KCML: a machine-learning framework for inference of multi-scale gene functions from genetic perturbation screens

A global genetic interaction network by single-cell imaging and machine learning

Cellular and organismal phenotypes are controlled by complex gene regulatory networks. However, reference maps of gene function are still scarce across different organisms. Here, we generated synthetic genetic interaction and cell morphology profiles of more than 6,800 genes in cultured Drosophila cells. The resulting map of genetic interactions was used for machine learning-based gene function discovery, assigning functions to genes in 47 modules. Furthermore, we devised Cytoclass as a method to dissect genetic interactions for discrete cell states at the single-cell resolution. This approach identified an interaction of Cdk2 and the Cop9 signalosome complex, triggering senescence-associated secretory phenotypes and immunogenic conversion in hemocytic cells. Together, our data constitute a genome-scale resource of functional gene profiles to uncover the mechanisms underlying genetic interactions and their plasticity at the single-cell level.

LiveCellMiner: A new tool to analyze mitotic progression

Live-cell imaging has become state of the art to accurately identify the nature of mitotic and cell cycle defects. Low- and high-throughput microscopy setups have yield huge data amounts of cells recorded in different experimental and pathological conditions. Tailored semi-automated and automated image analysis approaches allow the analysis of high-content screening data sets, saving time and avoiding bias. However, they were mostly designed for very specific experimental setups, which restricts their flexibility and usability. The general need for dedicated experiment-specific user-annotated training sets and experiment-specific user-defined segmentation parameters remains a major bottleneck for fully automating the analysis process. In this work we present LiveCellMiner, a highly flexible open-source software tool to automatically extract, analyze and visualize both aggregated and time-resolved image features with potential biological relevance. The software tool allows analysis across high-content data sets obtained in different platforms, in a quantitative and unbiased manner. As proof of principle application, we analyze here the dynamic chromatin and tubulin cytoskeleton features in human cells passing through mitosis highlighting the versatile and flexible potential of this tool set.

Mapping the multiscale structure of biological systems

Biological systems are by nature multiscale, consisting of subsystems that factor into progressively smaller units in a deeply hierarchical structure. At any level of the hierarchy, an ever-increasing diversity of technologies can be applied to characterize the corresponding biological units and their relations, resulting in large networks of physical or functional proximities-e.g., proximities of amino acids within a protein, of proteins within a complex, or of cell types within a tissue. Here, we review general concepts and progress in using network proximity measures as a basis for creation of multiscale hierarchical maps of biological systems. We discuss the functionalization of these maps to create predictive models, including those useful in translation of genotype to phenotype, along with strategies for model visualization and challenges faced by multiscale modeling in the near future. Collectively, these approaches enable a unified hierarchical approach to biological data, with application from the molecular to the macroscopic.

Artificial intelligence for the study of colorectal cancer tissue slides

Artificial intelligence (AI) is gaining incredible momentum as a companion diagnostic in a number of fields in oncology. In the present mini-review, we summarize the main uses and findings of AI applied to the analysis of digital histopathological images of slides from colorectal cancer (CRC) patients. Machine learning tools have been developed to automatically and objectively recognize specific CRC subtypes, such as those with microsatellite instability and high lymphocyte infiltration that would optimally respond to specific therapies. Also, AI-based classification in distinct prognostic groups with no studies of the basic biological features of the tumor have been attempted in a methodological approach that we called “biology-agnostic”.

DeepScratch: Single-cell based topological metrics of scratch wound assays

Changes in tissue architecture and multicellular organisation contribute to many diseases, including cancer and cardiovascular diseases. Scratch wound assay is a commonly used tool that assesses cells' migratory ability based on the area of a wound they cover over a certain time. However, analysis of changes in the organisational patterns formed by migrating cells following genetic or pharmacological perturbations are not well explored in these assays, in part because analysing the resulting imaging data is challenging. Here we present DeepScratch, a neural network that accurately detects the cells in scratch assays based on a heterogeneous set of markers. We demonstrate the utility of DeepScratch by analysing images of more than 232,000 lymphatic endothelial cells. In addition, we propose various topological measures of cell connectivity and local cell density (LCD) to characterise tissue remodelling during wound healing. We show that LCD-based metrics allow classification of CDH5 and CDC42 genetic perturbations that are known to affect cell migration through different biological mechanisms. Such differences cannot be captured when considering only the wound area. Taken together, single-cell detection using DeepScratch allows more detailed investigation of the roles of various genetic components in tissue topology and the biological mechanisms underlying their effects on collective cell migration.

Automation, Monitoring, and Standardization of Cell Product Manufacturing

Although regenerative medicine products are at the forefront of scientific research, technological innovation, and clinical translation, their reproducibility and large-scale production are compromised by automation, monitoring, and standardization issues. To overcome these limitations, new technologies at software (e.g., algorithms and artificial intelligence models, combined with imaging software and machine learning techniques) and hardware (e.g., automated liquid handling, automated cell expansion bioreactor systems, automated colony-forming unit counting and characterization units, and scalable cell culture plates) level are under intense investigation. Automation, monitoring and standardization should be considered at the early stages of the developmental cycle of cell products to deliver more robust and effective therapies and treatment plans to the bedside, reducing healthcare expenditure and improving services and patient care.

KCML: a machine-learning framework for inference of multi-scale gene functions from genetic perturbation screens

Characterising context-dependent gene functions is crucial for understanding the genetic bases of health and disease. To date, inference of gene functions from large-scale genetic perturbation screens is based on ad hoc analysis pipelines involving unsupervised clustering and functional enrichment. We present Knowledge- and Context-driven Machine Learning (KCML), a framework that systematically predicts multiple context-specific functions for a given gene based on the similarity of its perturbation phenotype to those with known function. As a proof of concept, we test KCML on three datasets describing phenotypes at the molecular, cellular and population levels and show that it outperforms traditional analysis pipelines. In particular, KCML identified an abnormal multicellular organisation phenotype associated with the depletion of olfactory receptors, and TGFβ and WNT signalling genes in colorectal cancer cells. We validate these predictions in colorectal cancer patients and show that olfactory receptors expression is predictive of worse patient outcomes. These results highlight KCML as a systematic framework for discovering novel scale-crossing and context-dependent gene functions. KCML is highly generalisable and applicable to various large-scale genetic perturbation screens.