TensorPLS: an R package for exploring molecular and temporal patterns in longitudinal omics data using PLS-DA
- 1Telethon Institute Of Genetics And Medicine: Naples, Campania, IT
Abstract
Longitudinal omics datasets combine high-dimensional repeated measurements with missing observations, complicating supervised modelling and temporal interpretation. We present TensorPLS, an R package integrating missing-data handling, matrix-based partial least squares discriminant analysis (PLS-DA), structured variable importance, subject-level nested cross-validation and downstream functional enrichment. Data are represented as subjects x features x time tensors. Missing values are handled by Tucker3 reconstruction or feature-time mean imputation, after which tensors are unfolded along the subject mode for PLS-DA. Cumulative variable importance in projection (VIP) scores are mapped to feature-time coordinates and summarised across time and cumulative PLS models. During nested cross-validation, imputation, component tuning, VIP-based feature selection and refitting are performed within training partitions. Full-cohort models are fitted separately for descriptive interpretation. We evaluated TensorPLS on two public longitudinal transcriptomic datasets using five-by-five nested cross-validation. In GSE68310 (109 subjects), Tucker3 reconstruction yielded Q2Y = 0.670, AUROC 0.971 and balanced accuracy 0.931. In GSE182616 (66 subjects), feature-time mean imputation yielded Q2Y = 0.294, AUROC 0.827 and balanced accuracy 0.756. Predictive metrics were calculated from pooled outer held-out predictions. TensorPLS supports predictive assessment, functional enrichment of selected genes and temporal interpretation of model-assigned feature importance.
Related
- Exploring the biogeographical patterns and driving mechanisms of microbial communities in four microhabitats of Zostera japonica beds
- Spatial and temporal patterns of human-elephant conflict and compensation in Nagaon District, Assam, India
- Temporal patterns of melanopsin-evoked calcium signaling engage NF-κB-associated transcriptional and phosphoproteomic responses
- Exploring the role of local sequence context on patterns of germline mutation
- Exploring the spatio-temporal functional connectome in PTSD: evidence of static and dynamic network alterations
BibTeX
@misc{giordano2026tensorpls,
title = {{TensorPLS: an R package for exploring molecular and temporal patterns in longitudinal omics data using PLS-DA}},
author = {A. Giordano and A. Conesa and L. Balzano Nogueira},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.03.763745},
url = {https://www.biorxiv.org/content/10.64898/2026.11.03.763745v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - TensorPLS: an R package for exploring molecular and temporal patterns in longitudinal omics data using PLS-DA
AU - A. Giordano
AU - A. Conesa
AU - L. Balzano Nogueira
PY - 2026
DA - 2026/11/03
PB - bioRxiv
DO - 10.64898/2026.11.03.763745
UR - https://www.biorxiv.org/content/10.64898/2026.11.03.763745v1
AB - Longitudinal omics datasets combine high-dimensional repeated measurements with missing observations, complicating supervised modelling and temporal interpretation. We present TensorPLS, an R package integrating missing-data handling, matrix-based partial least squares discriminant analysis (PLS-DA), structured variable importance, subject-level nested cross-validation and downstream functional enrichment. Data are represented as subjects x features x time tensors. Missing values are handled by Tucker3 reconstruction or feature-time mean imputation, after which tensors are unfolded along the subject mode for PLS-DA. Cumulative variable importance in projection (VIP) scores are mapped to feature-time coordinates and summarised across time and cumulative PLS models. During nested cross-validation, imputation, component tuning, VIP-based feature selection and refitting are performed within training partitions. Full-cohort models are fitted separately for descriptive interpretation. We evaluated TensorPLS on two public longitudinal transcriptomic datasets using five-by-five nested cross-validation. In GSE68310 (109 subjects), Tucker3 reconstruction yielded Q2Y = 0.670, AUROC 0.971 and balanced accuracy 0.931. In GSE182616 (66 subjects), feature-time mean imputation yielded Q2Y = 0.294, AUROC 0.827 and balanced accuracy 0.756. Predictive metrics were calculated from pooled outer held-out predictions. TensorPLS supports predictive assessment, functional enrichment of selected genes and temporal interpretation of model-assigned feature importance.
ER -