Data normalization is vital to single-cell sequencing, addressing limitations presented by low input material and various forms of bias or noise present in the sequencing process. Several such normalization methods exist, some of which rely on spike-in genes, molecules added in known quantities to serve as a basis for a normalization model. Depending on available information and the type of data, some methods may express certain advantages over others. We compare the effectiveness of seven available normalization methods designed specifically for single-cell sequencing using two real data sets containing spike-in genes and one simulation study. Additionally, we test those methods not dependent on spike-in genes using a real data set with three distinct cellcycle states and a real data set under the 10X Genomics GemCode platform with multiple cell types represented. We demonstrate the differences in effectiveness for the featured methods using visualization and classification assessment and conclude which methods are preferable for normalizing a certain type of data for further downstream analysis, such as classification or differential analysis. The comparison in computational time for all methods is addressed as well.

Motivation Single-cell RNA sequencing (scRNA-seq) has become an important tool to unravel cellular heterogeneity, discover new cell (sub)types, and understand cell development at single-cell resolution. However, one major challenge to scRNA-seq research is the presence of “drop-out” events, which usually is due to extremely low mRNA input or the stochastic nature of gene expression. In this paper, we present a novel Single-Cell RNA-seq Drop-Out Correction (scDoc) method, imputing drop-out events by borrowing information for the same gene from highly similar cells. Results scDoc is the first method that directly involves drop-out information to accounting for cell-to-cell similarity estimation, which is crucial in scRNA-seq drop-out imputation but has not been appropriately examined. We evaluated the performance of scDoc using both simulated data and real scRNA-seq studies. Results show that scDoc outperforms the existing imputation methods in reference to data visualization, cell subpopulation identification, and differential expression detection in scRNA-seq data. Availability R code is available at https://github.com/anlingUA/scDoc Supplementary information Supplementary data are available at Bioinformatics online.

Single-cell RNA sequencing (scRNA-seq) reveals the transcriptome diversity in heterogeneous cell populations as it allows researchers to study gene expression at single-cell resolution. The latest advances in scRNA-seq technology have made it possible to profile tens of thousands of individual cells simultaneously. However, the technology also increases the number of missing values, i. e, dropouts, from technical constraints, such as amplification failure during the reverse transcription step. The resulting sparsity of scRNA-seq count data can be very high, with greater than 90% of data entries being zeros, which becomes an obstacle for clustering cell types. Current imputation methods are not robust in the case of high sparsity. In this study, we develop a Neural Network-based Imputation for scRNA-seq count data, NISC. It uses autoencoder, coupled with a weighted loss function and regularization, to correct the dropouts in scRNA-seq count data. A systematic evaluation shows that NISC is an effective imputation approach for handling sparse scRNA-seq count data, and its performance surpasses existing imputation methods in cell type identification.

A straightforward method for classifying heavy metal ions in water is proposed using statistical classification and clustering techniques from non-specific microparticle scattering data. A set of carboxylated polystyrene microparticles of sizes 0.91, 0.75 and 0.40 µm was mixed with the solutions of nine heavy metal ions and two control cations, and scattering measurements were collected at two angles optimized for scattering from non-aggregated and aggregated particles. Classification of these observations was conducted and compared among several machine learning techniques, including linear discriminant analysis, support vector machine analysis, K-means clustering and K-medians clustering. This study found the highest classification accuracy using the linear discriminant and support vector machine analysis, each reporting high classification rates for heavy metal ions with respect to the model. This may be attributed to moderate correlation between detection angle and particle size. These classification models provide reasonable discrimination between most ion species, with the highest distinction seen for Pb(II), Cd(II), Ni(II) and Co(II), followed by Fe(II) and Fe(III), potentially due to its known sorption with carboxyl groups. The support vector machine analysis was also applied to three different mixture solutions representing leaching from pipes and mine tailings, and showed good correlation with single-species data, specifically with Pb(II) and Ni(II). With more expansive training data and further processing, this method shows promise for low-cost and portable heavy metal identification and sensing.