Image Super resolution is a widely-studied problem in computer vision, where the objective is to convert a lowresolution image to a high resolution image. Conventional methods for achieving super-resolution such as image priors, interpolation, sparse coding require a lot of pre/post processing and optimization. Recently, deep learning methods such as convolutional neural networks and generative adversarial networks are being used to perform super-resolution with results competitive to the state of the art but none of them have been used on microscopy images. In this thesis, a generative adversarial network, mSRGAN, is proposed for super resolution with a perceptual loss function consisting of a adversarial loss, mean squared error and content loss. The objective of our implementation is to learn an end to end mapping between the low / high resolution images and optimize the upscaled image for quantitative metrics as well as perceptual quality. We then compare our results with the current state of the art methods in super resolution, conduct a proof of concept segmentation study to show that super resolved images can be used as a effective pre processing step before segmentation and validate the findings statistically. / Image Super-resolution är ett allmänt studerad problem i datasyn, där målet är att konvertera en lågupplösningsbild till en högupplöst bild. Konventionella metoder för att uppnå superupplösning som image priors, interpolation, sparse coding behöver mycket föroch efterbehandling och optimering.Nyligen djupa inlärningsmetoder som convolutional neurala nätverk och generativa adversariella nätverk är användas för att utföra superupplösning med resultat som är konkurrenskraftiga mot toppmoderna teknik, men ingen av dem har använts på mikroskopibilder. I denna avhandling, ett generativ kontradiktorisktsnätverk, mSRGAN, är föreslås för superupplösning med en perceptuell förlustfunktion bestående av en motsatt förlust, medelkvadratfel och innehållförlust.Mål med vår implementering är att lära oss ett slut på att slut kartläggning mellan bilder med låg / hög upplösning och optimera den uppskalade bilden för kvantitativa metriks såväl som perceptuell kvalitet. Vi jämför sedan våra resultat med de nuvarande toppmoderna metoderna i superupplösning, och uppträdande ett bevis på konceptsegmenteringsstudie för att visa att superlösa bilder kan användas som ett effektivt förbehandling steg före segmentering och validera fynden statistiskt.

High-content screens are widely used to get insight on mechanistic organization of biological systems. Chemical and/or genomic interferences are used to modulate molecular machinery, then light microscopy and quantitative image analysis yield a large number of parameters describing phenotype. However, extracting functional information from such high-content datasets (e.g. links between cellular processes or functions of unknown genes) remains challenging. This work is devoted to the analysis of a multi-parametric image-based genomic screen of endocytosis, the process whereby cells uptake cargoes (signals and nutrients) and distribute them into different subcellular compartments. The complexity of the quantitative endocytic data was approached using different Machine Learning techniques, namely, Clustering methods, Bayesian networks, Principal and Independent component analysis, Artificial neural networks. The main goal of such an analysis is to predict possible modes of action of screened genes and also to find candidate genes that can be involved in a process of interest. The degree of freedom for the multidimensional phenotypic space was identified using the data distributions, and then the high-content data were deconvolved into separate signals from different cellular modules. Some of those basic signals (phenotypic traits) were straightforward to interpret in terms of known molecular processes; the other components gave insight into interesting directions for further research. The phenotypic profile of perturbation of individual genes are sparse in coordinates of the basic signals, and, therefore, intrinsically suggest their functional roles in cellular processes. Being a very fundamental process, endocytosis is specifically modulated by a variety of different pathways in the cell; therefore, endocytic phenotyping can be used for analysis of non-endocytic modules in the cell. Proposed approach can be also generalized for analysis of other high-content screens.:Contents Objectives Chapter 1 Introduction 1.1 High-content biological data 1.1.1 Different perturbation types for HCS 1.1.2 Types of observations in HTS 1.1.3 Goals and outcomes of MP HTS 1.1.4 An overview of the classical methods of analysis of biological HT- and HCS data 1.2 Machine learning for systems biology 1.2.1 Feature selection 1.2.2 Unsupervised learning 1.2.3 Supervised learning 1.2.4 Artificial neural networks 1.3 Endocytosis as a system process 1.3.1 Endocytic compartments and main players 1.3.2 Relation to other cellular processes Chapter 2 Experimental and analytical techniques 2.1 Experimental methods 2.1.1 RNA interference 2.1.2 Quantitative multiparametric image analysis 2.2 Detailed description of the endocytic HCS dataset 2.2.1 Basic properties of the endocytic dataset 2.2.2 Control subset of genes 2.3 Machine learning methods 2.3.1 Latent variables models 2.3.2 Clustering 2.3.3 Bayesian networks 2.3.4 Neural networks Chapter 3 Results 3.1 Selection of labeled data for training and validation based on KEGG information about genes pathways 3.2 Clustering of genes 3.2.1 Comparison of clustering techniques on control dataset 3.2.2 Clustering results 3.3 Independent components as basic phenotypes 3.3.1 Algorithm for identification of the best number of independent components 3.3.2 Application of ICA on the full dataset and on separate assays of the screen 3.3.3 Gene annotation based on revealed phenotypes 3.3.4 Searching for genes with target function 3.4 Bayesian network on endocytic parameters 3.4.1 Prediction of pathway based on parameters values using Naïve Bayesian Classifier 3.4.2 General Bayesian Networks 3.5 Neural networks 3.5.1 Autoencoders as nonlinear ICA 3.5.2 siRNA sequence motives discovery with deep NN 3.6 Biological results 3.6.1 Rab11 ZNF-specific phenotype found by ICA 3.6.2 Structure of BN revealed dependency between endocytosis and cell adhesion Chapter 4 Discussion 4.1 Machine learning approaches for discovery of phenotypic patterns 4.1.1 Functional annotation of unknown genes based on phenotypic profiles 4.1.2 Candidate genes search 4.2 Adaptation to other HCS data and generalization Chapter 5 Outlook and future perspectives 5.1 Handling sequence-dependent off-target effects with neural networks 5.2 Transition between machine learning and systems biology models Acknowledgements References Appendix A.1 Full list of cellular and endocytic parameters A.2 Description of independent components of the full dataset A.3 Description of independent components extracted from separate assays of the HCS

Gene therapy is the process of delivering genetic material, such as DNA (encoding for an important protein) into a patient’s cells in order to treat a particular disease such as a genetic disorder or heart disease. This process of DNA delivery into cells is known as “transfection” and it is important that the efficiency of transfection be optimized such that a patient can obtain maximum therapeutic benefit from such a treatment. DNA is susceptible to being destroyed by harsh physiological environments prior to reaching its target. This problem can be diminished with the use of vectors that not only protect against harsh conditions but also encourage entry into cells. By mixing 1) DNA with 2) positively charged polymers, “polyplexes” form which protect DNA from degradation and increase transfection efficiency. The development of effective polyplex formulations requires optimization. In the work presented here, it was discovered that when polyplexes contained specific sequences within the DNA called “CpG”, this lowered transfection efficiencies and increased inflammatory responses compared to DNA without CpG, as measured using a mouse lungs model. Thus, DNA composition played an important role in influencing DNA transfection efficiency of polyplexes. Another aspect to take into account is the degree of positive charge of the polymer. We tested a new polymer called poly(galactaramidoamine) or PGAA. We found that this PGAA can form polyplexes with DNA and could be used in gene therapy. At the present time, mechanisms by which the polyplexes get inside and transfect the cells are still unclear. We also introduced a new system called high-content screening to the gene delivery field. This system offers automated measurements of transfection efficiency and cytotoxicity and could be used to reveal the polyplexes trafficking inside cells.

<p><strong><em>Background</em></strong>: Chemotherapy and radiation resistance are major causes of failure in cancer treatment. The response to treatment in cancer cells depends on several mechanisms and pathways such as Janus kinases-signal transducers and activators of transcription JAK/STAT pathway. STAT1 was the first described transcription factor in the STAT family. STAT1 is activated by stimulation of signaling proteins such as type II interferon (IFN- γ) and the activated STAT1 translocates from cytoplasm to nucleus. The translocation of STAT1 would result in transcription and changes in the cell activity in terms of apoptosis, proliferation and angiogenesis. Overexpression of STAT1 is suggested to be involved in the development of resistance to chemotherapy and radiation. In this study, we were interested in finding an inhibitor of the STAT1 translocation. <strong><em>Material and methods</em></strong>: The cervix carcinoma cell line, HeLa, was exposed to test compounds for 2h and were then stimulated with IFN-γ to induce the translocation of STAT1. To detect STAT1-protein and the nucleus, the cells were stained with fluorescent antibodies and Hoescht 33324, respectively, using a STAT1 activator assay. The difference in fluorescence intensity between cytoplasm and nucleus was measured using a high-content microscope, ArrayScan^®. <strong><em>Results</em></strong>: β-lapachone and CRA-1 were found to be inhibitors of STAT1 translocation.</p>

Trauma to the central nervous system (CNS) results in an irreversible disruption of axon tracts, often leading to lifelong functional deficits. Despite a large body of research into the mechanisms that underlie the lack of axonal regeneration after CNS injury, there are currently no effective treatments. One major obstacle involves the presence at injury sites of CNS growth-inhibitory molecules, such as myelin proteins and astrocyte-derived chondroitin sulfate proteoglycans (CSPGs), which act as environmental barriers to axonal regeneration. Our lab recently described the identification and characterization of a novel compound, F05, which promotes growth on inhibitory substrates in vitro. I show that F05 improves regeneration in vivo after acute sensory axon transection as well as after optic nerve crush injury. F05 does not target known signaling molecules involved in CSPG or myelin mediated inhibition but does affect growth cone microtubule dynamics, suggesting a potentially novel mechanism of growth promotion. Using a protein microarray, I show that apoptotic signaling pathways may underlie glial-derived inhibition and its relief by F05. In addition, I employed a comparative gene microarray to show that F05 induces similar changes in gene expression as antipsychotics of the piperazine phenothiazine structural class (PhAPs). Indeed, PhAPs share F05’s ability to overcome glial-derived inhibition of cultured CNS neurons and do so through a mechanism dependent on antagonism of calmodulin. These studies have led to the identification of potentially novel clinical treatments for CNS injury as well as a better understanding of environmentally derived growth-inhibitory signaling mechanisms.

No description available.

The zebrafish larva is an ideal candidate for in vivo high-throughput screening: it is a small vertebrate, it is optically transparent, possesses complex organs, and is easy to culture. In addition, genetic mutants and models of human diseases are widely available. Despite these attractive features there are no tools capable of screening at sufficient throughput and resolution to fully exploit the zebrafish. Here, I present a collection of technologies that enable high-throughput studies on zebrafish larvae at cellular resolution. / Engineering and Applied Sciences

Background: Chemotherapy and radiation resistance are major causes of failure in cancer treatment. The response to treatment in cancer cells depends on several mechanisms and pathways such as Janus kinases-signal transducers and activators of transcription JAK/STAT pathway. STAT1 was the first described transcription factor in the STAT family. STAT1 is activated by stimulation of signaling proteins such as type II interferon (IFN- γ) and the activated STAT1 translocates from cytoplasm to nucleus. The translocation of STAT1 would result in transcription and changes in the cell activity in terms of apoptosis, proliferation and angiogenesis. Overexpression of STAT1 is suggested to be involved in the development of resistance to chemotherapy and radiation. In this study, we were interested in finding an inhibitor of the STAT1 translocation. Material and methods: The cervix carcinoma cell line, HeLa, was exposed to test compounds for 2h and were then stimulated with IFN-γ to induce the translocation of STAT1. To detect STAT1-protein and the nucleus, the cells were stained with fluorescent antibodies and Hoescht 33324, respectively, using a STAT1 activator assay. The difference in fluorescence intensity between cytoplasm and nucleus was measured using a high-content microscope, ArrayScan®. Results: β-lapachone and CRA-1 were found to be inhibitors of STAT1 translocation.

The current work entails the development of a novel high content platform for the measurement of kinetic ligand responses across cell signalling networks at the single-cell level in distinct PBMC subtypes ex vivo. Using automated sample preparation, fluorescent cellular barcoding and flow cytometry the platform is capable of detecting 21, 840 parallel cell signalling responses in each PBMC sample. We apply this platform to characterize the effects of neuropsychiatric treatments and CNS ligands on the T cell signalling repertoire. We apply it to define cell signalling network abnormalities in PBMCs from drug-naïve first-onset schizophrenia patients (n=12) relative to healthy controls (n=12) which are subsequently normalized in PBMCs from the same patients (n=10) after a six week course of clinical treatment with the atypical antipsychotic olanzapine. We then validate the abnormal cell signalling responses in PBMCs from an independent cohort of drug-naïve first-onset schizophrenia patients (n=25) relative to controls (n=25) and investigate the specificity of the abnormal PBMC responses in schizophrenia as compared to major depression (n=25), bipolar disorder (n=25) and autism spectrum disorder (n=25). Subsequently we conduct a phenotypic drug screen using the US Food and Drug Administration (FDA) approved compound library, in addition to experimental neuropsychiatric drug candidates and nutraceuticals, to identify compounds which selectively normalize the schizophrenia-associated cell signalling response. Finally these candidate compounds are characterized using structure-activity relationships to reveal specific chemical moieties implicated in the putative therapeutic effect.

abstract: Identifying chemical compounds that inhibit bacterial infection has recently gained a considerable amount of attention given the increased number of highly resistant bacteria and the serious health threat it poses around the world. With the development of automated microscopy and image analysis systems, the process of identifying novel therapeutic drugs can generate an immense amount of data - easily reaching terabytes worth of information. Despite increasing the vast amount of data that is currently generated, traditional analytical methods have not increased the overall success rate of identifying active chemical compounds that eventually become novel therapeutic drugs. Moreover, multispectral imaging has become ubiquitous in drug discovery due to its ability to provide valuable information on cellular and sub-cellular processes using florescent reagents. These reagents are often costly and toxic to cells over an extended period of time causing limitations in experimental design. Thus, there is a significant need to develop a more efficient process of identifying active chemical compounds. This dissertation introduces novel machine learning methods based on parallelized cellomics to analyze interactions between cells, bacteria, and chemical compounds while reducing the use of fluorescent reagents. Machine learning analysis using image-based high-content screening (HCS) data is compartmentalized into three primary components: (1) \textit{Image Analytics}, (2) \textit{Phenotypic Analytics}, and (3) \textit{Compound Analytics}. A novel software analytics tool called the Insights project is also introduced. The Insights project fully incorporates distributed processing, high performance computing, and database management that can rapidly and effectively utilize and store massive amounts of data generated using HCS biological assessments (bioassays). It is ideally suited for parallelized cellomics in high dimensional space. Results demonstrate that a parallelized cellomics approach increases the quality of a bioassay while vastly decreasing the need for control data. The reduction in control data leads to less fluorescent reagent consumption. Furthermore, a novel proposed method that uses single-cell data points is proven to identify known active chemical compounds with a high degree of accuracy, despite traditional quality control measurements indicating the bioassay to be of poor quality. This, ultimately, decreases the time and resources needed in optimizing bioassays while still accurately identifying active compounds. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2016