@misc{17362, abstract = {This is the supplementary data for the paper titled "Single-nucleus atlas of the Artemia female reproductive system suggests germline repression of the Z chromosome", where we described the generation and analysis of single-nucleus expression and chromatin-accessibility data from the female reproductive system of Artemia franciscana. We compared our dataset to the published Drosophila single-nucleus data (over 400 million years of divergence) and highlighted the extreme conservation of several of the molecular pathways of oogenesis and meiosis. We found evidence of global transcriptional quiescence and chromatin condensation in late germ cells, highlighting the conserved role of this repressive stage in arthropod oogenesis. Additionally, we explored the expression patterns of the ZW sex chromosomes during oogenesis. Our data shows that the Z-chromosome is consistently downregulated in germline cells. While this is partly driven by a lack of dosage compensation in the germline, a subset of cells show stronger repression of the Z chromosome.}, author = {Elkrewi, Marwan N and Vicoso, Beatriz}, publisher = {Institute of Science and Technology Austria}, title = {{Data for: "Single-nucleus atlas of the Artemia female reproductive system suggests germline repression of the Z chromosome"}}, doi = {10.15479/AT:ISTA:17362}, year = {2024}, } @article{15313, abstract = {Our goal is to investigate fundamental properties of the system of internally cooled convection. The system consists of an upward thermal flux at the lower boundary, a mean temperature lapse-rate and a constant cooling term in the bulk with the bulk cooling in thermal equilibrium with the input heat flux. This simple model represents idealised dry convection in the atmospheric boundary layer, where the cooling mimics the radiative cooling to space notably through longwave radiation. We perform linear stability analysis of the model for different values of the mean stratification to derive the critical forcing above which the fluid is convectively unstable to small perturbations. The dynamic behavior of the fluid system is described and the scaling of various important measured quantities such as the total vertical convective heat flux and the upward mass flux is measured. We introduce a lapse-rate dependent dimensionless Rayleigh-number Ray that determines the behavior of the system, finding that the convective heat-flux and mass-flux scale approximately as Ray0.5 and Ray0.7 respectively. The area-fraction of the domain that is occupied by upward and downward moving fluid and the skewness of the vertical velocity are studied to understand the asymmetry inherent in the system. We conclude with a short discussion on the relevance to atmospheric convection and the scope for further investigations of atmospheric convection using similar simplified approaches.}, author = {Agasthya, Lokahith N and Muller, Caroline J}, issn = {1007-5704}, journal = {Communications in Nonlinear Science and Numerical Simulation}, publisher = {Elsevier}, title = {{Dynamics and scaling of internally cooled convection}}, doi = {10.1016/j.cnsns.2024.108011}, volume = {134}, year = {2024}, } @inproceedings{17411, abstract = {We present PeFLL, a new personalized federated learning algorithm that improves over the state-of-the-art in three aspects: 1) it produces more accurate models, especially in the low-data regime, and not only for clients present during its training phase, but also for any that may emerge in the future; 2) it reduces the amount of on-client computation and client-server communication by providing future clients with ready-to-use personalized models that require no additional finetuning or optimization; 3) it comes with theoretical guarantees that establish generalization from the observed clients to future ones. At the core of PeFLL lies a learning-to-learn approach that jointly trains an embedding network and a hypernetwork. The embedding network is used to represent clients in a latent descriptor space in a way that reflects their similarity to each other. The hypernetwork takes as input such descriptors and outputs the parameters of fully personalized client models. In combination, both networks constitute a learning algorithm that achieves state-of-the-art performance in several personalized federated learning benchmarks}, author = {Scott, Jonathan A and Zakerinia, Hossein and Lampert, Christoph}, booktitle = {12th International Conference on Learning Representations}, location = {Vienna, Austria}, publisher = {OpenReview}, title = {{PEFLL: Personalized federated learning by learning to learn}}, year = {2024}, } @inproceedings{18121, abstract = {It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the network’s general behavior. In this paper, we demonstrate, for the first time, that sparsity can instead be incorporated into the interpretation process itself, as a sample-specific preprocessing step. Unlike previous work, this approach, which we call SPADE, does not place constraints on the trained model and does not affect its behavior during inference on the sample. Given a trained model and a target sample, SPADE uses sample-targeted pruning to provide a "trace" of the network’s execution on the sample, reducing the network to the most important connections prior to computing an interpretation. We demonstrate that preprocessing with SPADE significantly increases the accuracy of image saliency maps across several interpretability methods. Additionally, SPADE improves the usefulness of neuron visualizations, aiding humans in reasoning about network behavior. Our code is available at https://github.com/IST-DASLab/SPADE.}, author = {Moakhar, Arshia Soltani and Iofinova, Eugenia B and Frantar, Elias and Alistarh, Dan-Adrian}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, issn = {2640-3498}, location = {Vienna, Austria}, pages = {45955--45987}, publisher = {ML Research Press}, title = {{SPADE: Sparsity-guided debugging for deep neural networks}}, volume = {235}, year = {2024}, } @article{15146, abstract = {The extracellular matrix (ECM) serves as a scaffold for cells and plays an essential role in regulating numerous cellular processes, including cell migration and proliferation. Due to limitations in specimen preparation for conventional room-temperature electron microscopy, we lack structural knowledge on how ECM components are secreted, remodeled, and interact with surrounding cells. We have developed a 3D-ECM platform compatible with sample thinning by cryo-focused ion beam milling, the lift-out extraction procedure, and cryo-electron tomography. Our workflow implements cell-derived matrices (CDMs) grown on EM grids, resulting in a versatile tool closely mimicking ECM environments. This allows us to visualize ECM for the first time in its hydrated, native context. Our data reveal an intricate network of extracellular fibers, their positioning relative to matrix-secreting cells, and previously unresolved structural entities. Our workflow and results add to the structural atlas of the ECM, providing novel insights into its secretion and assembly.}, author = {Zens, Bettina and Fäßler, Florian and Hansen, Jesse and Hauschild, Robert and Datler, Julia and Hodirnau, Victor-Valentin and Zheden, Vanessa and Alanko, Jonna H and Sixt, Michael K and Schur, Florian KM}, issn = {1540-8140}, journal = {Journal of Cell Biology}, number = {6}, publisher = {Rockefeller University Press}, title = {{Lift-out cryo-FIBSEM and cryo-ET reveal the ultrastructural landscape of extracellular matrix}}, doi = {10.1083/jcb.202309125}, volume = {223}, year = {2024}, } @phdthesis{17485, abstract = {Large language models (LLMs) have made tremendous progress in the past few years, from being able to generate coherent text to matching or surpassing humans in a wide variety of creative, knowledge or reasoning tasks. Much of this can be attributed to massively increased scale, both in the size of the model as well as the amount of training data, from 100s of millions to 100s of billions, or even trillions. This trend is expected to continue, which, although exciting, also raises major practical concerns. Already today's 100+ billion parameter LLMs require top-of-the-line hardware just to run. Hence, it is clear that sustaining these developments will require significant efficiency advances. Historically, one of the most practical ways of improving model efficiency has been compression, especially in the form of sparsity or quantization. While this has been studied extensively in the past, existing accurate methods are all designed for models around 100 million parameters; scaling them up to ones literally 1000x larger is highly challenging. In this thesis, we introduce a new unified sparsification and quantization approach OBC, which through additional algorithmic enhancements leads to GPTQ and SparseGPT, the first techniques fast and accurate enough to compress 100+ billion parameter models to 4- or even 3-bit precision and 50% weight-sparsity, respectively. Additionally, we show how weight-only quantizion does not just bring space savings but also up to 4.5x faster generation speed, via custom GPU kernels. In fact, we show for the first time that it is possible to develop an FP16 times INT4 mixed-precision matrix multiplication kernel, called Marlin, which comes close to simultaneously maximizing both memory and compute utilization, making weight-only quantization highly practical even for multi-user serving. Further, we demonstrate that GPTQ can be scaled to widely overparametrized trillion-parameter models, where extreme sub-1-bit compression rates can be achieved without any inference slow-down, by co-designing a bespoke entropy coding scheme together with an efficient kernel. Finally, we also study compression from the perspective of someone with access to massive amounts of compute resources for training large models completely from scratch. Here the key questions evolve around the joint scaling behavior between compression, model size, and amount of training data used. Based on extensive experimental results for both vision and text models, we introduce the first scaling law which accurately captures the relationship between weight-sparsity, number of non-zero weights and data. This further allows us to characterize the optimal sparsity, which we find to increase the longer a fixed cost model is being trained. Overall, this thesis presents contributions to three different angles of large model efficiency: affordable but accurate algorithms, highly efficient systems implementations, and fundamental scaling laws for compressed training.}, author = {Frantar, Elias}, issn = {2663-337X}, pages = {129}, publisher = {Institute of Science and Technology Austria}, title = {{Compressing large neural networks: Algorithms, systems and scaling laws}}, doi = {10.15479/at:ista:17485}, year = {2024}, } @phdthesis{17490, abstract = {Deep learning is essential in numerous applications nowadays, with many recent advancements made possible by training very large models. Despite their broad applicability, training neural networks is often time-intensive, and it is usually impractical to manage large models and datasets on a single machine. To address these issues, distributed deep learning training has become increasingly important. However, distributed training requires synchronization among nodes, and the mini-batch stochastic gradient descent algorithm places a significant load on network connections. A possible solution to tackle the synchronization bottleneck is to reduce a message size by lossy compression. In this thesis, we investigate systems and algorithmic approaches to communication compression during training. From the systems perspective, we demonstrate that a common approach of expensive hardware overprovisioning can be replaced through a thorough system design. We introduce a framework that introduces efficient software support for compressed communication in machine learning applications, applicable to both multi-GPU single-node training and larger-scale multi-node training. Our framework integrates with popular ML frameworks, providing up to 3x speedups for multi-GPU nodes based on commodity hardware and order-of-magnitude improvements in the multi-node setting, with negligible impact on accuracy. Also, we consider an application of our framework to different communication schemes, such as Fully Sharded Data Parallel. We provide strong convergence guarantees for the compression in such a setup. Empirical validation shows that our method preserves model accuracy for GPT-family models with up to 1.3 billion parameters, while completely removing the communication bottlenecks of non-compressed alternatives, providing up to 2.2x speedups end-to-end. From the algorithmic side, we propose a general framework that dynamically adjusts the degree of compression across a model's layers during training. This approach enhances overall compression and results in significant speedups without compromising accuracy. Our algorithm utilizes an adaptive algorithm that automatically selects the optimal compression parameters for model layers, ensuring the best compression ratio while adhering to an error constraint. Our method is effective across all existing families of compression methods. It achieves up to 2.5x faster training and up to a 5x improvement in compression compared to efficient implementations of current approaches. Additionally, LGreCo can complement existing adaptive algorithms. }, author = {Markov, Ilia}, issn = {2663-337X}, pages = {102}, publisher = {Institute of Science and Technology Austria}, title = {{Communication-efficient distributed training of deep neural networks : An algorithms and systems perspective}}, doi = {10.15479/at:ista:17490}, year = {2024}, } @phdthesis{18766, abstract = {Poxviruses are large pleomorphic double-stranded DNA viruses that include well known members such as variola virus, the causative agent of smallpox, Mpox virus, as well as Vaccinia virus (VACV), which serves as a vaccination strain for formerly mentioned viruses. VACV is a valuable model for studying large pleomorphic DNA viruses in general and poxviruses specifically, as many features, such as core morphology and structural proteins, are well conserved within this family. Despite decades of research, our understanding of the structural components and proteins that comprise the poxvirus core in mature virions remains limited. Although major core proteins were identified via indirect experimental evidence, the core's complexity, with its large size, structure and number of involved proteins, has hindered efforts to achieve high-resolution insights and to define the roles of the individual proteins. The specific protein composition of the core's individual layers, including the palisade layer and the inner core wall, has remained unclear. In this study, we have merged multiple approaches, including single particle cryo electron microscopy of purified virus cores, cryo-electron tomography and subtomogram averaging of mature virions and molecular modeling to elucidate the structural determinants of the VACV core. Due to the lack of experimentally derived structures, either in situ or reconstituted in vitro, we used Alphafold to predict models of the putative major core protein candidates, A10, 23k, A3, A4, and L4. Our results show that the VACV core is composed of several layers with varying local symmetries, forming more intricate interactions than observed previously. This allowed us to identify several molecular building blocks forming the viral core lattice. In particular, we identified trimers of protein A10 as a major core structure that forms the palisade layer of the viral core. Additionally, we revealed that six petals of a flower shaped core pore within the core wall are composed of A10 trimers. Furthermore, we obtained a cryo-EM density for the inner core wall that could potentially accommodate an A3 dimer. Integrating descriptions of protein interactions from previous studies enabled us to provide a detailed structural model of the poxvirus core wall, and our findings indicate that the interactions within A10 trimers are likely consistent across orthopox- and parapoxviruses. This combined application of cryo-SPA and cryo-ET can help overcome obstacles in studying complex virus structures in the future, including their key assembly proteins, interactions, and the formation into a core lattice. Our work provides important fundamental new insights into poxvirus core architecture, also considering the recent re-emergence of poxviruses.}, author = {Datler, Julia}, isbn = {978-3-99078-049-7}, issn = {2663-337X}, keywords = {cryo-EM, cryo-ET, cryo-SPA, Structural Virology, Poxvirus, Vaccinia Virus, Structural Biology}, pages = {106}, publisher = {Institute of Science and Technology Austria}, title = {{Elucidating the structural determinants of the poxvirus core using multi-modal cryo-EM}}, doi = {10.15479/at:ista:18766}, year = {2024}, } @article{14979, abstract = {Poxviruses are among the largest double-stranded DNA viruses, with members such as variola virus, monkeypox virus and the vaccination strain vaccinia virus (VACV). Knowledge about the structural proteins that form the viral core has remained sparse. While major core proteins have been annotated via indirect experimental evidence, their structures have remained elusive and they could not be assigned to individual core features. Hence, which proteins constitute which layers of the core, such as the palisade layer and the inner core wall, has remained enigmatic. Here we show, using a multi-modal cryo-electron microscopy (cryo-EM) approach in combination with AlphaFold molecular modeling, that trimers formed by the cleavage product of VACV protein A10 are the key component of the palisade layer. This allows us to place previously obtained descriptions of protein interactions within the core wall into perspective and to provide a detailed model of poxvirus core architecture. Importantly, we show that interactions within A10 trimers are likely generalizable over members of orthopox- and parapoxviruses.}, author = {Datler, Julia and Hansen, Jesse and Thader, Andreas and Schlögl, Alois and Bauer, Lukas W and Hodirnau, Victor-Valentin and Schur, Florian KM}, issn = {1545-9985}, journal = {Nature Structural & Molecular Biology}, keywords = {Molecular Biology, Structural Biology}, pages = {1114--1123}, publisher = {Springer Nature}, title = {{Multi-modal cryo-EM reveals trimers of protein A10 to form the palisade layer in poxvirus cores}}, doi = {10.1038/s41594-023-01201-6}, volume = {31}, year = {2024}, } @phdthesis{17850, abstract = {Understanding the relationship between a given phenotype and its underlying genotype or genotypes is one of the most pressing challenges of biology, as it lies at the heart of not only basic understanding of evolutionary theory, but also of practical applications in medicine and bioengineering. Understanding this relationship is complicated by the ubiquitous phenomenon of epistasis, wherein mutation effects are dependent on their genetic context. Fitness landscapes — representations of phenotype as a function of genotype — are being increasingly used as a tool to study the effects and interactions of thousands of mutations, but are experimentally limited to exploring a small fraction of a protein’s theoretical sequence space. Furthermore, not all regions of said sequence space are necessarily equally informative. Thus, gene selection for landscape surveys should be carefully considered in order to maximize the usable output of necessarily limited data. In this work, we analyzed the fitness landscapes of orthologous green fluorescent proteins from four different species, by systematically measuring the phenotype, fluorescence, of tens of thousands of mutant genotypes from each protein. These landscapes were highly heterogeneous, with some genes being mutationally robust and displaying epistasis only rarely, and others being highly epistatic and mutationally fragile. We used this data to train machine learning models to predict fluorescence from genotype. Although the training data contained almost exclusively genotypes with less than 3% sequence divergence from the original wild-type sequences, we were able to create novel, functional genotypes with up to 20% sequence divergence. Counterintuitively however, genes with high mutational robustness and rare epistasis were more difficult to introduce large numbers of mutations into, not less. This represents the first study of large-scale fitness landscapes of a protein family, and provides insights into how to approach future landscape surveys and their applications in novel protein design.}, author = {Gonzalez Somermeyer, Louisa}, issn = {2663-337X}, pages = {89}, publisher = {Institute of Science and Technology Austria}, title = {{Fitness landscapes of orthologous green fluorescent proteins}}, doi = {10.15479/at:ista:17850}, year = {2024}, } @article{17202, abstract = {Gate-tunable transmons (gatemons) employing semiconductor Josephson junctions have recently emerged as building blocks for hybrid quantum circuits. In this study, we present a gatemon fabricated in planar Germanium. We induce superconductivity in a two-dimensional hole gas by evaporating aluminum atop a thin spacer, which separates the superconductor from the Ge quantum well. The Josephson junction is then integrated into an Xmon circuit and capacitively coupled to a transmission line resonator. We showcase the qubit tunability in a broad frequency range with resonator and two-tone spectroscopy. Time-domain characterizations reveal energy relaxation and coherence times up to 75 ns. Our results, combined with the recent advances in the spin qubit field, pave the way towards novel hybrid and protected qubits in a group IV, CMOS-compatible material.}, author = {Sagi, Oliver and Crippa, Alessandro and Valentini, Marco and Janik, Marian and Baghumyan, Levon and Fabris, Giorgio and Kapoor, Lucky and Hassani, Farid and Fink, Johannes M and Calcaterra, Stefano and Chrastina, Daniel and Isella, Giovanni and Katsaros, Georgios}, issn = {2041-1723}, journal = {Nature Communications}, publisher = {Springer Nature}, title = {{A gate tunable transmon qubit in planar Ge}}, doi = {10.1038/s41467-024-50763-6}, volume = {15}, year = {2024}, } @article{14257, abstract = {Mapping the complex and dense arrangement of cells and their connectivity in brain tissue demands nanoscale spatial resolution imaging. Super-resolution optical microscopy excels at visualizing specific molecules and individual cells but fails to provide tissue context. Here we developed Comprehensive Analysis of Tissues across Scales (CATS), a technology to densely map brain tissue architecture from millimeter regional to nanometer synaptic scales in diverse chemically fixed brain preparations, including rodent and human. CATS uses fixation-compatible extracellular labeling and optical imaging, including stimulated emission depletion or expansion microscopy, to comprehensively delineate cellular structures. It enables three-dimensional reconstruction of single synapses and mapping of synaptic connectivity by identification and analysis of putative synaptic cleft regions. Applying CATS to the mouse hippocampal mossy fiber circuitry, we reconstructed and quantified the synaptic input and output structure of identified neurons. We furthermore demonstrate applicability to clinically derived human tissue samples, including formalin-fixed paraffin-embedded routine diagnostic specimens, for visualizing the cellular architecture of brain tissue in health and disease.}, author = {Michalska, Julia M and Lyudchik, Julia and Velicky, Philipp and Korinkova, Hana and Watson, Jake and Cenameri, Alban and Sommer, Christoph M and Amberg, Nicole and Venturino, Alessandro and Roessler, Karl and Czech, Thomas and Höftberger, Romana and Siegert, Sandra and Novarino, Gaia and Jonas, Peter M and Danzl, Johann G}, issn = {1546-1696}, journal = {Nature Biotechnology}, pages = {1051--1064}, publisher = {Springer Nature}, title = {{Imaging brain tissue architecture across millimeter to nanometer scales}}, doi = {10.1038/s41587-023-01911-8}, volume = {42}, year = {2024}, } @unpublished{18677, abstract = {The information-processing capability of the brain’s cellular network depends on the physical wiring pattern between neurons and their molecular and functional characteristics. Mapping neurons and resolving their individual synaptic connections can be achieved by volumetric imaging at nanoscale resolution with dense cellular labeling. Light microscopy is uniquely positioned to visualize specific molecules but dense, synapse-level circuit reconstruction by light microscopy has been out of reach due to limitations in resolution, contrast, and volumetric imaging capability. Here we developed light-microscopy based connectomics (LICONN). We integrated specifically engineered hydrogel embedding and expansion with comprehensive deep-learning based segmentation and analysis of connectivity, thus directly incorporating molecular information in synapse-level brain tissue reconstructions. LICONN will allow synapse-level brain tissue phenotyping in biological experiments in a readily adoptable manner.}, author = {Tavakoli, Mojtaba and Lyudchik, Julia and Januszewski, Michał and Vistunou, Vitali and Agudelo Duenas, Nathalie and Vorlaufer, Jakob and Sommer, Christoph M and Kreuzinger, Caroline and Oliveira, Bárbara and Cenameri, Alban and Novarino, Gaia and Jain, Viren and Danzl, Johann G}, booktitle = {bioRxiv}, title = {{Light-microscopy based dense connectomic reconstruction of mammalian brain tissue}}, doi = {10.1101/2024.03.01.582884}, year = {2024}, } @unpublished{18688, abstract = {The human brain has remarkable computational power. It generates sophisticated behavioral sequences, stores engrams over an individual’s lifetime, and produces higher cognitive functions up to the level of consciousness. However, so little of our neuroscience knowledge covers the human brain, and it remains unknown whether this organ is truly unique, or is a scaled version of the extensively studied rodent brain. To address this fundamental question, we determined the cellular, synaptic, and connectivity rules of the hippocampal CA3 recurrent circuit using multicellular patch clamp-recording. This circuit is the largest autoassociative network in the brain, and plays a key role in memory and higher-order computations such as pattern separation and pattern completion. We demonstrate that human hippocampal CA3 employs sparse connectivity, in stark contrast to neocortical recurrent networks. Connectivity sparsifies from rodents to humans, providing a circuit architecture that maximizes associational power. Unitary synaptic events at human CA3–CA3 synapses showed both distinct species-specific and circuit-dependent properties, with high reliability, unique amplitude precision, and long integration times. We also identify differential scaling rules between hippocampal pathways from rodents to humans, with a moderate increase in the convergence of CA3 inputs per cell, but a marked increase in human mossy fiber innervation. Anatomically guided full-scale modeling suggests that the human brain’s sparse connectivity, expanded neuronal number, and reliable synaptic signaling combine to enhance the associative memory storage capacity of CA3. Together, our results reveal unique rules of connectivity and synaptic signaling in the human hippocampus, demonstrating the absolute necessity of human brain research and beginning to unravel the remarkable performance of our autoassociative memory circuits.}, author = {Watson, Jake F. and Vargas-Barroso, Victor and Morse-Mora, Rebecca J. and Navas-Olive, Andrea and Tavakoli, Mojtaba and Danzl, Johann G and Tomschik, Matthias and Rössler, Karl and Jonas, Peter M}, booktitle = {bioRxiv}, title = {{Human hippocampal CA3 uses specific functional connectivity rules for efficient associative memory}}, doi = {10.1101/2024.05.02.592169}, year = {2024}, } @inproceedings{18891, abstract = {Deep neural networks (DNNs) exhibit a surprising structure in their final layer known as neural collapse (NC), and a growing body of works has currently investigated the propagation of neural collapse to earlier layers of DNNs – a phenomenon called deep neural collapse (DNC). However, existing theoretical results are restricted to special cases: linear models, only two layers or binary classification. In contrast, we focus on non-linear models of arbitrary depth in multi-class classification and reveal a surprising qualitative shift. As soon as we go beyond two layers or two classes, DNC stops being optimal for the deep unconstrained features model (DUFM) – the standard theoretical framework for the analysis of collapse. The main culprit is a low-rank bias of multi-layer regularization schemes: this bias leads to optimal solutions of even lower rank than the neural collapse. We support our theoretical findings with experiments on both DUFM and real data, which show the emergence of the low-rank structure in the solution found by gradient descent.}, author = {Súkeník, Peter and Lampert, Christoph and Mondelli, Marco}, booktitle = {38th Annual Conference on Neural Information Processing Systems}, location = {Vancouver, Canada}, publisher = {Neural Information Processing Systems Foundation}, title = {{Neural collapse versus low-rank bias: Is deep neural collapse really optimal?}}, volume = {37}, year = {2024}, } @phdthesis{18515, abstract = {Understanding the role of evolutionary processes in shaping genetic variation has been a primary goal in evolutionary genetics. In this regard, a key question is how genetically distinct populations evolve in the face of gene flow, thereby generating genetic and phenotypic divergence and reproductive isolation (RI). This requires quantifying the role and relative contributions of prezygotic and postzygotic isolating mechanisms on the reduction of gene exchange between populations, and identifying regions in the genome that mediate RI, which is often polygenic. Further, this needs distinguishing neutral and selected regions in the genome, and discerning how selection influences patterns of neutral divergence. Population structure, defined as any deviation from panmixia, such as geographic distribution, movement and mating patterns of individuals, influences how genetic variation is structured in space and shapes the neutral null model. Availability of large scale spatial genomic datasets now enables us to detect signatures of population structure in genetic data and infer population genetic parameters. Such inferences are crucial and have wide applications in biodiversity, conservation genetics, population management and medical genetics. However, inferences are based on assumptions that do not always match the complex reality, thus leading to erroneous conclusions. Moreover, the role and interaction of heterogeneous population density and dispersal, which are ubiquitous in nature, has been challenging to study owing to their mathematical complexity. In such scenarios, feedback between theory, data and simulations can prove to be useful. In this thesis, I examine the effect of population structure on neutral genetic variation and barriers to gene exchange in hybridising populations, thereby bridging together the fields of spatial population genetics and speciation. Despite being a key concept in speciation, reproductive isolation (RI) lacks a quantitative definition and has been used and measured differently across different fields. Chapter 2 gives a quantitative definition of RI, in terms of the effect of genetic differences on gene flow. We give analytical predictions for RI in a range of scenarios, in terms of effective migration rates for discrete populations and barrier strength for continuous populations. In addition to this, we discuss current measures of RI and their limitations, and propose the need for new measures that combine organismal and genetic perspectives of RI. In chapter 3, I examine the combined effect of assortative mating, sexual selection and viability selection on RI. For this, we consider a polygenic ‘magic’ trait under a mainland-island model. We obtain novel theoretical predictions for molecular divergence in terms of effective migration rates, which bears a simple relationship to measurable fitness components of migrants and various early generation hybrids. We explore the conditions under which local adaptation can be maintained despite maladaptive gene flow and quantify the relative contributions of viability and sexual selection to genome-wide barriers to gene flow. The next two chapters of the thesis focus on a hybrid zone of Antirrhinum majus that consist of two subspecies- the magenta flowered A. m. pseudomajus and the yellow flowered A.m. striatum. Previous studies have suggested that flower colour is target of pollinator mediated selection and is influenced only by few genes. While these regions show high genetic differentiation between the subspecies, the rest of the genome is seen to be well mixed. Chapter 4 examines the effects of heterogeneous population density and leptokurtic dispersal on isolation by distance and the distribution of heterozygosity by focusing on non-flower colour markers. Chapter 5 analyses cline shapes and associations among 6 focal flower colour markers to understand how selection and dispersal maintain this hybrid zone. We see sharp coincident stepped clines at all loci and positive associations throughout the hybrid zone, contrary to the expected patterns from diffusive gene flow. With a novel scheme of inferring dispersal combined with multilocus simulations, we show that stepped clines do not reflect genetic barriers to gene flow, but are rather a result of long-distance migration. This framework allows us to get realistic estimates gene flow and selection and shows how traditional cline analysis may lead to inaccurate conclusions when assumptions of the theory are not met. Overall, this thesis investigates how different features of population structure leave detectable signatures in genetic variation, namely in patterns of isolation by distance, linkage disequilibrium and genetic divergence. It also highlights how effective migration rates provide useful way of analysing polygenic architectures and shed new light into hybrid zones. In doing so, I identify scenarios when simple models become insufficient and suggest possibe directions by combining genetic data with simulations.}, author = {Surendranadh, Parvathy}, issn = {2663-337X}, pages = {219}, publisher = {Institute of Science and Technology Austria}, title = {{Effect of population structure on neutral genetic variation and barriers to gene exchange}}, doi = {10.15479/at:ista:18515}, year = {2024}, } @phdthesis{15020, abstract = {This thesis consists of four distinct pieces of work within theoretical biology, with two themes in common: the concept of optimization in biological systems, and the use of information-theoretic tools to quantify biological stochasticity and statistical uncertainty. Chapter 2 develops a statistical framework for studying biological systems which we believe to be optimized for a particular utility function, such as retinal neurons conveying information about visual stimuli. We formalize such beliefs as maximum-entropy Bayesian priors, constrained by the expected utility. We explore how such priors aid inference of system parameters with limited data and enable optimality hypothesis testing: is the utility higher than by chance? Chapter 3 examines the ultimate biological optimization process: evolution by natural selection. As some individuals survive and reproduce more successfully than others, populations evolve towards fitter genotypes and phenotypes. We formalize this as accumulation of genetic information, and use population genetics theory to study how much such information can be accumulated per generation and maintained in the face of random mutation and genetic drift. We identify the population size and fitness variance as the key quantities that control information accumulation and maintenance. Chapter 4 reuses the concept of genetic information from Chapter 3, but from a different perspective: we ask how much genetic information organisms actually need, in particular in the context of gene regulation. For example, how much information is needed to bind transcription factors at correct locations within the genome? Population genetics provides us with a refined answer: with an increasing population size, populations achieve higher fitness by maintaining more genetic information. Moreover, regulatory parameters experience selection pressure to optimize the fitness-information trade-off, i.e. minimize the information needed for a given fitness. This provides an evolutionary derivation of the optimization priors introduced in Chapter 2. Chapter 5 proves an upper bound on mutual information between a signal and a communication channel output (such as neural activity). Mutual information is an important utility measure for biological systems, but its practical use can be difficult due to the large dimensionality of many biological channels. Sometimes, a lower bound on mutual information is computed by replacing the high-dimensional channel outputs with decodes (signal estimates). Our result provides a corresponding upper bound, provided that the decodes are the maximum posterior estimates of the signal.}, author = {Hledik, Michal}, issn = {2663-337X}, keywords = {Theoretical biology, Optimality, Evolution, Information}, pages = {158}, publisher = {Institute of Science and Technology Austria}, title = {{Genetic information and biological optimization}}, doi = {10.15479/at:ista:15020}, year = {2024}, } @phdthesis{17206, abstract = {Males and females exhibit numerous differences, from the initial stages of sex determination to the development of secondary sexual characteristics. In Drosophila, these differences have been thoroughly studied. Extensive research has been performed to understand the role and molecular mode of action of central sex in determining switch genes, such as transformer (tra) and Sex-lethal (Sxl). Furthermore, studies have highlighted differential gene expression as an essential mechanism to create sexual dimorphism. An alternative path to sexual dimorphism that has been less explored is alternative splicing, the mechanism through which genes can produce multiple transcripts with distinct properties and functions. The primary switch sex-determining gene Sxl is a good example of the role of alternative splicing for sex-specific functions: the inclusion of a specific exon determines the male or female form of the protein, which in turn switches on either the male or female developmental pathway. The genes that act upstream of Sxl and determine which form is expressed - the counter genes - have received less attention. This thesis addresses two critical questions about the molecular encoding of sexes in the Drosophila melanogaster genome: First, the use of splice forms in male and female tissues in D. melanogaster is examined, inferring the molecular and evolutionary parameters shaping the diversity of the splicing landscape. Second, the behaviour of counter genes in Drosophila-related species is investigated, shedding light on potential changes leading to their incorporation into the sex-determination pathway. For the alternative splicing analyses, long-read RNA sequencing of testes, ovaries, female and male midguts, heads, and whole bodies was performed. A novel pipeline was developed to assign unique transcript identifiers for each sequence of exons and introns in the read, enabling detailed comparisons of splicing variants in each tissue/sex. Alternative splicing was found to be more pervasive in females than males (22,201 exclusive splice forms in females versus 12,631 in males), especially when comparing ovaries to other tissues. The ovaries alone displayed 15,299 exclusive splice forms, suggesting most female exclusive splice forms originate there. Genome location and gene age were also correlated with the number of splice forms per gene. In particular, the X and 4th chromosomes (Muller elements A and F) showed more splice forms per gene than other chromosomes. Additionally, genes older than 63 million years exhibited more splice forms per gene than younger genes. Our results suggest that alternative splicing is more prevalent than previously believed, with numerous female-exclusive forms, age, and location playing significant roles in shaping its prevalence. For the counter genes analyses, we combined published gene expression, genomic, and gene interaction data from various clades (Bactrocera jarvisi, B. oleae, Ceratitis capitata, Mus musculus, Caenorhabditis elegans, Homo sapiens, and D. melanogaster). The counter genes scute (sc), extra macrochaetae (emc), groucho (gro), deadpan (dpn), daughterless (da), runt (run), Sxl, hermaphrodite (her), and tra maintain conserved Muller element locations between C. capitata and D. melanogaster, which are most of the counter genes identified in the C. capitata genome. Their expression patterns during early embryogenesis in B. jarvisi and D. melanogaster are also similar for counter genes dpn, gro, da, and emc. However, Sxl and sc are also found to have more extreme expression ratios between the species. Lastly, gene interactions within the counter genes are conserved, with da-sc and gro-dpn interactions occurring in Drosophila, worms, humans, and mice. Interactions such as dpn-sc, dpn-da, da-emc, and gro-run are present in Drosophila, mice, and humans, suggesting these genes were recruited by ancestral characteristics, primarily during embryogenesis. The conserved expression, location, and interactions of counter genes suggest serendipitous recruitment of such genes instead of a change in those characteristics as they were recruited for this function. }, author = {Raices, Julia}, issn = {2663-337X}, pages = {82}, publisher = {Institute of Science and Technology Austria}, title = {{Novel approaches to studying alternative splicing in Drosophila Melanogaster : Insights into sex-specific gene expression and the evolution of sex determination}}, doi = {10.15479/at:ista:17206}, year = {2024}, } @article{17890, abstract = {Our understanding of the molecular pathways that regulate oogenesis and define cellular identity in the Arthropod female reproductive system and the extent of their conservation is currently very limited. This is due to the focus on model systems, including Drosophila and Daphnia, which do not reflect the observed diversity of morphologies, reproductive modes, and sex chromosome systems. We use single-nucleus RNA and ATAC sequencing to produce a comprehensive single nucleus atlas of the adult Artemia franciscana female reproductive system. We map our data to the Fly Cell Atlas single-nucleus dataset of the Drosophila melanogaster ovary, shedding light on the conserved regulatory programs between the two distantly related Arthropod species. We identify the major cell types known to be present in the Artemia ovary, including germ cells, follicle cells, and ovarian muscle cells. Additionally, we use the germ cells to explore gene regulation and expression of the Z chromosome during meiosis, highlighting its unique regulatory dynamics and allowing us to explore the presence of meiotic sex chromosome silencing in this group.}, author = {Elkrewi, Marwan N and Vicoso, Beatriz}, issn = {1553-7404}, journal = {PLoS Genetics}, number = {8}, publisher = {Public Library of Science}, title = {{Single-nucleus atlas of the Artemia female reproductive system suggests germline repression of the Z chromosome}}, doi = {10.1371/journal.pgen.1011376}, volume = {20}, year = {2024}, } @phdthesis{18531, abstract = {Sex chromosomes and autosomes exhibit very different evolutionary dynamics. The Y chromosome usually degenerates, leaving many X-linked loci hemizygous in males. Since recessive X-linked mutations are always exposed to selection in males, selection is more efficient on the X chromosome than on autosomes on recessive mutations, leading to faster adaptation on the X chromosome than other genomic regions, if beneficial mutations are on average recessive (known as the Faster-X effect). In the presence of the functional, but non-recombining gametolog on the Y (as is often the case in young non-recombining regions), recessive mutations are sheltered from selection on the X chromosome. We model this scenario and show that the efficiency of selection is reduced on diploid X loci due to sheltering by the Y chromosome. Reduced efficiency of selection leads to slower adaptation and increased accumulation of deleterious mutations (Slower-X effect). We extended this model to explore the effect of sex-specific selection on degeneration of sex chromosomes, showing theoretically that male-limited genes degenerate on the X chromosome and female-biased genes degenerate on the Y chromosome. This prediction depends on the effective population size and the mutation rate, explaining the variety of sex chromosome degeneration patterns observed in nature. To test for direct evidence of a Slower-X (or Slower-Z) effect, we analyzed the ZW sex chromosomes of the flatworm Schistosoma japonicum, which have a very young non-recombining region with non-degenerated W. Diploid Z-linked genes have higher ratios of non-synonymous to synonymous polymorphisms than autosomal genes, supporting reduced efficiency of selection on the diploid Z region. These results provide evidence of sheltering by the W chromosome, a mechanism that could contribute to Z (X) chromosome degeneration, and illustrate contrasting evolutionary patterns in old and young sex chromosome regions. In addition, genes with sexspecific patterns of expression show opposite patterns of selection in the young (diploid) and old (hemizygous) Z, showing the complex manner in which sex-specific selection shapes the evolutionary patterns of sex chromosomes. }, author = {Mrnjavac, Andrea}, issn = {2663-337X}, keywords = {Sex chromosomes, evolution, selection, sheltering}, pages = {181}, publisher = {Institute of Science and Technology Austria}, title = {{Early stages of sex chromosome evolution}}, doi = {10.15479/at:ista:18531}, year = {2024}, }