| 1. |
- Harrison, Philip John, 1977-
(författare)
-
Deep learning approaches for image cytometry: assessing cellular morphological responses to drug perturbations
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Image cytometry is the analysis of cell properties from microscopy image data and is used ubiquitously in basic cell biology, medical diagnosis and drug development. In recent years deep learning has shown impressive results for many image cytometry tasks, including image processing, segmentation, classification and detection. Deep learning enables a more data-driven and end-to-end approach than was previously possible with conventional methods. This thesis investigates deep learning-based approaches for assessing cellular morphological responses to drug perturbations. In paper I we demonstrated the benefit of combining convolutional neural networks and transfer learning for predicting mechanism of action and nucleus translocation. In paper II we showed, using convolutional and recurrent neural networks applied to time-lapse microscopy data, that it is possible to predict if mRNA delivery via nanoparticles has been effective based on cell morphology changes at time points prior to the protein production evidence of successful delivery. In paper III we used convolutional neural networks, adversarial training and privileged information to faithfully generate fluorescence imaging channels of adipocyte cells from their corresponding z-stack of brightfield images. Our models were both faithful at the fluorescence image level and at the level of the features extracted from these images, features that are commonly used for downstream analysis, including the design of effective drug therapies. In paper IV we showed that convolutional neural networks trained on brightfield image data provide similar, and in some cases superior, performance to models trained on fluorescence image data for predicting mechanism of action, due to the brightfield images possessing additional information not available in the fluorescence images. In paper V we applied deep learning models to brightfield time-lapse image data to explore the evolution of cellular morphological changes after drug administration for a diverse set of compounds, compounds that are often used as positive controls in image-based assays.
|
|
| 2. |
- Horvath, Robert, 1988-
(författare)
-
Population genomic analyses of regulatory variation and selection in Brassicaceae species
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The impact of selection on regulatory variation and the contribution of regulatory changes to phenotypic variation has long been debated in evolutionary genetics. Because cis-regulatory elements such as promoters and enhancers can be difficult to identify, it has been more challenging to quantify the impact of selection on variation in cis-regulatory regions than in protein-coding regions. In this thesis, I use genomic tools to investigate gene expression variation and selection in Brassicaceae species. First, I investigated the genomic impact of selection on putative cis-regulatory regions in the genome of the crucifer species Capsella grandiflora (Brassicaceae) (Paper I). I used an assay for transposase-accessible chromatin with high throughput sequencing (ATAC-seq) to empirically identify putative cis-regulatory regions as those located in accessible chromatin regions (ACRs) in the genome of the crucifer species Capsella grandiflora. Based on whole-genome resequencing data from a natural population, I then showed that ACRs are under stronger purifying selection than other intergenic regions and that they are depleted for transposable element (TE) insertions and enriched for expression quantitative trait loci (eQTL), as would be expected if ACRs are enriched for functional elements affecting gene expression. Second, I explored how the location and silencing of transposable elements (TEs) affects selection against TEs (Paper II). Specifically, I tested a trade-off model on epigenetic TE silencing, according to which the positive effects of TE silencing on preventing TE movement conflict with negative effects of TE silencing on nearby gene expression. I found that TE silencing through the RNA-directed DNA methylation (RdDM) pathway affects selection against TEs close to genes in C. grandiflora, which is consistent with the trade-off model. Third, I used Arabidopsis thaliana single-cell expression data to investigate the relationship between gene body methylation (gbM) and transcriptional regulation (Paper III). I found that there was an indirect correlation between gbM and gene expression noise as well as a direct correlation between gbM and gene expression consistency and potentially intron retention in Arabidopsis thaliana. Fourth, I investigated the impact of demographic history on genomic signatures of selection at linked sites (linked selection) (Paper IV). This study revealed that neutral genetic diversity in C. grandiflora with a stable effective population size is influenced by linked selection whereas in Arabidopsis lyrata, which underwent a recent and strong bottleneck, neutral diversity is mainly affected by population size change. In summary, this thesis offers new insights into determinants of gene expression variation, selection on genomic features linked to gene expression alteration, as well as on the effect of demographic history on linked selection patterns in Brassicaceae.
|
|
| 3. |
- Matuszewski, Damian J., 1988-
(författare)
-
Image and Data Analysis for Biomedical Quantitative Microscopy
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis presents automatic image and data analysis methods to facilitate and improve microscopy-based research and diagnosis. New technologies and computational tools are necessary for handling the ever-growing amounts of data produced in life science. The thesis presents methods developed in three projects with different biomedical applications.In the first project, we analyzed a large high-content screen aimed at enabling personalized medicine for glioblastoma patients. We focused on capturing drug-induced cell-cycle disruption in fluorescence microscopy images of cancer cell cultures. Our main objectives were to identify drugs affecting the cell-cycle and to increase the understanding of different drugs’ mechanisms of action. Here we present tools for automatic cell-cycle analysis and identification of drugs of interest and their effective doses.In the second project, we developed a feature descriptor for image matching. Image matching is a central pre-processing step in many applications. For example, when two or more images must be matched and registered to create a larger field of view or to analyze differences and changes over time. Our descriptor is rotation-, scale-, and illumination-invariant and it has a short feature vector which makes it computationally attractive. The flexibility to combine it with any feature detector and the customization possibility make it a very versatile tool.In the third project, we addressed two general problems for bridging the gap between deep learning method development and their use in practical scenarios. We developed a method for convolutional neural network training using minimally annotated images. In many biomedical applications, the objects of interest cannot be accurately delineated due to their fuzzy shape, ambiguous morphology, image quality, or the expert knowledge and time it requires. The minimal annotations, in this case, consist of center-points or centerlines of target objects of approximately known size. We demonstrated our training method in a challenging application of a multi-class semantic segmentation of viruses in transmission electron microscopy images. We also systematically explored the influence of network architecture hyper-parameters on its size and performance and show the possibility to substantially reduce the size of a network without compromising its performance.All methods in this thesis were designed to work with little or no input from biomedical experts but of course, require fine-tuning for new applications. The usefulness of the tools has been demonstrated by collaborators and other researchers and has inspired further development of related algorithms.
|
|
