Dataset Information

Inferring phenotypic properties from single-cell characteristics.

ABSTRACT: Flow cytometry provides multi-dimensional data at the single-cell level. Such data contain information about the cellular heterogeneity of bulk samples, making it possible to correlate single-cell features with phenotypic properties of bulk tissues. Predicting phenotypes from single-cell measurements is a difficult challenge that has not been extensively studied. The 6th Dialogue for Reverse Engineering Assessments and Methods (DREAM6) invited the research community to develop solutions to a computational challenge: classifying acute myeloid leukemia (AML) positive patients and healthy donors using flow cytometry data. DREAM6 provided flow cytometry data for 359 normal and AML samples, and the class labels for half of the samples. Researchers were asked to predict the class labels of the remaining half. This paper describes one solution that was constructed by combining three algorithms: spanning-tree progression analysis of density-normalized events (SPADE), earth mover's distance, and a nearest-neighbor classifier called Relief. This solution was among the top-performing methods that achieved 100% prediction accuracy.

SUBMITTER: Qiu P

PROVIDER: S-EPMC3360688 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Inferring phenotypic properties from single-cell characteristics.

Qiu Peng P

PloS one 20120525 5

Flow cytometry provides multi-dimensional data at the single-cell level. Such data contain information about the cellular heterogeneity of bulk samples, making it possible to correlate single-cell features with phenotypic properties of bulk tissues. Predicting phenotypes from single-cell measurements is a difficult challenge that has not been extensively studied. The 6th Dialogue for Reverse Engineering Assessments and Methods (DREAM6) invited the research community to develop solutions to a com ...[more]

PMID: 22662133

Similar Datasets

Project description:Mucosa-associated invariant T (MAIT) cells are unconventional, innate-like T lymphocytes that recognize vitamin B metabolites of microbial origin among other antigens displayed by the monomorphic molecule MHC class I-related protein 1 (MR1). Abundant in human tissues, reactive to local inflammatory cues, and endowed with immunomodulatory and cytolytic functions, MAIT cells are likely to play key roles in human malignancies. They accumulate in various tumor microenvironments (TMEs) where they often lose some of their functional capacities. However, the potential roles of MAIT cells in anticancer immunity or cancer progression and their significance in shaping clinical outcomes remain largely unknown. In this study, we analyzed publicly available bulk and single-cell tumor transcriptomic datasets to investigate the tissue distribution, phenotype, and prognostic significance of MAIT cells across several human cancers. We found that expanded MAIT cell clonotypes were often shared between the blood, tumor tissue and adjacent healthy tissue of patients with colorectal, hepatocellular, and non-small cell lung carcinomas. Gene expression comparisons between tumor-infiltrating and healthy tissue MAIT cells revealed the presence of activation and/or exhaustion programs within the TMEs of primary hepatocellular and colorectal carcinomas. Interestingly, in basal and squamous cell carcinomas of the skin, programmed cell death-1 (PD-1) blockade upregulated the expression of several effector genes in tumor-infiltrating MAIT cells. We derived a signature comprising stable and specific MAIT cell gene markers across several tissue compartments and cancer types. By applying this signature to estimate MAIT cell abundance in pan-cancer gene expression data, we demonstrate that a heavier intratumoral MAIT cell presence is positively correlated with a favorable prognosis in esophageal carcinoma but predicts poor overall survival in colorectal and squamous cell lung carcinomas. Finally, in colorectal carcinoma and four other cancer types, we found a positive correlation between MR1 expression and estimated MAIT cell abundance. Collectively, our findings indicate that MAIT cells serve important but diverse roles in human cancers. Our work provides useful models and resources that employ gene expression data platforms to enable future studies in the realm of MAIT cell biology.

Project description:BackgroundCopy number alteration (CNA) is one of the major genomic variations that frequently occur in cancers, and accurate inference of CNAs is essential for unmasking intra-tumor heterogeneity (ITH) and tumor evolutionary history. Single-cell DNA sequencing (scDNA-seq) makes it convenient to profile CNAs at single-cell resolution, and thus aids in better characterization of ITH. Despite that several computational methods have been proposed to decipher single-cell CNAs, their performance is limited in either breakpoint detection or copy number estimation due to the high dimensionality and noisy nature of read counts data.ResultsBy treating breakpoint detection as a process to segment high dimensional read count sequence, we develop a novel method called DeepCNA for cross-cell segmentation of read count sequence and per-cell inference of CNAs. To cope with the difficulty of segmentation, an autoencoder (AE) network is employed in DeepCNA to project the original data into a low-dimensional space, where the breakpoints can be efficiently detected along each latent dimension and further merged to obtain the final breakpoints. Unlike the existing methods that manually calculate certain statistics of read counts to find breakpoints, the AE model makes it convenient to automatically learn the representations. Based on the inferred breakpoints, we employ a mixture model to predict copy numbers of segments for each cell, and leverage expectation-maximization algorithm to efficiently estimate cell ploidy by exploring the most abundant copy number state. Benchmarking results on simulated and real data demonstrate our method is able to accurately infer breakpoints as well as absolute copy numbers and surpasses the existing methods under different test conditions. DeepCNA can be accessed at: https://github.com/zhyu-lab/deepcna .ConclusionsProfiling single-cell CNAs based on deep learning is becoming a new paradigm of scDNA-seq data analysis, and DeepCNA is an enhancement to the current arsenal of computational methods for investigating cancer genomics.

Dataset Information

Inferring phenotypic properties from single-cell characteristics.

Publications

Inferring phenotypic properties from single-cell characteristics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets