An Automated Strategy for Unbiased Morphometric Analyses and Classifications of Growth Cones In Vitro

During neural circuit development, attractive or repulsive guidance cue molecules direct growth cones (GCs) to their targets by eliciting cytoskeletal remodeling, which is reflected in their morphology. The experimental power of in vitro neuronal cultures to assay this process and its molecular mechanisms is well established, however, a method to rapidly find and quantify multiple morphological aspects of GCs is lacking. To this end, we have developed a free, easy to use, and fully automated Fiji macro, Conographer, which accurately identifies and measures many morphological parameters of GCs in 2D explant culture images. These measurements are then subjected to principle component analysis and k-means clustering to mathematically classify the GCs as “collapsed” or “extended”. The morphological parameters measured for each GC are found to be significantly different between collapsed and extended GCs, and are sufficient to classify GCs as such with the same level of accuracy as human observers. Application of a known collapse-inducing ligand results in significant changes in all parameters, resulting in an increase in ‘collapsed’ GCs determined by k-means clustering, as expected. Our strategy provides a powerful tool for exploring the relationship between GC morphology and guidance cue signaling, which in particular will greatly facilitate high-throughput studies of the effects of drugs, gene silencing or overexpression, or any other experimental manipulation in the context of an in vitro axon guidance assay.     

Improved tree-ring visualization using autofluorescence

The great diversity of wood anatomical features found in trees worldwide results in a broad variety of growth-ring boundary types that are not always easy to recognize, especially in tropical woods. However, the presence of clearly visible limits between tree rings is essential for any tree-ring studies. Here, we propose the use of autofluorescence of wood in order to enhance tree-ring visualization. The multispectral light emitted from the fluorescence stereomicroscope can be filtered in specific wavelengths to improve the visualization of wood anatomical features. To evaluate the effectiveness of this technique, we compared visualization under natural light, GFP (green fluorescent protein) filter, RFP (red fluorescent protein) filter and UV filter. We tested this technique with a set of 38 tree species with different types of growth-ring boundaries. Although results are species-specific, fluorescence has been shown to improve the visualization of growth-ring boundaries by enhancing the contrast among cell types. It may highlight fibrous zones (e.g. Cavanillesia arborea, Aspidosperma polyneuron), different porosity patterns (e.g. Myracrodruon urundeuva), secretory canals (e.g. Copaifera langsdorffii), and parenchyma bands (e.g. Tipuana tipu). Fluorescence allows the visualization of growth-ring boundaries in species that were previously described as having indistinct growth rings under natural light. For species with clear tree-ring boundaries such as Cedrela fissilis and Hymenaea courbaril, this approach aids the identification of false rings. In addition to the visualization of growth-ring boundaries, autofluorescence may be useful for other qualitative and quantitative analyses of wood anatomy, such as wood identification and automated measurements of anatomical features. Scientists struggling with tree-ring counting and cross-dating due to difficult tree-ring visualization may find fluorescence useful. It may also aid to identify new species suitable for tree-ring studies.     

Seeking functional homogeneity: A framework for definition and classification of fish assemblage types to support assessment tools on temperate reefs

Due to their important role in the ecosystem and high economic value, there is a need to assess the effect of anthropogenic impacts on marine fish assemblages. However, this can only be achieved if variations due to natural causes are known. Moreover, while most assessment tools rely on functional traits, bottom-up habitat classification frameworks tend to use species composition. The present study proposes an innovative framework to define fish assemblage types through metric pairwise constrained k-means (MPCK-means) clustering of sites based on functional guild categories and univariate metrics, an approach that takes into account within-site variability due to the sampling method and natural causes. This was followed by a label-based ensemble clustering approach, which finds patterns that minimise information loss when integrating clustering results from individual metrics. In order to test the method, fish assemblages on 14 nearshore rocky reefs along the Portuguese coast were sampled. The final typology configuration achieved through ensemble clustering consisted of three assemblage types and maintained an average normalised mutual information of 0.605 with the individual clustering results. Nested PERMANOVA found differences among types and the most variable metrics in the face of natural variation were identified. Ultimately, a k-nearest neighbours classifier is proposed to label new sites, based only on environmental variables that are unlikely to be directly affected by the presence of anthropogenic impacts. Optimal performance for the classification model was achieved with inverse distance-weighted voting of the 4 nearest neighbours with an average classification accuracy of 96.08%.     

DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

The proper biogenesis, morphogenesis, and dynamics of subcellular organelles are essential to their metabolic functions. Conventional techniques for identifying, classifying, and quantifying abnormalities in organelle morphology are largely manual and time-consuming, and require specific expertise. Deep learning has the potential to revolutionize image-based screens by greatly improving their scope, speed, and efficiency. Here, we used transfer learning and a convolutional neural network (CNN) to analyze over 47,000 confocal microscopy images from Arabidopsis wild-type and mutant plants with abnormal division of one of three essential energy organelles: chloroplasts, mitochondria, or peroxisomes. We have built a deep-learning framework, DeepLearnMOR (Deep Learning of the Morphology of Organelles), which can rapidly classify image categories and identify abnormalities in organelle morphology with over 97% accuracy. Feature visualization analysis identified important features used by the CNN to predict morphological abnormalities, and visual clues helped to better understand the decision-making process, thereby validating the reliability and interpretability of the neural network. This framework establishes a foundation for future larger-scale research with broader scopes and greater data set diversity and heterogeneity.

An automated and explainable deep-learning framework allows rapidly classifying abnormalities in organelle morphology.     

Predicting membrane protein types by fusing composite protein sequence features into pseudo amino acid composition

Membrane proteins are vital type of proteins that serve as channels, receptors, and energy transducers in a cell. Prediction of membrane protein types is an important research area in bioinformatics. Knowledge of membrane protein types provides some valuable information for predicting novel example of the membrane protein types. However, classification of membrane protein types can be both time consuming and susceptible to errors due to the inherent similarity of membrane protein types. In this paper, neural networks based membrane protein type prediction system is proposed. Composite protein sequence representation (CPSR) is used to extract the features of a protein sequence, which includes seven feature sets; amino acid composition, sequence length, 2 gram exchange group frequency, hydrophobic group, electronic group, sum of hydrophobicity, and R-group. Principal component analysis is then employed to reduce the dimensionality of the feature vector. The probabilistic neural network (PNN), generalized regression neural network, and support vector machine (SVM) are used as classifiers. A high success rate of 86.01% is obtained using SVM for the jackknife test. In case of independent dataset test, PNN yields the highest accuracy of 95.73%. These classifiers exhibit improved performance using other performance measures such as sensitivity, specificity, Mathew's correlation coefficient, and F-measure. The experimental results show that the prediction performance of the proposed scheme for classifying membrane protein types is the best reported, so far. This performance improvement may largely be credited to the learning capabilities of neural networks and the composite feature extraction strategy, which exploits seven different properties of protein sequences. The proposed Mem-Predictor can be accessed at http://111.68.99.218/Mem-Predictor.     

Feasibility study of stain-free classification of cell apoptosis based on diffraction imaging flow cytometry and supervised machine learning techniques

This study was to explore the feasibility of prediction and classification of cells in different stages of apoptosis with a stain-free method based on diffraction images and supervised machine learning. Apoptosis was induced in human chronic myelogenous leukemia K562 cells by cis-platinum (DDP). A newly developed technique of polarization diffraction imaging flow cytometry (p-DIFC) was performed to acquire diffraction images of the cells in three different statuses (viable, early apoptotic and late apoptotic/necrotic) after cell separation through fluorescence activated cell sorting with Annexin V-PE and SYTOX® Green double staining. The texture features of the diffraction images were extracted with in-house software based on the Gray-level co-occurrence matrix algorithm to generate datasets for cell classification with supervised machine learning method. Therefore, this new method has been verified in hydrogen peroxide induced apoptosis model of HL-60. Results show that accuracy of higher than 90% was achieved respectively in independent test datasets from each cell type based on logistic regression with ridge estimators, which indicated that p-DIFC system has a great potential in predicting and classifying cells in different stages of apoptosis.     

OpenCyto: An Open Source Infrastructure for Scalable,Robust, Reproducible,and Automated,End-to-End Flow Cytometry Data Analysis

Flow cytometry is used increasingly in clinical research for cancer, immunology and vaccines. Technological advances in cytometry instrumentation are increasing the size and dimensionality of data sets, posing a challenge for traditional data management and analysis. Automated analysis methods, despite a general consensus of their importance to the future of the field, have been slow to gain widespread adoption. Here we present OpenCyto, a new BioConductor infrastructure and data analysis framework designed to lower the barrier of entry to automated flow data analysis algorithms by addressing key areas that we believe have held back wider adoption of automated approaches. OpenCyto supports end-to-end data analysis that is robust and reproducible while generating results that are easy to interpret. We have improved the existing, widely used core BioConductor flow cytometry infrastructure by allowing analysis to scale in a memory efficient manner to the large flow data sets that arise in clinical trials, and integrating domain-specific knowledge as part of the pipeline through the hierarchical relationships among cell populations. Pipelines are defined through a text-based csv file, limiting the need to write data-specific code, and are data agnostic to simplify repetitive analysis for core facilities. We demonstrate how to analyze two large cytometry data sets: an intracellular cytokine staining (ICS) data set from a published HIV vaccine trial focused on detecting rare, antigen-specific T-cell populations, where we identify a new subset of CD8 T-cells with a vaccine-regimen specific response that could not be identified through manual analysis, and a CyTOF T-cell phenotyping data set where a large staining panel and many cell populations are a challenge for traditional analysis. The substantial improvements to the core BioConductor flow cytometry packages give OpenCyto the potential for wide adoption. It can rapidly leverage new developments in computational cytometry and facilitate reproducible analysis in a unified environment.

This is a PLOS Computational Biology Software Article.

     

ChrNet: A re-trainable chromosome-based 1D convolutional neural network for predicting immune cell types

Cells from our immune system detect and kill pathogens to protect our body against various diseases. However, current methods for determining cell types have some major limitations, such as being time-consuming and with low throughput, etc. Immune cells that are associated with cancer tissues play a critical role in revealing tumor development. Identifying the immune composition within tumor microenvironment in a timely manner will be helpful in improving clinical prognosis and therapeutic management for cancer. Although unsupervised clustering approaches have been prevailing to process scRNA-seq datasets, their results vary among studies with different input parameters and sizes, and the identification of the cell types of the clusters is still very challenging. Genes in human genome can be aligned to chromosomes with specific orders. Hence, we hypothesize incorporating this information into our learning model will potentially improve the cell type classification performance. In order to utilize gene positional information, we introduced ChrNet, a novel chromosome-specific re-trainable supervised learning method based on one-dimensional convolutional neural network (1D-CNN). By benchmarking with several models, our model shows superior performance in immune cell type profiling with larger than 90% accuracy. It is expected that this approach can become a reference architecture for other cell type classification methods. Our ChrNet tool is available online at: https://github.com/Krisloveless/ChrNet.     

PanClassif: Improving pan cancer classification of single cell RNA-seq gene expression data using machine learning

Cancer is one of the major causes of human death per year. In recent years, cancer identification and classification using machine learning have gained momentum due to the availability of high throughput sequencing data. Using RNA-seq, cancer research is blooming day by day and new insights of cancer and related treatments are coming into light. In this paper, we propose PanClassif, a method that requires a very few and effective genes to detect cancer from RNA-seq data and is able to provide performance gain in several wide range machine learning classifiers. We have taken 22 types of cancer samples from The Cancer Genome Atlas (TCGA) having 8287 cancer samples and 680 normal samples. Firstly, PanClassif uses k-Nearest Neighbour (k-NN) smoothing to smooth the samples to handle noise in the data. Then effective genes are selected by Anova based test. For balancing the train data, PanClassif applies an oversampling method, SMOTE. We have performed comprehensive experiments on the datasets using several classification algorithms. Experimental results shows that PanClassif outperform existing state-of-the-art methods available and shows consistent performance for two single cell RNA-seq datasets taken from Gene Expression Omnibus (GEO). PanClassif improves performances of a wide variety of classifiers for both binary cancer prediction and multi-class cancer classification. PanClassif is available as a python package (https://pypi.org/project/panclassif/). All the source code and materials of PanClassif are available at https://github.com/Zwei-inc/panclassif.     

Ultrasonic Vocalizations of Male Mice Differ among Species and Females Show Assortative Preferences for Male Calls

Male house mice (Mus musculus) emit ultrasonic vocalizations (USVs) during courtship, which attract females, and we aimed to test whether females use these vocalizations for species or subspecies recognition of potential mates. We recorded courtship USVs of males from different Mus species, Mus musculus subspecies, and populations (F1 offspring of wild-caught Mus musculus musculus, Mus musculus domesticus (and F1 hybrid crosses), and Mus spicilegus), and we conducted playback experiments to measure female preferences for male USVs. Male vocalizations contained at least seven distinct syllable types, whose frequency of occurrence varied among species, subspecies, and populations. Detailed analyses of multiple common syllable types indicated that Mus musculus and Mus spicilegus could be discriminated based on spectral and temporal characteristics of their vocalizations, and populations of Mus musculus were also distinctive regardless of the classification model used. Females were able to discriminate USVs from different species, and showed assortative preferences for conspecific males. We found no evidence that females discriminate USVs of males from a different subspecies or separate populations of the same species, even though our spectral analyses identified acoustic features that differ between species, subspecies, and populations of the same species. Our results provide the first comparison of USVs between Mus species or between Mus musculus subspecies, and the first evidence that male USVs potentially facilitate species recognition.     

In situ quantification of microcarrier animal cell cultures using near-infrared spectroscopy

In-line monitoring tools are still required to understand and control animal cell processes, particularly in the case of vaccine production. Here, in situ near-infrared spectroscopy (NIRS) quantification of components in culture media was performed using microcarrier-based cultivations of adherent Vero cells. Because microcarriers were found to interfere with NIRS spectra acquisition, a suitable and innovative in situ calibration was developed for bioreactor cultures. A reliable and accurate NIRS technique for the quantification of glucose and lactate was established, with a calibration standard error of 0.30 and 0.21 g l⁻¹, respectively. The robustness of this method was evaluated by performing NIRS calibration with operating conditions similar to those of industrial processes, including parameters such as microcarrier concentrations, cell seeding states and changes in analyte concentration due to feed and harvest strategies. Based on this calibration procedure, the predicted analyte concentrations in unknown samples was measured by NIRS analyses with an accuracy of 0.36 g l⁻¹ for glucose and 0.29 g l⁻¹ for lactate.     

Two-color fluorescent probes for imaging the dipole potential of cell plasma membranes

The dipole potential (Ψ_d) constitutes a large and functionally important part of the electrostatic potential of cell plasma membranes. However, its direct measurement is not possible. Herein, new 3-hydroxyflavone fluorescent probes were developed that respond strongly to Ψ_d changes by a variation of the intensity ratio of their two well-separated fluorescence bands. Using fluorescence spectroscopy with cell suspensions and confocal microscopy with adherent cells, we showed, for the first time, two-color fluorescence ratiometric measurement and visualization of Ψ_d in cell plasma membranes. Using this new tool, a heterogeneous distribution of this potential within the membrane was evidenced.     

Profiling 26,000 Aplysia californica neurons by single cell mass spectrometry reveals neuronal populations with distinct neuropeptide profiles

Neuropeptides are a chemically diverse class of cell-to-cell signaling molecules that are widely expressed throughout the central nervous system, often in a cell-specific manner. While cell-to-cell differences in neuropeptides is expected, it is often unclear how exactly neuropeptide expression varies among neurons. Here we created a microscopy-guided, high-throughput single cell matrix-assisted laser desorption/ionization mass spectrometry approach to investigate the neuropeptide heterogeneity of individual neurons in the central nervous system of the neurobiological model Aplysia californica, the California sea hare. In all, we analyzed more than 26,000 neurons from 18 animals and assigned 866 peptides from 66 prohormones by mass matching against an in silico peptide library generated from known Aplysia prohormones retrieved from the UniProt database. Louvain–Jaccard (LJ) clustering of mass spectra from individual neurons revealed 40 unique neuronal populations, or LJ clusters, each with a distinct neuropeptide profile. Prohormones and their related peptides were generally found in single cells from ganglia consistent with the prohormones’ previously known ganglion localizations. Several LJ clusters also revealed the cellular colocalization of behaviorally related prohormones, such as an LJ cluster exhibiting achatin and neuropeptide Y, which are involved in feeding, and another cluster characterized by urotensin II, small cardiac peptide, sensorin A, and FRFa, which have shown activity in the feeding network or are present in the feeding musculature. This mass spectrometry–based approach enables the robust categorization of large cell populations based on single cell neuropeptide content and is readily adaptable to the study of a range of animals and tissue types.     

Trustworthiness and metrics in visualizing similarity of gene expression

Background

Conventionally, the first step in analyzing the large and high-dimensional data sets measured by microarrays is visual exploration. Dendrograms of hierarchical clustering, self-organizing maps (SOMs), and multidimensional scaling have been used to visualize similarity relationships of data samples. We address two central properties of the methods: (i) Are the visualizations trustworthy, i.e., if two samples are visualized to be similar, are they really similar? (ii) The metric. The measure of similarity determines the result; we propose using a new learning metrics principle to derive a metric from interrelationships among data sets.

Results

The trustworthiness of hierarchical clustering, multidimensional scaling, and the self-organizing map were compared in visualizing similarity relationships among gene expression profiles. The self-organizing map was the best except that hierarchical clustering was the most trustworthy for the most similar profiles. Trustworthiness can be further increased by treating separately those genes for which the visualization is least trustworthy. We then proceed to improve the metric. The distance measure between the expression profiles is adjusted to measure differences relevant to functional classes of the genes. The genes for which the new metric is the most different from the usual correlation metric are listed and visualized with one of the visualization methods, the self-organizing map, computed in the new metric.

Conclusions

The conjecture from the methodological results is that the self-organizing map can be recommended to complement the usual hierarchical clustering for visualizing and exploring gene expression data. Discarding the least trustworthy samples and improving the metric still improves it.

     

In situ quantification of microcarrier animal cell cultures using near-infrared spectroscopy

In-line monitoring tools are still required to understand and control animal cell processes, particularly in the case of vaccine production. Here, in situ near-infrared spectroscopy (NIRS) quantification of components in culture media was performed using microcarrier-based cultivations of adherent Vero cells. Because microcarriers were found to interfere with NIRS spectra acquisition, a suitable and innovative in situ calibration was developed for bioreactor cultures. A reliable and accurate NIRS technique for the quantification of glucose and lactate was established, with a calibration standard error of 0.30 and 0.21 g l⁻¹, respectively. The robustness of this method was evaluated by performing NIRS calibration with operating conditions similar to those of industrial processes, including parameters such as microcarrier concentrations, cell seeding states and changes in analyte concentration due to feed and harvest strategies. Based on this calibration procedure, the predicted analyte concentrations in unknown samples was measured by NIRS analyses with an accuracy of 0.36 g l⁻¹ for glucose and 0.29 g l⁻¹ for lactate.     

Digital cell quantification identifies global immune cell dynamics during influenza infection

Hundreds of immune cell types work in coordination to maintain tissue homeostasis. Upon infection, dramatic changes occur with the localization, migration, and proliferation of the immune cells to first alert the body of the danger, confine it to limit spreading, and finally extinguish the threat and bring the tissue back to homeostasis. Since current technologies can follow the dynamics of only a limited number of cell types, we have yet to grasp the full complexity of global in vivo cell dynamics in normal developmental processes and disease. Here, we devise a computational method, digital cell quantification (DCQ), which combines genome‐wide gene expression data with an immune cell compendium to infer in vivo changes in the quantities of 213 immune cell subpopulations. DCQ was applied to study global immune cell dynamics in mice lungs at ten time points during 7 days of flu infection. We find dramatic changes in quantities of 70 immune cell types, including various innate, adaptive, and progenitor immune cells. We focus on the previously unreported dynamics of four immune dendritic cell subtypes and suggest a specific role for CD103⁺ CD11b⁻ DCs in early stages of disease and CD8⁺ pDC in late stages of flu infection.     

Defining reference sequences for Nocardia species by similarity and clustering analyses of 16S rRNA gene sequence data

Background

The intra- and inter-species genetic diversity of bacteria and the absence of ‘reference’, or the most representative, sequences of individual species present a significant challenge for sequence-based identification. The aims of this study were to determine the utility, and compare the performance of several clustering and classification algorithms to identify the species of 364 sequences of 16S rRNA gene with a defined species in GenBank, and 110 sequences of 16S rRNA gene with no defined species, all within the genus Nocardia.

Methods

A total of 364 16S rRNA gene sequences of Nocardia species were studied. In addition, 110 16S rRNA gene sequences assigned only to the Nocardia genus level at the time of submission to GenBank were used for machine learning classification experiments. Different clustering algorithms were compared with a novel algorithm or the linear mapping (LM) of the distance matrix. Principal Components Analysis was used for the dimensionality reduction and visualization.

Results

The LM algorithm achieved the highest performance and classified the set of 364 16S rRNA sequences into 80 clusters, the majority of which (83.52%) corresponded with the original species. The most representative 16S rRNA sequences for individual Nocardia species have been identified as ‘centroids’ in respective clusters from which the distances to all other sequences were minimized; 110 16S rRNA gene sequences with identifications recorded only at the genus level were classified using machine learning methods. Simple kNN machine learning demonstrated the highest performance and classified Nocardia species sequences with an accuracy of 92.7% and a mean frequency of 0.578.

Conclusion

The identification of centroids of 16S rRNA gene sequence clusters using novel distance matrix clustering enables the identification of the most representative sequences for each individual species of Nocardia and allows the quantitation of inter- and intra-species variability.     

Characterization of a new liver- and kidney-specific pfkfb3 isozyme that is downregulated by cell proliferation and dedifferentiation

The bifunctional enzyme 6-phosphofructo-2-kinase/fructose 2,6-bisphosphatase (PFK-2) catalyzes the synthesis and degradation of fructose 2,6-bisphosphate (Fru-2,6-P₂), a signalling molecule that controls the balance between glycolysis and gluconeogenesis in several cell types. Four genes, designated Pfkfb1-4, code several PFK-2 isozymes that differ in their kinetic properties, molecular masses, and regulation by protein kinases. In rat tissues, Pfkfb3 gene accounts for eight splice variants and two of them, ubiquitous and inducible PFK-2 isozymes, have been extensively studied and related to cell proliferation and tumour metabolism. Here, we characterize a new kidney- and liver-specific Pfkfb3 isozyme, a product of the RB2K3 splice variant, and demonstrate that its expression, in primary cultured hepatocytes, depends on hepatic cell proliferation and dedifferentiation. In parallel, our results provide further evidence that ubiquitous PFK-2 is a crucial isozyme in supporting growing and proliferant cell metabolism.