All repositories released under the TrACEr project can be reached through: https://github.com/TrACEr-Project
For the latest version of each repo, please check the original repository. Here are some of these repos:
AO-ADMM-based Data Fusion Toolbox: Our flexible algorithmic framework for coupled matrix and tensor factorizations which utilizes Alternating Optimization (AO) and the Alternating Direction Method of Multipliers (ADMM) facilitates the use of a variety of constraints, loss functions and couplings with linear transformations. The formulation relies on CMTF models, where higher-order tensors are analyzed using CANDECOMP/PARAFAC (CP) or PARAFAC2 tensor models.
C. Schenker, J. E. Cohen, E. Acar. A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings, IEEE Journal of Selected Topics in Signal Processing, 15(3), 2021
C. Schenker, X. Wang, E. Acar. PARAFAC2-based Coupled Matrix and Tensor Factorizations, ICASSP’23: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2023
Main Contact: Carla Schenker (carla@simula.no)
AO-ADMM for Constrained PARAFAC2: An AO-ADMM-based algorithmic approach that allows the flexibility to have various constraints in all modes when fitting a PARAFAC2 model.
M. Roald, C. Schenker, V. Calhoun, T. Adali, R. Bro, J. E. Cohen, E. Acar, An AO-ADMM approach to constraining PARAFAC2 on all modes, SIAM Journal on Mathematics of Data Science (SIMODS), 2022
M. Roald, C. Schenker, J. E. Cohen, E. Acar, PARAFAC2 AO-ADMM: Constraints in all modes, EUSIPCO’21: Proceedings of the 29th European Signal Processing Conference, 2021
There are both Python and MATLAB codes for the AO-ADMM approach. Experiments in the papers are carried out using the Python code - see https://github.com/MarieRoald/PARAFAC2-AOADMM-SIMODS
Main Contact: Carla Schenker (carla@simula.no), Marie Roald (mariero@simula.no)
Analysis of Simulated Postprandial Metabolomics Data: Simulated postprandial metabolomics data using a human whole-body metabolic model and its analysis using a CANDECOMP/PARAFAC (CP) model
L. Li, S. Yan, B. M. Bakker, H. Hoefsloot, B. Chawes, D. Horner, M. A. Rasmussen, A. K. Smilde, E. Acar. Analyzing postprandial metabolomics data using multiway models: A simulation study, BMC Bioinformatics, 25:94, 2024
Analysis of Real Postprandial Metabolomics Data: The repository shows the pipeline to analyze metabolomics measurements (from a Nightingale NMR panel) of plasma samples collected during a meal challenge test. The data is assumed to be arranged as a third-order tensor with modes: subjects, time and metabolites, and analyzed using a CANDECOMP/PARAFAC (CP) tensor factorization model.
S. Yan, L. Li, D. Horner, P. Ebrahimi, B. Chawes, L. O. Dragsted, M. A. Rasmussen, A. K. Smilde, E. Acar. Characterizing human postprandial metabolic response using multiway data analysis, Metabolomics, 20:50, 2024