Detection of PatIent-Level distances from single cell genomics and pathomics data with Optimal Transport (PILOT)

Joodaki, Mehdi; Shaigan, Mina; Parra, Víctor M.; Bülow, Roman David; Kuppe, Christoph; Hölscher, David L.; Cheng, Mingbo; Nagai, James Shiniti; Bouteldja, Nassim; Tesař, Vladimı́r; Barratt, Jonathan; Roberts, Ian S.; Coppo, Rosanna; Kramann, Rafael; Costa, Ivan G.

doi:10.1101/2022.12.16.520739

Cited by 8 publications

(15 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These limitations, however, are shared across current tissue-centric tailored methods. In contrast, models based on generative deep learning (De Donno et al , 2022; Boyeau et al , 2022) and the Wasserstein metric (Joodaki et al , 2022; Chen et al , 2020) can take advantage of single-cell measurements to estimate sample-level heterogeneity, but the interpretability of their estimated latent space is limited in comparison to the MOFA models, where features and cell-types can be associated with each factor.…”

Section: Discussionmentioning

confidence: 99%

Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease

Flores

Lanzer

Dimitrov

et al. 2023

Preprint

View full text Add to dashboard Cite

Single-cell atlases across conditions are essential in the characterization of human disease. In these complex experimental designs, patient samples are profiled across distinct cell-types and clinical conditions to describe disease processes at the cellular level. However, most of the current analysis tools are limited to pairwise cross-condition comparisons, disregarding the multicellular nature of disease processes and the effects of other biological and technical factors in the variation of gene expression. Here we propose a computational framework for an unsupervised analysis of samples from cross-condition single-cell atlases and for the identification of multicellular programs associated with disease. Our strategy, that repurposes multi-omics factor analysis, incorporates the variation of patient samples across cell-types and enables the joint analysis of multiple patient cohorts, facilitating integration of atlases. We applied our analysis to a collection of acute and chronic human heart failure single-cell datasets and described multicellular processes of cardiac remodeling that were conserved in independent spatial and bulk transcriptomics datasets. In sum, our framework serves as an exploratory tool for unsupervised analysis of cross-condition single-cell atlas and allows for the integration of the measurements of patient cohorts across distinct data modalities, facilitating the generation of comprehensive tissue-centric understanding of disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease

Flores

Lanzer

Dimitrov

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The same study also showed that pathomics data can be used for predictive modeling of long-term kidney survival in Immunoglobulin A-Nephropathy (IgAN) patients and showed the applicability of pathomics for complex biocomputation analysis used in other OMICs-fields, such as transcriptomics. This analysis delineated a trajectory of glomerular morphometric progression of IgAN-patient with progressive tuft deformation [6 ▪▪ ,21].…”

Section: Deep Learning Applications In Nephropathologymentioning

confidence: 99%

Deep learning applications for kidney histology analysis

Pilva,

Bülow,

Boor

2024

Current Opinion in Nephrology &Amp; Hypertension

View full text Add to dashboard Cite

Purpose of review Nephropathology is increasingly incorporating computational methods to enhance research and diagnostic accuracy. The widespread adoption of digital pathology, coupled with advancements in deep learning, will likely transform our pathology practices. Here, we discuss basic concepts of deep learning, recent applications in nephropathology, current challenges in implementation and future perspectives. Recent findings Deep learning models have been developed and tested in various areas of nephropathology, for example, predicting kidney disease progression or diagnosing diseases based on imaging and clinical data. Despite their promising potential, challenges remain that hinder a wider adoption, for example, the lack of prospective evidence and testing in real-world scenarios. Summary Deep learning offers great opportunities to improve quantitative and qualitative kidney histology analysis for research and clinical nephropathology diagnostics. Although exciting approaches already exist, the potential of deep learning in nephropathology is only at its beginning and we can expect much more to come.

show abstract

“…Recently, Patient level distance with Optimal Transport (PILOT) ( [19]) has been proposed to investigate the patient level distance using the Wasserstein distance. Compared to PILOT, our method (QOT-Adaptive) could be seen as the generalized version of PILOT.…”

Section: Link To Relevant Prior Workmentioning

confidence: 99%

QOT: Efficient Computation of Sample Level Distance Matrix from Single-Cell Omics Data through Quantized Optimal Transport

Wang,

Zhan,

Yang

et al. 2024

Preprint

View full text Add to dashboard Cite

Single-cell technologies have emerged as a transformative technology enabling high-dimensional characterization of cell populations at an unprecedented scale. The data's innate complexity and voluminous nature pose significant computational and analytical challenges, especially in comparative studies delineating cellular architectures across various biological conditions (i.e., generation of sample level distance matrices). Optimal Transport (OT) is a mathematical tool that captures the intrinsic structure of data geometrically and has been applied to many bioinformatics tasks. In this paper, we propose QOT (Quantized Optimal Transport), a new method enables efficient computation of sample level distance matrix from large-scale single-cell omics data through a quantization step. We apply our algorithm to real-world single-cell genomics and pathomics datasets, aiming to extrapolate cell-level insights to inform sample level categorizations. Our empirical study shows that QOT outperforms OT-based algorithms in terms of accuracy and robustness when obtaining a distance matrix at the sample level from high throughput single-cell measures. Moreover, the sample level distance matrix could be used in downstream analysis (i.e. uncover the trajectory of disease progression), highlighting its usage in biomedical informatics and data science.

show abstract

Detection of PatIent-Level distances from single cell genomics and pathomics data with Optimal Transport (PILOT)

Cited by 8 publications

References 51 publications

Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease

Multicellular factor analysis of single-cell data for a tissue-centric understanding of disease

Deep learning applications for kidney histology analysis

QOT: Efficient Computation of Sample Level Distance Matrix from Single-Cell Omics Data through Quantized Optimal Transport

Contact Info

Product

Resources

About