Search

The plant breeding industry has shown growing interest in using the genotype data of relevant markers for performing selection of new competitive varieties. The selection usually benefits from large amounts of marker data and it is therefore crucial to dispose of data collection methods that are both cost-effective and reliable. Computational methods such as genotype imputation have been proposed earlier in several plant science studies for addressing the cost challenge. Genotype imputation methods have though been used more frequently and investigated more extensively in human genetics research. The various algorithms that exist have shown lower accuracy at inferring the genotype of genetic variants occurring at low frequency, while these rare variants can have great significance and impact in the genetic studies that underlie selection. In contrast, pooling is a technique that can efficiently identify low-frequency items in a population and it has been successfully used for detecting the samples that carry rare variants in a population. In this study, we propose to combine pooling and imputation, and demonstrate this by simulating a hypothetical microarray for genotyping a population of recombinant inbred lines in a cost-effective and accurate manner, even for rare variants. We show that with an adequate imputation model, it is feasible to accurately predictthe individual genotypes at lower cost than sample-wise genotyping and time-effectively. Moreover, we provide code resources for reproducing the results presented in this study in the form of a containerized workflow., eSSENCE - An eScience Collaboration

Since the first human genome assembly’s release, our knowledge of the genetic architecture of complex traits and diseases has grown steadily. Genome-wide association studies (GWAS) played a major role but are limited to common traits and single-nucleotide polymorphisms (SNPs). Technologies and resources like next-generation sequencing, Mendelian Randomization (MR), long-read sequencing and improved reference genomes enable the investigation of variants inaccessible to GWAS, such as copy number variations (CNVs), rare variants and variants in previously unresolved regions. In project I, we performed a GWAS of estradiol measurements using data from UK Biobank and quantified estradiol’s effect on bone mineral density (BMD) using MR. 14 loci were associated with estradiol levels in males, of which one was also significant in females and an additional female-specific locus. We found a significant effect of estradiol on BMD, confirming previous research of estrogen’s importance for skeletal health. In project II, we used the GWAS results from project I to investigate the effect of endogenous estradiol on breast, endometrial and ovarian cancer using MR. Estradiol was associated with ovarian cancer and nominally associated with estrogen receptor-positive breast cancer, demonstrating the effect of endogenous estrogen on cancer risk. In project III, we quantified the effect of 184,182 CNVs on 438 blood plasma proteins using whole-genome sequencing (WGS) data from a Northern Swedish cohort and validated our findings using long-read sequencing in a subcohort. 15 CNVs were associated with 16 proteins of which four could be validated using long reads and three more were more complex variation. Our findings show the effects of CNVs on the plasma proteome and highlight the application different sequencing technologies for CNV detection. In project IV, we evaluated the use of T2T-CHM13 as reference for the SweGen cohort. Compared to GRCh38, mapping quality improved and we identifie

Prehistoric chewed pitch has proven to be a useful source of ancient DNA, both from humans and their microbiomes. Here we present the metagenomic analysis of three pieces of chewed pitch from Huseby Klev, Sweden, that were dated to 9,890-9,540 before present. The metagenomic profile exposes a Mesolithic oral microbiome that includes opportunistic oral pathogens. We compared the data with healthy and dysbiotic microbiome datasets and we identified increased abundance of periodontitis-associated microbes. In addition, trained machine learning models predicted dysbiosis with 70-80% probability. Moreover, we identified DNA sequences from eukaryotic species such as red fox, hazelnut, red deer and apple. Our results indicate a case of poor oral health during the Scandinavian Mesolithic, and show that pitch pieces have the potential to provide information on material use, diet and oral health.

Background: Transcriptome assembly from RNA-sequencing data in species without a reliable reference genome has to be performed de novo, but studies have shown that de novo methods often have inadequate ability to reconstruct transcript isoforms. We address this issue by constructing an assembly pipeline whose main purpose is to produce a comprehensive set of transcript isoforms. Results: We present the de novo transcript isoform assembler ClusTrast, which takes short read RNA-seq data as input, assembles a primary assembly, clusters a set of guiding contigs, aligns the short reads to the guiding contigs, assembles each clustered set of short reads individually, and merges the primary and clusterwise assemblies into the final assembly. We tested ClusTrast on real datasets from six eukaryotic species, and showed that ClusTrast reconstructed more expressed known isoforms than any of the other tested de novo assemblers, at a moderate reduction in precision. For recall, ClusTrast was on top in the lower end of expression levels (<15% percentile) for all tested datasets, and over the entire range for almost all datasets. Reference transcripts were often (35–69% for the six datasets) reconstructed to at least 95% of their length by ClusTrast, and more than half of reference transcripts (58–81%) were reconstructed with contigs that exhibited polymorphism, measuring on a subset of reliably predicted contigs. ClusTrast recall increased when using a union of assembled transcripts from more than one assembly tool as primary assembly. Conclusion: We suggest that ClusTrast can be a useful tool for studying isoforms in species without a reliable reference genome, in particular when the goal is to produce a comprehensive transcriptome set with polymorphic variants., Not duplicate with DiVA 1810720QC 20240215

Accurately predicting the tool remaining useful life (RUL) is critical for maximizing tool utilization and saving machining costs. Various physical model-based or data-driven prediction methods have been developed and successfully applied in different machining operations. However, many uncertain factors affect tool RUL during the cutting process, making it challenging to create a precise physical model to characterize the degradation of tool performance. The success of the purely data-driven technique depends on the amount and quality of the training samples, it does not consider the physical law of tool wear, and the interpretability of the prediction results is poor. This paper presents a data-model linkage approach for tool RUL prediction based on deep feature fusion and Wiener process to address the above limitations. A convolutional stacked bidirectional long short-term memory network with time-space attention mechanism (CSBLSTM-TSAM) is developed in the data-driven module to fuse the multi-sensor signals collected during the cutting process and then obtain the mapping relationship between signal features and tool wear values. In the physical modeling module, a three-stage tool RUL prediction model based on the nonlinear Wiener process is established by considering the evolution law of different wear stages and multi-layer uncertainty, and the corresponding probability density function is derived. The real-time estimated tool wear of the data-driven module is used as the observed value of the physical model, and the model parameters are dynamically updated by the weight-optimized particle filter (WOPF) algorithm under a Bayesian framework, thereby realizing the data-model linkage tool RUL prediction. Milling experiments demonstrate that the proposed method not only improves RUL prediction accuracy, but also has good generalization ability and robustness for prediction tasks under different working conditions., QC 20240201

Spatial biology is a rapidly growing field that has seen tremendous progress over the last decade. We are now able to measure how the morphology, genome, transcriptome, and proteome of a tissue vary across space. Datasets generated by spatial technologies reflect the complexity of the systems they measure: They are multi-modal, high-dimensional, and layer an intricate web of dependencies between biological compartments at different length scales. To add to this complexity, measurements are often sparse and noisy, obfuscating the underlying biological signal and making the data difficult to interpret. In this thesis, we describe how data from spatial biology experiments can be analyzed with methods from deep learning and generative modeling to accelerate biological discovery. The thesis is divided into two parts. The first part provides an introduction to the fields of deep learning and spatial biology, and how the two can be combined to model spatial biology data. The second part consists of four papers describing methods that we have developed for this purpose. Paper I presents a method for inferring spatial gene expression from hematoxylin and eosin stains. The proposed method offers a data-driven approach to analyzing histopathology images without relying on expert annotations and could be a valuable tool for cancer screening and diagnosis in the clinics. Paper II introduces a method for jointly modeling spatial gene expression with histology images. We show that the method can predict super-resolved gene expression and transcriptionally characterize small-scale anatomical structures. Paper III proposes a method for learning flexible Markov kernels to model continuous and discrete data distributions. We demonstrate the method on various image synthesis tasks, including unconditional image generation and inpainting. Paper IV leverages the techniques introduced in Paper III to integrate data from different spatial biology experiments. The proposed method can be use, Spatial biologi är ett snabbt växande forskningsområde som har sett en hög utvecklingstakt under det senaste decenniet. Vi kan idag mäta hur en vävnads morfologi, genom, transkriptom och proteom varierar i rummet. Dataset skapade av spatiala teknologier återspeglar komplexiteten i de system de mäter: De är multimodala, högdimensionella och är uppbyggda av ett intrikat nätverk av beroenden mellan biologiska strukturer som existerar på olika längdskalor. Som om denna komplexitet inte var nog, är mätningarna ofta både glesa och brusiga, vilket försvårar tolkningen av den underliggande biologiska signalen. I denna avhandling beskriver vi hur data från experiment inom spatial biologi kan analyseras med hjälp av djupinlärning och generativ modellering för att accelerera biologiska upptäckter. Avhandlingen är uppdelad i två delar. Den första delen ger en introduktion till fälten djupinlärning och spatial biologi, och hur dessa kan kombineras för att modellera data inom spatial biologi. Den andra delen består av fyra artiklar som beskriver metoder som vi har utvecklat för detta ändamål. Artikel I presenterar en metod för att skatta spatialt genuttryck från hematoxylin-eosin-färgningar. Den föreslagna metoden erbjuder ett datadrivet tillvägagångssätt för att analysera histopatologi-bilder utan användning av expertannoteringar och kan utgöra ett värdefullt verktyg för cancerscreening och diagnos i kliniken. Artikel II introducerar en metod för sammodellering av spatialt genuttryck och histologibilder. Vi visar att metoden kan användas för att predicera superupplöst genuttryck och transkriptionellt karakterisera småskaliga anatomiska strukturer. Artikel III beskriver en metod för modellering av kontinuerliga och diskreta datafördelningar med flexibla Markovkärnor. Vi demonstrerar metoden på olika bildgenereringsuppgifter, inklusive obetingad datagenerering och inpainting. Artikel IV utnyttjar teknikerna från Artikel III för att integrera data från olika experiment inom spatial, QC 2024-01-09

MOTIVATION: In pathway analysis, we aim to establish a connection between the activity of a particular biological pathway and a difference in phenotype. There are many available methods to perform pathway analysis, many of them rely on an upstream differential expression analysis, and many model the relations between the abundances of the analytes in a pathway as linear relationships. RESULTS: Here, we propose a new method for pathway analysis, MIPath, that relies on information theoretical principles and, therefore, does not model the association between pathway activity and phenotype, resulting in relatively few assumptions. For this, we construct a graph of the data points for each pathway using a nearest-neighbor approach and score the association between the structure of this graph and the phenotype of these same samples using Mutual Information while adjusting for the effects of random chance in each score. The initial nearest neighbor approach evades individual gene-level comparisons, hence making the method scalable and less vulnerable to missing values. These properties make our method particularly useful for single-cell data. We benchmarked our method on several single-cell datasets, comparing it to established and new methods, and found that it produces robust, reproducible, and meaningful scores. AVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/statisticalbiotechnology/mipath, or through Python Package Index as "mipathway.", QC 20240130

The information conveyed by genetic markers, such as single nucleotide polymorphisms (SNPs), has been widely used in biomedical research to study human diseases and is increasingly valued in agriculture for genomic selection purposes. Specific markers can be identified as a genetic signature that correlates with certain characteristics in a living organism, e.g. a susceptibility to disease or high-yield traits. Capturing these signatures with sufficient statistical power often requires large volumes of data, with thousands of samples to be analysed and potentially millions of genetic markers to be screened. Relevant effects are particularly delicate to detect when the genetic variations involved occur at low frequencies. The cost of producing such marker genotype data is therefore a critical part of the analysis. Despite recent technological advances, production costs can still be prohibitive on a large scale and genotype imputation strategies have been developed to address this issue. Genotype imputation methods have been extensively studied in human data and, to a lesser extent, in crop and animal species. A recognised weakness of imputation methods is their lower accuracy in predicting the genotypes for rare variants, whereas those can be highly informative in association studies and improve the accuracy of genomic selection. In this respect, pooling strategies can be well suited to complement imputation, as pooling is efficient at capturing the low-frequency items in a population. Pooling also reduces the number of genotyping tests required, making its use in combination with imputation a cost-effective compromise between accurate but expensive high-density genotyping of each sample individually and stand-alone imputation. However, due to the nature of genotype data and the limitations of genotype testing techniques, decoding pooled genotypes into unique data resolutions is challenging. In this work, we study the characteristics of decoded genotype data from po

The protein sequence determines how it will fold into its unique three-dimensional structure. Once folded, proteins perform their functions by interacting with other proteins or molecules called ligands within the cell. Experimental determination of protein structure and function is tedious. Computational approaches aim to accurately predict the properties of proteins to complement experimental efforts of understanding biochemical mechanisms within the cell. This thesis introduces computational techniques that predict the structure of protein complexes and identify protein residues involved in interactions with common biomolecules, such as metal ions and nucleic acids, based on sequence information. AlphaFold, a method that predicted protein structure using sequence information with almost experimental accuracy, was a critical breakthrough that shaped the field of protein structure prediction. Subsequently, approaches such as FoldDock adapted the AlphaFold pipeline for dimer complexes. Paper I applies the FoldDock protocol to understand toxin-antitoxin systems. These protein complexes are highly evolutionary conserved, and high-confidence dimer predictions were generated. Paper II applies the FoldDock protocol to study protein-protein interactions in the human proteome. To verify the reliability of machine-learning-based computational methods, they must be tested on independent data different from the data used to train the method. Paper III involves generating and using a homology-reduced independent test set to benchmark the performance of protein complex structure predictors, including the recent AlphaFold release adapted for multi-chain proteins – AlphaFold-Multimer. A confidence score (pDockQ2) was proposed to estimate the quality of the interfaces within multimers. Paper I, Paper II and Paper III are associated with predicting and evaluating protein-protein interactions. Representation learning involves finding effective representations of input data to maxi

Short tandem repeat (STR) mutations are prevalent in colorectal cancer (CRC), especially in tumours with the microsatellite instability (MSI) phenotype. While STR length variations are known to regulate gene expression under physiological conditions, the functional impact of STR mutations in CRC remains unclear. Here, we integrate STR mutation data with clinical information and gene expression data to study the gene regulatory effects of STR mutations in CRC. We confirm that STR mutability in CRC highly depends on the MSI status, repeat unit size, and repeat length. Furthermore, we present a set of 1244 putative expression STRs (eSTRs) for which the STR length is associated with gene expression levels in CRC tumours. The length of 73 eSTRs is associated with expression levels of cancer-related genes, nine of which are CRC-specific genes. We show that linear models describing eSTR-gene expression relationships allow for predictions of gene expression changes in response to eSTR mutations. Moreover, we found an increased mutability of eSTRs in MSI tumours. Our evidence of gene regulatory roles for eSTRs in CRC highlights a mostly overlooked way through which tumours may modulate their phenotypes. Future extensions of these findings could uncover new STR-based targets in the treatment of cancer.

Deep learning has the potential to be used to improve and streamline EEG analysis. At the present, classifiers and supervised learning dominate the field. Supervised learning depends on target labels which most often are created by human experts manually classifying data. A problem with supervised learning is intra- and interrater agreement which in some instances are far from perfect. This can affect the training and make evaluation more difficult. This thesis includes three papers where self-supervised deep neural networks were developed. In self-supervised learning, the input data to the networks themselves contain structures that are used as targets for the training and no labeling is necessary. In paper I, deep neural networks were trained to increase the number of-, or to recreate missing EEG-channels. The performance was at least on the same level as that of spherical interpolation, but unlike in the case of interpolation, missing data does not have to be identified manually first. Papers II and III involved developing deep neural networks for clustering analysis. The networks produced two-dimensional representations of EEG data and the training strategy was based on the principle of t-distributed stochastic neighbor embedding (t-SNE). In paper II, comparisons were made to parametric t-SNE and EEG-features obtained from time-frequency methods. The deep neural networks produced more distinct clustering when tested on data annotated for epileptiform discharges, seizure activity, or sleep-wakefulness. In paper III, the newly developed method was used to compare annotations of epileptiform discharges. Two experts performed independent annotations and classifiers were trained on these, using supervised learning, which in turn produced new annotations. The agreement when comparing two sets of annotations was not larger between the two experts than between an expert and a classifier. The analysis showed that differences in the annotations by the experts infl, Funding: The work was funded by Saad Nagi (grants RÖ-974228, RÖ-962769, and RÖ-941377), Magnus Thordstein (grant RÖ-986017), and Håkan Olaus-son (grants LIO-936017 and RÖ-941359).

The brain is the most metabolically active organ in the human body and therefore rely on a continuous supply of oxygen and glucose. Neuronal stimulation in specific regions of the leads to the firing of action potentials, a process facilitated by voltage-gated ion channels in the neurons’ cell membranes. This activation of the ion channels significantly elevates the brain’s metabolic energy demand, compelling neurons to ramp up their metabolic activity in response. Concurrently, this neuronal activation also initiates a signalling cascade that induces vasodilation and increases blood flow, thereby ensuring that regions with elevated neural activity are adequately supplied with oxygen and nutrients. This dynamic interplay between neuronal activity and cerebral blood flow (CBF) regulation constitutes the neurovascular coupling (NVC). The NVC is a cornerstone in interpreting functional Magnetic Resonance Imaging (fMRI) Blood Oxygen Level-Dependent (BOLD) responses. The BOLD response is an indirect, non-invasive, and highly sensitive indicator of neuronal activity, reflecting changes in blood oxygenation and flow associated with the neuronal and metabolic activity in the brain. By examining these responses, we can gain insights into the complex interactions between neuronal activity, energy metabolism, and CBF. Additionally, techniques such as 13C Metabolic Flux Analysis (13C MFA) makes it possible to gain further insight into the cerebral metabolism. This method enables a detailed examination of metabolic pathways and fluxes by tracking the incorporation of 13C-labelled substrates into various metabolites. By using 13C MFA, researchers can quantify the flow of substrates through metabolic networks, offering a deeper understanding of how cell such as neurons adapt their metabolism during different functional states and conditions. Central to exploring these multifaceted aspects of cerebral metabolism is the use of mathematical modelling and systems biology. These discip

One of the ways that a vascular network grows is through the process of angiogenesis, wherebya new blood vessel forms as a branch from an existing vessel towards an area which isstimulating vascular growth. Due to the demands for nutrients and waste transport, growingtumour cells will access the surrounding vascular network by inducing angiogenesis. Once thetumour is connected with the vascular system it can grow further and colonize distant organs.Given the critical nature of this step in tumour development, there is a demand for mathematicaland computational models to provide an understanding of the process for treatment in predictivemedicine. These models allow us to generate vascular networks that demonstrate similarbehaviour to that of the observed networks; however, there is a lack of quantifiable measures ofsimilarity between generated networks, or, of a generated and real network. Furthermore, thereis not an established way to determine which measures hold the most relevance todistinguishing similarity. To construct such a measure we transform our generated vascularnetworks into an abstract graph representation which allows exploration of the plethora of graphcentralities. We propose to determine the relevance of a centrality by finding one that acts as asynthetic likelihood function for estimating the model's parameters with minimal error.Evaluating the relevance of many centralities, it is then possible to suggest which centralitiesshould be used to quantitatively determine similarity. This allows for a way to measure howrealistic a model's growth is, and if given sufficient data, to distinguish between regular andtumour-induced angiogenesis and use it within cancer screening.

Pancreatic ductal adenocarcinoma (PDAC) is an aggressive disease with poor survival. Novel biomarkers are urgently needed to improve the outcome through early detection. Here, we aimed to discover novel biomarkers for early PDAC detection using multi-omics profiling in pre-diagnostic plasma samples biobanked after routine health examinations. A nested case-control study within the Northern Sweden Health and Disease Study was designed. Pre-diagnostic plasma samples from 37 future PDAC patients collected within 2.3 years before diagnosis and 37 matched healthy controls were included. We analyzed metabolites using liquid chromatography mass spectrometry and gas chromatography mass spectrometry, microRNAs by HTG edgeseq, proteins by multiplex proximity extension assays, as well as three clinical biomarkers using milliplex technology. Supervised and unsupervised multi-omics integration were performed as well as univariate analyses for the different omics types and clinical biomarkers. Multiple hypothesis testing was corrected using Benjamini-Hochberg's method and a false discovery rate (FDR) below 0.1 was considered statistically significant. Carbohydrate antigen (CA) 19-9 was associated with PDAC risk (OR [95 % CI] = 3.09 [1.31–7.29], FDR = 0.03) and increased closer to PDAC diagnosis. Supervised multi-omics models resulted in poor discrimination between future PDAC cases and healthy controls with obtained accuracies between 0.429–0.500. No single metabolite, microRNA, or protein was differentially altered (FDR < 0.1) between future PDAC cases and healthy controls. CA 19-9 levels increase up to two years prior to PDAC diagnosis but extensive multi-omics analysis including metabolomics, microRNAomics and proteomics in this cohort did not identify novel early biomarkers for PDAC., CC BY 4.0Corresponding author at: University Hospital of Umeå, 901 85 Umeå, Sweden. E-mail address: emmy.borgmastars@umu.se (E. Borgmästars)The authors thank Hanna Nyström, and Daniel Öhlund at Umeå University for valuable assistance in data collection. We thank Xiaoshuang Feng at International Agency for Research of Cancer, Lyon, France for guidance in statistical analyses. The authors would also like to thank Swedish Metabolomics Centre, Umeå, Sweden (www.swedishmetabolomicscentre.se) and Biobanken Norr. Funding: This study was funded by Umeå University, the Swedish Research Council [2016-02990, 2019-01690], the Swedish Cancer Society [CAN 2016/643, 19 0273], Region Västerbotten [RV-583411, RV-549731, RV-583411, RV-841551, RV 967602], Finska Läkaresällskapet, Medicinska Understödsföreningen Liv och Hälsa, the Sjöberg Foundation, The JC Kempe Memorial Foundation Scholarship Fund, The Royal Swedish Academy of Sciences (PE Lindahl Foundation, LM2021-0010 and LM2023-0012), The Swedish Society of Medicine (SLS-960379), Cancerforskningsfonden i Norrland (LP 23-2337), Bengt Ihre foundation (SLS-960529 and SLS-986656), and Bengt Ihre Research Fellowship Grant. The sponsors had no role in the study design, collection, analysis and interpretation of data, writing of the report, or in the decision to submit the article for publication.

The influence of natural image transformations on receptive field responses is crucial for modelling visual operations in computer vision and biological vision. In this regard, covariance properties with respect to geometric image transformations in the earliest layers of the visual hierarchy are essential for expressing robust image operations, and for formulating invariant visual operations at higher levels. This paper defines and proves a set of joint covariance properties for spatio-temporal receptive fields in terms of spatio-temporal derivative operators applied to spatio-temporally smoothed image data under compositions of spatial scaling transformations, spatial affine transformations, Galilean transformations and temporal scaling transformations. Specifically, the derived relations show how the parameters of the receptive fields need to be transformed, in order to match the output from spatio-temporal receptive fields under composed spatio-temporal image transformations. For this purpose, we also fundamentally extend the notion of scale-normalized derivatives to affine-normalized derivatives, that are computed based on spatial smoothing with affine Gaussian kernels, and analyze the covariance properties of the resulting affine-normalized derivatives for the affine group as well as for important subgroups thereof. We conclude with a geometric analysis, showing how the derived joint covariance properties make it possible to relate or match spatio-temporal receptive field responses, when observing, possibly moving, local surface patches from different views, under locally linearized perspective or projective transformations, as well as when observing different instances of spatio-temporal events, that may occur either faster or slower between different views of similar spatio-temporal events. We do furthermore describe how the parameters in the studied composed spatio-temporal image transformation models directly relate to geometric entities in the image forma, QC 20240709

This paper presents an in-depth theoretical analysis of the orientation selectivity properties of simple cells and complex cells, that can be well modelled by the generalized Gaussian derivative model for visual receptive fields, with the purely spatial component of the receptive fields determined by oriented affine Gaussian derivatives for different orders of spatial differentiation. A detailed mathematical analysis is presented for the three different cases of either: (i) purely spatial receptive fields, (ii) space-time separable spatio-temporal receptive fields and (iii) velocity-adapted spatio-temporal receptive fields. Closed-form theoretical expressions for the orientation selectivity curves for idealized models of simple and complex cells are derived for all these main cases, and it is shown that the orientation selectivity of the receptive fields becomes more narrow, as a scale parameter ratio $\kappa$, defined as the ratio between the scale parameters in the directions perpendicular to vs. parallel with the preferred orientation of the receptive field, increases. It is also shown that the orientation selectivity becomes more narrow with increasing order of spatial differentiation in the underlying affine Gaussian derivative operators over the spatial domain. Additionally, we also derive closed-form expressions for the resultant and the bandwidth descriptors of the orientation selectivity curves, which have previously been used as compact descriptors of the orientation selectivity properties for biological neurons. These results together show that the properties of the affine Gaussian derivative model for visual receptive fields can be analyzed in closed form, which can be highly useful when to relate the results from biological experiments to computational models of the functional properties of simple cells and complex cells in the primary visual cortex. For comparison, we also present a corresponding theoretical orientation selectivity analysis for purely, QC 20240410

This paper presents the results of combining (i) theoretical analysis regarding connections between the orientation selectivity and the elongation of receptive fields for the affine Gaussian derivative model with (ii) biological measurements of orientation selectivity in the primary visual cortex to investigate if (iii) the receptive fields can be regarded as spanning a variability in the degree of elongation. From an in-depth theoretical analysis of idealized models for the receptive fields of simple and complex cells in the primary visual cortex, we established that the orientation selectivity becomes more narrow with increasing elongation of the receptivefields. Combined with previously established biological results, concerning broad vs. sharp orientation tuning of visual neurons in the primary visual cortex, as well as previous experimental results concerning distributions of the resultant of the orientation selectivity curves for simple and complex cells, we show that these results are consistent with the receptive fields spanning a variability over the degree of elongation of the receptive fields. We also show that our principled theoretical model for visual receptive fields leads to qualitatively similar types of deviations from a uniform histogram of the resultant descriptor of the orientation selectivity curves for simple cells, as can be observed in the results from biological experiments. To firmly determine if the underlying working hypothesis, regarding the receptive fields spanning a variability in the degree of elongation, would truly hold for the receptive fields in the primary visual cortex of higher mammals, we formulate a set of testable predictions, that can be used for investigate this property experimentally, and, if applicable, then also characterize if such a variability would, in a structured way, be related to the pinwheel structure in the visual cortex., QC 20240410

The influence of natural image transformations on receptive field responses is crucial for modelling visual operations in computer vision and biological vision. In this regard, covariance properties with respect to geometric image transformations in the earliest layers of the visual hierarchy are essential for expressing robust image operations, and for formulating invariant visual operations at higher levels. This paper defines and proves a set of joint covariance properties under compositions of spatial scaling transformations, spatial affine transformations, Galilean transformations and temporal scaling transformations, which make it possible to characterize how different types of image transformations interact with each other and the associated spatio-temporal receptive field responses. In this regard, we also extend the notion of scale-normalized derivatives to affine-normalized derivatives, to be able to obtain true affine-covariant properties of spatial derivatives, that are computed based on spatial smoothing with affine Gaussian kernels. The derived relations show how the parameters of the receptive fields need to be transformed, in order to match the output from spatio-temporal receptive fields under composed spatio-temporal image transformations. As a side effect, the presented proof for the joint covariance property over the integrated combination of the different geometric image transformations also provides specific proofs for the individual transformation properties, which have not previously been fully reported in the literature. We conclude with a geometric analysis, showing how the derived joint covariance properties make it possible to relate or match spatio-temporal receptive field responses, when observing, possibly moving, local surface patches from different views, under locally linearized perspective or projective transformations, as well as when observing different instances of spatio-temporal events that may occur either faster or slower be, QC 20240429, Covariant and invariant deep networks

The COVID-19 pandemic highlighted the need for a rapid, convenient, and scalable diagnostic method for detecting a novel pathogen amidst a global pandemic. While command-line interface tools offer automation for SARS-CoV-2 Oxford Nanopore Technology sequencing data analysis, they are inapplicable to users with limited programming skills. A solution is to establish such automated workflows within a graphical user interface software. We developed two workflows in the software Geneious Prime 2022.1.1, adapted for data obtained from the Midnight and Artic's nCoV-2019 sequencing protocols. Both workflows perform trimming, read mapping, consensus generation, and annotation on SARS-CoV-2 Nanopore sequencing data. Additionally, one workflow includes phylogenetic assignment using the bioinformatic tools pangolin and Nextclade as plugins. The basic workflow was validated in 2020, adhering to the requirements of the European Centre for Disease Prevention and Control for SARS-CoV-2 sequencing and analysis. The enhanced workflow, providing phylogenetic assignment, underwent validation at Uppsala University Hospital by analysing 96 clinical samples. It provided accurate diagnoses matching the original results of the basic workflow while also reducing manual clicks and analysis time. These bioinformatic workflows streamline SARS-CoV-2 Nanopore data analysis in Geneious Prime, saving time and manual work for operators lacking programming knowledge.

Transmission electron microscopy (TEM) is an imaging technique used to visualize and analyze nano-sized structures and objects such as virus particles. Light microscopy can be used to diagnose diseases or characterize e.g. blood cells. Since samples under microscopes exhibit certain symmetries, such as global rotation invariance, equivariant neural networks are presumed to be useful. In this study, a baseline convolutional neural network is constructed in the form of the commonly used VGG16 classifier. Thereafter, it is modified to be equivariant to the p4 symmetry group of rotations of multiples of 90 degrees using group convolutions. This yields a number of benefits on a TEM virus dataset, including higher top validation set accuracy by on average 7.6% and faster convergence during training by on average 23.1% of that of the baseline. Similarly, when training and testing on images of blood cells, the convergence time for the equivariant neural network is 7.9% of that of the baseline. From this it is concluded that augmentation strategies for rotation can be skipped. Furthermore, when modelling the accuracy versus amount of TEM virus training data with a power law, the equivariant network has a slope of - 0.43 compared to - 0.26 of the baseline. Thus the equivariant network learns faster than the baseline when more training data is added. This study extends previous research on equivariant neural networks applied to images which exhibit symmetries to isometric transformations.

Artificial intelligence (AI) and high-content imaging (HCI) are contributing to advancements in drug discovery, propelled by the recent progress in deep neural networks. This review highlights AI's role in analysis of HCI data from fixed and livecell imaging, enabling novel label-free and multi-channel fluorescent screening methods, and improving compound profiling. HCI experiments are rapid and cost-effective, facilitating large data set accumulation for AI model training. However, the success of AI in drug discovery also depends on highquality data, reproducible experiments, and robust validation to ensure model performance. Despite challenges like the need for annotated compounds and managing vast image data, AI's potential in phenotypic screening and drug profiling is significant. Future improvements in AI, including increased interpretability and integration of multiple modalities, are expected to solidify AI and HCI's role in drug discovery.

There has been a long-standing bottleneck in the quantitative analysis of the frequencies of homoblock polyads beyond triads using 1H and 13C NMR for linear polysaccharides, primarily because monosaccharides within a long homoblock share similar chemical environments due to identical neighboring units, resulting in indistinct NMR peaks. In this study, through rigorous mathematical induction, inequality relations were established that enabled the calculation of frequency ranges of homoblock polyads from historically reported NMR-derived frequency values of diads and/or triads of alginates, chitosans, homogalacturonans, and galactomannans. The calculated homoblock frequency ranges were then applied to evaluate three chain growth statistical models, including the Bernoulli chain, first-order Markov chain, and second-order Markov chain, for predicting homoblock frequencies in these polysaccharides. Furthermore, based on the mathematically derived inequality relations, a novel 2D array was constructed, enabling the graphical visualization of homoblock features in polysaccharides. It was demonstrated, as a proof of concept, that the novel 2D array, along with a 1D code generated from it, could serve as an effective feature engineering tool for polymer classification using machine learning algorithms., QC 20240618

In this thesis we studied synaptic plasticity and neuronal computation in single striatal projection neurons (SPNs), which have a major role in goal-directed learning. Goal-directed or reward learning means to learn, based on sensory information from the body and the environment, to select actions out of all the behavioral repertoire that lead to obtaining a goal or reward (such as food or water). In mammals, all the behavioral motor repertoire is under constant, tonic inhibition, and the direct-pathway SPNs (dSPNs) select (disinhibit) goal-obtaining actions. The learning process is guided by the neuromodulator dopamine which signals the positive or negative out-come of an action. The synapses from cortical neurons on to the dSPNs, called corticostriatal synapses, are responsive to dopamine signals, and can strengthen and weaken based on the (positive or negative) action outcome. This promotes or discourages future actions in the same or similar sensory context. Within a collaborative computational modeling effort, we studied the biochemical circuitry in the corticostriatal synapses with multiscale modeling and simulations. This circuitry in the corticostriatal synapses responds to neuromodulatory signals and controls the expression of synaptic plasticity. Multiscale modeling and simulations enable studying a system at multiple temporal and spatial scales, and integrating the results across the different scales. Based on molecular dynamics simulations of the enzyme which transduces extracellular neuromodulatory signals into an intracellular second messenger molecule, and Brownian dynamics simulations of regulator molecules binding to the enzyme, we constructed a kinetic model ofthe enzyme-based signal transduction network. The kinetic model showed that two co-occuring neuromodulatory signals, a dopamine peak and an acetylcholine pause, are required to produce the second messenger and thus enable strengthening of corticostriatal synapses onto dSPNs, and that only the, I denna avhandling studerades synaptisk plasticitet samt förmågan till lokalberäkning i de striatala projektionsneuronens (SPNs) dendriter. Detta har direkt relevans för förståelsen av s.k. målstyrd inlärning. Målstyrd inlärning och belöningsinlärning innebär att man, baserat på sensorisk informationfrån kroppen och omgivningen, lär sig selektera hur man skall agera/handla så att man uppnår ett mål eller erhåller en belöning (t.ex. mat eller vatten). Hos alla däggdjur är motoriska/exekutiva centra i hjärnstammen och thalamus under konstant tonisk inhibition via basala ganglierna, men när manaktiverar SPNs i den s.k. direkta vägen genom basala ganglierna (dSPN) så disinhiberas de motoriska centra som behövs för att initiera specifika mål-styrda beteenden. Inlärningsprocessen för detta guidas av bl.a. dopamin, en neuromodulator som signalerar huruvida ett beteende ger positivt eller negativt resultat. Synapserna från kortikala projektionsneuron till dSPNs, s.k. kortikostriatala synapser, påverkas av dopamin och de kan förstärkas eller försvagas baserat på om dopaminsignalen signalerar ett positivt eller negativt utfall. Detta antingen främjar eller motverkar att man väljer samma beteende/handlingar under en liknande situation i framtiden. Via samarbete med andra beräkningsbiologigrupper kunde vi studera de biokemiska signaleringsnätverken i de kortikostriatala synapserna med hjälp av multiskal modeller och simuleringar. Synapsens intracellulära biokemiska signaleringsnätverk kontrollerar synaptisk plasticitet och påverkas av neuro-modulering. Genom att använda multiskalsimuleringar kunde vi studera systemet över multipla temporala och spatiala skalor, och integrera resultaten över de olika skalorna. Baserat på molekylärdynamiska simuleringar av det enzym som överför de extracellulära neuromodulatoriska signalerna till en intracellulär s.k. 2nd messenger molekyl, och Brownianska dynamiksimuleringar av de regulatoriska molekyler som binder till enzymet, kunde vi konstru, QC 20240904

DNA binding proteins in the form of transcription factors are crucial for gene expression. These enzymes recognize their target gene by a regulatory element on the DNA molecule. The unique combination of nucleotides in regulatory sequences gives rise to very specific interactions with the target protein. Due to this sequence specificity, mutations on regulatory elements can have devastating consequences for an organism. The mutated sequence can lead to decreased affinity of the target protein, and thus decreased gene expression, a cause of several genetic diseases. Not all mutations affect the protein-DNA binding in the same way. Depending on the type of mutation and its location, the severity of its effects can differ greatly. Uncovering this relationship between mutation and sequence affinity can lead to a better understanding of gene expression and genetic diseases. In this project, two Deep Learning models were trained on regulatory DNA sequences with the goal of predicting sequence affinity. One was a convolutional neural network and the other a transformer neural network. The goal was to create an accurate Deep Learning model that can predict binding rates and sequence affinity using only a DNA strand as input. Using a dataset of sequences with measured values for binding rates and affinities, the models achieved promising results. They were able to reliably predict these values with high accuracy. When comparing the Deep Learning models performance with the one of a simpler linear model, they both showed significant improvements. This study showed that neural networks are well suited for this task, achieving accurate results and that a transformer neural network is the superior model when solving this problem.

Background: Biomedical data are usually collections of longitudinal data assessed at certain points in time. Clinical observations assess the presences and severity of symptoms, which are the basis for the description and modeling of disease progression. Deciphering potential underlying unknowns from the distinct observation would substantially improve the understanding of pathological cascades. Hidden Markov Models (HMMs) have been successfully applied to the processing of possibly noisy continuous signals. We apply ensembles of HMMs to categorically distributed multivariate time series data, leaving space for expert domain knowledge in the prediction process. Methods: We use an ensemble of HMMs to predict the loss of free walking ability as one major clinical deterioration in the most common autosomal dominantly inherited ataxia disorder worldwide. Results: We present a prediction pipeline that processes data paired with a configuration file, enabling us to train, validate and query an ensemble of HMMs. In particular, we provide a theoretical and practical framework for multivariate time-series inference based on HMMs that includes constructing multiple HMMs, each to predict a particular observable variable. Our analysis is conducted on pseudo-data, but also on biomedical data based on Spinocerebellar ataxia type 3 disease. Conclusions: We find that the model shows promising results for the data we tested. The strength of this approach is that HMMs are well understood, probabilistic and interpretable models, setting it apart from most Deep Learning approaches. We publish all code and evaluation pseudo-data in an open-source repository.

We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a residue number system, with individual residues represented by high-dimensional, complex-valued vectors. These are composed into a single vector representing position by a similarity-preserving, conjunctive vector-binding operation. Self-consistency between the representations of the overall position and of the individual residues is enforced by a modular attractor network whose modules correspond to the grid cell modules in entorhinal cortex. The vector binding operation can also associate different contexts to spatial representations, yielding a model for entorhinal cortex and hippocampus. We show that the model achieves normative desiderata including superlinear scaling of patterns with dimension, robust error correction, and hexagonal, carry-free encoding of spatial position. These properties in turn enable robust path integration and association with sensory inputs. More generally, the model formalizes how compositional computations could occur in the hippocampal formation and leads to testable experimental predictions., arXiv:2406.18808 PMID: 38979486

Conformal prediction has seen many applications in pharmaceutical science, being able to calibrate outputs of machine learning models and producing valid prediction intervals. We here present the open source software CPSign that is a complete implementation of conformal prediction for cheminformatics modeling. CPSign implements inductive and transductive conformal prediction for classification and regression, and probabilistic prediction with the Venn-ABERS methodology. The main chemical representation is signatures but other types of descriptors are also supported. The main modeling methodology is support vector machines (SVMs), but additional modeling methods are supported via an extension mechanism, e.g. DeepLearning4J models. We also describe features for visualizing results from conformal models including calibration and efficiency plots, as well as features to publish predictive models as REST services. We compare CPSign against other common cheminformatics modeling approaches including random forest, and a directed message-passing neural network. The results show that CPSign produces robust predictive performance with comparative predictive efficiency, with superior runtime and lower hardware requirements compared to neural network based models. CPSign has been used in several studies and is in production-use in multiple organizations. The ability to work directly with chemical input files, perform descriptor calculation and modeling with SVM in the conformal prediction framework, with a single software package having a low footprint and fast execution time makes CPSign a convenient and yet flexible package for training, deploying, and predicting on chemical data. CPSign can be downloaded from GitHub at https://github.com/arosbio/cpsign. Scientific contribution: CPSign provides a single software that allows users to perform data preprocessing, modeling and make predictions directly on chemical structures, using conformal and probabilistic prediction. Building

Recombination of short DNA fragments via horizontal gene transfer (HGT) can introduce beneficial alleles, create genomic disharmony through negative epistasis, and create adaptive gene combinations through positive epistasis. For non-core (accessory) genes, the negative epistatic cost is likely to be minimal because the incoming genes have not co-evolved with the recipient genome and are frequently observed as tightly linked cassettes with major effects. By contrast, interspecific recombination in the core genome is expected to be rare because disruptive allelic replacement is likely to introduce negative epistasis. Why then is homologous recombination common in the core of bacterial genomes? To understand this enigma, we take advantage of an exceptional model system, the common enteric pathogens Campylobacter jejuni and C. coli that are known for very high magnitude interspecies gene flow in the core genome. As expected, HGT does indeed disrupt co-adapted allele pairings, indirect evidence of negative epistasis. However, multiple HGT events enable recovery of the genome’s co-adaption between introgressing alleles, even in core metabolism genes (e.g., formate dehydrogenase). These findings demonstrate that, even for complex traits, genetic coalitions can be decoupled, transferred, and independently reinstated in a new genetic background—facilitating transition between fitness peaks. In this example, the two-step recombinational process is associated with C. coli that are adapted to the agricultural niche.

Campylobacter is a leading cause of food-borne gastroenteritis worldwide, linked to the consumption of contaminated poultry meat. Targeting this pathogen at source, vaccines for poultry can provide short-term caecal reductions in Campylobacter numbers in the chicken intestine. However, this approach is unlikely to reduce Campylobacter in the food chain or human incidence. This is likely as vaccines typically target only a subset of the high genomic strain diversity circulating among chicken flocks, and rapid evolution diminishes vaccine efficacy over time. To address this, we used a genomic approach to develop a whole-cell autogenous vaccine targeting isolates harbouring genes linked to survival outside of the host. We hyper-immunised a whole major UK breeder farm to passively target offspring colonisation using maternally-derived antibody. Monitoring progeny, broiler flocks revealed a near-complete shift in the post-vaccination Campylobacter population with an ~50% reduction in isolates harbouring extra-intestinal survival genes and a significant reduction of Campylobacter cells surviving on the surface of meat. Based on these findings, we developed a logistic regression model that predicted that vaccine efficacy could be extended to target 65% of a population of clinically relevant strains. Immuno-manipulation of poultry microbiomes towards less harmful commensal isolates by competitive exclusion, has major potential for reducing pathogens in the food production chain.

Objectives Integrating pathogen genomic surveillance with bioinformatics can enhance public health responses by identifying risk and guiding interventions. This study focusses on the two predominant Campylobacter species, which are commonly found in the gut of birds and mammals and often infect humans via contaminated food. Rising incidence and antimicrobial resistance (AMR) are a global concern and there is an urgent need to quantify the main routes to human infection. Methods During routine US national surveillance (2009-2019), 8,856 Campylobacter genomes from human infections and 16,703 from possible sources were sequenced. Using machine learning and probabilistic models, we target genetic variation associated with host adaptation to attribute the source of human infections and estimate the importance of different disease reservoirs. Results Poultry was identified as the primary source of human infections, responsible for an estimated 68% of cases, followed by cattle (28%), and only a small contribution from wild birds (3%) and pork sources (1%). There was also evidence of an increase in multidrug resistance, particularly among isolates attributed to chickens. Conclusions National surveillance and source attribution can guide policy, and our study suggests that interventions targeting poultry will yield the greatest reductions in campylobacteriosis and spread of AMR in the US.

Objectives Antimicrobial resistant (AMR) Campylobacter is a global health threat; however, there is limited information on genomic determinants of resistance in low- and middle-income countries. We evaluated genomic determinants of AMR using a collection of whole genome sequenced Campylobacter jejuni and C. coli isolates from Iquitos, Peru. Methods Campylobacter isolates from two paediatric cohort studies enriched with isolates that demonstrated resistance to ciprofloxacin and azithromycin were sequenced and mined for AMR determinants. Results The gyrA mutation leading to the Thr86Ile amino acid change was the only gyrA mutation associated with fluoroquinolone resistance identified. The A2075G mutation in 23S rRNA was present, but three other 23S rRNA mutations previously associated with macrolide resistance were not identified. A resistant-enhancing variant of the cmeABC efflux pump genotype (RE-cmeABC) was identified in 36.1% (35/97) of C. jejuni genomes and 17.9% (12/67) of C. coli genomes. Mutations identified in the CmeR-binding site, an inverted repeat sequence in the cmeABC promoter region that increases expression of the operon, were identified in 24/97 C. jejuni and 14/67 C. coli genomes. The presence of these variants, in addition to RE-cmeABC, was noted in 18 of the 24 C. jejuni and 9 of the 14 C. coli genomes. Conclusions Both RE-cmeABC and mutations in the CmeR-binding site were strongly associated with the MDR phenotype in C. jejuni and C. coli. This is the first report of RE-cmeABC in Peru and suggests it is a major driver of resistance to the principal therapies used to treat human campylobacteriosis in this setting.

Sex estimation of the individuals in a sample is fundamental for any bioarchaeological study to define a particular demographic assemblage or to classify isolated remains. Long bones are an excellent alternative for sex estimation when the most dimorphic anatomical parts are not preserved or are highly altered. Here we propose a set of discriminant functions and classification models to estimate the sex of prehistoric individuals using linear discriminant analysis and machine learning approaches. Different osteometric variables were taken from the humeri, ulnae, radii, femurs and tibias of a sample of 109 articulated skeletons buried in the collective tomb of Camino del Molino (Region of Murcia, SE-Spain), dated to the 3rd millennium BC. Sex was estimated based on standard anthropological methods and ancient DNA analysis of a control sample. Fifty-two discriminant functions with prediction thresholds higher than 0.8 on the ROC curve were obtained using independent (22) and combined variables (30). The best LDA models for sex prediction were those based on proximal epiphyseal widths or their combination with other variables, reaching values close to 0.98 on the ROC curve. The random forest-based model obtained an accuracy of 0.94 and confirmed the importance of epiphyseal widths in sex classification. This analysis is more comprehensive than univariate LDA, as it allows for ranking the importance of bones in sex discrimination and considers correlations between long bones rather than treating them as independent observations. In contrast, applying LDA to each bone makes it easier to predict the sex of other coeval collections that do not have such a complete sample. This work aims to overcome the scarcity of methods that can be applied to sex estimation of the large volume of isolated remains from Camino del Molino and for other Mediterranean skeletal series from the Late Prehistory with high biological affinity and that share similar environmental conditions.

Massively parallel sequencing (MPS) is increasingly applied in forensic short tandem repeat (STR) analysis. The presence of stutter artefacts and other PCR or sequencing errors in the MPS-STR data partly limits the detection of low DNA amounts, e.g., in complex mixtures. Unique molecular identifiers (UMIs) have been applied in several scientific fields to reduce noise in sequencing. UMIs consist of a stretch of random nucleotides, a unique barcode for each starting DNA molecule, that is incorporated in the DNA template using either ligation or PCR. The barcode is used to generate consensus reads, thus removing errors. The SiMSen-Seq (Simple, multiplexed, PCR-based barcoding of DNA for sensitive mutation detection using sequencing) method relies on PCR-based introduction of UMIs and includes a sophisticated hairpin design to reduce unspecific primer binding as well as PCR protocol adjustments to further optimize the reaction. In this study, SiMSen-Seq is applied to develop a proof-of-concept seven STR multiplex for MPS library preparation and an associated bioinformatics pipeline. Additionally, machine learning (ML) models were evaluated to further improve UMI allele calling. Overall, the seven STR multiplex resulted in complete detection and concordant alleles for 47 single-source samples at 1 ng input DNA as well as for low-template samples at 62.5 pg input DNA. For twelve challenging mixtures with minor contributions of 10 pg to 150 pg and ratios of 1–15% relative to the major donor, 99.2% of the expected alleles were detected by applying the UMIs in combination with an ML filter. The main impact of UMIs was a substantially lowered number of artefacts as well as reduced stutter ratios, which were generally below 5% of the parental allele. In conclusion, UMI-based STR sequencing opens new means for improved analysis of challenging crime scene samples including complex mixtures. © 2024 The Authors, We thank Froste Svensson for input on the bioinformatics pipeline and Nelly Gyll\u00F6 Lind and Markus Andr\u00E9 Soma for practical assistance in pre-studies. This study was funded by VINNOVA: Project title \u201CUltrak\u00E4nsliga analyser f\u00F6r b\u00E4ttre h\u00E4lsa och kriminalteknik (ULTRA-UDI)\u201D and reference number 2020\u201304141, and V\u00E4stra G\u00F6talandsregionen RUN 2021\u201300059. Anders St\u00E5hlberg was funded by Region V\u00E4stra G\u00F6taland; Swedish Cancer Society [22\u20132080]; Swedish Childhood Cancer Foundation [2022\u20130030]; Swedish Research Council [2021\u201301008]; the Swedish state under the agreement between the Swedish government and the county councils, the ALF-agreement [965065]; Sweden's Innovation Agency [2018\u201300421, 2020\u201304141] and the Sj\u00F6berg Foundation. Points of view in this document are those of the NIST-affiliated authors and do not necessarily represent the official position or policies of the U.S. Department of Commerce. Certain equipment, instruments, software, or materials are identified in this paper to specify the experimental procedure adequately. Such identification is not intended to imply recommendation or endorsement of any product or service by NIST, nor is it intended to imply that the materials or equipment identified are necessarily the best available for the purpose. All work performed at NIST has been reviewed and approved by the U. S. National Institute of Standards and Technology Research Protections Office. This study was determined to be \u201Cnot human subjects research\u201D (often referred to as research not involving human subjects) as defined in U. S. Department of Commerce Regulations, 15 CFR 27, also known as the Common Rule (45 CFR 46, Subpart A), for the Protection of Human Subjects by the NIST Human Research Protections Office and therefore not subject to oversight by the NIST Institutional Review Board (MML-16\u20130080). All data handling performed in Sweden w

Human age and gender prediction from facial images has garnered significant attention due to its importance in various applications. Traditional models struggle with large-scale variations in unfiltered images. Convolutional Neural Networks (CNNs) have emerged as effective tools for facial analysis due to their robust performance. This paper presents a novel CNN approach for robust age and gender classification using unconstrained real-world images. The CNN architecture includes convolution, pooling, and fully connected layers for feature extraction, dimension reduction, and mapping to output classes. Adience and UTKFace datasets were utilized, with the best training and testing accuracies achieved using an 80% training and 20% testing data split. Robust image pre-processing and data augmentation techniques were applied to handle dataset variations. The proposed approach outperformed existing methods, achieving age prediction accuracies of 86.42% and 81.96%, and gender prediction accuracies of 97.65% and 96.32% on the Adience and UTKFace datasets, respectively., Full text license: CC BY-NC-ND 4.0

Metabolic fluxes and their control mechanisms are fundamental in cellular metabolism, offering insights for the study of biological systems and biotechnological applications. However, quantitative and predictive understanding of controlling biochemical reactions in microbial cell factories, especially at the system level, is limited. In this work, we present ARCTICA, a computational framework that integrates constraint-based modelling with machine learning tools to address this challenge. Using the model cyanobacterium Synechocystis sp. PCC 6803 as chassis, we demonstrate that ARCTICA effectively simulates global-scale metabolic flux control. Key findings are that (i) the photosynthetic bioproduction is mainly governed by enzymes within the Calvin-Benson-Bassham (CBB) cycle, rather than by those involve in the biosynthesis of the end-product, (ii) the catalytic capacity of the CBB cycle limits the photosynthetic activity and downstream pathways and (iii) ribulose-1,5-bisphosphate carboxylase/oxygenase (RuBisCO) is a major, but not the most, limiting step within the CBB cycle. Predicted metabolic reactions qualitatively align with prior experimental observations, validating our modelling approach. ARCTICA serves as a valuable pipeline for understanding cellular physiology and predicting rate-limiting steps in genome-scale metabolic networks, and thus provides guidance for bioengineering of cyanobacteria.

During drug development, a key step is the identification of relevant covariates predicting between-subject variations in drug response. The full random effects model (FREM) is one of the full-covariate approaches used to identify relevant covariates in nonlinear mixed effects models. Here we explore the ability of FREM to handle missing (both missing completely at random (MCAR) and missing at random (MAR)) covariate data and compare it to the full fixed-effects model (FFEM) approach, applied either with complete case analysis or mean imputation. A global health dataset (20 421 children) was used to develop a FREM describing the changes of height for age Z-score (HAZ) over time. Simulated datasets (n = 1000) were generated with variable rates of missing (MCAR) covariate data (0%-90%) and different proportions of missing (MAR) data condition on either observed covariates or predicted HAZ. The three methods were used to re-estimate model and compared in terms of bias and precision which showed that FREM had only minor increases in bias and minor loss of precision at increasing percentages of missing (MCAR) covariate data and performed similarly in the MAR scenarios. Conversely, the FFEM approaches either collapsed at ≥70% of missing (MCAR) covariate data (FFEM complete case analysis) or had large bias increases and loss of precision (FFEM with mean imputation). Our results suggest that FREM is an appropriate approach to covariate modeling for datasets with missing (MCAR and MAR) covariate data, such as in global health studies.

Nano-impact (NIE) (also referred to as collision) single-entity electrochemistry is an emerging technique that enables electrochemical investigation of individual entities, ranging from metal nanoparticles to single cells and biomolecules. To obtain meaningful information from NIE experiments, analysis and feature extraction on large datasets are necessary. Herein, a method is developed for the automated analysis of NIE data based on unsupervised machine learning and template matching approaches. Template matching not only facilitates downstream processing of the NIE data but also provides a more accurate analysis of the NIE signal characteristics and variations that are difficult to discern with conventional data analysis techniques, such as the height threshold method. The developed algorithm enables fast automated processing of large experimental datasets recorded with different systems, requiring minimal human intervention and thereby eliminating human bias in data analysis. As a result, it improves the standardization of data processing and NIE signal interpretation across various experiments and applications. Nano-impact (NIE) electrochemistry is an emerging technique for studying individual entities. Analyzing large NIE datasets, often with low signal-to-noise ratios, is challenging. Herein, an automated approach is introduced using unsupervised machine learning and template matching for accurate feature extraction from spike-shaped NIE signals. It improves data processing, accuracy and standardization, reducing human bias in signal interpretation across experiments.image (c) 2023 WILEY-VCH GmbH

Summary: Nanometa Live presents a user-friendly interface designed for real-time metagenomic data analysis and pathogen identification utilizing Oxford Nanopore Technologies’ MinION and Flongle flow cells. It offers an efficient workflow and graphical interface for the visualization and interpretation of metagenomic data as it is being generated. Key features include automated BLAST validation, streamlined handling of custom Kraken2 databases, and a simplified graphical user interface for enhanced user experience. Nanometa Live is particularly notable for its capability to run without constant internet or server access once installed, setting it apart from similar tools. It provides a comprehensive view of taxonomic composition and facilitates the detection of user-defined pathogens or other species of interest, catering to both researchers and clinicians. Availability and implementation: Nanometa Live has been implemented as a local web application using the Dash framework with Snakemake handling the data processing. The source code is freely accessible on the GitHub repository at https://github.com/FOIBioinformatics/nanometa_live and it is easily installable using Bioconda. It includes containerization support via Docker and Singularity, ensuring ease of use, reproducibility, and portability.

The COVID-19 pandemic demonstrates that a top priority for society, now and in the future, is to be able to respond quickly to diseases with effective treatments. Among the new tools that pharmaceutical industries and researchers have in their hands nowadays, there are the extensive computer simulations capable of evaluating in-silico the interaction between possible drugs and the target proteins. The central goal of the LIGATE project is to create and validate a leading application solution for drug discovery in High-Performance Computing (HPC) systems up to the exascale level. The overall project purpose is the automation of the drug design process, which is currently performed with substantial human effort throughout the different phases of the process: preparation of input parameters, management of data sets with billions of molecules, interaction with HPC queue management systems to handle jobs, and optimization of scoring function parameters and thresholds., QC 20240822

Marine ecosystems harbour a vast microbial diversity which play a crucial role in ecosystemfunctioning. Advancements in DNA sequencing technologies have transformed our ability to analyse microbial populations comprehensively. Metagenomic sequencing has emerged as a pivotal tool for characterising microbial communities across various environments. Bioinformatics, an interdisciplinary field, facilitates the analysis and interpretation of large biological datasets, including microbiome data. This thesis aims to enhance bioinformatics approaches for analysing marine microbiomes. It comprises four papers covering bioinformatic developments and genomic data analysis across multiple topics, including metagenomics, pangenomics, comparative genomics and population genomics: Paper I evaluated three assembly strategies for constructing gene catalogues from metagenomic samples: individual sample assembly with gene clustering, co-assembly of all samples, and a new hybrid approach, mix assembly. The efficacy of the mix-assembly approach was highlighted for maximising information extraction from metagenomic samples, offering opportunities for further exploration in microbial ecology and environmental genomics. Using the mix-assembly approach, we conducted a comprehensive analysis of 124 metagenomic samples sourced from the Baltic Sea, resulting in the refinement of the Baltic Sea Gene Set (BAGS v1.1), which now encompasses 66.53 million genes annotated for both functionality and taxonomy. In Paper II, we introduced an open-access initiative that provided the mix-assembly pipeline code. We also developed the BAGS-Shiny web application to facilitate user interaction with this extensive gene catalogue. Paper III focused on whole-genome sequencing and assembly of 82 environmental V. vulnificus strains from the Baltic Sea, enabling comprehensive comparative genomic analysis. I developed the PhyloBOTL pipeline, which uses a phylogeny-based approach to identify genes associated with pat, Havsmiljöer hyser en enorm mikrobiell mångfald som spelar en avgörande roll för ekosystemens funktion. Framsteg inom DNA-sekvenseringstekniker har revolutionerat vår förmåga att analysera den mikrobiella populationen på ett omfattande sätt. Metagenomisk sekvensering har framträtt som ett centralt verktyg för att karakterisera mikrobiella samhällen i olika miljöer. Bioinformatik, ett tvärvetenskapligt fält, underlättar analys och tolkning av stora biologiska dataset, inklusive mikrobiomdata. Den här avhandlingen syftar till att förbättra bioinformatiska metoder för att analysera marina mikrobiom. Den består av fyra artiklar som täcker bioinformatisk utveckling och analys av genomdata inom flera områden, inklusive metagenomik, pangenom, jämförande genomik och populationsgenetik: Artikel I utvärderade tre monteringsstrategier för att konstruera genkataloger från metagenomiska prover: montering av enskilda prover med genglustering, sammontering av alla prover och en ny hybridmetod, mixmontering. Effektiviteten hos mixmonteringsmetoden lyftes fram för att maximera informationsutvinning från metagenomiska prover, vilket öppnar för vidare utforskning inom mikrobiell ekologi och miljögenomik. Med hjälp av mixmonteringsmetoden genomförde vi en omfattande analys av 124 metagenomiska prover från Östersjön, vilket resulterade i förfiningen av Östersjöns gensets (BAGS v1.1), som nu omfattar 66,53 miljoner gener annoterade för både funktion och taxonomi. I artikel II introducerade vi ett öppet initiativ som tillhandahöll koden för mixmonterings-pipeline. Vi utvecklade också BAGS-Shiny webbapplikationen för att underlätta användarinteraktion med denna omfattande gensetskatalog. Artikel III fokuserade på helgenomsekvensering och montering av 82 miljörelaterade V. vulnificus-stammar från Östersjön, vilket möjliggjorde omfattande jämförande genomisk analys. Jag utvecklade PhyloBOTL-pipelinen, som använder en fylogenibaserad metod för att identifiera gener associerade med patogenicite, QC 2024-05-15

The present work focuses on predicting the steel melt temperature following the vacuum treatment step in a vacuum tank degasser (VTD). The primary objective is to establish a comprehensive methodology for developing and validating machine learning (ML) models within this context. Another objective is to evaluate the model by analyzing the alignment of the SHAP values with metallurgical domain expectations, thereby validating the model’s predictions from a metallurgical perspective. The proposed methodology employs a Random Forest model, incorporating a grid search with domain-informed variables grouped into batches, and a robust model-selection criterion that ensures optimal predictive performance, while keeping the model as simple and stable as possible. Furthermore, the Shapley Additive Explanations (SHAP) algorithm is employed to interpret the model’s predictions. The selected model achieved a mean adjusted (Formula presented.) of 0.631 and a hit ratio of 75.3% for a prediction error within ±5 °C. Despite the moderate predictive performance, SHAP highlighted several aspects consistent with metallurgical domain expertise, emphasizing the importance of domain knowledge in interpreting ML models. Improving data quality and refining the model framework could enhance predictive performance., QC 20240820

Clonal tree inference brings crucial insights to the analysis of tumor heterogeneity and cancer evolution. Recent progress in single cell sequencing has prompted a demand for more advanced probabilistic models of copy number evolution, coupled with inference methods which can account for the noisy nature of the data along with dependencies between adjacent sites in copy number profiles. We present VICTree, a variational inference based algorithm for joint Bayesian inference of clonal trees, together with a novel Tree-structured Mixture Hidden Markov Model (TSMHMM) which combines HMMs related through a tree with a mixture model. For the tree inference, we introduce a new algorithm, LARS, for sampling directed labeled multifurcating trees. To evaluate our proposed method, we conduct experiments on simulated data and on samples of multiple myeloma and breast cancer. We demonstrate VICTree’s capacity for reliable clustering, clonal tree reconstruction, copy number evolution and the utility of the ELBO for model selection. Lastly, VICTree’s results are compared in terms of quality and speed of inference to other state-of-the-art methods. The code for VICTree is available on GitHub: github.com/Lagergren-Lab/victree and the full paper on bioRxiv., Part of ISBN: 978-107163988-7QC 20240613

Within less than four decades, the nanopore sequencing technology accelerated from an implausible idea scribbled on a notebook page to one of the decisive contributors to the complete sequence of the human genome. Its rapid evolution, particularly in recent years, is driven not only by its inherent innovation of the nanopores but also by synergistic advancements in complementary fields, such as GPU acceleration and deep neural networks, as well as cross-disciplinary influences from domains like speech recognition. However, during this rapid advancement, certain methods within nanopore sequencing remain relatively unexplored. This oversight has the potential to create bottlenecks in the technology's further development. In this thesis work, we delve into these uncharted areas, seeking to fill critical gaps and branch the technology into new frontiers. Our objective is to unleash its potential, enabling further breakthroughs in genomic research and beyond. Through our research, we have developed two novel algorithms and two innovative models tailored to address these under-explored aspects of nanopore sequencing. The two algorithms, the GMBS and the LFBS, both belonging to the MBS group, offer innovative solutions to the challenging decoding problems inherent in HHMMs. They are two distinct variations tailored to different scenarios. While the GMBS is specifically suited for decoding lengthy sequences, such as those encountered in long-read basecalling, the LFBS is optimized for parallel programming and excels in processing short-length sequences. The two innovative models developed in this research, each leveraging variations of HHMMs and employing an end-to-end approach, exhibit distinguished structures. The first model, a hybrid of EDHMM and DNN, showcases the effectiveness of integrating both knowledge-driven and data-driven techniques. In contrast, the second model, a custom-designed Helicase HMM, draws inspiration from pioneering studies on motor proteins found, Inom mindre än fyra decennier har nanopore-sekvenseringsteknologin accelererat från en otrolig idé som skissades i en antckningsbok till en avgörande teknologi som bidragit till den kompletta sekvensensieringen av det mänskliga genomet. Denna snabba utveckling, särskilt under de senaste åren, drivs inte bara av innovation kring nanoporer utan också av synergistiska framsteg inom kompletterande områden, såsom GPU-acceleration och djupa neurala nätverk, samt tvärvetenskapligt inflytande från domäner som taligenkänning. Under denna snabba utveckling har do vissa metoder inom nanopore sekvensering förblivit relativt outforskade. Detta förbiseende riskerar att skapa flaskhalsar i teknologins vidareutveckling. I denna avhandling utforskar vi dessa outforskade områden, i syfte att fylla kritiska luckor och utveckla tekniken mot nya fronter. Vårt mål är att frigöra dess fulla potential och möjliggöra ytterligare genombrott inom genomisk forskning och därutöver. Som del av vår forskning har vi utvecklat två nya algoritmer och två innovativa modeller anpassade för att adressera dessa underutredda aspekter av nanopore sekvensering. De två algoritmerna, GMBS och LFBS, som är instanser av det mer generella ramverket av MBS-algorithmer (\emph{eng.} marginalised beam search), erbjuder innovativa lösningar på de utmanande avkodningsproblemen som är inneboende i HHMM:er. De är två distinkta variationer anpassade för olika scenarier. Medan GMBS är speciellt lämpad för avkodning av långa sekvenser, såsom de som stöts på vid läsning av långa sekvenser, är LFBS optimerad för parallell programmering och utmärker sig i bearbetning av korta sekvenser. De två innovativa modellerna som utvecklats i denna forskning, vilka båda utnyttjar variationer av HHMM:er och använder en ``end-to-end''-ansats, uppvisar distinkta strukturer. Den första modellen, en hybrid av EDHMM och DNN, visar effektiviteten av att integrera både kunskapsdrivna och datadrivna tekniker. I kontrast till detta, drar den and, QC 20240502Hybrid attendance: https://kth-se.zoom.us/j/66248893067

Evaluating the computational accuracy of Spiking Neural Network (SNN) implemented as in-situ learning on large-scale memristor crossbars remains a challenge due to the lack of a versatile model for the variations in non-ideal memristors. This brief proposes a novel behavioral variation model along with a four-stage pipeline for physical memristors. The proposed variation model combines both absolute and relative variations. Therefore, it can better characterize different memristor cycle-to-cycle (C2C) variations in practice. The proposed variation model has been used to simulate the behavior of two physical memristors. Adopting the non-ideal memristor model, the trace-based spiking-timing dependent plasticity (STDP) unsupervised in-memristor learning system is simulated. Although the synaptic-level weight simulation shows a performance degradation of 7.99% and 4.07% increase in the relative root mean square error (RRMSE), the network-level simulation results show no accuracy loss on the MNIST benchmark. Furthermore, the impacts of absolute and relative C2C variations on network performance are simulated and analyzed through two sets of univariate experiments., QC 20240412

Oscillations arise in many real-world systems and are associated with both functional and dysfunctional states. Whether a network can oscillate can be estimated if we know the strength of interaction between nodes. But in real-world networks (in particular in biological networks) it is usually not possible to know the exact connection weights. Therefore, it is important to determine the structural properties of a network necessary to generate oscillations. Here, we provide a proof that uses dynamical system theory to prove that an odd number of inhibitory nodes and strong enough connections are necessary to generate oscillations in a single cycle threshold-linear network. We illustrate these analytical results in a biologically plausible network with either firing-rate based or spiking neurons. Our work provides structural properties necessary to generate oscillations in a network. We use this knowledge to reconcile recent experimental findings about oscillations in basal ganglia with classical findings., QC 20240405

There is growing interest in uncovering genetic kinship patterns in past societies using low-coverage palaeogenomes. Here, we benchmark four tools for kinship estimation with such data: lcMLkin, NgsRelate, KIN, and READ, which differ in their input, IBD estimation methods, and statistical approaches. We used pedigree and ancient genome sequence simulations to evaluate these tools when only a limited number (1 to 50 K, with minor allele frequency ≥0.01) of shared SNPs are available. The performance of all four tools was comparable using ≥20 K SNPs. We found that first-degree related pairs can be accurately classified even with 1 K SNPs, with 85% F1 scores using READ and 96% using NgsRelate or lcMLkin. Distinguishing third-degree relatives from unrelated pairs or second-degree relatives was also possible with high accuracy (F1 > 90%) with 5 K SNPs using NgsRelate and lcMLkin, while READ and KIN showed lower success (69 and 79% respectively). Meanwhile, noise in population allele frequencies and inbreeding (first-cousin mating) led to deviations in kinship coefficients, with different sensitivities across tools. We conclude that using multiple tools in parallel might be an effective approach to achieve robust estimates on ultra-low-coverage genomes.

Motivation: Substrings of length k, commonly referred to as k-mers, play a vital role in sequence analysis. However, k-mers are limited to exact matches between sequences leading to alternative constructs. We recently introduced a class of new constructs, strobemers, that can match across substitutions and smaller insertions and deletions. Randstrobes, the most sensitive strobemer proposed in Sahlin (Effective sequence similarity detection with strobemers. Genome Res 2021a;31:2080–94. https://doi.org/10.1101/gr.275648.121), has been used in several bioinformatics applications such as read classification, short-read mapping, and read overlap detection. Recently, we showed that the more pseudo-random the behavior of the construction (measured in entropy), the more efficient the seeds for sequence similarity analysis. The level of pseudo-randomness depends on the construction operators, but no study has investigated the efficacy. Results: In this study, we introduce novel construction methods, including a Binary Search Tree-based approach that improves time complexity over previous methods. To our knowledge, we are also the first to address biases in construction and design three metrics for measuring bias. Our evaluation shows that our methods have favorable speed and sampling uniformity compared to existing approaches. Lastly, guided by our results, we change the seed construction in strobealign, a short-read mapper, and find that the results change substantially. We suggest combining the two results to improve strobealign’s accuracy for the shortest reads in our evaluated datasets. Our evaluation highlights sampling biases that can occur and provides guidance on which operators to use when implementing randstrobes. Availability and implementation: All methods and evaluation benchmarks are available in a public Github repository at https://github.com/Moein-Karami/RandStrobes. The scripts for running the strobealign analysis are found at https://github.com/NBISweden/s

Automated electrocardiogram (ECG) analysis using deep neural networks has seen promising results in recent years in various fields such as arrhythmia diagnosis and mortality prediction through age proxies. However, these deep learning models are susceptible to small indistinguishable perturbations that change the model prediction. These models also perform significantly worse when faced with domain shifts when applied to new data distributions not previously trained on. This thesis investigates how training on worst-case artificial samples through adversarial training can help generate models that can readily be adapted through fine-tuning to new datasets. Investigations are done by conducting robustness and transferability experiments using adversarial training on three different tasks in ECG analysis: atrial fibrillation diagnosis, sex classification, and age prediction. These experiments show that adversarial training creates models that generalize better and can be more efficiently adapted to new datasets with higher performance than non-adversarially trained models. This work thus paves the way for models that perform better on new datasets thus requiring less data for fine-tuning. This enables the use of high-performing models in settings where data is more scarce, thus enabling ECG analysis tools suitable in developing countries and smaller hospitals. The experiments also show that adversarial training improves the robustness of the trained models and that this robustness is retained to a smaller degree when transferred to new settings. This yields models that can withstand smaller directed perturbations without significantly changing their prediction. Thus this work also enables more consistent models, which in turn yields models that are more trustworthy., Analys av elektrokardiogram (EKG) med hjälp av djupinlärning har sett stora framsteg senaste åren, bland annat vid diagnostik av hjärtarytmi, förutsägande av ålder utifrån EKG samt dödlighetsanalyser via åldersregressioner. Dessa modeller är dock känsliga till algoritmer som introducerar mycket små omärkbara förändringar i indatan som får modellen att ge ett så inkorrekt svar som möjligt. Dessutom preseterar dessutom dessa modeller betydligt sämre när de appliceras i nya miljöer som de inte tränats på. Denna masteruppsats avser därmed undersöka hur träning på artificiell indata genererad genom adversarial attacks, så kallad motstridig träning (eng. adversarial training), kan skapa nya modeller som är så pass allmänna att de motstår både adversarial attacks och effektivt kan appliceras i nya miljöer via finjustering av modellparametrarna. Detta görs genom robusthets- och överförbarhetsexperiment som använder sig av motstridig träning i tre tillämpningsområden för djuplärning inom EKG-analys: diagnos av förmaksflimmer, könsklassificering och åldersregression. Experimenten visar att motstridig träning skapar modeller som generaliserar bättre och som kan anpassas till nya dataset och där prestera bättre än motsvarande vanliga djupinlärningsmodeller. Detta masterarbete främjar därför modeller som presterar bättre på nya dataset och därmed kräver mindre data för finjustering. Detta bidrar därmed till högpresterande modeller i miljöer där data är begränsad. Detta kan i sin tur vara användbart i analys av EKG i utvecklingsländer eller mindre sjukhus där data är betydligt mer svårtillgänglig. Experimenten visar att motstridig träning kraftigt reducerar känsligheten gentemot små, avsiktliga förändringar och därmed skapar robustare modeller och att de även är robustare efter finjustering. Detta skapar modeller som därmed kan motstå små förändringar i indatan utan motsvarande stora förändringar i utdatan. Detta arbete visar därmed hur mer konsekventa modeller kan skapas, vilket

An adequate ADME/PK (absorption, distribution, metabolism, excretion, pharmacokinetics) profile is an essential quality for a drug. As part of the drug discovery process, leads are iteratively designed and optimized in order to simultaneously satisfy various properties such as appropriate ADME/PK levels and high biological activity for a target. The drug discovery process can be accelerated by improving the likelihood that a designed compound fulfils the necessary pharmacologic properties, and thus reducing the number of needed iterations. A promising technique is de novo drug design, where molecules are computationally generated based on a set of desired attributes. Our project aimed to benchmark the effectiveness of the ANDROMEDA ADME/PK conformal prediction models in guiding the generation of compounds toward an area of chemical space with good ADME/PK properties. For this, we used the REINVENT reinforcement learning framework built by the Molecular AI team at AstraZeneca. Here, we integrated 4 out the 14 available ANDROMEDA models (fabs , fdiss, CLint and Vss) as oracles in the scoring component of the generative model. Oral bioavailability (F) is a secondary parameter that was computed with the help of the aforementioned models and fu(unbound fraction in plasma), and serves as the fifth ADME/PK oracle in our analysis. We aimed to rediscover DRD2 bioactives with a good ADME/PK profile. Our results show that the ANDROMEDA models have a slight influence on the predicted ADME/PK properties of the generated compounds. The results do not show an increased likelihood of generating DRD2 ligands in the case of the primary ANDROMEDA models. However, when using the oral bioavailability oracle, the sampling likelihood increases for some of the approved DRD2 ligands. In conclusion, the oral bioavailability ANDROMEDA model can be a promising option for guiding the generation of novel compounds towards an area of chemical space with good ADME/PK properties.

Treating cancer is difficult as the disease is complex and drug responses often depend on the patient's characteristics. Precision medicine aims to solve this by selecting individualized treatments. Since this involves the analysis of large datasets, machine learning can be used to make the drug selection process more efficient. Traditionally, such models utilize bulk gene expression data. However, this potentially masks information from small cell populations and fails to address tumor heterogeneity. Therefore, this thesis applies data deconvolution methods to bulk gene expression data and estimates the corresponding cell type-specific gene expression profiles. This "increases" the resolution of the input data for the drug response prediction. A hold-out dataset, LODOCV and LOCOCV were used for the evaluation of this approach. Furthermore, all results are compared against a baseline model, which was trained on bulk data. Overall, the accuracy of the cell type-specific model did not show an improvement compared to the bulk model. It also prioritizes information from bulk samples, which makes the additional data unnecessary. The robustness of the cell type-specific model is slightly lower than that of the bulk model. Note, that these outcomes are not necessarily due to a flaw in the underlying concept, but may be connected to poor deconvolution results as the same reference matrix was used for the deconvolution of all bulk samples regardless of the cancer type or disease.