MISC: missing imputation for single-cell RNA sequencing data

How missing value imputation is confounded with batch effects and what you can do about it

In data-processing pipelines, upstream steps can influence downstream processes because of their sequential nature. Among these data-processing steps, batch effect (BE) correction (BEC) and missing value imputation (MVI) are crucial for ensuring data suitability for advanced modeling and reducing the likelihood of false discoveries. Although BEC-MVI interactions are not well studied, they are ultimately interdependent. Batch sensitization can improve the quality of MVI. Conversely, accounting for missingness also improves proper BE estimation in BEC. Here, we discuss how BEC and MVI are interconnected and interdependent. We show how batch sensitization can improve any MVI and bring attention to the idea of BE-associated missing values (BEAMs). Finally, we discuss how batch-class imbalance problems can be mitigated by borrowing ideas from machine learning.

Multidimensional landscape of non-alcoholic fatty liver disease-related disease spectrum uncovered by big omics data: Profiling evidence and new perspectives

Characterized by hepatic lipid accumulation, non-alcoholic fatty liver disease (NAFLD) is a multifactorial metabolic disorder that could promote the progression of non-alcoholic steatohepatitis (NASH), cirrhosis, and hepatocellular carcinoma (HCC). Benefiting from recent advances in omics technologies, such as high-throughput sequencing, voluminous profiling data in HCC-integrated molecular science into clinical medicine helped clinicians with rational guidance for treatments. In this review, we conclude the majority of publicly available omics data on the NAFLD-related disease spectrum and bring up new insights to inspire next-generation therapeutics against this increasingly prevalent disease spectrum in the post-genomic era.

Correcting Bias in Allele Frequency Estimates Due to an Observation Threshold: A Markov Chain Analysis

There are many problems in biology and related disciplines involving stochasticity, where a signal can only be detected when it lies above a threshold level, while signals lying below threshold are simply not detected. A consequence is that the detected signal is conditioned to lie above threshold, and is not representative of the actual signal. In this work, we present some general results for the conditioning that occurs due to the existence of such an observational threshold. We show that this conditioning is relevant, for example, to gene-frequency trajectories, where many loci in the genome are simultaneously measured in a given generation. Such a threshold can lead to severe biases of allele frequency estimates under purifying selection. In the analysis presented, within the context of Markov chains such as the Wright-Fisher model, we address two key questions: (1) "What is a natural measure of the strength of the conditioning associated with an observation threshold?" (2) "What is a principled way to correct for the effects of the conditioning?". We answer the first question in terms of a proportion. Starting with a large number of trajectories, the relevant quantity is the proportion of these trajectories that are above threshold at a later time and hence are detected. The smaller the value of this proportion, the stronger the effects of conditioning. We provide an approximate analytical answer to the second question, that corrects the bias produced by an observation threshold, and performs to reasonable accuracy in the Wright-Fisher model for biologically plausible parameter values.

Correlation between targeted RNAseq signature of breast cancer CTCs and onset of bone-only metastases

BACKGROUND

Bone is the most frequent site of metastases from breast cancer (BC), but no biomarkers are yet available to predict skeletal dissemination.

METHODS

We attempted to identify a gene signature correlated with bone metastasis (BM) onset in circulating tumour cells (CTCs), isolated by a DEPArray-based protocol from 40 metastatic BC patients and grouped according to metastasis sites, namely "BM" (bone-only), "ES" (extra-skeletal) or BM + ES (bone + extra-skeletal).

RESULTS

A 134-gene panel was first validated through targeted RNA sequencing (RNAseq) on sub-clones of the MDA-MB-231 BC cell line with variable organotropism, which successfully shaped their clustering. The panel was then applied to CTC groups and, in particular, the "BM" vs "ES" CTC comparison revealed 31 differentially expressed genes, including MAF, CAPG, GIPC1 and IL1B, playing key prognostic roles in BC.

CONCLUSION

Such evidence confirms that CTCs are suitable biological sources for organotropism investigation through targeted RNAseq and might deserve future applications in wide-scale prospective studies.

Statistics or biology: the zero-inflation controversy about scRNA-seq data

Researchers view vast zeros in single-cell RNA-seq data differently: some regard zeros as biological signals representing no or low gene expression, while others regard zeros as missing data to be corrected. To help address the controversy, here we discuss the sources of biological and non-biological zeros; introduce five mechanisms of adding non-biological zeros in computational benchmarking; evaluate the impacts of non-biological zeros on data analysis; benchmark three input data types: observed counts, imputed counts, and binarized counts; discuss the open questions regarding non-biological zeros; and advocate the importance of transparent analysis.

Single-Cell Analysis of the Transcriptome and Epigenome

Epigenome regulation has emerged as an important mechanism for the maintenance of organ function in health and disease. Dissecting epigenomic alterations and resultant gene expression changes in single cells provides unprecedented resolution and insight into cellular diversity, modes of gene regulation, transcription factor dynamics and 3D genome organization. In this chapter, we summarize the transformative single-cell epigenomic technologies that have deepened our understanding of the fundamental principles of gene regulation. We provide a historical perspective of these methods, brief procedural outline with emphasis on the computational tools used to meaningfully dissect information. Our overall goal is to aid scientists using these technologies in their favorite system of interest.

A review of computational strategies for denoising and imputation of single-cell transcriptomic data

MOTIVATION

The advancements of single-cell sequencing methods have paved the way for the characterization of cellular states at unprecedented resolution, revolutionizing the investigation on complex biological systems. Yet, single-cell sequencing experiments are hindered by several technical issues, which cause output data to be noisy, impacting the reliability of downstream analyses. Therefore, a growing number of data science methods has been proposed to recover lost or corrupted information from single-cell sequencing data. To date, however, no quantitative benchmarks have been proposed to evaluate such methods.

RESULTS

We present a comprehensive analysis of the state-of-the-art computational approaches for denoising and imputation of single-cell transcriptomic data, comparing their performance in different experimental scenarios. In detail, we compared 19 denoising and imputation methods, on both simulated and real-world datasets, with respect to several performance metrics related to imputation of dropout events, recovery of true expression profiles, characterization of cell similarity, identification of differentially expressed genes and computation time. The effectiveness and scalability of all methods were assessed with regard to distinct sequencing protocols, sample size and different levels of biological variability and technical noise. As a result, we identify a subset of versatile approaches exhibiting solid performances on most tests and show that certain algorithmic families prove effective on specific tasks but inefficient on others. Finally, most methods appear to benefit from the introduction of appropriate assumptions on noise distribution of biological processes.

Multiomic Big Data Analysis Challenges: Increasing Confidence in the Interpretation of Artificial Intelligence Assessments

The need for holistic molecular measurements to better understand disease initiation, development, diagnosis, and therapy has led to an increasing number of multiomic analyses. The wealth of information available from multiomic assessments, however, requires both the evaluation and interpretation of extremely large data sets, limiting analysis throughput and ease of adoption. Computational methods utilizing artificial intelligence (AI) provide the most promising way to address these challenges, yet despite the conceptual benefits of AI and its successful application in singular omic studies, the widespread use of AI in multiomic studies remains limited. Here, we discuss present and future capabilities of AI techniques in multiomic studies while introducing analytical checks and balances to validate the computational conclusions.

An efficient ensemble method for missing value imputation in microarray gene expression data

BACKGROUND

The genomics data analysis has been widely used to study disease genes and drug targets. However, the existence of missing values in genomics datasets poses a significant problem, which severely hinders the use of genomics data. Current imputation methods based on a single learner often explores less known genomic data information for imputation and thus causes the imputation performance loss.

RESULTS

In this study, multiple single imputation methods are combined into an imputation method by ensemble learning. In the ensemble method, the bootstrap sampling is applied for predictions of missing values by each component method, and these predictions are weighted and summed to produce the final prediction. The optimal weights are learned from known gene data in the sense of minimizing a cost function about the imputation error. And the expression of the optimal weights is derived in closed form. Additionally, the performance of the ensemble method is analytically investigated, in terms of the sum of squared regression errors. The proposed method is simulated on several typical genomic datasets and compared with the state-of-the-art imputation methods at different noise levels, sample sizes and data missing rates. Experimental results show that the proposed method achieves the improved imputation performance in terms of the imputation accuracy, robustness and generalization.

CONCLUSION

The ensemble method possesses the superior imputation performance since it can make use of known data information more efficiently for missing data imputation by integrating diverse imputation methods and learning the integration weights in a data-driven way.

A systematic review of machine learning-based missing value imputation techniques

Purpose

The primary aim of this study is to review the studies from different dimensions including type of methods, experimentation setup and evaluation metrics used in the novel approaches proposed for data imputation, particularly in the machine learning (ML) area. This ultimately provides an understanding about how well the proposed framework is evaluated and what type and ratio of missingness are addressed in the proposals. The review questions in this study are (1) what are the ML-based imputation methods studied and proposed during 2010–2020? (2) How the experimentation setup, characteristics of data sets and missingness are employed in these studies? (3) What metrics were used for the evaluation of imputation method?

Design/methodology/approach

The review process went through the standard identification, screening and selection process. The initial search on electronic databases for missing value imputation (MVI) based on ML algorithms returned a large number of papers totaling at 2,883. Most of the papers at this stage were not exactly an MVI technique relevant to this study. The literature reviews are first scanned in the title for relevancy, and 306 literature reviews were identified as appropriate. Upon reviewing the abstract text, 151 literature reviews that are not eligible for this study are dropped. This resulted in 155 research papers suitable for full-text review. From this, 117 papers are used in assessment of the review questions.

Findings

This study shows that clustering- and instance-based algorithms are the most proposed MVI methods. Percentage of correct prediction (PCP) and root mean square error (RMSE) are most used evaluation metrics in these studies. For experimentation, majority of the studies sourced the data sets from publicly available data set repositories. A common approach is that the complete data set is set as baseline to evaluate the effectiveness of imputation on the test data sets with artificially induced missingness. The data set size and missingness ratio varied across the experimentations, while missing datatype and mechanism are pertaining to the capability of imputation. Computational expense is a concern, and experimentation using large data sets appears to be a challenge.

Originality/value

It is understood from the review that there is no single universal solution to missing data problem. Variants of ML approaches work well with the missingness based on the characteristics of the data set. Most of the methods reviewed lack generalization with regard to applicability. Another concern related to applicability is the complexity of the formulation and implementation of the algorithm. Imputations based on k-nearest neighbors (kNN) and clustering algorithms which are simple and easy to implement make it popular across various domains.

Single-Cell Multi-Omics and Its Prospective Application in Cancer Biology

In recent years, the emergence of single-cell omics technologies, which can profile genomics, transcriptomics, epigenomics, and proteomics, has provided unprecedented insights into characteristics of cancer, enabling higher resolution and accuracy to decipher the cellular and molecular mechanisms relating to tumorigenesis, evolution, metastasis, and immune responses. Single-cell multi-omics technologies, which are developed based on the combination of multiple single-cell mono-omics technologies, can simultaneously analyze RNA expression, single nucleotide polymorphism, epigenetic modification, or protein abundance, enabling the in-depth understanding of gene expression regulatory mechanisms. In this review, the state-of-the-art single-cell multi-omics technologies are summarized and the prospects of their application in cancer biology are discussed.

Correction to: MISC: missing imputation for single-cell RNA sequencing data

It was highlighted that the original article [1] contained a typesetting error in the last name of Allon Canaan. This was incorrectly captured as Allon Canaann in the original article which has since been updated.