CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq

He, Bryan; Thomson, Matt; Subramaniam, Meena; Perez, Richard; Ye, Chun Jimmie; Zou, James

doi:10.1142/9789811250477_0031

Cited by 5 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Phenotype Prediction Using Single-cell RNA-Seq. CloudPred (He et al, 2021) models the individual points as samples from a mixture of Gaussians, probabilistically assigns points to clusters, then estimates prevalence of the subpopulations and use it to predict the phenotype of that patient. scPheno (Zeng et al, 2022) constructs gene expression profiles by a joint distribution of cell states and disease phenotypes based on a deep generative probabilistic model, and feeds the distribution as the predictive features to support vector machine (SVM) for the phenotype prediction.…”

Section: Related Workmentioning

confidence: 99%

“…For the second strategy of interactively analyzing all cells, the encoding of a given cell will be affected by others in the same sample and can potentially capture correlations between cells. Vanilla attention layer (Vaswani et al, 2017) and CloudPred (He et al, 2021) we try (5 and 20). Notably, baseline Attention is equivalent to using the ScRAT without sample mixup module.…”

Section: Baselinesmentioning

confidence: 99%

“…Here we present ScRAT, a clinical phenotype prediction framework that can learn from limited numbers of scRNA-seq samples with minimal dependence on celltype annotations. Compared to most available scRNA-seq analysis algorithms that model gene expression profiles of different cell clusters by separate Gaussian distributions (He et al, 2021;Zeng et al, 2022), the first contribution in ScRAT is that we utilize the attention mechanism to measure interactions between cells as their correlations, or attention weights. For each cell, we incorporate all of its interaction patterns and attention weights to establish its connections with the corresponding phenotypes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Clinical Phenotype Prediction From Single-cell RNA-seq Data using Attention-Based Neural Networks

Mao

Lin

Wong³

et al. 2023

Preprint

View full text Add to dashboard Cite

Motivation: A patient's disease phenotype can be driven and determined by specific groups of cells whose marker genes are either unknown, or can only be detected at late-stage using conventional bulk assays such as RNA-Seq technology. Recent advances in single-cell RNA sequencing (scRNA-seq) enable gene expression profiling in cell-level resolution, and therefore have the potential to identify those cells driving the disease phenotype even while the number of these cells is small. However, most existing methods rely heavily on accurate cell type detection, and the number of available annotated samples is usually too small for training deep learning predictive models. Results: Here we propose the method ScRAT for clinical phenotype prediction using scRNA-seq data. To train ScRAT with a limited number of samples of different phenotypes, such as COVID and non-COVID, ScRAT first applies a mixup module to increase the number of training samples. A multi-head attention mechanism is employed to learn the most informative cells for each phenotype without relying on a given cell type annotation. Using three public COVID datasets, we show that ScRAT outperforms other phenotype prediction methods. The performance edge of ScRAT over its competitors increases as the number of training samples decreases, indicating the efficacy of our sample mixup. Critical cell types detected based on high-attention cells also support novel findings in the original papers and the recent literature. This suggests that ScRAT overcomes the challenge of missing marker genes and limited sample number with great potential revealing novel molecular mechanisms and/or therapies.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Baselinesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Clinical Phenotype Prediction From Single-cell RNA-seq Data using Attention-Based Neural Networks

Mao

Lin

Wong³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Meena Subramaniam et al. also found that monocytes from SLE patients highly expressed ISGs ( 29 ). Both of these studies comprehensively illuminated the cytological changes of SLEs.…”

Section: Introductionmentioning

confidence: 98%

Accurate Machine Learning Model to Diagnose Chronic Autoimmune Diseases Utilizing Information From B Cells and Monocytes

Chen

Wang

et al. 2022

Front. Immunol.

View full text Add to dashboard Cite

Heterogeneity and limited comprehension of chronic autoimmune disease pathophysiology cause accurate diagnosis a challenging process. With the increasing resources of single-cell sequencing data, a reasonable way could be found to address this issue. In our study, with the use of large-scale public single-cell RNA sequencing (scRNA-seq) data, analysis of dataset integration (3.1 × 105 PBMCs from fifteen SLE patients and eight healthy donors) and cellular cross talking (3.8 × 105 PBMCs from twenty-eight SLE patients and eight healthy donors) were performed to identify the most crucial information characterizing SLE. Our findings revealed that the interactions among the PBMC subpopulations of SLE patients may be weakened under the inflammatory microenvironment, which could result in abnormal emergences or variations in signaling patterns within PBMCs. In particular, the alterations of B cells and monocytes may be the most significant findings. Utilizing this powerful information, an efficient mathematical model of unbiased random forest machine learning was established to distinguish SLE patients from healthy donors via not only scRNA-seq data but also bulk RNA-seq data. Surprisingly, our mathematical model could also accurately identify patients with rheumatoid arthritis and multiple sclerosis, not just SLE, via bulk RNA-seq data (derived from 688 samples). Since the variations in PBMCs should predate the clinical manifestations of these diseases, our machine learning model may be feasible to develop into an efficient tool for accurate diagnosis of chronic autoimmune diseases.

show abstract

“…In recent years, machine learning and artificial intelligence have been widely adopted in biomedical fields and show their superior performance over conventional models. , For example, single-cell RNA-sequencing data have been used to predict patient phenotypes, determine disease status, and stratify immune responses. , These methods are limited in practical use because of high cost and relatively low number of cells . High-multiplex cytometry is relatively affordable to characterize dozens of samples or more through machine learning algorithms DGCyTOF and DeepCyTOF. , But the studies on predicting disease status and progression are still very limited due to the complexity and expensive instruments.…”

Section: Introductionmentioning

confidence: 99%

Rapid, High-Throughput Single-Cell Multiplex In Situ Tagging (MIST) Analysis of Immunological Disease with Machine Learning

et al. 2023

View full text Add to dashboard Cite

The cascade of immune responses involves activation of diverse immune cells and release of a large amount of cytokines, which leads to either normal, balanced inflammation or hyperinflammatory responses and even organ damage by sepsis. Conventional diagnosis of immunological disorders based on multiple cytokines in the blood serum has varied accuracy, and it is difficult to distinguish normal inflammation from sepsis. Herein, we present an approach to detect immunological disorders through rapid, ultrahigh-multiplex analysis of T cells using single-cell multiplex in situ tagging (scMIST) technology. scMIST permits simultaneous detection of 46 markers and cytokines from single cells without the assistance of special instruments. A cecal ligation and puncture sepsis model was built to supply T cells from two groups of mice that survived the surgery or died after 1 day. The scMIST assays have captured the T cell features and the dynamics over the course of recovery. Compared with cytokines in the peripheral blood, T cell markers show different dynamics and cytokine levels. We have applied a random forest machine learning model to single T cells from two groups of mice. Through training, the model has been able to predict the group of mice through T cell classification and majority rule with 94% accuracy. Our approach pioneers the direction of single-cell omics and could be widely applicable to human diseases.

show abstract

CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq

Cited by 5 publications

References 0 publications

Clinical Phenotype Prediction From Single-cell RNA-seq Data using Attention-Based Neural Networks

Clinical Phenotype Prediction From Single-cell RNA-seq Data using Attention-Based Neural Networks

Accurate Machine Learning Model to Diagnose Chronic Autoimmune Diseases Utilizing Information From B Cells and Monocytes

Rapid, High-Throughput Single-Cell Multiplex In Situ Tagging (MIST) Analysis of Immunological Disease with Machine Learning

Contact Info

Product

Resources

About