Thanh Tung Khuat, Robert Bassett, Ellen Otte, Bogdan Gabrys
Biopharmaceutical products, particularly monoclonal antibodies (mAbs), have gained prominence in the pharmaceutical market due to their high specificity and efficacy. As these products are projected to constitute a substantial portion of global pharmaceutical sales, the application of machine learning models in mAb development and manufacturing is gaining momentum. This paper addresses the critical need for uncertainty quantification in machine learning predictions, particularly in scenarios with limited training data. Leveraging ensemble learning and Monte Carlo simulations, our proposed method generates additional input samples to enhance the robustness of the model in small training datasets. We evaluate the efficacy of our approach through two case studies: predicting antibody concentrations in advance and real-time monitoring of glucose concentrations during bioreactor runs using Raman spectra data. Our findings demonstrate the effectiveness of the proposed method in estimating the uncertainty levels associated with process performance predictions and facilitating real-time decision-making in biopharmaceutical manufacturing. This contribution not only introduces a novel approach for uncertainty quantification but also provides insights into overcoming challenges posed by small training datasets in bioprocess development. The evaluation demonstrates the effectiveness of our method in addressing key challenges related to uncertainty estimation within upstream cell cultivation, illustrating its potential impact on enhancing process control and product quality in the dynamic field of biopharmaceuticals.
生物制药产品，尤其是单克隆抗体（mAbs），因其高度的特异性和有效性而在医药市场中占据重要地位。由于这些产品预计将在全球药品销售中占据相当大的比例，因此机器学习模型在 mAb 开发和制造中的应用正日益壮大。本文探讨了机器学习预测中不确定性量化的关键需求，尤其是在训练数据有限的情况下。利用集合学习和蒙特卡罗模拟，我们提出的方法生成了额外的输入样本，以增强模型在小训练数据集中的鲁棒性。我们通过两个案例研究评估了我们方法的有效性：提前预测抗体浓度和使用拉曼光谱数据实时监控生物反应器运行过程中的葡萄糖浓度。我们的发现证明了所提出的方法在估算与工艺性能预测相关的不确定性水平和促进生物制药生产中的实时决策方面的有效性。这一贡献不仅为不确定性量化引入了一种新方法，还为克服生物工艺开发中因训练数据集较小而带来的挑战提供了见解。评估证明了我们的方法在解决上游细胞培养中与不确定性估计相关的关键挑战方面的有效性，说明了它对加强生物制药动态领域的过程控制和产品质量的潜在影响。
{"title":"Uncertainty Quantification Using Ensemble Learning and Monte Carlo Sampling for Performance Prediction and Monitoring in Cell Culture Processes","authors":"Thanh Tung Khuat, Robert Bassett, Ellen Otte, Bogdan Gabrys","doi":"arxiv-2409.02149","DOIUrl":"https://doi.org/arxiv-2409.02149","url":null,"abstract":"Biopharmaceutical products, particularly monoclonal antibodies (mAbs), have\u0000gained prominence in the pharmaceutical market due to their high specificity\u0000and efficacy. As these products are projected to constitute a substantial\u0000portion of global pharmaceutical sales, the application of machine learning\u0000models in mAb development and manufacturing is gaining momentum. This paper\u0000addresses the critical need for uncertainty quantification in machine learning\u0000predictions, particularly in scenarios with limited training data. Leveraging\u0000ensemble learning and Monte Carlo simulations, our proposed method generates\u0000additional input samples to enhance the robustness of the model in small\u0000training datasets. We evaluate the efficacy of our approach through two case\u0000studies: predicting antibody concentrations in advance and real-time monitoring\u0000of glucose concentrations during bioreactor runs using Raman spectra data. Our\u0000findings demonstrate the effectiveness of the proposed method in estimating the\u0000uncertainty levels associated with process performance predictions and\u0000facilitating real-time decision-making in biopharmaceutical manufacturing. This\u0000contribution not only introduces a novel approach for uncertainty\u0000quantification but also provides insights into overcoming challenges posed by\u0000small training datasets in bioprocess development. The evaluation demonstrates\u0000the effectiveness of our method in addressing key challenges related to\u0000uncertainty estimation within upstream cell cultivation, illustrating its\u0000potential impact on enhancing process control and product quality in the\u0000dynamic field of biopharmaceuticals.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The formation, dissolution, and dynamics of multi-particle complexes is of fundamental interest in the study of stochastic chemical systems. In 1976, Masao Doi introduced a Fock space formalism for modeling classical particles. Doi's formalism, however, does not support the assembly of multiple particles into complexes. Starting in the 2000's, multiple groups developed rule-based methods for computationally simulating biochemical systems involving large macromolecular complexes. However, these methods are based on graph-rewriting rules and/or process algebras that are mathematically disconnected from the statistical physics methods generally used to analyze equilibrium and nonequilibrium systems. Here we bridge these two approaches by introducing an operator algebra for the rule-based modeling of multi-particle complexes. Our formalism is based on a Fock space that supports not only the creation and annihilation of classical particles, but also the assembly of multiple particles into complexes, as well as the disassembly of complexes into their components. Rules are specified by algebraic operators that act on particles through a manifestation of Wick's theorem. We further describe diagrammatic methods that facilitate rule specification and analytic calculations. We demonstrate our formalism on systems in and out of thermal equilibrium, and for nonequilibrium systems we present a stochastic simulation algorithm based on our formalism. The results provide a unified approach to the mathematical and computational study of stochastic chemical systems in which multi-particle complexes play an important role.
{"title":"Algebraic and diagrammatic methods for the rule-based modeling of multi-particle complexes","authors":"Rebecca J. Rousseau, Justin B. Kinney","doi":"arxiv-2409.01529","DOIUrl":"https://doi.org/arxiv-2409.01529","url":null,"abstract":"The formation, dissolution, and dynamics of multi-particle complexes is of\u0000fundamental interest in the study of stochastic chemical systems. In 1976,\u0000Masao Doi introduced a Fock space formalism for modeling classical particles.\u0000Doi's formalism, however, does not support the assembly of multiple particles\u0000into complexes. Starting in the 2000's, multiple groups developed rule-based\u0000methods for computationally simulating biochemical systems involving large\u0000macromolecular complexes. However, these methods are based on graph-rewriting\u0000rules and/or process algebras that are mathematically disconnected from the\u0000statistical physics methods generally used to analyze equilibrium and\u0000nonequilibrium systems. Here we bridge these two approaches by introducing an\u0000operator algebra for the rule-based modeling of multi-particle complexes. Our\u0000formalism is based on a Fock space that supports not only the creation and\u0000annihilation of classical particles, but also the assembly of multiple\u0000particles into complexes, as well as the disassembly of complexes into their\u0000components. Rules are specified by algebraic operators that act on particles\u0000through a manifestation of Wick's theorem. We further describe diagrammatic\u0000methods that facilitate rule specification and analytic calculations. We\u0000demonstrate our formalism on systems in and out of thermal equilibrium, and for\u0000nonequilibrium systems we present a stochastic simulation algorithm based on\u0000our formalism. The results provide a unified approach to the mathematical and\u0000computational study of stochastic chemical systems in which multi-particle\u0000complexes play an important role.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"111 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Designing network parameters that can effectively represent complex networks is of significant importance for the analysis of time-varying complex networks. This paper introduces a novel thermodynamic framework for analyzing complex networks, focusing on Spectral Core Entropy (SCE), Node Energy, internal energy and temperature to measure structural changes in dynamic complex network. This framework provides a quantitative representation of network characteristics, capturing time-varying structural changes. We apply this framework to study brain activity in autism versus control subjects, illustrating its potential to identify significant structural changes and brain state transitions. By treating brain networks as thermodynamic systems, important parameters such as node energy and temperature are derived to depict brain activities. Our research has found that in our designed framework the thermodynamic parameter-temperature, is significantly correlated with the transitions of brain states. Statistical tests confirm the effectiveness of our approach. Moreover, our study demonstrates that node energy effectively captures the activity levels of brain regions and reveals biologically proven differences between autism patients and controls, offering a powerful tool for exploring the characteristics of complex networks in various applications.
{"title":"Exploring Neurofunctional Phase Transition Patterns in Autism Spectrum Disorder: A Thermodynamics Parameters Analysis Approach","authors":"Dayu Qin, Yuzhe Chen, Ercan Engin Kuruoglu","doi":"arxiv-2409.01039","DOIUrl":"https://doi.org/arxiv-2409.01039","url":null,"abstract":"Designing network parameters that can effectively represent complex networks\u0000is of significant importance for the analysis of time-varying complex networks.\u0000This paper introduces a novel thermodynamic framework for analyzing complex\u0000networks, focusing on Spectral Core Entropy (SCE), Node Energy, internal energy\u0000and temperature to measure structural changes in dynamic complex network. This\u0000framework provides a quantitative representation of network characteristics,\u0000capturing time-varying structural changes. We apply this framework to study\u0000brain activity in autism versus control subjects, illustrating its potential to\u0000identify significant structural changes and brain state transitions. By\u0000treating brain networks as thermodynamic systems, important parameters such as\u0000node energy and temperature are derived to depict brain activities. Our\u0000research has found that in our designed framework the thermodynamic\u0000parameter-temperature, is significantly correlated with the transitions of\u0000brain states. Statistical tests confirm the effectiveness of our approach.\u0000Moreover, our study demonstrates that node energy effectively captures the\u0000activity levels of brain regions and reveals biologically proven differences\u0000between autism patients and controls, offering a powerful tool for exploring\u0000the characteristics of complex networks in various applications.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ramón Nartallo-Kaluarachchi, Paul Expert, David Beers, Alexander Strang, Morten L. Kringelbach, Renaud Lambiotte, Alain Goriely
Disentangling irreversible and reversible forces from random fluctuations is a challenging problem in the analysis of stochastic trajectories measured from real-world dynamical systems. We present an approach to approximate the dynamics of a stationary Langevin process as a discrete-state Markov process evolving over a graph-representation of phase-space, reconstructed from stochastic trajectories. Next, we utilise the analogy of the Helmholtz-Hodge decomposition of an edge-flow on a contractible simplicial complex with the associated decomposition of a stochastic process into its irreversible and reversible parts. This allows us to decompose our reconstructed flow and to differentiate between the irreversible currents and reversible gradient flows underlying the stochastic trajectories. We validate our approach on a range of solvable and nonlinear systems and apply it to derive insight into the dynamics of flickering red-blood cells and healthy and arrhythmic heartbeats. In particular, we capture the difference in irreversible circulating currents between healthy and passive cells and healthy and arrhythmic heartbeats. Our method breaks new ground at the interface of data-driven approaches to stochastic dynamics and graph signal processing, with the potential for further applications in the analysis of biological experiments and physiological recordings. Finally, it prompts future analysis of the convergence of the Helmholtz-Hodge decomposition in discrete and continuous spaces.
{"title":"Decomposing force fields as flows on graphs reconstructed from stochastic trajectories","authors":"Ramón Nartallo-Kaluarachchi, Paul Expert, David Beers, Alexander Strang, Morten L. Kringelbach, Renaud Lambiotte, Alain Goriely","doi":"arxiv-2409.07479","DOIUrl":"https://doi.org/arxiv-2409.07479","url":null,"abstract":"Disentangling irreversible and reversible forces from random fluctuations is\u0000a challenging problem in the analysis of stochastic trajectories measured from\u0000real-world dynamical systems. We present an approach to approximate the\u0000dynamics of a stationary Langevin process as a discrete-state Markov process\u0000evolving over a graph-representation of phase-space, reconstructed from\u0000stochastic trajectories. Next, we utilise the analogy of the Helmholtz-Hodge\u0000decomposition of an edge-flow on a contractible simplicial complex with the\u0000associated decomposition of a stochastic process into its irreversible and\u0000reversible parts. This allows us to decompose our reconstructed flow and to\u0000differentiate between the irreversible currents and reversible gradient flows\u0000underlying the stochastic trajectories. We validate our approach on a range of\u0000solvable and nonlinear systems and apply it to derive insight into the dynamics\u0000of flickering red-blood cells and healthy and arrhythmic heartbeats. In\u0000particular, we capture the difference in irreversible circulating currents\u0000between healthy and passive cells and healthy and arrhythmic heartbeats. Our\u0000method breaks new ground at the interface of data-driven approaches to\u0000stochastic dynamics and graph signal processing, with the potential for further\u0000applications in the analysis of biological experiments and physiological\u0000recordings. Finally, it prompts future analysis of the convergence of the\u0000Helmholtz-Hodge decomposition in discrete and continuous spaces.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"104 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tim Jakobi, Simon Watkins, Alex Fisher, Sridhar Ravi
Insects excel in trajectory and attitude handling during flight, yet the specific kinematic behaviours they use for maintaining stability in air disturbances are not fully understood. This study investigates the adaptive strategies of bumblebees when exposed to gust disturbances directed from three different angles within a plane cross-sectional to their flight path. By analyzing characteristic wing motions during gust traversal, we aim to uncover the mechanisms that enable bumblebees to maintain control in unsteady environments. We utilised high-speed cameras to capture detailed flight paths, allowing us to extract dynamic information. Our results reveal that bees make differential bilateral kinematic adjustments based on gust direction: sideward gusts elicit posterior shifts in the wing closest to the gust, while upward gusts trigger coordinated posterior shifts in both wings. Downward gusts prompted broader flapping and increased flapping frequencies, along with variations in flap timing and sweep angle. Stroke sweep angle was a primary factor influencing recovery responses, coupled with motion around the flap axis. The adaptive behaviours strategically position the wings to optimize gust reception and enhance wing-generated forces. These strategies can be distilled into specific behavioural patterns for analytical modelling to inform the design of robotic flyers. We observed a characteristic posterior shift of wings when particular counteractive manoeuvres were required. This adjustment reduced the portion of the stroke during which the wing receiving gust forces was positioned in front of the centre of gravity, potentially enhancing manoeuvrability and enabling more effective recovery manoeuvres. These findings deepen our understanding of insect flight dynamics and offer promising strategies for enhancing the stability and manoeuvrability of MAVs in turbulent environments.
{"title":"Bumblebees Exhibit Adaptive Flapping Responses to Air Disturbances","authors":"Tim Jakobi, Simon Watkins, Alex Fisher, Sridhar Ravi","doi":"arxiv-2409.01299","DOIUrl":"https://doi.org/arxiv-2409.01299","url":null,"abstract":"Insects excel in trajectory and attitude handling during flight, yet the\u0000specific kinematic behaviours they use for maintaining stability in air\u0000disturbances are not fully understood. This study investigates the adaptive\u0000strategies of bumblebees when exposed to gust disturbances directed from three\u0000different angles within a plane cross-sectional to their flight path. By\u0000analyzing characteristic wing motions during gust traversal, we aim to uncover\u0000the mechanisms that enable bumblebees to maintain control in unsteady\u0000environments. We utilised high-speed cameras to capture detailed flight paths,\u0000allowing us to extract dynamic information. Our results reveal that bees make\u0000differential bilateral kinematic adjustments based on gust direction: sideward\u0000gusts elicit posterior shifts in the wing closest to the gust, while upward\u0000gusts trigger coordinated posterior shifts in both wings. Downward gusts\u0000prompted broader flapping and increased flapping frequencies, along with\u0000variations in flap timing and sweep angle. Stroke sweep angle was a primary\u0000factor influencing recovery responses, coupled with motion around the flap\u0000axis. The adaptive behaviours strategically position the wings to optimize gust\u0000reception and enhance wing-generated forces. These strategies can be distilled\u0000into specific behavioural patterns for analytical modelling to inform the\u0000design of robotic flyers. We observed a characteristic posterior shift of wings\u0000when particular counteractive manoeuvres were required. This adjustment reduced\u0000the portion of the stroke during which the wing receiving gust forces was\u0000positioned in front of the centre of gravity, potentially enhancing\u0000manoeuvrability and enabling more effective recovery manoeuvres. These findings\u0000deepen our understanding of insect flight dynamics and offer promising\u0000strategies for enhancing the stability and manoeuvrability of MAVs in turbulent\u0000environments.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pedro MateusDepartment of Radiation Oncology, Swier GarstSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the NetherlandsDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jing YuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Davy CatsSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Alexander G. J. HarmsBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Mahlet BirhanuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Marian BeekmanSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, P. Eline SlagboomSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Marcel ReindersDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jeroen van der GrondDepartment of Radiology, Leiden University Medical Center, Leiden, the Netherlands, Andre DekkerDepartment of Radiation Oncology, Jacobus F. A. JansenDepartment of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the NetherlandsMental Health & Neuroscience Research Institute, Maastricht University, Maastricht, the NetherlandsDepartment of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands, Magdalena BeranDepartment of Internal Medicine, School for Cardiovascular Diseases, Miranda T. SchramDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Internal Medicine, School for Cardiovascular Diseases, Pieter Jelle VisserAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the Netherlands, Justine MoonenAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the NetherlandsAmsterdam Neuroscience, Neurodegeneration, Amsterdam, The Netherlands, Mohsen GhanbariDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Gennady RoshchupkinBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Dina VojinovicDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Inigo BermejoDepartment of Radiation Oncology, Hailiang MeiSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Esther E. BronBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands
Biological age scores are an emerging tool to characterize aging by estimating chronological age based on physiological biomarkers. Various scores have shown associations with aging-related outcomes. This study assessed the relation between an age score based on brain MRI images (BrainAge) and an age score based on metabolomic biomarkers (MetaboAge). We trained a federated deep learning model to estimate BrainAge in three cohorts. The federated BrainAge model yielded significantly lower error for age prediction across the cohorts than locally trained models. Harmonizing the age interval between cohorts further improved BrainAge accuracy. Subsequently, we compared BrainAge with MetaboAge using federated association and survival analyses. The results showed a small association between BrainAge and MetaboAge as well as a higher predictive value for the time to mortality of both scores combined than for the individual scores. Hence, our study suggests that both aging scores capture different aspects of the aging process.
{"title":"MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning","authors":"Pedro MateusDepartment of Radiation Oncology, Swier GarstSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the NetherlandsDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jing YuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Davy CatsSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Alexander G. J. HarmsBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Mahlet BirhanuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Marian BeekmanSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, P. Eline SlagboomSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Marcel ReindersDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jeroen van der GrondDepartment of Radiology, Leiden University Medical Center, Leiden, the Netherlands, Andre DekkerDepartment of Radiation Oncology, Jacobus F. A. JansenDepartment of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the NetherlandsMental Health & Neuroscience Research Institute, Maastricht University, Maastricht, the NetherlandsDepartment of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands, Magdalena BeranDepartment of Internal Medicine, School for Cardiovascular Diseases, Miranda T. SchramDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Internal Medicine, School for Cardiovascular Diseases, Pieter Jelle VisserAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the Netherlands, Justine MoonenAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the NetherlandsAmsterdam Neuroscience, Neurodegeneration, Amsterdam, The Netherlands, Mohsen GhanbariDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Gennady RoshchupkinBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Dina VojinovicDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Inigo BermejoDepartment of Radiation Oncology, Hailiang MeiSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Esther E. BronBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands","doi":"arxiv-2409.01235","DOIUrl":"https://doi.org/arxiv-2409.01235","url":null,"abstract":"Biological age scores are an emerging tool to characterize aging by\u0000estimating chronological age based on physiological biomarkers. Various scores\u0000have shown associations with aging-related outcomes. This study assessed the\u0000relation between an age score based on brain MRI images (BrainAge) and an age\u0000score based on metabolomic biomarkers (MetaboAge). We trained a federated deep\u0000learning model to estimate BrainAge in three cohorts. The federated BrainAge\u0000model yielded significantly lower error for age prediction across the cohorts\u0000than locally trained models. Harmonizing the age interval between cohorts\u0000further improved BrainAge accuracy. Subsequently, we compared BrainAge with\u0000MetaboAge using federated association and survival analyses. The results showed\u0000a small association between BrainAge and MetaboAge as well as a higher\u0000predictive value for the time to mortality of both scores combined than for the\u0000individual scores. Hence, our study suggests that both aging scores capture\u0000different aspects of the aging process.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Protein function prediction is a crucial task in bioinformatics, with significant implications for understanding biological processes and disease mechanisms. While the relationship between sequence and function has been extensively explored, translating protein structure to function continues to present substantial challenges. Various models, particularly, CNN and graph-based deep learning approaches that integrate structural and functional data, have been proposed to address these challenges. However, these methods often fall short in elucidating the functional significance of key residues essential for protein functionality, as they predominantly adopt a retrospective perspective, leading to suboptimal performance. Inspired by region proposal networks in computer vision, we introduce the Protein Region Proposal Network (ProteinRPN) for accurate protein function prediction. Specifically, the region proposal module component of ProteinRPN identifies potential functional regions (anchors) which are refined through the hierarchy-aware node drop pooling layer favoring nodes with defined secondary structures and spatial proximity. The representations of the predicted functional nodes are enriched using attention mechanisms and subsequently fed into a Graph Multiset Transformer, which is trained with supervised contrastive (SupCon) and InfoNCE losses on perturbed protein structures. Our model demonstrates significant improvements in predicting Gene Ontology (GO) terms, effectively localizing functional residues within protein structures. The proposed framework provides a robust, scalable solution for protein function annotation, advancing the understanding of protein structure-function relationships in computational biology.
蛋白质功能预测是生物信息学的一项重要任务，对了解生物过程和疾病机制具有重要意义。虽然序列与功能之间的关系已被广泛探索，但将蛋白质结构转化为功能仍面临巨大挑战。为了应对这些挑战，人们提出了各种模型，特别是整合了结构和功能数据的 CNN 和基于图谱的深度学习方法。然而，这些方法在阐明对蛋白质功能至关重要的关键残基的功能意义方面往往存在不足，因为它们主要采用的是回顾性视角，导致性能不理想。受计算机视觉中区域提议网络的启发，我们引入了用于准确预测蛋白质功能的蛋白质区域提议网络（ProteinRPN）。具体来说，ProteinRPN 的区域建议模块组件识别潜在的功能区域（锚点），并通过层级感知的节点丢弃池层（node drop pooling layer）对这些锚点进行细化，优先选择具有确定次级结构和空间邻近性的节点。预测功能节点的表征通过注意力机制得到丰富，随后输入到图形多集变换器中，该变换器通过对扰动蛋白质结构的监督对比（SupCon）和 InfoNCE 损失进行训练。我们的模型证明了在预测基因本体（GO）术语方面的显著改进，有效地定位了蛋白质结构中的功能残基。所提出的框架为蛋白质功能注释提供了一个稳健、可扩展的解决方案，推动了计算生物学对蛋白质结构-功能关系的理解。
{"title":"ProteinRPN: Towards Accurate Protein Function Prediction with Graph-Based Region Proposals","authors":"Shania Mitra, Lei Huang, Manolis Kellis","doi":"arxiv-2409.00610","DOIUrl":"https://doi.org/arxiv-2409.00610","url":null,"abstract":"Protein function prediction is a crucial task in bioinformatics, with\u0000significant implications for understanding biological processes and disease\u0000mechanisms. While the relationship between sequence and function has been\u0000extensively explored, translating protein structure to function continues to\u0000present substantial challenges. Various models, particularly, CNN and\u0000graph-based deep learning approaches that integrate structural and functional\u0000data, have been proposed to address these challenges. However, these methods\u0000often fall short in elucidating the functional significance of key residues\u0000essential for protein functionality, as they predominantly adopt a\u0000retrospective perspective, leading to suboptimal performance. Inspired by region proposal networks in computer vision, we introduce the\u0000Protein Region Proposal Network (ProteinRPN) for accurate protein function\u0000prediction. Specifically, the region proposal module component of ProteinRPN\u0000identifies potential functional regions (anchors) which are refined through the\u0000hierarchy-aware node drop pooling layer favoring nodes with defined secondary\u0000structures and spatial proximity. The representations of the predicted\u0000functional nodes are enriched using attention mechanisms and subsequently fed\u0000into a Graph Multiset Transformer, which is trained with supervised contrastive\u0000(SupCon) and InfoNCE losses on perturbed protein structures. Our model\u0000demonstrates significant improvements in predicting Gene Ontology (GO) terms,\u0000effectively localizing functional residues within protein structures. The\u0000proposed framework provides a robust, scalable solution for protein function\u0000annotation, advancing the understanding of protein structure-function\u0000relationships in computational biology.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"203 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rheumatoid arthritis (RA) has an intricate etiology that includes environmental factors as well as genetics. Organophosphate esters (OPEs) are frequently used as chemical additives in many personal care products and household items. However, there has been limited research on their potential effects on rheumatoid arthritis (RA). The specific associations between OPEs and RA remain largely unexplored. This study investigates any potential associations between adult rheumatoid arthritis risk and exposure to OPEs. We investigated data from the National Health and Nutrition Examination Survey (NHANES) 2011-2018 among participants over 20 years old. In two models, multivariable logistic regression was utilized to investigate the relationship between exposure to OPEs and RA. Furthermore, subgroup analyses stratified by age, gender, and dose exposure response were evaluated. Generalized additive models and smooth curve fits were used to characterize the nonlinear relationship between RA and OPEs. In conclusion, 5490 individuals (RA: 319, Non-RA: 5171) were analyzed. Higher quantiles (Q4) of DPHP and DBUP showed a higher prevalence of RA than the lowest quantiles. Our findings show that adult RA prevalence is higher in those who have been exposed to OPEs (DPHP, DBUP). These correlations seem to be stronger among women, the elderly, those with higher BMIs, and those who have diabetes. The dose-response curve for DPHP and DBUP demonstrated an upward-sloping trend. In contrast, BCEP and BCPP showed a U-shaped relationship and an inverted U-shaped relationship with the probability of RA. BDCPP demonstrates a complex relationship with a peak at lower concentrations followed by a decrease. Our study concludes that exposure to OPEs plays a crucial role in the pathogenesis of RA.
类风湿性关节炎（RA）的病因错综复杂，包括环境因素和遗传因素。有机磷酸酯（OPEs）是许多个人护理产品和家居用品中经常使用的化学添加剂。然而，有关它们对类风湿性关节炎（RA）潜在影响的研究却十分有限。OPE 与类风湿性关节炎之间的具体关联在很大程度上仍未得到探讨。本研究调查了成人类风湿性关节炎风险与暴露于 OPE 之间的潜在关联。我们调查了 2011-2018 年美国国家健康与营养调查（NHANES）中 20 岁以上参与者的数据。在两个模型中，我们利用多变量逻辑回归研究了暴露于OPE与RA之间的关系。此外，还评估了按年龄、性别和剂量暴露反应分层的亚组分析。使用广义加法模型和平滑曲线拟合来描述 RA 与 OPE 之间的非线性关系。最后，对 5490 人（RA：319 人，非 RA：5171 人）进行了分析。DPHP和DBUP的较高量值（Q4）比最低量值显示出更高的RA患病率。我们的研究结果表明，接触过 OPEs（DPHP、DBUP）的人群中，成人 RA 患病率较高；女性、老年人、体重指数（BMI）较高的人群和糖尿病患者的相关性似乎更强。DPHP 和 DBUP 的剂量反应曲线呈上升趋势。相比之下，BCEP 和 BCPP 与发生 RA 的概率呈 U 型关系和倒 U 型关系。BDCPP 显示出一种复杂的关系，在浓度较低时达到峰值，随后下降。我们的研究得出结论，暴露于 OPEs 在 RA 的发病机制中起着至关重要的作用。
{"title":"Associations between exposure to OPEs and rheumatoid arthritis risk among adults in NHANES, 2011-2018","authors":"Sneha Singh, Elsa Pirouz, Amir Shahmoradi","doi":"arxiv-2409.00745","DOIUrl":"https://doi.org/arxiv-2409.00745","url":null,"abstract":"Rheumatoid arthritis (RA) has an intricate etiology that includes\u0000environmental factors as well as genetics. Organophosphate esters (OPEs) are\u0000frequently used as chemical additives in many personal care products and\u0000household items. However, there has been limited research on their potential\u0000effects on rheumatoid arthritis (RA). The specific associations between OPEs\u0000and RA remain largely unexplored. This study investigates any potential\u0000associations between adult rheumatoid arthritis risk and exposure to OPEs. We\u0000investigated data from the National Health and Nutrition Examination Survey\u0000(NHANES) 2011-2018 among participants over 20 years old. In two models,\u0000multivariable logistic regression was utilized to investigate the relationship\u0000between exposure to OPEs and RA. Furthermore, subgroup analyses stratified by\u0000age, gender, and dose exposure response were evaluated. Generalized additive\u0000models and smooth curve fits were used to characterize the nonlinear\u0000relationship between RA and OPEs. In conclusion, 5490 individuals (RA: 319,\u0000Non-RA: 5171) were analyzed. Higher quantiles (Q4) of DPHP and DBUP showed a\u0000higher prevalence of RA than the lowest quantiles. Our findings show that adult\u0000RA prevalence is higher in those who have been exposed to OPEs (DPHP, DBUP).\u0000These correlations seem to be stronger among women, the elderly, those with\u0000higher BMIs, and those who have diabetes. The dose-response curve for DPHP and\u0000DBUP demonstrated an upward-sloping trend. In contrast, BCEP and BCPP showed a\u0000U-shaped relationship and an inverted U-shaped relationship with the\u0000probability of RA. BDCPP demonstrates a complex relationship with a peak at\u0000lower concentrations followed by a decrease. Our study concludes that exposure\u0000to OPEs plays a crucial role in the pathogenesis of RA.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alessandro Dutto, Anton Kan, Zoubeir Saraw, Aline Maillard, Daniel Zindel, André R. Studart
Microorganisms hosted in abiotic structures have led to engineered living materials that can grow, sense and adapt in ways that mimic biological systems. Although porous structures should favor colonization by microorganisms, they have not yet been exploited as abiotic scaffolds for the development of living materials. Here, we report porous ceramics that are colonized by bacteria to form an engineered living material with self-regulated and genetically programmable carbon capture and gas-sensing functionalities. The carbon capture capability is achieved using wild-type photosynthetic cyanobacteria, whereas the gas-sensing function is generated utilizing genetically engineered E. coli. Hierarchical porous clay is used as ceramic scaffold and evaluated in terms of bacterial growth, water uptake and mechanical properties. Using state-of-the-art chemical analysis techniques, we demonstrate the ability of the living porous ceramics to capture CO2 directly from the air and to metabolically turn minute amounts of a toxic gas into a benign scent detectable by humans.
{"title":"Living porous ceramics for bacteria-regulated gas sensing and carbon capture","authors":"Alessandro Dutto, Anton Kan, Zoubeir Saraw, Aline Maillard, Daniel Zindel, André R. Studart","doi":"arxiv-2409.00789","DOIUrl":"https://doi.org/arxiv-2409.00789","url":null,"abstract":"Microorganisms hosted in abiotic structures have led to engineered living\u0000materials that can grow, sense and adapt in ways that mimic biological systems.\u0000Although porous structures should favor colonization by microorganisms, they\u0000have not yet been exploited as abiotic scaffolds for the development of living\u0000materials. Here, we report porous ceramics that are colonized by bacteria to\u0000form an engineered living material with self-regulated and genetically\u0000programmable carbon capture and gas-sensing functionalities. The carbon capture\u0000capability is achieved using wild-type photosynthetic cyanobacteria, whereas\u0000the gas-sensing function is generated utilizing genetically engineered E. coli.\u0000Hierarchical porous clay is used as ceramic scaffold and evaluated in terms of\u0000bacterial growth, water uptake and mechanical properties. Using\u0000state-of-the-art chemical analysis techniques, we demonstrate the ability of\u0000the living porous ceramics to capture CO2 directly from the air and to\u0000metabolically turn minute amounts of a toxic gas into a benign scent detectable\u0000by humans.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, we explore the application of Physics-Informed Neural Networks (PINNs) to the analysis of bifurcation phenomena in ecological migration models. By integrating the fundamental principles of diffusion-advection-reaction equations with deep learning techniques, we address the complexities of species migration dynamics, particularly focusing on the detection and analysis of Hopf bifurcations. Traditional numerical methods for solving partial differential equations (PDEs) often involve intricate calculations and extensive computational resources, which can be restrictive in high-dimensional problems. In contrast, PINNs offer a more flexible and efficient alternative, bypassing the need for grid discretization and allowing for mesh-free solutions. Our approach leverages the DeepXDE framework, which enhances the computational efficiency and applicability of PINNs in solving high-dimensional PDEs. We validate our results against conventional methods and demonstrate that PINNs not only provide accurate bifurcation predictions but also offer deeper insights into the underlying dynamics of diffusion processes. Despite these advantages, the study also identifies challenges such as the high computational costs and the sensitivity of PINN performance to network architecture and hyperparameter settings. Future work will focus on optimizing these algorithms and expanding their application to other complex systems involving bifurcations. The findings from this research have significant implications for the modeling and analysis of ecological systems, providing a powerful tool for predicting and understanding complex dynamical behaviors.
{"title":"Adapting Physics-Informed Neural Networks for Bifurcation Detection in Ecological Migration Models","authors":"Lujie Yin, Xing Lv","doi":"arxiv-2409.00651","DOIUrl":"https://doi.org/arxiv-2409.00651","url":null,"abstract":"In this study, we explore the application of Physics-Informed Neural Networks\u0000(PINNs) to the analysis of bifurcation phenomena in ecological migration\u0000models. By integrating the fundamental principles of\u0000diffusion-advection-reaction equations with deep learning techniques, we\u0000address the complexities of species migration dynamics, particularly focusing\u0000on the detection and analysis of Hopf bifurcations. Traditional numerical\u0000methods for solving partial differential equations (PDEs) often involve\u0000intricate calculations and extensive computational resources, which can be\u0000restrictive in high-dimensional problems. In contrast, PINNs offer a more\u0000flexible and efficient alternative, bypassing the need for grid discretization\u0000and allowing for mesh-free solutions. Our approach leverages the DeepXDE\u0000framework, which enhances the computational efficiency and applicability of\u0000PINNs in solving high-dimensional PDEs. We validate our results against\u0000conventional methods and demonstrate that PINNs not only provide accurate\u0000bifurcation predictions but also offer deeper insights into the underlying\u0000dynamics of diffusion processes. Despite these advantages, the study also\u0000identifies challenges such as the high computational costs and the sensitivity\u0000of PINN performance to network architecture and hyperparameter settings. Future\u0000work will focus on optimizing these algorithms and expanding their application\u0000to other complex systems involving bifurcations. The findings from this\u0000research have significant implications for the modeling and analysis of\u0000ecological systems, providing a powerful tool for predicting and understanding\u0000complex dynamical behaviors.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"94 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：