Quantitative Biology
New submissions
[ showing up to 2000 entries per page: fewer  more ]
New submissions for Tue, 19 Oct 21
 [1] arXiv:2110.08348 [pdf, other]

Title: Estimating individual admixture from finite reference databasesComments: 17 pages, 3 figuresSubjects: Populations and Evolution (qbio.PE); Statistics Theory (math.ST)
The concept of individual admixture (IA) assumes that the genome of individuals is composed of alleles inherited from $K$ ancestral populations. Each copy of each allele has the same chance $q_k$ to originate from population $k$, and together with the allele frequencies in all populations $p$ comprises the admixture model, which is the basis for software like {\sc STRUCTURE} and {\sc ADMIXTURE}. Here, we assume that $p$ is given through a finite reference database, and $q$ is estimated via maximum likelihood. Above all, we are interested in efficient estimation of $q$, and the variance of the estimator which originates from finiteness of the reference database, i.e.\ a variance in $p$. We provide a central limit theorem for the maximumlikelihood estimator, give simulation results, and discuss applications in forensic genetics.
 [2] arXiv:2110.08457 [pdf, other]

Title: Metagenome assembly of highfidelity long reads with hifiasmmetaSubjects: Genomics (qbio.GN)
Current metagenome assemblers developed for short sequence reads or noisy long readswere not optimized for accurate long reads. Here we describe hifiasmmeta, a new metagenome assembler that exploits the high accuracy of recent data. Evaluated on seven empirical datasets, hifiasmmeta reconstructed tens to hundreds of complete circular bacterial genomes per dataset, consistently outperforming other metagenome assemblers.
 [3] arXiv:2110.08575 [pdf, other]

Title: Cellular resource allocation strategies for cell size and shape control in bacteriaComments: Review article, 13 pages, 5 figures,Subjects: Cell Behavior (qbio.CB); Biological Physics (physics.bioph)
Bacteria are highly adaptive microorganisms that thrive in a wide range of growth conditions via changes in cell morphologies and macromolecular composition. How bacterial morphologies are regulated in diverse environmental conditions is a longstanding question. Regulation of cell size and shape implies control mechanisms that couple the growth and division of bacteria to their cellular environment and macromolecular composition. In the past decade, simple quantitative laws have emerged that connect cell growth to proteomic composition and the nutrient availability. However, the relationships between cell size, shape and growth physiology remain challenging to disentangle and unifying models are lacking. In this review, we focus on regulatory models of cell size control that reveal the connections between bacterial cell morphology and growth physiology. In particular, we discuss how changes in nutrient conditions and translational perturbations regulate the cell size, growth rate and proteome composition. Integrating quantitative models with experimental data, we identify the physiological principles of bacterial size regulation, and discuss the optimization strategies of cellular resource allocation for size control.
 [4] arXiv:2110.08621 [pdf]

Title: When heart beats differently in depression: a review of HRV measuresComments: 30 pages, 0 figures, 1 TableSubjects: Neurons and Cognition (qbio.NC)
Background and Objective: The connection between depression and autonomous nervous system (ANS) is well documented in scientific literature. Heart rate variability (HRV) is a rich source of information for studying the dynamics of this relation. Disturbed heart dynamics in depression seriously increases mortality risk. Technical sciences help improve early detection and monitoring and offer more accurate management of treatment. Based on advances in computational power, information theory, complex systems dynamics, and nonlinear analysis applied to physiological complexity, we can now turn to novel biomarkers extracted from electrophysiological signals. This work is a crosssectional analysis with methodological commentary of application of nonlinear measures of HRV related to depression. Methods: We systematically searched online for papers exploring the connection of depression and HRV, using both conventional and nonlinear analysis. We scrutinized chosen publications and methodologically analyzed and compared them. Results: Sixtyseven publications on the connection of HRV measures and depression meeting our inclusion criteria are selected. The effectiveness of the applied methods of electrocardiogram (ECG) analysis are compared and discussed in the light of detection and prevention of depressionrelated cardiac diseases. Conclusions: It is clear that aberrated ANS dynamics can be detected via ECG analysis, where nonlinear measures show to be more sensitive and accurate than standard time and spectral ones. With the portable ECG devices and cloudbased telehealth applications, monitoring of outpatients could be done anytime anywhere. We appeal for early screening for cardiovascular abnormalities in depressive patients to prevent possible deleterious events.
 [5] arXiv:2110.08947 [pdf, ps, other]

Title: On the dynamics of the contagious rate under isolation measuresComments: 31 pages, 8 figuresSubjects: Populations and Evolution (qbio.PE); Biological Physics (physics.bioph); Medical Physics (physics.medph)
The infection dynamics of a population under stationary isolation conditions is modeled. It is underlined that the stationary character of the isolation measures can be expected to imply that an effective SIR model with constant parameters should describe the infection process. Then, a derivation of this property is presented, assuming that the statistical fluctuations in the number of infection and recovered cases are disregarded. This effective SIR model shows a reduced population number and a constant $\beta$ parameter. The effects of also including the retardation between recovery and infection process is also considered. Next, it is shown that any solution of the effective SIR also solves the linear problem to which the SIR equations reduce when the total population is much larger than the number of the infected cases. Then, it is also argued that this equivalence follows for a specific contagious parameter $\beta(t)$ which time dependence is analytically derived here. Then, two equivalent predictive calculational methods for the infection dynamics under stationary isolation measures are proposed. The results represent a solutions for the known and challenging problem of defining the time dependence of the contagion parameter, when the SIR parameter $N$ is assumed to be the whole population number. Finally, the model is applied to describe the known infection curves for countries that already had passed the epidemic process under strict stationary isolation measures. The cases of Iceland, New Zealand, Korea and Cuba were considered. Although, non subject to stationary isolation measures the cases of U.S.A. and Mexico are also examined due to their interest. The results support the argued validity of SIR model including retardation.
 [6] arXiv:2110.09017 [pdf]

Title: Anatomy of a superorganism  structure and growth dynamics of army ant bivouacsAuthors: Thomas Bochynek, Florian Schiffers, André Aichert, Oliver Cossairt, Simon Garnier, Michael RubensteinSubjects: Quantitative Methods (qbio.QM)
Beyond unicellular and multicellular organisms, there is a third type of structural complexity in living animals: that of the mechanical selfassembly of groups of distinct multicellular organisms into dynamical, functional structures. One of the most striking examples of such structures is the army ant bivouac, a nest which selfassembles solely from the interconnected bodies of hundreds of thousands of individuals. These bivouacs are difficult to study because they rapidly disassemble when disturbed, and hence little is known about the structure and rules that individuals follow during their formation. Here we use a custombuilt Computed Tomography scanner to investigate the details of the internal structure and growth process of army ant bivouacs. We show that bivouacs are heterogeneous structures, which throughout their growth maintain a thick shell surrounding a less dense interior that contains empty spaces akin to nest chambers. We find that ants within the bivouac do not carry more than approximately eight times their weight regardless of the size of the structure or their position within it. This observation suggests that bivouac size is not limited by physical constraints of the ants' morphology. This study brings us closer to understanding the rules used by individuals to govern the formation of these exceptional superorganismal structures, and provides insight into how to create engineered selfassembling systems with, for instance, swarms of robots or active matter.
 [7] arXiv:2110.09204 [pdf, other]

Title: Pathintegral solution of MacArthur's resourcecompetition model for large ecosystems with random speciesresources couplingsComments: This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Chaos 31, 103113 (2021) and may be found at this https URLJournalref: Chaos 31, 103113 (2021)Subjects: Populations and Evolution (qbio.PE); Disordered Systems and Neural Networks (condmat.disnn); Statistical Mechanics (condmat.statmech)
We solve MacArthur's resourcecompetition model with random speciesresource couplings in the `thermodynamic' limit of infinitely many species and resources using dynamical pathintegrals a la De Domincis. We analyze how the steady state picture changes upon modifying several parameters, including the degree of heterogeneity of metabolic strategies (encoding the preferences of species) and of maximal resource levels (carrying capacities), and discuss its stability. Ultimately, the scenario obtained by other approaches is recovered by analyzing an effective onespeciesoneresource ecosystem that is fully equivalent to the original multispecies one. The technique used here can be applied for the analysis of other model ecosystems related to the version of MacArthur's model considered here.
 [8] arXiv:2110.09336 [pdf]

Title: Preterm neonates distinguish rhythm violation through a hierarchy of cortical processingAuthors: Mohammadreza Edalati, Mahdi Mahmoudzadeh, Guy Kongolo, Ghida Ghostine, Javad Safaie, Fabrice Wallois, Sahar MoghimiSubjects: Neurons and Cognition (qbio.NC)
Rhythm is a fundamental component of the auditory world, present even during the prenatal life. While there is evidence that some auditory capacities are already present before birth, whether and how the premature neural networks process auditory rhythm is yet not known. We investigated the neural response of premature neonates at 3034 weeks gestational age to violations from rhythmic regularities in an auditory sequence using highresolution electroencephalography and eventrelated potentials. Unpredicted rhythm violations elicited a frontocentral mismatch response, indicating that the premature neonates detected the rhythmic regularities. Next, we examined the cortical effective connectivity underlying the elicited mismatch response using dynamic causal modeling. We examined the connectivity between cortical sources using a set of 16 generative models that embedded alternate hypotheses about the role of the frontal cortex as well as backward frontotemporal connection. Our results demonstrated that the processing of rhythm violations was not limited to the primary auditory areas, and as in the case of adults, encompassed a hierarchy of temporofrontal cortical structures. The result also emphasized the importance of topdown (backward) projections from the frontal cortex in explaining the mismatch response. Our findings demonstrate a sophisticated cortical structure underlying predictive rhythm processing at the onset of the thalamocortical and corticocortical circuits, two months before term.
 [9] arXiv:2110.09413 [pdf, other]

Title: SGEN: Singlecell Sequencing Graph Selfsupervised Embedding NetworkComments: 6 pages body + 2 pages referenceSubjects: Genomics (qbio.GN); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Singlecell sequencing has a significant role to explore biological processes such as embryonic development, cancer evolution, and cell differentiation. These biological properties can be presented by a twodimensional scatter plot. However, singlecell sequencing data generally has very high dimensionality. Therefore, dimensionality reduction should be used to process the high dimensional sequencing data for 2D visualization and subsequent biological analysis. The traditional dimensionality reduction methods, which do not consider the structure characteristics of singlecell sequencing data, are difficult to reveal the data structure in the 2D representation. In this paper, we develop a 2D feature representation method based on graph convolutional networks (GCN) for the visualization of singlecell data, termed singlecell sequencing graph embedding networks (SGEN). This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot. The results show SGEN achieves obvious 2D distribution and preserves the highdimensional relationship of different cells. Meanwhile, similar cell clusters have spatial continuity rather than relying heavily on random initialization, which can reflect the trajectory of cell development in this scatter plot.
 [10] arXiv:2110.09439 [pdf, other]

Title: Coherent oscillations in balanced neural networks driven by endogenous fluctuationsSubjects: Neurons and Cognition (qbio.NC); Disordered Systems and Neural Networks (condmat.disnn)
We present a detailed analysis of the dynamical regimes observed in a balanced network of identical Quadratic IntegrateandFire (QIF) neurons with a sparse connectivity for homogeneous and heterogeneous indegree distribution. Depending on the parameter values, either an asynchronous regime or periodic oscillations spontaneously emerge. Numerical simulations are compared with a mean field model based on a selfconsistent FokkerPlanck equation (FPE). The FPE reproduces quite well the asynchronous dynamics in the homogeneous case by either assuming a Poissonian or renewal distribution for the incoming spike trains. An exact self consistent solution for the mean firing rate obtained in the limit of infinite indegree allows identifying balanced regimes that can be either mean or fluctuationdriven. A lowdimensional reduction of the FPE in terms of circular cumulants is also considered. Two cumulants suffice to reproduce the transition scenario observed in the network. The emergence of periodic collective oscillations is well captured both in the homogeneous and heterogeneous setups by the mean field models upon tuning either the connectivity, or the input DC current. In the heterogeneous situation we analyze also the role of structural heterogeneity.
Crosslists for Tue, 19 Oct 21
 [11] arXiv:2110.08253 (crosslist from cs.LG) [pdf, other]

Title: A Field Guide to Scientific XAI: Transparent and Interpretable Deep Learning for Bioinformatics ResearchSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Genomics (qbio.GN)
Deep learning has become popular because of its potential to achieve high accuracy in prediction tasks. However, accuracy is not always the only goal of statistical modelling, especially for models developed as part of scientific research. Rather, many scientific models are developed to facilitate scientific discovery, by which we mean to abstract a humanunderstandable representation of the natural world. Unfortunately, the opacity of deep neural networks limit their role in scientific discovery, creating a new demand for models that are transparently interpretable. This article is a field guide to transparent model design. It provides a taxonomy of transparent model design concepts, a practical workflow for putting design concepts into practice, and a general template for reporting design choices. We hope this field guide will help researchers more effectively design transparently interpretable models, and thus enable them to use deep learning for scientific discovery.
 [12] arXiv:2110.08465 (crosslist from cs.LG) [pdf, other]

Title: A Heterogeneous Graph Based Framework for Multimodal Neuroimaging Fusion LearningSubjects: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Neurons and Cognition (qbio.NC)
Here, we present a Heterogeneous Graph neural network for Multimodal neuroimaging fusion learning (HGM). Traditional GNNbased models usually assume the brain network is a homogeneous graph with single type of nodes and edges. However, vast literatures have shown the heterogeneity of the human brain especially between the two hemispheres. Homogeneous brain network is insufficient to model the complicated brain state. Therefore, in this work we firstly model the brain network as heterogeneous graph with multitype nodes (i.e., left and right hemispheric nodes) and multitype edges (i.e., intra and interhemispheric edges). Besides, we also propose a selfsupervised pretraining strategy based on heterogeneou brain network to address the overfitting problem due to the complex model and small sample size. Our results on two datasets show the superiority of proposed model over other multimodal methods for disease prediction task. Besides, ablation experiments show that our model with pretraining strategy can alleviate the problem of limited training sample size.
 [13] arXiv:2110.08471 (crosslist from math.OC) [pdf, other]

Title: Fast Projection onto the Capped Simplex withApplications to Sparse Regression in BioinformaticsComments: 12 pages, 5 figuresSubjects: Optimization and Control (math.OC); Machine Learning (cs.LG); Genomics (qbio.GN)
We consider the problem of projecting a vector onto the socalled kcapped simplex, which is a hypercube cut by a hyperplane. For an ndimensional input vector with bounded elements, we found that a simple algorithm based on Newton's method is able to solve the projection problem to high precision with a complexity roughly about O(n), which has a much lower computational cost compared with the existing sortingbased methods proposed in the literature. We provide a theory for partial explanation and justification of the method.
We demonstrate that the proposed algorithm can produce a solution of the projection problem with high precision on large scale datasets, and the algorithm is able to significantly outperform the stateoftheart methods in terms of runtime (about 68 times faster than a commercial software with respect to CPU time for input vector with 1 million variables or more).
We further illustrate the effectiveness of the proposed algorithm on solving sparse regression in a bioinformatics problem. Empirical results on the GWAS dataset (with 1,500,000 singlenucleotide polymorphisms) show that, when using the proposed method to accelerate the Projected QuasiNewton (PQN) method, the accelerated PQN algorithm is able to handle hugescale regression problem and it is more efficient (about 36 times faster) than the current stateoftheart methods.  [14] arXiv:2110.08744 (crosslist from cs.AI) [pdf]

Title: A model for full local image interpretationComments: Published in the Proceedings of the 37th Annual Meeting of the Cognitive Science Society (CogSci), 2015Journalref: https://cogsci.mindmodeling.org/2015/papers/0048/Subjects: Artificial Intelligence (cs.AI); Neurons and Cognition (qbio.NC)
We describe a computational model of humans' ability to provide a detailed interpretation of components in a scene. Humans can identify in an image meaningful components almost everywhere, and identifying these components is an essential part of the visual process, and of understanding the surrounding scene and its potential meaning to the viewer. Detailed interpretation is beyond the scope of current models of visual recognition. Our model suggests that this is a fundamental limitation, related to the fact that existing models rely on feedforward but limited topdown processing. In our model, a first recognition stage leads to the initial activation of class candidates, which is incomplete and with limited accuracy. This stage then triggers the application of classspecific interpretation and validation processes, which recover richer and more accurate interpretation of the visible scene. We discuss implications of the model for visual interpretation by humans and by computer vision models.
 [15] arXiv:2110.08850 (crosslist from physics.socph) [pdf]

Title: Understanding the network formation pattern for better link predictionComments: 21 pages, 3 figures, 18 tables, and 29 referencesSubjects: Physics and Society (physics.socph); Machine Learning (cs.LG); Social and Information Networks (cs.SI); Molecular Networks (qbio.MN); Machine Learning (stat.ML)
As a classical problem in the field of complex networks, link prediction has attracted much attention from researchers, which is of great significance to help us understand the evolution and dynamic development mechanisms of networks. Although various network typespecific algorithms have been proposed to tackle the link prediction problem, most of them suppose that the network structure is dominated by the Triadic Closure Principle. We still lack an adaptive and comprehensive understanding of network formation patterns for predicting potential links. In addition, it is valuable to investigate how network local information can be better utilized. To this end, we proposed a novel method named Link prediction using Multiple Order Local Information (MOLI) that exploits the local information from the neighbors of different distances, with parameters that can be a priordriven based on prior knowledge, or datadriven by solving an optimization problem on observed networks. MOLI defined a local network diffusion process via random walks on the graph, resulting in better use of network information. We show that MOLI outperforms the other 11 widely used link prediction algorithms on 11 different types of simulated and realworld networks. We also conclude that there are different patterns of local information utilization for different networks, including social networks, communication networks, biological networks, etc. In particular, the classical common neighborbased algorithm is not as adaptable to all social networks as it is perceived to be; instead, some of the social networks obey the Quadrilateral Closure Principle which preferentially connects paths of length three.
 [16] arXiv:2110.08918 (crosslist from cs.LG) [pdf, other]

Title: Using Clinical Drug Representations for Improving Mortality and Length of Stay PredictionsComments: Published in IEEE CIBCB 2021Subjects: Machine Learning (cs.LG); Quantitative Methods (qbio.QM)
Drug representations have played an important role in cheminformatics. However, in the healthcare domain, drug representations have been underused relative to the rest of Electronic Health Record (EHR) data, due to the complexity of high dimensional drug representations and the lack of proper pipeline that will allow to convert clinical drugs to their representations. Timevarying vital signs, laboratory measurements, and related timeseries signals are commonly used to predict clinical outcomes. In this work, we demonstrated that using clinical drug representations in addition to other clinical features has significant potential to increase the performance of mortality and length of stay (LOS) models. We evaluate the two different drug representation methods (ExtendedConnectivity FingerprintECFP and SMILESTransformer embedding) on clinical outcome predictions. The results have shown that the proposed multimodal approach achieves substantial enhancement on clinical tasks over baseline models. Using clinical drug representations as additional features improve the LOS prediction for Area Under the Receiver Operating Characteristics (AUROC) around %6 and for Area Under PrecisionRecall Curve (AUPRC) by around %5. Furthermore, for the mortality prediction task, there is an improvement of around %2 over the time series baseline in terms of AUROC and %3.5 in terms of AUPRC. The code for the proposed method is available at https://github.com/tanlab/MIMICIIIClinicalDrugRepresentations.
 [17] arXiv:2110.08967 (crosslist from stat.AP) [pdf, other]

Title: Assessing Ecosystem State Space Models: Identifiability and EstimationSubjects: Applications (stat.AP); Quantitative Methods (qbio.QM)
Bayesian methods are increasingly being applied to parameterize mechanistic process models used in environmental prediction and forecasting. In particular, models describing ecosystem dynamics with multiple states that are linear and autoregressive at each step in time can be treated as statistical state space models. In this paper we examine this subset of ecosystem models, giving closed form Gibbs sampling updates for latent states and process precision parameters when process and observation errors are normally distributed. We use simulated data from an example model (DALECev) to assess the performance of parameter estimation and identifiability under scenarios of gaps in observations. We show that process precision estimates become unreliable as temporal gaps between observed state data increase. To improve estimates, particularly precisions, we introduce a method of tuning the timestep of the latent states to leverage higherfrequency driver information. Further, we show that data cloning is a suitable method for assessing parameter identifiability in this class of models. Overall, our study helps inform the application of state space models to ecological forecasting applications where 1) data are not available for all states and transfers at the operational timestep for the ecosystem model and 2) process uncertainty estimation is desired.
 [18] arXiv:2110.09006 (crosslist from cs.CV) [pdf, other]

Title: Natural Image Reconstruction from fMRI using Deep Learning: A SurveySubjects: Computer Vision and Pattern Recognition (cs.CV); Neurons and Cognition (qbio.NC); Machine Learning (stat.ML)
With the advent of brain imaging techniques and machine learning tools, much effort has been devoted to building computational models to capture the encoding of visual information in the human brain. One of the most challenging brain decoding tasks is the accurate reconstruction of the perceived natural images from brain activities measured by functional magnetic resonance imaging (fMRI). In this work, we survey the most recent deep learning methods for natural image reconstruction from fMRI. We examine these methods in terms of architectural design, benchmark datasets, and evaluation metrics and present a fair performance evaluation across standardized evaluation metrics. Finally, we discuss the strengths and limitations of existing studies and present potential future directions.
 [19] arXiv:2110.09143 (crosslist from stat.ME) [pdf, other]

Title: Variance Reduction in Stochastic Reaction Networks using Control VariatesComments: arXiv admin note: substantial text overlap with arXiv:1905.00854Subjects: Methodology (stat.ME); Systems and Control (eess.SY); Molecular Networks (qbio.MN); Quantitative Methods (qbio.QM)
Monte Carlo estimation in plays a crucial role in stochastic reaction networks. However, reducing the statistical uncertainty of the corresponding estimators requires sampling a large number of trajectories. We propose control variates based on the statistical moments of the process to reduce the estimators' variances. We develop an algorithm that selects an efficient subset of infinitely many control variates. To this end, the algorithm uses resampling and a redundancyaware greedy selection. We demonstrate the efficiency of our approach in several case studies.
 [20] arXiv:2110.09165 (crosslist from condmat.disnn) [pdf, other]

Title: A reservoir of timescales in random neural networksSubjects: Disordered Systems and Neural Networks (condmat.disnn); Chaotic Dynamics (nlin.CD); Neurons and Cognition (qbio.NC)
The temporal activity of many biological systems, including neural circuits, exhibits fluctuations simultaneously varying over a large range of timescales. The mechanisms leading to this temporal heterogeneity are yet unknown. Here we show that random neural networks endowed with a distribution of selfcouplings, representing functional neural clusters of different sizes, generate multiple timescales activity spanning several orders of magnitude. When driven by a timedependent broadband input, slow and fast neural clusters preferentially entrain slow and fast spectral components of the input, respectively, suggesting a potential mechanism for spectral demixing in cortical circuits.
 [21] arXiv:2110.09317 (crosslist from condmat.disnn) [pdf, other]

Title: Kclique percolation in free association networks. The mechanism behind the $7 \pm 2 $ law ?Subjects: Disordered Systems and Neural Networks (condmat.disnn); Neurons and Cognition (qbio.NC)
It is important to reveal the mechanisms of propagation in different cognitive networks. In this study we discuss the kclique percolation phenomenon on the free association networks including "English Small World of Words project" (SWOWEN). We compare different semantic networks and networks of free associations for different languages. Surprisingly it turned out that $k$clique percolation for all $k<k_c=(67)$ is possible on SWOWEN and Dutch language network. Our analysis suggests the new universality patterns for a community organization of free association networks. We conjecture that our result can provide the qualitative explanation of the Miller's $7\pm 2$ rule for the capacity limit of working memory. The new model of network evolution extending the preferential attachment is suggested which provides the observed value of $k_c$.
 [22] arXiv:2110.09473 (crosslist from eess.IV) [pdf, other]

Title: DBSegment: Fast and robust segmentation of deep brain structures  Evaluation of transportability across acquisition domainsAuthors: Mehri Baniasadi, Mikkel V. Petersen, Jorge Goncalves, Andreas Horn, Vanja Vlasov, Frank Hertel, Andreas HuschSubjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Neurons and Cognition (qbio.NC)
Segmenting deep brain structures from magnetic resonance images is important for patient diagnosis, surgical planning, and research. Most current stateoftheart solutions follow a segmentationbyregistration approach, where subject MRIs are mapped to a template with welldefined segmentations. However, registrationbased pipelines are timeconsuming, thus, limiting their clinical use. This paper uses deep learning to provide a robust and efficient deep brain segmentation solution. The method consists of a preprocessing step to conform all MRI images to the same orientation, followed by a convolutional neural network using the nnUNet framework. We use a total of 14 datasets from both research and clinical collections. Of these, seven were used for training and validation and seven were retained for independent testing. We trained the network to segment 30 deep brain structures, as well as a brain mask, using labels generated from a registrationbased approach. We evaluated the generalizability of the network by performing a leaveonedatasetout crossvalidation, and extensive testing on external datasets. Furthermore, we assessed crossdomain transportability by evaluating the results separately on different domains. We achieved an average DSC of 0.89 $\pm$ 0.04 on the independent testing datasets when compared to the registrationbased gold standard. On our test system, the computation time decreased from 42 minutes for a reference registrationbased pipeline to 1 minute. Our proposed method is fast, robust, and generalizes with high reliability. It can be extended to the segmentation of other brain structures. The method is publicly available on GitHub, as well as a pip package for convenient usage.
Replacements for Tue, 19 Oct 21
 [23] arXiv:2005.13074 (replaced) [pdf, other]

Title: Different eigenvalue distributions encode the same temporal tasks in recurrent neural networksAuthors: Cecilia JarneComments: 18 pages, 10 FiguresSubjects: Neurons and Cognition (qbio.NC); Disordered Systems and Neural Networks (condmat.disnn)
 [24] arXiv:2009.00664 (replaced) [pdf, other]

Title: VeRNAl: Mining RNA Structures for Fuzzy Base Pairing Network MotifsAuthors: Carlos Oliver, Vincent Mallet, Pericles Philippopoulos, William L. Hamilton, Jerome WaldispuhlSubjects: Molecular Networks (qbio.MN); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
 [25] arXiv:2102.07768 (replaced) [pdf, other]

Title: Distance to healthy cardiovascular dynamics from fetal heart rate scaledependent features in pregnant sheep model of human labor predicts cardiovascular decompensationComments: 34 pages (preprint version) 10 figuresJournalref: Frontiers in Pediatrics 9 p710 (2021)Subjects: Medical Physics (physics.medph); Quantitative Methods (qbio.QM)
 [26] arXiv:2105.05221 (replaced) [pdf, other]

Title: SHREC 2021: Retrieval and classification of protein surfaces equipped with physical and chemical propertiesAuthors: Andrea Raffo, Ulderico Fugacci, Silvia Biasotti, Walter Rocchia, Yonghuai Liu, Ekpo Otu, Reyer Zwiggelaar, David Hunter, Evangelia I. Zacharaki, Eleftheria Psatha, Dimitrios Laskos, Gerasimos Arvanitis, Konstantinos Moustakas, Tunde Aderinwale, Charles Christoffer, WoongHee Shin, Daisuke Kihara, Andrea Giachetti, HuuNghia Nguyen, TuanDuy Nguyen, VinhThuyen NguyenTruong, Danh LeThanh, HaiDang Nguyen, MinhTriet TranJournalref: Computers & Graphics 99 (2021) 121Subjects: Biomolecules (qbio.BM)
 [27] arXiv:2106.04427 (replaced) [pdf, other]

Title: On the relation between statistical learning and perceptual distancesSubjects: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Neurons and Cognition (qbio.NC)
 [28] arXiv:2110.00987 (replaced) [pdf, other]

Title: Motifbased Graph SelfSupervised Learning for Molecular Property PredictionComments: Accepted by NeurIPS'21Subjects: Quantitative Methods (qbio.QM); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
 [29] arXiv:2110.04624 (replaced) [pdf, other]

Title: Iterative Refinement Graph Neural Network for Antibody SequenceStructure CodesignSubjects: Biomolecules (qbio.BM); Machine Learning (cs.LG)
[ showing up to 2000 entries per page: fewer  more ]
Disable MathJax (What is MathJax?)
Links to: arXiv, form interface, find, qbio, recent, 2110, contact, help (Access key information)