Machine learning and computer vision approaches for phenotypic profiling

Machine learning models predict coagulopathy in spontaneous intracerebral hemorrhage patients in ER

AIMS

Coagulation abnormality is one of the primary concerns for patients with spontaneous intracerebral hemorrhage admitted to ER. Conventional laboratory indicators require hours for coagulopathy diagnosis, which brings difficulties for appropriate intervention within the optimal window. This study evaluates the possibility of building efficient coagulopathy prediction models using data mining and machine learning algorithms.

METHODS

A retrospective cohort enrolled 1668 cases with acute spontaneous intracerebral hemorrhage from three medical centers, excluding those under antithrombotic therapies. Coagulopathy-related clinical parameters were initially screened by univariate analysis. Two machine learning algorithms, the random forest and the support vector machine, were deployed via an approach of four-fold cross-validation to screen out the most important parameters contributing to the occurrence of coagulopathy. Model discrimination was assessed using metrics, including accuracy, precision, recall, and F1 score.

RESULTS

Albumin/globulin ratio, neutrophil count, lymphocyte percentage, aspartate transaminase, alanine transaminase, hemoglobin, platelet count, white blood cell count, neutrophil percentage, systolic and diastolic pressure were identified as major predictors to the occurrence of acute coagulopathy. Compared to support vector machine, the model based on the random forest algorithm showed better accuracy (93.1%, 95% confidence interval [CI]: 0.913-0.950), precision (92.4%, 95% CI: 0.897-0.951), F1 score (91.5%, 95% CI: 0.889-0.964), and recall score (93.6%, 95% CI: 0.909-0.964), and yielded higher area under the receiver operating characteristic curve (AU-ROC) (0.962, 95% CI: 0.942-0.982).

CONCLUSION

The constructed models exhibit good prediction accuracy and efficiency. It might be used in clinical practice to facilitate target intervention for acute coagulopathy in patients with spontaneous intracerebral hemorrhage.

Systematic High-Content Screening of Fluorescently Tagged Yeast Double Mutant Strains

We describe a protocol for high-content screening in budding yeast that can be used to study genetic interactions from a cell biological perspective. This approach can be used to map genetic interactions by monitoring one or more subcellular fluorescent markers of interest. In this case, changes in the morphology or abundance of a subcellular compartment, pathway or bioprocess are monitored in the background of a systematic array of yeast double mutants. Alternatively, the protocol can be used to monitor proteome-wide abundance and localization changes in a double mutant of interest by screening the yeast ORF-GFP collection. The protocol can be readily adapted for high-content screening of triple mutants, other large-scale yeast collections or expanded to screening of multiple growth conditions.

Critical comparison of image analysis workflows for quantitative cell morphological evaluation in assessing cell response to biomaterials

Quantitative image analysis is an important tool in understanding cell fate processes through the study of cell morphological changes in terms of size, shape, number, and orientation. In this context, this work explores systematically the main challenges involved in the quantitative analysis of fluorescence microscopy images and also proposes a new protocol while comparing its outcome with the widely used Image J analysis. It is important to mention that fluorescence microscopy is by far most widely used in biocompatibility analysis (observing cell fate changes) of implantable biomaterials. In this study, we employed two different image analyses toolsets: (i) the conventionally employed ImageJ software, and (ii) a recently developed automated digital image analyses framework, called ImageMKS. While ImageJ offers a powerful toolset for image analyses, it requires sophisticated user expertise to design and iteratively refine the analyses workflow. This workflow primarily comprises a sequence of image transformations that typically involve de-noising and labelling of features. On the other hand, ImageMKS automates the image analyses protocol to a large extent, and thereby mitigates the influence of the user bias on the final results. This aspect is addressed using a case study of C2C12 mouse myoblast cells grown on Poly(vinyldiene difluoride) based polymeric substrates in the presence of an external electric field. In particular, we used a number of fluorescence microscopy images of murine myoblasts (muscle precursor cells) grown on Poly (vinylidene difluoride), PVDF based nanobiocomposites under the influence of electric field. It was observed that when compared with the findings obtained from ImageJ, ImageMKS workflows consistently produced more reliable results that correlated better with the prior studies. Furthermore, the MKS workflows required much less user time, because of their automation.

Next-Generation Lineage Tracing and Fate Mapping to Interrogate Development

Lineage tracing and fate mapping, overlapping yet distinct disciplines to follow cells and their progeny, have evolved rapidly over the last century. Lineage tracing aims to identify all progeny arising from an individual cell, placing them within a lineage hierarchy. The recent emergence of genomic technologies, such as single-cell and spatial transcriptomics, has fostered sophisticated new methods to reconstruct lineage relationships at high resolution. In contrast, fate maps, schematics showing which parts of the embryo will develop into which tissue, have remained relatively static since the 1970s. However, fate maps provide spatial information, often lost in lineage reconstruction, that can offer fundamental mechanistic insight into development. Here, we broadly review the origins of fate mapping and lineage tracing approaches. We focus on the most recent developments in lineage tracing, permitted by advances in single-cell genomics. Finally, we explore the current potential to leverage these new technologies to synthesize high-resolution fate maps and discuss their potential for interrogating development at new depths.

Guidelines for establishing a 3-D printing biofabrication laboratory

Advanced manufacturing and 3D printing are transformative technologies currently undergoing rapid adoption in healthcare, a traditionally non-manufacturing sector. Recent development in this field, largely enabled by merging different disciplines, has led to important clinical applications from anatomical models to regenerative bioscaffolding and devices. Although much research to-date has focussed on materials, designs, processes, and products, little attention has been given to the design and requirements of facilities for enabling clinically relevant biofabrication solutions. These facilities are critical to overcoming the major hurdles to clinical translation, including solving important issues such as reproducibility, quality control, regulations, and commercialization. To improve process uniformity and ensure consistent development and production, large-scale manufacturing of engineered tissues and organs will require standardized facilities, equipment, qualification processes, automation, and information systems. This review presents current and forward-thinking guidelines to help design biofabrication laboratories engaged in engineering model and tissue constructs for therapeutic and non-therapeutic applications.

Towards systems tissue engineering: Elucidating the dynamics, spatial coordination, and individual cells driving emergent behaviors

Biomaterial systems have enabled the in vitro production of complex, emergent tissue behaviors that were not possible with conventional two-dimensional culture systems, allowing for analysis of both normal development and disease processes. We propose that the path towards developing the design parameters for biomaterial systems lies with identifying the molecular drivers of emergent behavior through leveraging technological advances in systems biology, including single cell omics, genetic engineering, and high content imaging. This growing research opportunity at the intersection of the fields of tissue engineering and systems biology - systems tissue engineering - can uniquely interrogate the mechanisms by which complex tissue behaviors emerge with the potential to capture the contribution of i) dynamic regulation of tissue development and dysregulation, ii) single cell heterogeneity and the function of rare cell types, and iii) the spatial distribution and structure of individual cells and cell types within a tissue. By leveraging advances in both biological and materials data science, systems tissue engineering can facilitate the identification of biomaterial design parameters that will accelerate basic science discovery and translation.

Functional genomics, genetic risk profiling and cell phenotypes in neurodegenerative disease

Human genetics provides unbiased insights into the causes of human disease, which can be used to create a foundation for effective ways to more accurately diagnose patients, stratify patients for more successful clinical trials, discover and develop new therapies, and ultimately help patients choose the safest and most promising therapeutic option based on their risk profile. But the process for translating basic observations from human genetics studies into pathogenic disease mechanisms and treatments is laborious and complex, and this challenge has particularly slowed the development of interventions for neurodegenerative disease. In this review, we discuss the many steps in the process, the important considerations at each stage, and some of the latest tools and technologies that are available to help investigators translate insights from human genetics into diagnostic and therapeutic strategies that will lead to the sort of advances in clinical care that make a difference for patients.

AI on a chip

Artificial intelligence (AI) has dramatically changed the landscape of science, industry, defence, and medicine in the last several years. Supported by considerably enhanced computational power and cloud storage, the field of AI has shifted from mostly theoretical studies in the discipline of computer science to diverse real-life applications such as drug design, material discovery, speech recognition, self-driving cars, advertising, finance, medical imaging, and astronomical observation, where AI-produced outcomes have been proven to be comparable or even superior to the performance of human experts. In these applications, what is essentially important for the development of AI is the data needed for machine learning. Despite its prominent importance, the very first process of the AI development, namely data collection and data preparation, is typically the most laborious task and is often a limiting factor of constructing functional AI algorithms. Lab-on-a-chip technology, in particular microfluidics, is a powerful platform for both the construction and implementation of AI in a large-scale, cost-effective, high-throughput, automated, and multiplexed manner, thereby overcoming the above bottleneck. On this platform, high-throughput imaging is a critical tool as it can generate high-content information (e.g., size, shape, structure, composition, interaction) of objects on a large scale. High-throughput imaging can also be paired with sorting and DNA/RNA sequencing to conduct a massive survey of phenotype-genotype relations whose data is too complex to analyze with traditional computational tools, but is analyzable with the power of AI. In addition to its function as a data provider, lab-on-a-chip technology can also be employed to implement the developed AI for accurate identification, characterization, classification, and prediction of objects in mixed, heterogeneous, or unknown samples. In this review article, motivated by the excellent synergy between AI and lab-on-a-chip technology, we outline fundamental elements, recent advances, future challenges, and emerging opportunities of AI with lab-on-a-chip technology or "AI on a chip" for short.

Probing the characteristics and biofunctional effects of disease-affected cells and drug response via machine learning applications

Drug-induced transformations in disease characteristics at the cellular and molecular level offers the opportunity to predict and evaluate the efficacy of pharmaceutical ingredients whilst enabling the optimal design of new and improved drugs with enhanced pharmacokinetics and pharmacodynamics. Machine learning is a promising in-silico tool used to simulate cells with specific disease properties and to determine their response toward drug uptake. Differences in the properties of normal and infected cells, including biophysical, biochemical and physiological characteristics, plays a key role in developing fundamental cellular probing platforms for machine learning applications. Cellular features can be extracted periodically from both the drug treated, infected, and normal cells via image segmentations in order to probe dynamic differences in cell behavior. Cellular segmentation can be evaluated to reflect the levels of drug effect on a distinct cell or group of cells via probability scoring. This article provides an account for the use of machine learning methods to probe differences in the biophysical, biochemical and physiological characteristics of infected cells in response to pharmacokinetics uptake of drug ingredients for application in cancer, diabetes and neurodegenerative disease therapies.

Image-based high-content screening in drug discovery

While target-based drug discovery strategies rely on the precise knowledge of the identity and function of the drug targets, phenotypic drug discovery (PDD) approaches allow the identification of novel drugs based on knowledge of a distinct phenotype. Image-based high-content screening (HCS) is a potent PDD strategy that characterizes small-molecule effects through the quantification of features that depict cellular changes among or within cell populations, thereby generating valuable data sets for subsequent data analysis. However, these data can be complex, making image analysis from large HCS campaigns challenging. Technological advances in image acquisition, processing, and analysis as well as machine-learning (ML) approaches for the analysis of multidimensional data sets have rendered HCS as a viable technology for small-molecule drug discovery. Here, we discuss HCS concepts, current workflows as well as opportunities and challenges of image-based phenotypic screening and data analysis.

Predicting cell lineages using autoencoders and optimal transport

Lineage tracing involves the identification of all ancestors and descendants of a given cell, and is an important tool for studying biological processes such as development and disease progression. However, in many settings, controlled time-course experiments are not feasible, for example when working with tissue samples from patients. Here we present ImageAEOT, a computational pipeline based on autoencoders and optimal transport for predicting the lineages of cells using time-labeled datasets from different stages of a cellular process. Given a single-cell image from one of the stages, ImageAEOT generates an artificial lineage of this cell based on the population characteristics of the other stages. These lineages can be used to connect subpopulations of cells through the different stages and identify image-based features and biomarkers underlying the biological process. To validate our method, we apply ImageAEOT to a benchmark task based on nuclear and chromatin images during the activation of fibroblasts by tumor cells in engineered 3D tissues. We further validate ImageAEOT on chromatin images of various breast cancer cell lines and human tissue samples, thereby linking alterations in chromatin condensation patterns to different stages of tumor progression. Our results demonstrate the promise of computational methods based on autoencoding and optimal transport principles for lineage tracing in settings where existing experimental strategies cannot be used.

Many key biological processes, such as development and disease progression, require analyzing lineages of cells backwards as well as forwards in time. However, current single-cell experiments tend to be destructive to cells, so that a single lineage can only be measured at one point in time. In this work, we introduce a computational framework for predicting the lineage of cells from a single snapshot in time based on measurements of other cells at other time points. The method generates these lineages by computing the most plausible path for a population of cells to transition from one time point to the next, assuming that a cell is more likely to transition to similar cells compared to dissimilar cells. We validate our computational method on imaging data of fibroblasts and cancer cells, though our method could also be applied to other modalities of single-cell data such as genomics and transcriptomics as well as multi-modal single-cell datasets.

Multiple particle tracking analysis in isolated nuclei reveals the mechanical phenotype of leukemia cells

The nucleus is fundamentally composed by lamina and nuclear membranes that enclose the chromatin, nucleoskeletal components and suspending nucleoplasm. The functional connections of this network integrate external stimuli into cell signals, including physical forces to mechanical responses of the nucleus. Canonically, the morphological characteristics of the nucleus, as shape and size, have served for pathologists to stratify and diagnose cancer patients; however, novel biophysical techniques must exploit physical parameters to improve cancer diagnosis. By using multiple particle tracking (MPT) technique on chromatin granules, we designed a SURF (Speeded Up Robust Features)-based algorithm to study the mechanical properties of isolated nuclei and in living cells. We have determined the apparent shear stiffness, viscosity and optical density of the nucleus, and how the chromatin structure influences on these biophysical values. Moreover, we used our MPT-SURF analysis to study the apparent mechanical properties of isolated nuclei from patients of acute lymphoblastic leukemia. We found that leukemia cells exhibited mechanical differences compared to normal lymphocytes. Interestingly, isolated nuclei from high-risk leukemia cells showed increased viscosity than their counterparts from normal lymphocytes, whilst nuclei from relapsed-patient's cells presented higher density than those from normal lymphocytes or standard- and high-risk leukemia cells. Taken together, here we presented how MPT-SURF analysis of nuclear chromatin granules defines nuclear mechanical phenotypic features, which might be clinically relevant.

Efficient phenotypic sex classification of zebrafish using machine learning methods

Sex determination in zebrafish by manual approaches according to current guidelines relies on human observation. These guidelines for sex recognition have proven to be subjective and highly labor-intensive. To address this problem, we present a methodology to automatically classify the phenotypic sex using two machine learning methods: Deep Convolutional Neural Networks (DCNNs) based on the whole fish appearance and Support Vector Machine (SVM) based on caudal fin coloration. Machine learning techniques in sex classification provide potential efficiency with the advantage of automatization and robustness in the prediction process. Furthermore, since developmental plasticity can be influenced by environmental conditions, we have investigated the impact of elevated water temperature during embryogenesis on sex and sex-related differences in color intensity of adult zebrafish. The estimated color intensity based on SVM was then applied to detect the association between coloration and body weight and length. Phenotypic sex classifications using machine learning methods resulted in a high degree of association with the real sex in nontreated animals. In temperature-induced animals, DCNNs reached a performance of 100%, whereas 20% of males were misclassified using SVM due to a lower color intensity. Furthermore, a positive association between color intensity and body weight and length was observed in males. Our study demonstrates that high ambient temperature leads to a lower color intensity in male animals and a positive association of male caudal fin coloration with body weight and length, which appears to play a significant role in sexual attraction. The software developed for sex classification in this study is readily applicable to other species with sex-linked visible phenotypic differences.

Qualifying antibodies for image-based immune profiling and multiplexed tissue imaging

Multiplexed tissue imaging enables precise, spatially resolved enumeration and characterization of cell types and states in human resection specimens. A growing number of methods applicable to formalin-fixed, paraffin-embedded (FFPE) tissue sections have been described, the majority of which rely on antibodies for antigen detection and mapping. This protocol provides step-by-step procedures for confirming the selectivity and specificity of antibodies used in fluorescence-based tissue imaging and for the construction and validation of antibody panels. Although the protocol is implemented using tissue-based cyclic immunofluorescence (t-CyCIF) as an imaging platform, these antibody-testing methods are broadly applicable. We demonstrate assembly of a 16-antibody panel for enumerating and localizing T cells and B cells, macrophages, and cells expressing immune checkpoint regulators. The protocol is accessible to individuals with experience in microscopy and immunofluorescence; some experience in computation is required for data analysis. A typical 30-antibody dataset for 20 FFPE slides can be generated within 2 weeks.

Morphology-based prediction of cancer cell migration using an artificial neural network and a random decision forest

Metastasis is the cause of death in most patients of breast cancer and other solid malignancies. Identification of cancer cells with highly migratory capability to metastasize relies on markers for epithelial-to-mesenchymal transition (EMT), a process increasing cell migration and metastasis. Marker-based approaches are limited by inconsistences among patients, types of cancer, and partial EMT states. Alternatively, we analyzed cancer cell migration behavior using computer vision. Using a microfluidic single-cell migration chip and high-content imaging, we extracted morphological features and recorded migratory direction and speed of breast cancer cells. By applying a Random Decision Forest (RDF) and an Artificial Neural Network (ANN), we achieved over 99% accuracy for cell movement direction prediction and 91% for speed prediction. Unprecedentedly, we identified highly motile cells and non-motile cells based on microscope images and a machine learning model, and pinpointed and validated morphological features determining cell migration, including not only known features related to cell polarization but also novel ones that can drive future mechanistic studies. Predicting cell movement by computer vision and machine learning establishes a ground-breaking approach to analyze cell migration and metastasis.

Integrating Imaging and Omics: Computational Methods and Challenges

Fluorescence microscopy imaging has long been complementary to DNA sequencing- and mass spectrometry–based omics in biomedical research, but these approaches are now converging. On the one hand, omics methods are moving from in vitro methods that average across large cell populations to in situ molecular characterization tools with single-cell sensitivity. On the other hand, fluorescence microscopy imaging has moved from a morphological description of tissues and cells to quantitative molecular profiling with single-molecule resolution. Recent technological developments underpinned by computational methods have started to blur the lines between imaging and omics and have made their direct correlation and seamless integration an exciting possibility. As this trend continues rapidly, it will allow us to create comprehensive molecular profiles of living systems with spatial and temporal context and subcellular resolution. Key to achieving this ambitious goal will be novel computational methods and successfully dealing with the challenges of data integration and sharing as well as cloud-enabled big data analysis.

Patient Registries in Idiopathic Pulmonary Fibrosis

Over the past decade, several large registries of patients with idiopathic pulmonary fibrosis (IPF) have been established. These registries are collecting a wealth of longitudinal data on thousands of patients with this rare disease. The data collected in these registries will be complementary to data collected in clinical trials because the patient populations studied in registries have a broader spectrum of disease severity and comorbidities and can be followed for a longer period of time. Maintaining the quality and completeness of registry databases presents administrative and resourcing challenges, but it is important to ensuring the robustness of the analyses. Data from patient registries have already helped improve understanding of the clinical characteristics of patients with IPF, the impact that the disease has on their quality of life and survival, and current practices in diagnosis and management. In the future, analyses of biospecimens linked to detailed patient profiles will provide the opportunity to identify biomarkers linked to disease progression, facilitating the development of precision medicine approaches for prognosis and therapy in patients with IPF.

A practical guide to intelligent image-activated cell sorting

Intelligent image-activated cell sorting (iIACS) is a machine-intelligence technology that performs real-time intelligent image-based sorting of single cells with high throughput. iIACS extends beyond the capabilities of fluorescence-activated cell sorting (FACS) from fluorescence intensity profiles of cells to multidimensional images, thereby enabling high-content sorting of cells or cell clusters with unique spatial chemical and morphological traits. Therefore, iIACS serves as an integral part of holistic single-cell analysis by enabling direct links between population-level analysis (flow cytometry), cell-level analysis (microscopy), and gene-level analysis (sequencing). Specifically, iIACS is based on a seamless integration of high-throughput cell microscopy (e.g., multicolor fluorescence imaging, bright-field imaging), cell focusing, cell sorting, and deep learning on a hybrid software-hardware data management infrastructure, enabling real-time automated operation for data acquisition, data processing, intelligent decision making, and actuation. Here, we provide a practical guide to iIACS that describes how to design, build, characterize, and use an iIACS machine. The guide includes the consideration of several important design parameters, such as throughput, sensitivity, dynamic range, image quality, sort purity, and sort yield; the development and integration of optical, microfluidic, electrical, computational, and mechanical components; and the characterization and practical usage of the integrated system. Assuming that all components are readily available, a team of several researchers experienced in optics, electronics, digital signal processing, microfluidics, mechatronics, and flow cytometry can complete this protocol in ~3 months.

An artificial-vision- and statistical-learning-based method for studying the biodegradation of type I collagen scaffolds in bone regeneration systems

This work proposes a method based on image analysis and machine and statistical learning to model and estimate osteocyte growth (in type I collagen scaffolds for bone regeneration systems) and the collagen degradation degree due to cellular growth. To achieve these aims, the mass of collagen -subjected to the action of osteocyte growth and differentiation from stem cells- was measured on 3 days during each of 2 months, under conditions simulating a tissue in the human body. In addition, optical microscopy was applied to obtain information about cellular growth, cellular differentiation, and collagen degradation. Our first contribution consists of the application of a supervised classification random forest algorithm to image texture features (the structure tensor and entropy) for estimating the different regions of interest in an image obtained by optical microscopy: the extracellular matrix, collagen, and image background, and nuclei. Then, extracellular-matrix and collagen regions of interest were determined by the extraction of features related to the progression of the cellular growth and collagen degradation (e.g., mean area of objects and the mode of an intensity histogram). Finally, these critical features were statistically modeled depending on time via nonparametric and parametric linear and nonlinear models such as those based on logistic functions. Namely, the parametric logistic mixture models provided a way to identify and model the degradation due to biological activity by estimating the corresponding proportion of mass loss. The relation between osteocyte growth and differentiation from stem cells, on the one hand, and collagen degradation, on the other hand, was determined too and modeled through analysis of image objects' circularity and area, in addition to collagen mass loss. This set of imaging techniques, machine learning procedures, and statistical tools allowed us to characterize and parameterize type I collagen biodegradation when collagen acts as a scaffold in bone regeneration tasks. Namely, the parametric logistic mixture models provided a way to identify and model the degradation due to biological activity and thus to estimate the corresponding proportion of mass loss. Moreover, the proposed methodology can help to estimate the degradation degree of scaffolds from the information obtained by optical microscopy.

DeepPhagy: a deep learning framework for quantitatively measuring autophagy activity in Saccharomyces cerevisiae

Seeing is believing. The direct observation of GFP-Atg8 vacuolar delivery under confocal microscopy is one of the most useful end-point measurements for monitoring yeast macroautophagy/autophagy. However, manually labelling individual cells from large-scale sets of images is time-consuming and labor-intensive, which has greatly hampered its extensive use in functional screens. Herein, we conducted a time-course analysis of nitrogen starvation-induced autophagy in wild-type and knockout mutants of 35 AuTophaGy-related (ATG) genes in Saccharomyces cerevisiae and obtained 1,944 confocal images containing > 200,000 cells. We manually labelled 8,078 autophagic and 18,493 non-autophagic cells as a benchmark dataset and developed a new deep learning tool for autophagy (DeepPhagy), which exhibited superior accuracy in recognizing autophagic cells compared to other existing methods, with an area under the curve (AUC) value of 0.9710 from 10-fold cross-validations. We further used DeepPhagy to automatically analyze all the images and quantitatively classified the autophagic phenotypes of the 35 atg knockout mutants into 3 classes. The high consistency in our computational and biochemical results indicated the reliability of DeepPhagy for measuring autophagic activity. Moreover, we used DeepPhagy to analyze 3 additional types of autophagic phenotypes, including the targeting of Atg1-GFP to the vacuole, the vacuolar delivery of GFP-Atg19, and the disintegration of autophagic bodies indicated by GFP-Atg8, all with satisfying accuracies. Taken together, our study not only enables the GFP-Atg8 fluorescence assay to become a quantitative measurement for analyzing autophagic phenotypes in S. cerevisiae but also demonstrates that deep learning-based methods could potentially be applied to different types of autophagy.Abbreviations: Ac: accuracy; ALP: alkaline phosphatase; ALR: autophagic lysosomal reformation; ATG: AuTophaGy-related; AUC: area under the curve; CNN: convolutional neural network; Cvt: cytoplasm-to-vacuole targeting; DeepPhagy: deep learning for autophagy; fc_2: second fully connected; GFP: green fluorescent protein; MAP1LC3/LC3: microtubule-associated protein 1 light chain 3 beta; HAT: histone acetyltransferase; HemI: Heat map Illustrator; JRE: Java Runtime Environment; KO: knockout; LRN: local response normalization; MCC: Mathew Correlation Coefficient; OS: operating system; PAS: phagophore assembly site; PC: principal component; PCA: principal component analysis; PPI: protein-protein interaction; Pr: precision; QPSO: Quantum-behaved Particle Swarm Optimization; ReLU: rectified linear unit; RF: random forest; ROC: receiver operating characteristic; ROI: region of interest; SD: systematic derivation; SGD: stochastic gradient descent; Sn: sensitivity; Sp: specificity; SRG: seeded region growing; t-SNE: t-distributed stochastic neighbor embedding; 2D: 2-dimensional; WT: wild-type.

Digging deeper: methodologies for high-content phenotyping in Caenorhabditis elegans

Deep phenotyping is an emerging conceptual paradigm and experimental approach aimed at measuring and linking many aspects of a phenotype to understand its underlying biology. To date, deep phenotyping has been applied mostly in cultured cells and used less in multicellular organisms. However, in the past decade, it has increasingly been recognized that deep phenotyping could lead to a better understanding of how genetics, environment and stochasticity affect the development, physiology and behavior of an organism. The nematode Caenorhabditis elegans is an invaluable model system for studying how genes affect a phenotypic trait, and new technologies have taken advantage of the worm's physical attributes to increase the throughput and informational content of experiments. Coupling of these technical advancements with computational and analytical tools has enabled a boom in deep-phenotyping studies of C. elegans. In this Review, we highlight how these new technologies and tools are digging into the biological origins of complex, multidimensional phenotypes.

Biomedical Image Processing with Containers and Deep Learning: An Automated Analysis Pipeline: Data architecture, artificial intelligence, automated processing, containerization, and clusters orchestration ease the transition from data acquisition to insights in medium-to-large datasets

Here, a streamlined, scalable, laboratory approach is discussed that enables medium-to-large dataset analysis. The presented approach combines data management, artificial intelligence, containerization, cluster orchestration, and quality control in a unified analytic pipeline. The unique combination of these individual building blocks creates a new and powerful analysis approach that can readily be applied to medium-to-large datasets by researchers to accelerate the pace of research. The proposed framework is applied to a project that counts the number of plasmonic nanoparticles bound to peripheral blood mononuclear cells in dark-field microscopy images. By using the techniques presented in this article, the images are automatically processed overnight, without user interaction, streamlining the path from experiment to conclusions.

Machine Learning with Optical Phase Signatures for Phenotypic Profiling of Cell Lines

Robust and reproducible profiling of cell lines is essential for phenotypic screening assays. The goals of this study were to determine robust and reproducible optical phase signatures of cell lines for classification with machine learning and to correlate optical phase parameters to motile behavior. Digital holographic microscopy (DHM) reconstructed phase maps of cells from two pairs of cancer and non-cancer cell lines. Seventeen image parameters were extracted from each cell's phase map, used for linear support vector machine learning, and correlated to scratch wound closure and Boyden chamber chemotaxis. The classification accuracy was between 90% and 100% for the six pairwise cell line comparisons. Several phase parameters correlated with wound closure rate and chemotaxis across the four cell lines. The level of cell confluence in culture affected phase parameters in all cell lines tested. Results indicate that optical phase features of cell lines are a robust set of quantitative data of potential utility for phenotypic screening and prediction of motile behavior. © 2019 International Society for Advancement of Cytometry.

Genomic Selection in Aquaculture: Application, Limitations and Opportunities With Special Reference to Marine Shrimp and Pearl Oysters

Within aquaculture industries, selection based on genomic information (genomic selection) has the profound potential to change genetic improvement programs and production systems. Genomic selection exploits the use of realized genomic relationships among individuals and information from genome-wide markers in close linkage disequilibrium with genes of biological and economic importance. We discuss the technical advances, practical requirements, and commercial applications that have made genomic selection feasible in a range of aquaculture industries, with a particular focus on molluscs (pearl oysters, Pinctada maxima) and marine shrimp (Litopenaeus vannamei and Penaeus monodon). The use of low-cost genome sequencing has enabled cost-effective genotyping on a large scale and is of particular value for species without a reference genome or access to commercial genotyping arrays. We highlight the pitfalls and offer the solutions to the genotyping by sequencing approach and the building of appropriate genetic resources to undertake genomic selection from first-hand experience. We describe the potential to capture large-scale commercial phenotypes based on image analysis and artificial intelligence through machine learning, as inputs for calculation of genomic breeding values. The application of genomic selection over traditional aquatic breeding programs offers significant advantages through being able to accurately predict complex polygenic traits including disease resistance; increasing rates of genetic gain; minimizing inbreeding; and negating potential limiting effects of genotype by environment interactions. Further practical advantages of genomic selection through the use of large-scale communal mating and rearing systems are highlighted, as well as presenting rate-limiting steps that impact on attaining maximum benefits from adopting genomic selection. Genomic selection is now at the tipping point where commercial applications can be readily adopted and offer significant short- and long-term solutions to sustainable and profitable aquaculture industries.

Arrayed functional genetic screenings in pluripotency reprogramming and differentiation

Thoroughly understanding the molecular mechanisms responsible for the biological properties of pluripotent stem cells, as well as for the processes involved in reprograming, differentiation, and transition between Naïve and Primed pluripotent states, is of great interest in basic and applied research. Although pluripotent cells have been extensively characterized in terms of their transcriptome and miRNome, a comprehensive understanding of how these gene products specifically impact their biology, depends on gain- or loss-of-function experimental approaches capable to systematically interrogate their function. We review all studies carried up to date that used arrayed screening approaches to explore the function of these genetic elements on those biological contexts, using focused or genome-wide genetic libraries. We further discuss the limitations and advantages of approaches based on assays with population-level primary readouts, derived from single-parameter plate readers, or cell-level primary readouts, obtained using multiparametric flow cytometry or quantitative fluorescence microscopy (i.e., high-content screening). Finally, we discuss technical limitation and future perspectives, highlighting how the integration of screening data may lead to major advances in the field of stem cell research and therapy.

DeepNEU: cellular reprogramming comes of age - a machine learning platform with application to rare diseases research

BACKGROUND

Conversion of human somatic cells into induced pluripotent stem cells (iPSCs) is often an inefficient, time consuming and expensive process. Also, the tendency of iPSCs to revert to their original somatic cell type over time continues to be problematic. A computational model of iPSCs identifying genes/molecules necessary for iPSC generation and maintenance could represent a crucial step forward for improved stem cell research. The combination of substantial genetic relationship data, advanced computing hardware and powerful nonlinear modeling software could make the possibility of artificially-induced pluripotent stem cells (aiPSC) a reality. We have developed an unsupervised deep machine learning technology, called DeepNEU that is based on a fully-connected recurrent neural network architecture with one network processing layer for each input. DeepNEU was used to simulate aiPSC systems using a defined set of reprogramming transcription factors. Genes/proteins that were reported to be essential in human pluripotent stem cells (hPSC) were used for system modelling.

RESULTS

The Mean Squared Error (MSE) function was used to assess system learning. System convergence was defined at MSE < 0.001. The markers of human iPSC pluripotency (N = 15) were all upregulated in the aiPSC final model. These upregulated/expressed genes in the aiPSC system were entirely consistent with results obtained for iPSCs.

CONCLUSION

This research introduces and validates the potential use of aiPSCs as computer models of human pluripotent stem cell systems. Disease-specific aiPSCs have the potential to improve disease modeling, prototyping of wet lab experiments, and prediction of genes relevant and necessary for aiPSC production and maintenance for both common and rare diseases in a cost-effective manner.

Yeast Systems Biology: The Continuing Challenge of Eukaryotic Complexity

Research on yeast has produced a plethora of tools and resources that have been central to the progress of systems biology. This chapter reviews these resources, explains the innovations that have been made since the first edition of this book, and introduces the constituent chapters of the current edition. The value of these resources not only in building and testing models of the functional networks of the yeast cell, but also in providing a foundation for network studies on the molecular basis of complex human diseases is considered. The gaps in this vast compendium of data, including enzyme kinetic characteristics, biomass composition, transport processes, and cell-cell interactions are discussed, as are the interactions between yeast cells and those of other species. The relevance of these studies to both traditional and advanced biotechnologies and to human medicine is considered, and the opportunities and challenges in using unicellular yeasts to model the systems of multicellular organisms are presented.

Artificial intelligence in drug development: present status and future prospects

Artificial intelligence (AI) uses personified knowledge and learns from the solutions it produces to address not only specific but also complex problems. Remarkable improvements in computational power coupled with advancements in AI technology could be utilised to revolutionise the drug development process. At present, the pharmaceutical industry is facing challenges in sustaining their drug development programmes because of increased R&D costs and reduced efficiency. In this review, we discuss the major causes of attrition rates in new drug approvals, the possible ways that AI can improve the efficiency of the drug development process and collaboration of pharmaceutical industry giants with AI-powered drug discovery firms.

Morphologically constrained and data informed cell segmentation of budding yeast

Motivation

Although high-content image cytometry is becoming increasingly routine, processing the large amount of data acquired during time-lapse experiments remains a challenge. The majority of approaches for automated single-cell segmentation focus on flat, uniform fields of view covered with a single layer of cells. In the increasingly popular microfluidic devices that trap individual cells for long term imaging, these conditions are not met. Consequently, most techniques for segmentation perform poorly. Although potentially constraining the generalizability of software, incorporating information about the microfluidic features, flow of media and the morphology of the cells can substantially improve performance.

Results

Here we present DISCO (Data Informed Segmentation of Cell Objects), a framework for using the physical constraints imposed by microfluidic traps, the shape based morphological constraints of budding yeast and temporal information about cell growth and motion to allow tracking and segmentation of cells in microfluidic devices. Using manually curated datasets, we demonstrate substantial improvements in both tracking and segmentation when compared with existing software.

Availability and implementation

The MATLAB code for the algorithm and for measuring performance is available at https://github.com/pswain/segmentation-software and the test images and the curated ground-truth results used for comparing the algorithms are available at http://datashare.is.ed.ac.uk/handle/10283/2002.

Contact

mcrane2@uw.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

Machine learning and image-based profiling in drug discovery

The increase in imaging throughput, new analytical frameworks and high-performance computational resources open new avenues for data-rich phenotypic profiling of small molecules in drug discovery. Image-based profiling assays assessing single-cell phenotypes have been used to explore mechanisms of action, target efficacy and toxicity of small molecules. Technological advances to generate large data sets together with new machine learning approaches for the analysis of high-dimensional profiling data create opportunities to improve many steps in drug discovery. In this review, we will discuss how recent studies applied machine learning approaches in functional profiling workflows with a focus on chemical genetics. While their utility in image-based screening and profiling is predictably evident, examples of novel insights beyond the status quo based on the applications of machine learning approaches are just beginning to emerge. To enable discoveries, future studies also need to develop methodologies that lower the entry barriers to high-throughput profiling experiments by streamlining image-based profiling assays and providing applications for advanced learning technologies such as easy to deploy deep neural networks.

Image-Based Profiling of Synaptic Connectivity in Primary Neuronal Cell Culture

Neurological disorders display a broad spectrum of clinical manifestations. Yet, at the cellular level, virtually all these diseases converge into a common phenotype of dysregulated synaptic connectivity. In dementia, synapse dysfunction precedes neurodegeneration and cognitive impairment by several years, making the synapse a crucial entry point for the development of diagnostic and therapeutic strategies. Whereas high-resolution imaging and biochemical fractionations yield detailed insight into the molecular composition of the synapse, standardized assays are required to quickly gauge synaptic connectivity across large populations of cells under a variety of experimental conditions. Such screening capabilities have now become widely accessible with the advent of high-throughput, high-content microscopy. In this review, we discuss how microscopy-based approaches can be used to extract quantitative information about synaptic connectivity in primary neurons with deep coverage. We elaborate on microscopic readouts that may serve as a proxy for morphofunctional connectivity and we critically analyze their merits and limitations. Finally, we allude to the potential of alternative culture paradigms and integrative approaches to enable comprehensive profiling of synaptic connectivity.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Nuclear Mechanopathology and Cancer Diagnosis

Abnormalities in nuclear and chromatin organization are hallmarks of many diseases including cancer. In this review, we highlight our understanding of how the cellular microenvironment regulates nuclear morphology and, with it, the spatial organization of chromosomes and genes, resulting in cell type-specific genomic programs. We also discuss the molecular basis for maintaining nuclear and genomic integrity and how alterations in nuclear mechanotransduction pathways result in various diseases. Finally, we highlight the importance of digital pathology based on nuclear morphometric features combined with single-cell genomics for early cancer diagnostics.

Machine Learning Enables Live Label-Free Phenotypic Screening in Three Dimensions

There is a large amount of information in brightfield images that was previously inaccessible by using traditional microscopy techniques. This information can now be exploited by using machine-learning approaches for both image segmentation and the classification of objects. We have combined these approaches with a label-free assay for growth and differentiation of leukemic colonies, to generate a novel platform for phenotypic drug discovery. Initially, a supervised machine-learning algorithm was used to identify in-focus colonies growing in a three-dimensional (3D) methylcellulose gel. Once identified, unsupervised clustering and principle component analysis of texture-based phenotypic profiles were applied to group similar phenotypes. In a proof-of-concept study, we successfully identified a novel phenotype induced by a compound that is currently in clinical trials for the treatment of leukemia. We believe that our platform will be of great benefit for the utilization of patient-derived 3D cell culture systems for both drug discovery and diagnostic applications.

Machine Learning for Nuclear Mechano-Morphometric Biomarkers in Cancer Diagnosis

Current cancer diagnosis employs various nuclear morphometric measures. While these have allowed accurate late-stage prognosis, early diagnosis is still a major challenge. Recent evidence highlights the importance of alterations in mechanical properties of single cells and their nuclei as critical drivers for the onset of cancer. We here present a method to detect subtle changes in nuclear morphometrics at single-cell resolution by combining fluorescence imaging and deep learning. This assay includes a convolutional neural net pipeline and allows us to discriminate between normal and human breast cancer cell lines (fibrocystic and metastatic states) as well as normal and cancer cells in tissue slices with high accuracy. Further, we establish the sensitivity of our pipeline by detecting subtle alterations in normal cells when subjected to small mechano-chemical perturbations that mimic tumor microenvironments. In addition, our assay provides interpretable features that could aid pathological inspections. This pipeline opens new avenues for early disease diagnostics and drug discovery.

Regulation of genome organization and gene expression by nuclear mechanotransduction

It is well established that cells sense chemical signals from their local microenvironment and transduce them to the nucleus to regulate gene expression programmes. Although a number of experiments have shown that mechanical cues can also modulate gene expression, the underlying mechanisms are far from clear. Nevertheless, we are now beginning to understand how mechanical cues are transduced to the nucleus and how they influence nuclear mechanics, genome organization and transcription. In particular, recent progress in super-resolution imaging, in genome-wide application of RNA sequencing, chromatin immunoprecipitation and chromosome conformation capture and in theoretical modelling of 3D genome organization enables the exploration of the relationship between cell mechanics, 3D chromatin configurations and transcription, thereby shedding new light on how mechanical forces regulate gene expression.

Label-free detection of cellular drug responses by high-throughput bright-field imaging and machine learning

In the last decade, high-content screening based on multivariate single-cell imaging has been proven effective in drug discovery to evaluate drug-induced phenotypic variations. Unfortunately, this method inherently requires fluorescent labeling which has several drawbacks. Here we present a label-free method for evaluating cellular drug responses only by high-throughput bright-field imaging with the aid of machine learning algorithms. Specifically, we performed high-throughput bright-field imaging of numerous drug-treated and -untreated cells (N = ~240,000) by optofluidic time-stretch microscopy with high throughput up to 10,000 cells/s and applied machine learning to the cell images to identify their morphological variations which are too subtle for human eyes to detect. Consequently, we achieved a high accuracy of 92% in distinguishing drug-treated and -untreated cells without the need for labeling. Furthermore, we also demonstrated that dose-dependent, drug-induced morphological change from different experiments can be inferred from the classification accuracy of a single classification model. Our work lays the groundwork for label-free drug screening in pharmaceutical science and industry.

Label-free detection of cellular drug responses by high-throughput bright-field imaging and machine learning

In the last decade, high-content screening based on multivariate single-cell imaging has been proven effective in drug discovery to evaluate drug-induced phenotypic variations. Unfortunately, this method inherently requires fluorescent labeling which has several drawbacks. Here we present a label-free method for evaluating cellular drug responses only by high-throughput bright-field imaging with the aid of machine learning algorithms. Specifically, we performed high-throughput bright-field imaging of numerous drug-treated and -untreated cells (N = ~240,000) by optofluidic time-stretch microscopy with high throughput up to 10,000 cells/s and applied machine learning to the cell images to identify their morphological variations which are too subtle for human eyes to detect. Consequently, we achieved a high accuracy of 92% in distinguishing drug-treated and -untreated cells without the need for labeling. Furthermore, we also demonstrated that dose-dependent, drug-induced morphological change from different experiments can be inferred from the classification accuracy of a single classification model. Our work lays the groundwork for label-free drug screening in pharmaceutical science and industry.

Data-analysis strategies for image-based cell profiling

Image-based cell profiling is a high-throughput strategy for the quantification of phenotypic differences among a variety of cell populations. It paves the way to studying biological systems on a large scale by using chemical and genetic perturbations. The general workflow for this technology involves image acquisition with high-throughput microscopy systems and subsequent image processing and analysis. Here, we introduce the steps required to create high-quality image-based (i.e., morphological) profiles from a collection of microscopy images. We recommend techniques that have proven useful in each stage of the data analysis process, on the basis of the experience of 20 laboratories worldwide that are refining their image-based cell-profiling methodologies in pursuit of biological discovery. The recommended techniques cover alternatives that may suit various biological goals, experimental designs, and laboratories' preferences.

Multicellular tumor invasion and plasticity in biomimetic materials

Cancer cell invasion through the extracellular matrix is associated with metastatic spread and therapeutic resistance. In carcinomas, the detachment and dissemination of individual cells has been associated with an epithelial-mesenchymal transition, but tumors can also invade using collective, multicellular phenotypes. This malignant tumor progression is also associated with alignment and stiffening of the surrounding extracellular matrix. Historically, tumor invasion has been investigated using 2D monolayer culture, small animal models or patient histology. These assays have been complemented by the use of natural biomaterials such as reconstituted basement membrane and collagen I. More recently, engineered materials with well-defined physical, chemical and biomolecular properties have enabled more controlled microenvironments. In this review, we highlight recent developments in multicellular tumor invasion based on microfabricated structures or hydrogels. We emphasize the role of interfacial geometries, biomaterial stiffness, matrix remodeling, and co-culture models. Finally, we discuss future directions for the field, particularly integration with precision measurements of biomaterial properties and single cell heterogeneity, standardization and scale-up of these platforms, as well as integration with patient-derived samples.

Automated analysis of high-content microscopy data with deep learning

Existing computational pipelines for quantitative analysis of high‐content microscopy data rely on traditional machine learning approaches that fail to accurately classify more than a single dataset without substantial tuning and training, requiring extensive analysis. Here, we demonstrate that the application of deep learning to biological image data can overcome the pitfalls associated with conventional machine learning classifiers. Using a deep convolutional neural network (DeepLoc) to analyze yeast cell images, we show improved performance over traditional approaches in the automated classification of protein subcellular localization. We also demonstrate the ability of DeepLoc to classify highly divergent image sets, including images of pheromone‐arrested cells with abnormal cellular morphology, as well as images generated in different genetic backgrounds and in different laboratories. We offer an open‐source implementation that enables updating DeepLoc on new microscopy datasets. This study highlights deep learning as an important tool for the expedited analysis of high‐content microscopy data.

Machine learning applications in cell image analysis

Machine learning (ML) refers to a set of automatic pattern recognition methods that have been successfully applied across various problem domains, including biomedical image analysis. This review focuses on ML applications for image analysis in light microscopy experiments with typical tasks of segmenting and tracking individual cells, and modelling of reconstructed lineage trees. After describing a typical image analysis pipeline and highlighting challenges of automatic analysis (for example, variability in cell morphology, tracking in presence of clutters) this review gives a brief historical outlook of ML, followed by basic concepts and definitions required for understanding examples. This article then presents several example applications at various image processing stages, including the use of supervised learning methods for improving cell segmentation, and the application of active learning for tracking. The review concludes with remarks on parameter setting and future directions.