta
- Vol. 1249, 340909
PARAFAC2×N: Coupled decomposition of multi-modal data with drift in N modes
- Open Access
- 19 January 2023
- Published by Springer Nature in Research Square
Tutorial on PARADISe: PARAFAC2-based Deconvolution and Identification System for processing GC–MS data
The present protocol provides general guidelines for users working with PARADISe, a deconvolution and identification system for processing GC-MS data. This tool allows users to perform untargeted analysis of large datasets efficiently and minimizes inter-user variability. The final output is a peak table, in excel format, containing the peak area and the purified spectrum for each resolved compound.
- 19 January 2023
- Published by Springer Nature in Research Square
Open AccessTutorial on PARADISe: PARAFAC2-based Deconvolution and Identification System for processing GC–MS data
The present protocol provides general guidelines for users working with PARADISe, a deconvolution and identification system for processing GC-MS data. This tool allows users to perform untargeted analysis of large datasets efficiently and minimizes inter-user variability. The final output is a peak table, in excel format, containing the peak area and the purified spectrum for each resolved compound.
- Open Access
- 1 June 2020
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 1 (2) , 025011
The probabilistic tensor decomposition toolbox
This article introduces the probabilistic tensor decomposition toolbox-a MATLAB toolbox for tensor decomposition using Variational Bayesian inference and Gibbs sampling. An introduction and overview of probabilistic tensor decomposition and its connection with classical tensor decomposition methods based on maximum likelihood is provided. We subsequently describe the probabilistic tensor decomposition toolbox which encompasses the Canonical Polyadic, Tucker, and Tensor Train decomposition models. Currently, unconstrained, non-negative, orthogonal, and sparse factors are supported. Bayesian inference forms a principled way of incorporating prior knowledge, prediction of held-out data, and estimating posterior probabilities. Furthermore, it facilitates automatic model order determination, automatic regularization on factors (e.g. sparsity), and inherently penalizes model complexity which is beneficial when inferring hierarchical models, such as heteroscedastic noise modelling. The toolbox allows researchers to easily apply Bayesian tensor decomposition methods without the need to derive or implement these methods themselves. Furthermore, it serves as a reference implementation for comparing existing and new tensor decomposition methods. The software is available from https://github.com/JesperLH/prob-tensor-toolbox/.
- 1 June 2020
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 1 (2) , 025011
Open AccessThe probabilistic tensor decomposition toolbox
This article introduces the probabilistic tensor decomposition toolbox-a MATLAB toolbox for tensor decomposition using Variational Bayesian inference and Gibbs sampling. An introduction and overview of probabilistic tensor decomposition and its connection with classical tensor decomposition methods based on maximum likelihood is provided. We subsequently describe the probabilistic tensor decomposition toolbox which encompasses the Canonical Polyadic, Tucker, and Tensor Train decomposition models. Currently, unconstrained, non-negative, orthogonal, and sparse factors are supported. Bayesian inference forms a principled way of incorporating prior knowledge, prediction of held-out data, and estimating posterior probabilities. Furthermore, it facilitates automatic model order determination, automatic regularization on factors (e.g. sparsity), and inherently penalizes model complexity which is beneficial when inferring hierarchical models, such as heteroscedastic noise modelling. The toolbox allows researchers to easily apply Bayesian tensor decomposition methods without the need to derive or implement these methods themselves. Furthermore, it serves as a reference implementation for comparing existing and new tensor decomposition methods. The software is available from https://github.com/JesperLH/prob-tensor-toolbox/.
- 5 November 2019
- Published by Springer Nature in Advances in Health Sciences Education
- Vol. 25 (3) , 581-606
Social ties between team members affect patient satisfaction: a data-driven approach to handling complex network analyses
Research from outside the medical field suggests that social ties between team-members influence knowledge sharing, improve coordination, and facilitate task completion. However, the relative importance of social ties among team-members for patient satisfaction remains unknown. In this study, we explored the association between social ties within emergency teams performing simulated caesarean sections (CS) and patient-actor satisfaction. Two hundred seventy-two participants were allocated to 33 teams performing two emergency CSs in a simulated setting. We collected data on social ties between team-members, measured as affective, personal and professional ties. Ties were rated on 5-point Likert scales. In addition, participants’ clinical experience, demographic data and their knowledge about team members’ roles were surveyed. Perceived patient satisfaction was measured on a 5-point Likert scale. Data was analysed with a linear regression model using elastic net regularization. In total, 109 predictor variables were analysed including 84 related to social ties and 25 related to clinical experience, demographics and knowledge test scores. Of the 84 variables reflecting social ties, 34 (41%) had significant association with patient satisfaction, p < 0.01. By contrast, a significant association with patient satisfaction was found for only one (4%) of the 25 variables reflecting clinical experience, demographics and knowledge of team roles. Affective ties and personal ties were found to be far more important predictors in the statistical model than professional ties and predictors relating to clinical experience. Social ties between emergency team members may be important predictors of patient satisfaction. The results from this study help to enhance our conceptual understanding of social ties and their implications for team-dynamics. Our study challenges existing views of team-performance by placing emphasis on achieving collective competence through affective and personal social ties, rather than focusing on traditional measures of expertise.
- 5 November 2019
- Published by Springer Nature in Advances in Health Sciences Education
- Vol. 25 (3) , 581-606
Social ties between team members affect patient satisfaction: a data-driven approach to handling complex network analyses
Research from outside the medical field suggests that social ties between team-members influence knowledge sharing, improve coordination, and facilitate task completion. However, the relative importance of social ties among team-members for patient satisfaction remains unknown. In this study, we explored the association between social ties within emergency teams performing simulated caesarean sections (CS) and patient-actor satisfaction. Two hundred seventy-two participants were allocated to 33 teams performing two emergency CSs in a simulated setting. We collected data on social ties between team-members, measured as affective, personal and professional ties. Ties were rated on 5-point Likert scales. In addition, participants’ clinical experience, demographic data and their knowledge about team members’ roles were surveyed. Perceived patient satisfaction was measured on a 5-point Likert scale. Data was analysed with a linear regression model using elastic net regularization. In total, 109 predictor variables were analysed including 84 related to social ties and 25 related to clinical experience, demographics and knowledge test scores. Of the 84 variables reflecting social ties, 34 (41%) had significant association with patient satisfaction, p < 0.01. By contrast, a significant association with patient satisfaction was found for only one (4%) of the 25 variables reflecting clinical experience, demographics and knowledge of team roles. Affective ties and personal ties were found to be far more important predictors in the statistical model than professional ties and predictors relating to clinical experience. Social ties between emergency team members may be important predictors of patient satisfaction. The results from this study help to enhance our conceptual understanding of social ties and their implications for team-dynamics. Our study challenges existing views of team-performance by placing emphasis on achieving collective competence through affective and personal social ties, rather than focusing on traditional measures of expertise.
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Probabilistic Tensor Train Decomposition
- 1 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Probabilistic Tensor Train Decomposition
- 12 August 2019
- Published by Wiley in Human Brain Mapping
- Vol. 40 (17) , 4965-4981
Classification of social anhedonia using temporal and spatial network features from a social cognition fMRI task
Previous studies have suggested that the degree of social anhedonia reflects the vulnerability for developing schizophrenia. However, only few studies have investigated how functional network changes are related to social anhedonia. The aim of this fMRI study was to classify subjects according to their degree of social anhedonia using supervised machine learning. More specifically, we extracted both spatial and temporal network features during a social cognition task from 70 subjects, and used support vector machines for classification. Since impairment in social cognition is well established in schizophrenia-spectrum disorders, the subjects performed a comic strip task designed to specifically probe theory of mind (ToM) and empathy processing. Features representing both temporal (time series) and network dynamics were extracted using task activation maps, seed region analysis, independent component analysis (ICA), and a newly developed multi-subject archetypal analysis (MSAA), which here aimed to further bridge aspects of both seed region analysis and decomposition by incorporating a spotlight approach.We found significant classification of subjects with elevated levels of social anhedonia when using the times series extracted using MSAA, indicating that temporal dynamics carry important information for classification of social anhedonia. Interestingly, we found that the same time series yielded the highest classification performance in a task classification of the ToM condition. Finally, the spatial network corresponding to that time series included both prefrontal and temporal-parietal regions as well as insula activity, which previously have been related schizotypy and the development of schizophrenia.
- 12 August 2019
- Published by Wiley in Human Brain Mapping
- Vol. 40 (17) , 4965-4981
Classification of social anhedonia using temporal and spatial network features from a social cognition fMRI task
Previous studies have suggested that the degree of social anhedonia reflects the vulnerability for developing schizophrenia. However, only few studies have investigated how functional network changes are related to social anhedonia. The aim of this fMRI study was to classify subjects according to their degree of social anhedonia using supervised machine learning. More specifically, we extracted both spatial and temporal network features during a social cognition task from 70 subjects, and used support vector machines for classification. Since impairment in social cognition is well established in schizophrenia-spectrum disorders, the subjects performed a comic strip task designed to specifically probe theory of mind (ToM) and empathy processing. Features representing both temporal (time series) and network dynamics were extracted using task activation maps, seed region analysis, independent component analysis (ICA), and a newly developed multi-subject archetypal analysis (MSAA), which here aimed to further bridge aspects of both seed region analysis and decomposition by incorporating a spotlight approach.We found significant classification of subjects with elevated levels of social anhedonia when using the times series extracted using MSAA, indicating that temporal dynamics carry important information for classification of social anhedonia. Interestingly, we found that the same time series yielded the highest classification performance in a task classification of the ToM condition. Finally, the spatial network corresponding to that time series included both prefrontal and temporal-parietal regions as well as insula activity, which previously have been related schizotypy and the development of schizophrenia.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
VARIATIONAL BAYESIAN PARTIALLY OBSERVED NON-NEGATIVE TENSOR FACTORIZATION
Non-negative matrix and tensor factorization (NMF/NTF) have become important tools for extracting part based representations in data. It is however unclear when an NMF or NTF approach is most suited for data and how reliably the models predict when trained on partially observed data. We presently extend a recently proposed variational Bayesian NMF (VB-NMF) to non-negative tensor factorization (VB-NTF) for partially observed data. This admits bi- and multi-linear structure quantification considering both model prediction and evidence. We evaluate the developed VB-NTF on synthetic and a real dataset of gene expression in the human brain and contrast the performance to VB-NMF and conventional NMF/NTF. We find that the gene expressions are better accounted for by VB-NMF than VB-NTF and that VB-NMF/VB-NTF more robustly handle partially observed data than conventional NMF/NTF. In particular, probabilistic modeling is beneficial when large amounts of data is missing and/or the model order over-specified.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
VARIATIONAL BAYESIAN PARTIALLY OBSERVED NON-NEGATIVE TENSOR FACTORIZATION
Non-negative matrix and tensor factorization (NMF/NTF) have become important tools for extracting part based representations in data. It is however unclear when an NMF or NTF approach is most suited for data and how reliably the models predict when trained on partially observed data. We presently extend a recently proposed variational Bayesian NMF (VB-NMF) to non-negative tensor factorization (VB-NTF) for partially observed data. This admits bi- and multi-linear structure quantification considering both model prediction and evidence. We evaluate the developed VB-NTF on synthetic and a real dataset of gene expression in the human brain and contrast the performance to VB-NMF and conventional NMF/NTF. We find that the gene expressions are better accounted for by VB-NMF than VB-NTF and that VB-NMF/VB-NTF more robustly handle partially observed data than conventional NMF/NTF. In particular, probabilistic modeling is beneficial when large amounts of data is missing and/or the model order over-specified.