| 1. |
- Alevronta, Eleftheria, et al.
(författare)
-
Dose-response relationships of intestinal organs and excessive mucus discharge after gynaecological radiotherapy
- 2021
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203 .- 1932-6203. ; 16:4 April
-
Tidskriftsartikel (refereegranskat)abstract
- Background The study aims to determine possible dose-volume response relationships between the rectum, sigmoid colon and small intestine and the ‘excessive mucus discharge’ syndrome after pelvic radiotherapy for gynaecological cancer. Methods and materials From a larger cohort, 98 gynaecological cancer survivors were included in this study. These survivors, who were followed for 2 to 14 years, received external beam radiation therapy but not brachytherapy and not did not have stoma. Thirteen of the 98 developed excessive mucus discharge syndrome. Three self-assessed symptoms were weighted together to produce a score interpreted as ‘excessive mucus discharge’ syndrome based on the factor loadings from factor analysis. The dose-volume histograms (DVHs) for rectum, sigmoid colon, small intestine for each survivor were exported from the treatment planning systems. The dose-volume response relationships for excessive mucus discharge and each organ at risk were estimated by fitting the data to the Probit, RS, LKB and gEUD models. Results The small intestine was found to have steep dose-response curves, having estimated dose-response parameters: γ : 1.28, 1.23, 1.32, D : 61.6, 63.1, 60.2 for Probit, RS and LKB respectively. The sigmoid colon (AUC: 0.68) and the small intestine (AUC: 0.65) had the highest AUC values. For the small intestine, the DVHs for survivors with and without excessive mucus discharge were well separated for low to intermediate doses; this was not true for the sigmoid colon. Based on all results, we interpret the results for the small intestine to reflect a relevant link. Conclusion An association was found between the mean dose to the small intestine and the occurrence of ‘excessive mucus discharge’. When trying to reduce and even eliminate the incidence of ‘excessive mucus discharge’, it would be useful and important to separately delineate the small intestine and implement the dose-response estimations reported in the study.
|
|
| 2. |
- Allerbo, Oskar, 1985, et al.
(författare)
-
Elastic Gradient Descent, an Iterative Optimization Method Approximating the Solution Paths of the Elastic Net
- 2023
-
Ingår i: Journal of Machine Learning Research. - 1533-7928 .- 1532-4435. ; 24, s. 1-35
-
Tidskriftsartikel (refereegranskat)abstract
- The elastic net combines lasso and ridge regression to fuse the sparsity property of lasso with the grouping property of ridge regression. The connections between ridge regression and gradient descent and between lasso and forward stagewise regression have previously been shown. Similar to how the elastic net generalizes lasso and ridge regression, we introduce elastic gradient descent, a generalization of gradient descent and forward stagewise regression. We theoretically analyze elastic gradient descent and compare it to the elastic net and forward stagewise regression. Parts of the analysis are based on elastic gradient flow, a piecewise analytical construction, obtained for elastic gradient descent with infinitesimal step size. We also compare elastic gradient descent to the elastic net on real and simulated data and show that it provides similar solution paths, but is several orders of magnitude faster. Compared to forward stagewise regression, elastic gradient descent selects a model that, although still sparse, provides considerably lower prediction and estimation errors.
|
|
| 3. |
- Allerbo, Oskar, 1985, et al.
(författare)
-
Flexible, non-parametric modeling using regularized neural networks
- 2022
-
Ingår i: Computational Statistics. - : Springer Science and Business Media LLC. - 0943-4062 .- 1613-9658. ; 37:4, s. 2029-2047
-
Tidskriftsartikel (refereegranskat)abstract
- Non-parametric, additive models are able to capture complex data dependencies in a flexible, yet interpretable way. However, choosing the format of the additive components often requires non-trivial data exploration. Here, as an alternative, we propose PrAda-net, a one-hidden-layer neural network, trained with proximal gradient descent and adaptive lasso. PrAda-net automatically adjusts the size and architecture of the neural network to reflect the complexity and structure of the data. The compact network obtained by PrAda-net can be translated to additive model components, making it suitable for non-parametric statistical modelling with automatic model selection. We demonstrate PrAda-net on simulated data, where we compare the test error performance, variable importance and variable subset identification properties of PrAda-net to other lasso-based regularization approaches for neural networks. We also apply PrAda-net to the massive U.K. black smoke data set, to demonstrate how PrAda-net can be used to model complex and heterogeneous data with spatial and temporal components. In contrast to classical, statistical non-parametric approaches, PrAda-net requires no preliminary modeling to select the functional forms of the additive components, yet still results in an interpretable model representation. © 2021, The Author(s).
|
|
| 4. |
- Allerbo, Oskar, 1985, et al.
(författare)
-
Non-linear, sparse dimensionality reduction via path lasso penalized autoencoders
- 2021
-
Ingår i: Journal of Machine Learning Research. - : Microtome Publishing. - 1532-4435 .- 1533-7928. ; 22
-
Tidskriftsartikel (refereegranskat)abstract
- High-dimensional data sets are often analyzed and explored via the construction of a latent low-dimensional space which enables convenient visualization and efficient predictive modeling or clustering. For complex data structures, linear dimensionality reduction techniques like PCA may not be sufficiently flexible to enable low-dimensional representation. Non-linear dimension reduction techniques, like kernel PCA and autoencoders, suffer from loss of interpretability since each latent variable is dependent of all input dimensions. To address this limitation, we here present path lasso penalized autoencoders. This structured regularization enhances interpretability by penalizing each path through the encoder from an input to a latent variable, thus restricting how many input variables are represented in each latent dimension. Our algorithm uses a group lasso penalty and non-negative matrix factorization to construct a sparse, non-linear latent representation. We compare the path lasso regularized autoencoder to PCA, sparse PCA, autoencoders and sparse autoencoders on real and simulated data sets. We show that the algorithm exhibits much lower reconstruction errors than sparse PCA and parameter-wise lasso regularized autoencoders for low-dimensional representations. Moreover, path lasso representations provide a more accurate reconstruction match, i.e. preserved relative distance between objects in the original and reconstructed spaces. ©2021 Oskar Allerbo and Rebecka Jörnsten.
|
|
| 5. |
- Almstedt, Elin, 1988-, et al.
(författare)
-
Integrative discovery of treatments for high-risk neuroblastoma
- 2020
-
Ingår i: Nature Communications. - : Springer Science and Business Media LLC. - 2041-1723 .- 2041-1723. ; 11:1
-
Tidskriftsartikel (refereegranskat)abstract
- Despite advances in the molecular exploration of paediatric cancers, approximately 50% of children with high-risk neuroblastoma lack effective treatment. To identify therapeutic options for this group of high-risk patients, we combine predictive data mining with experimental evaluation in patient-derived xenograft cells. Our proposed algorithm, TargetTranslator, integrates data from tumour biobanks, pharmacological databases, and cellular networks to predict how targeted interventions affect mRNA signatures associated with high patient risk or disease processes. We find more than 80 targets to be associated with neuroblastoma risk and differentiation signatures. Selected targets are evaluated in cell lines derived from high-risk patients to demonstrate reversal of risk signatures and malignant phenotypes. Using neuroblastoma xenograft models, we establish CNR2 and MAPK8 as promising candidates for the treatment of high-risk neuroblastoma. We expect that our method, available as a public tool (targettranslator.org), will enhance and expedite the discovery of risk-associated targets for paediatric and adult cancers.
|
|
| 6. |
- Andersson, Viktor, 1995, et al.
(författare)
-
Controlled Decent Training
- 2023
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- In this work, a novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve training convergence rate. Dynamic label augmentation is proposed within the framework of gradient descent training where the convergence of training loss is controlled. First, we capture the training behavior with the help of empirical Neural Tangent Kernels (NTK) and borrow tools from systems and control theory to analyze both the local and global training dynamics (e.g. stability, reachability). Second, we propose to dynamically alter the gradient descent training mechanism via fictitious labels as control inputs and an optimal state feedback policy. In this way, we enforce locally H2 optimal and convergent training behavior. The novel algorithm, Controlled Descent Training (CDT), guarantees local convergence. CDT unleashes new potentials in the analysis, interpretation, and design of ANN architectures. The applicability of the method is demonstrated on standard regression and classification problems.
|
|
| 7. |
- Andersson, Viktor, 1995, et al.
(författare)
-
Controlled Descent Training
- 2024
-
Ingår i: International Journal of Robust and Nonlinear Control. - 1099-1239 .- 1049-8923. ; 34
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, a novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve training convergence rate. Dynamic label augmentation is proposed within the framework of gradient descent training where the convergence of training loss is controlled. First, we capture the training behavior with the help of empirical Neural Tangent Kernels (NTK) and borrow tools from systems and control theory to analyze both the local and global training dynamics (e.g. stability, reachability). Second, we propose to dynamically alter the gradient descent training mechanism via fictitious labels as control inputs and an optimal state feedback policy. In this way, we enforce locally H2 optimal and convergent training behavior. The novel algorithm, Controlled Descent Training (CDT), guarantees local convergence. CDT unleashes new potentials in the analysis, interpretation, and design of ANN architectures. The applicability of the method is demonstrated on standard regression and classification problems.
|
|
| 8. |
- Björnsson, Bergthor, et al.
(författare)
-
Digital twins to personalize medicine
- 2020
-
Ingår i: Genome Medicine. - : Springer Science and Business Media LLC. - 1756-994X. ; 12:1
-
Forskningsöversikt (refereegranskat)abstract
- Personalized medicine requires the integration and processing of vast amounts of data. Here, we propose a solution to this challenge that is based on constructing Digital Twins. These are high-resolution models of individual patients that are computationally treated with thousands of drugs to find the drug that is optimal for the patient.
|
|
| 9. |
|
|
| 10. |
- Cook, Daniel John, 1986, et al.
(författare)
-
Molecular natural history of breast cancer: Leveraging transcriptomics to predict breast cancer progression and aggressiveness
- 2020
-
Ingår i: Cancer Medicine. - : Wiley. - 2045-7634. ; 9:10, s. 3551-3562
-
Tidskriftsartikel (refereegranskat)abstract
- Cancer Medicine published by John Wiley & Sons Ltd. Background: Characterizing breast cancer progression and aggressiveness relies on categorical descriptions of tumor stage and grade. Interpreting these categorical descriptions is challenging because stage convolutes the size and spread of the tumor and no consensus exists to define high/low grade tumors. Methods: We address this challenge of heterogeneity in patient-specific cancer samples by adapting and applying several tools originally created for understanding heterogeneity and phenotype development in single cells (specifically, single-cell topological data analysis and Wanderlust) to create a continuous metric describing breast cancer progression using bulk RNA-seq samples from individual patient tumors. We also created a linear regression-based method to predict tumor aggressiveness in vivo from bulk RNA-seq data. Results: We found that breast cancer proceeds along three convergent phenotype trajectories: luminal, HER2-enriched, and basal-like. Furthermore, 31 296 genes (for luminal cancers), 17 827 genes (for HER2-enriched), and 18 505 genes (for basal-like) are dynamically differentially expressed during breast cancer progression. Across progression trajectories, our results show that expression of genes related to ADP-ribosylation decreased as tumors progressed (while PARP1 and PARP2 increased or remained stable), suggesting the potential for a differential response to PARP inhibitors based on cancer progression. Additionally, we developed a 132-gene expression regression equation to predict mitotic index and a 23-gene expression regression equation to predict growth rate from a single breast cancer biopsy. Conclusion: Our results suggest that breast cancer dynamically changes during disease progression, and growth rate of the cancer cells is associated with distinct transcriptional profiles.
|
|
| 11. |
- Gustafsson, Johan, 1976, et al.
(författare)
-
DSAVE: Detection of misclassified cells in single-cell RNA-Seq data
- 2020
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203 .- 1932-6203. ; 15:12 December
-
Tidskriftsartikel (refereegranskat)abstract
- Single-cell RNA sequencing has become a valuable tool for investigating cell types in complex tissues, where clustering of cells enables the identification and comparison of cell populations. Although many studies have sought to develop and compare different clustering approaches, a deeper investigation into the properties of the resulting populations is lacking. Specifically, the presence of misclassified cells can influence downstream analyses, highlighting the need to assess subpopulation purity and to detect such cells. We developed DSAVE (Down-SAmpling based Variation Estimation), a method to evaluate the purity of single-cell transcriptome clusters and to identify misclassified cells. The method utilizes down-sampling to eliminate differences in sampling noise and uses a log-likelihood based metric to help identify misclassified cells. In addition, DSAVE estimates the number of cells needed in a population to achieve a stable average gene expression profile within a certain gene expression range. We show that DSAVE can be used to find potentially misclassified cells that are not detectable by similar tools and reveal the cause of their divergence from the other cells, such as differing cell state or cell type. With the growing use of single-cell RNA-seq, we foresee that DSAVE will be an increasingly useful tool for comparing and purifying subpopulations in single-cell RNA-Seq datasets.
|
|
| 12. |
- Gustafsson, Johan, 1976, et al.
(författare)
-
Generation and analysis of context-specific genome-scale metabolic models derived from single-cell RNA-Seq data
- 2023
-
Ingår i: Proceedings of the National Academy of Sciences of the United States of America. - : Proceedings of the National Academy of Sciences. - 0027-8424 .- 1091-6490. ; 120:6
-
Tidskriftsartikel (refereegranskat)abstract
- Single-cell RNA sequencing combined with genome-scale metabolic models (GEMs) has the potential to unravel the differences in metabolism across both cell types and cell states but requires new computational methods. Here, we present a method for generating cell-type-specific genome-scale models from clusters of single-cell RNA-Seq profiles. Specifically, we developed a method to estimate the minimum number of cells required to pool to obtain stable models, a bootstrapping strategy for estimating statistical inference, and a faster version of the task-driven integrative network inference for tissues algorithm for generating context-specific GEMs. In addition, we evaluated the effect of different RNA-Seq normalization methods on model topology and differences in models generated from single-cell and bulk RNA-Seq data. We applied our methods on data from mouse cortex neurons and cells from the tumor microenvironment of lung cancer and in both cases found that almost every cell subtype had a unique metabolic profile. In addition, our approach was able to detect cancer-associated metabolic differences between cancer cells and healthy cells, showcasing its utility. We also contextualized models from 202 single-cell clusters across 19 human organs using data from Human Protein Atlas and made these available in the web portal Metabolic Atlas, thereby providing a valuable resource to the scientific community. With the ever-increasing availability of single-cell RNA-Seq datasets and continuously improved GEMs, their combination holds promise to become an important approach in the study of human metabolism.
|
|
| 13. |
- Gustafsson, Johan, 1976, et al.
(författare)
-
Generation and analysis of context-specific genome-scale metabolic models derived from single-cell RNA-Seq data
- 2022
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Single-cell RNA sequencing has the potential to unravel the differences in metabolism across cell types and cell states in both the healthy and diseased human body. The use of existing knowledge in the form of genome-scale metabolic models (GEMs) holds promise to strengthen such analyses, but the combined use of these two methods requires new computational methods. Here, we present a method for generating cell-type-specific genome-scale models from clusters of single-cell RNA-Seq profiles. Specifically, we developed a method to estimate the number of cells required to pool to obtain stable models, a bootstrapping strategy for estimating statistical inference, and a faster version of the tINIT algorithm for generating context-specific GEMs. In addition, we evaluated the effect of different RNA-Seq normalization methods on model topology and differences in models generated from single-cell and bulk RNA-Seq data. We applied our methods on data from mouse cortex neurons and cells from the tumor microenvironment of lung cancer and in both cases found that almost every cell subtype had a unique metabolic profile, emphasizing the need to study them separately rather than to build models from bulk RNA-Seq data. In addition, our approach was able to detect cancer-associated metabolic differences between cancer cells and healthy cells, showcasing its utility. With the ever-increasing availability of single-cell RNA-Seq datasets and continuously improved GEMs, their combination holds promise to become an important approach in the study of human metabolism.
|
|
| 14. |
- Gustafsson, Johan, 1976, et al.
(författare)
-
Sources of variation in cell-type RNA-Seq profiles
- 2020
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 15:9
-
Tidskriftsartikel (refereegranskat)abstract
- Cell-type specific gene expression profiles are needed for many computational methods operating on bulk RNA-Seq samples, such as deconvolution of cell-type fractions and digital cytometry. However, the gene expression profile of a cell type can vary substantially due to both technical factors and biological differences in cell state and surroundings, reducing the efficacy of such methods. Here, we investigated which factors contribute most to this variation. We evaluated different normalization methods, quantified the variance explained by different factors, evaluated the effect on deconvolution of cell type fractions, and examined the differences between UMI-based single-cell RNA-Seq and bulk RNA-Seq. We investigated a collection of publicly available bulk and single-cell RNA-Seq datasets containing B and T cells, and found that the technical variation across laboratories is substantial, even for genes specifically selected for deconvolution, and this variation has a confounding effect on deconvolution. Tissue of origin is also a substantial factor, highlighting the challenge of using cell type profiles derived from blood with mixtures from other tissues. We also show that much of the differences between UMI-based single-cell and bulk RNA-Seq methods can be explained by the number of read duplicates per mRNA molecule in the single-cell sample. Our work shows the importance of either matching or correcting for technical factors when creating cell-type specific gene expression profiles that are to be used together with bulk samples.
|
|
| 15. |
- Krona, Cecilia, et al.
(författare)
-
GLIOBLASTOMA GROWTH IS SHAPED BY INVASION ROUTE-SPECIFIC FUNCTIONAL SIGNATURES
- 2023
-
Ingår i: Neuro-Oncology. - 1522-8517. ; 25:Supplement: 5, MODL-16
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- One of the defining features of glioblastomas (GBMs) is the capacity for invasive growth along multiple anatomical pathways in the brain. GBM is well-studied on a genetic and molecular level, but clinically relevant and experimentally tractable models of invasive growth are largely lacking. Here, we report an integrated study of patient-matched information, genomic- and molecular profiles with growth in mouse brains to expose treatments and biomarkers associated with glioblastoma invasion and recurrence. In total, 64 patient-derived cell lines (PDCLs) were injected into the striatum of n ≥ 4 mice each. The 45 tumor-forming PDCLs were each scored for 10 distinct growth characteristics (n = 182 mice). The repertoire of phenotypes was highly divergent, and our material included clear cases of perivascular route invasion, white matter route invasion, perineuronal satellitosis, and gliosarcoma. We explored if cellular pathways, monitored by RNA-sequencing, could account for these differences. GSEA highlighted a positive enrichment for highly proliferative proneural tumors characterized by Notch activation, neuronal signaling, and epigenetic gene regulatory programs in the tumor-initiating lines. Transcriptional signatures were also strongly predictive of route-specific invasion. Diffuse invasion was predominantly seen in classical-subtype PDCLs with astrocytic or outer radial glia-like signatures. Proneural PDCLs, in turn, grew as solid tumors with an invasive peripheral region around vasculature, and mesenchymal tumors were more demarcated. To explore the therapeutic implications of our findings, we used our data-driven method (TargetTranslator, Nat Comm 2020) to predict the drug vulnerabilities of different types of invasive glioblastoma. Defined GBM tumors with perivascular invasion are characterized by increased IGFR1, MAPK/ERK, PI3K/AKT/mTOR, and JAK2 signaling. Diffusively growing GBM tumors, on the other hand, depend more on Wnt/β-catenin signaling, neuronal signaling, and active inflammatory response. Using a sphere invasion assay, we confirm that targeting both PI3K- and Wnt signaling selectively reduces glioblastoma invasion, highlighting their therapeutic potential.
|
|
| 16. |
|
|
| 17. |
|
|
| 18. |
- Larsson, Ida, et al.
(författare)
-
Modeling glioblastoma heterogeneity as a dynamic network of cell states
- 2021
-
Ingår i: Molecular Systems Biology. - : EMBO. - 1744-4292. ; 17:9
-
Tidskriftsartikel (refereegranskat)abstract
- Tumor cell heterogeneity is a crucial characteristic of malignant brain tumors and underpins phenomena such as therapy resistance and tumor recurrence. Advances in single-cell analysis have enabled the delineation of distinct cellular states of brain tumor cells, but the time-dependent changes in such states remain poorly understood. Here, we construct quantitative models of the time-dependent transcriptional variation of patient-derived glioblastoma (GBM) cells. We build the models by sampling and profiling barcoded GBM cells and their progeny over the course of 3 weeks and by fitting a mathematical model to estimate changes in GBM cell states and their growth rates. Our model suggests a hierarchical yet plastic organization of GBM, where the rates and patterns of cell state switching are partly patient-specific. Therapeutic interventions produce complex dynamic effects, including inhibition of specific states and altered differentiation. Our method provides a general strategy to uncover time-dependent changes in cancer cells and offers a way to evaluate and predict how therapy affects cell state composition.
|
|
| 19. |
- Martinez, David, et al.
(författare)
-
NCAE: data-driven representations using a deep network-coherent DNA methylation autoencoder identify robust disease and risk factor signatures
- 2023
-
Ingår i: Briefings in Bioinformatics. - : OXFORD UNIV PRESS. - 1467-5463 .- 1477-4054. ; 24:5
-
Tidskriftsartikel (refereegranskat)abstract
- Precision medicine relies on the identification of robust disease and risk factor signatures from omics data. However, current knowledge-driven approaches may overlook novel or unexpected phenomena due to the inherent biases in biological knowledge. In this study, we present a data-driven signature discovery workflow for DNA methylation analysis utilizing network-coherent autoencoders (NCAEs) with biologically relevant latent embeddings. First, we explored the architecture space of autoencoders trained on a large-scale pan-tissue compendium (n = 75 272) of human epigenome-wide association studies. We observed the emergence of co-localized patterns in the deep autoencoder latent space representations that corresponded to biological network modules. We determined the NCAE configuration with the strongest co-localization and centrality signals in the human protein interactome. Leveraging the NCAE embeddings, we then trained interpretable deep neural networks for risk factor (aging, smoking) and disease (systemic lupus erythematosus) prediction and classification tasks. Remarkably, our NCAE embedding-based models outperformed existing predictors, revealing novel DNA methylation signatures enriched in gene sets and pathways associated with the studied condition in each case. Our data-driven biomarker discovery workflow provides a generally applicable pipeline to capture relevant risk factor and disease information. By surpassing the limitations of knowledge-driven methods, our approach enhances the understanding of complex epigenetic processes, facilitating the development of more effective diagnostic and therapeutic strategies.
|
|
