Longitudinal alignments and syntheses of multimodal clinical data for personalized medicine with the PULSE framework

Multimodal models capable of imputing diverse data used in single-cell biology studies provide potential foundational opportunities in clinical practice. However, patient data uniquely comprise longitudinal mosaic measurements that reflect underlying physiological dynamics and exhibit temporal covariation, demanding a specialized approach. Here we present Patient Unified Longitudinal Signal Engine (PULSE), a longitudinal self-supervised framework that explicitly encodes personalized past states (historical paired modalities) to reconstruct full profiles from subsequent unpaired measurements, thus enhancing current visit multimodal alignment and generation. Applied to the UK Biobank, PULSE accurately generates metabolomic profiles and proteomic profiles from sparse routine blood tests. Compared with the ground truth metabolomic data (251 biomarkers), PULSE-generated profiles outperformed all benchmark methods. Furthermore, the framework accommodates incorporation of retinal images, electronic health records and blood markers with disease prediction: models trained on the generated proteomic profiles achieved areas under the curve of 0.72-0.83 for six common diseases, comparable to that using ground-truth proteomic data. The PULSE framework demonstrates that cross-modal alignment captures the continuous spectrum of disease physiology and extracts robust features that transcend the limitations of traditional binary case-controls.

Authors

Institutions

Publication Details

Journal
Nature Computational Science
Published
2026-08-26
DOI
https://doi.org/10.1038/s43588-026-01026-5
Citations
1
Primary Topic
Single-cell and spatial transcriptomics
Type
article
Field-Weighted Citation Impact
3.06

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Longitudinal alignments and syntheses of multimodal clinical data for personalized medicine with the PULSE framework

I. Kenneth Chong, Charlotte L Zhang, B Li, John E.J. Rasko et al.
1 citations
Nature Computational Science
Single-cell and spatial transcriptomics
3.06
article

Longitudinal alignments and syntheses of multimodal clinical data for personalized medicine with the PULSE framework

I. Kenneth Chong, Charlotte L Zhang, B Li, John E.J. Rasko, Jinghang Li, Alexandre Loupy, Saleem Al Dajani, Kang Zhang, Yun Yin, Fei Liu, Kai Wang, Zixing Zou, Wei Wu, Eric Oermann, Jonathan Gootenberg, Cheng Tang, Changxi Hu, Haodi Xiao, Hang Wong, Hao Zhu, Sian Liu, Zhuo Sun, Omar O. Abudayyeh, Hui Xu, Vadim N. Gladyshev, Gen Li, Wenyang Lu
article en
1 citations

Abstract

Multimodal models capable of imputing diverse data used in single-cell biology studies provide potential foundational opportunities in clinical practice. However, patient data uniquely comprise longitudinal mosaic measurements that reflect underlying physiological dynamics and exhibit temporal covariation, demanding a specialized approach. Here we present Patient Unified Longitudinal Signal Engine (PULSE), a longitudinal self-supervised framework that explicitly encodes personalized past states (historical paired modalities) to reconstruct full profiles from subsequent unpaired measurements, thus enhancing current visit multimodal alignment and generation. Applied to the UK Biobank, PULSE accurately generates metabolomic profiles and proteomic profiles from sparse routine blood tests. Compared with the ground truth metabolomic data (251 biomarkers), PULSE-generated profiles outperformed all benchmark methods. Furthermore, the framework accommodates incorporation of retinal images, electronic health records and blood markers with disease prediction: models trained on the generated proteomic profiles achieved areas under the curve of 0.72-0.83 for six common diseases, comparable to that using ground-truth proteomic data. The PULSE framework demonstrates that cross-modal alignment captures the continuous spectrum of disease physiology and extracts robust features that transcend the limitations of traditional binary case-controls.

Nature Computational Science
Macau University of Science and Technology (MO), Brigham and Women's Hospital (US), Harvard University (US), Inserm (FR), University of Pittsburgh (US), Peking University (CN), University of Macau (MO), Université Paris Cité (FR), Wenzhou Medical University (CN), King Center (US), NYU Langone Health (US), Affiliated Eye Hospital of Wenzhou Medical College (CN), Guangzhou Experimental Station (CN), Assistance Publique – Hôpitaux de Paris (FR), Paris Cardiovascular Research Center (FR), Changzhou Third People's Hospital (CN), Center for Life Sciences (CN), Mass General Brigham (US), Massachusetts Institute of Technology (US), City University of Macau (MO)
Wenzhou Medical University, National Natural Science Foundation of China, National Health Commission of the People's Republic of China
Openalex Percentile: Top 6%
Single-cell and spatial transcriptomics
3.06
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.