Lithium salts have strong medical properties in neurological disorders such as bipolar disorder and primary headaches, and has recently gathered attention due to its preventive effect on viral attacks. Though the therapeutic effect of lithium was documented by Cade already in the late 1940s, the underlying mechanism of action is still disputed. Acute lithium exposure has an activating effect on excitable organic tissue and organisms, and is highly toxic. The therapeutic effect is achieved through long-term exposure to lower doses, where it, opposite to acute doses, alleviates excessive cellular activity, and induces a strong metabolic response in the organism, with large changes in phospholipid and cholesterol expression. This review investigates how lithium ions affect membrane composition and function, and how lithium response might in fact be the body's attempt to counteract the physical presence of lithium ions at cell level. The presence of lithium ions strongly affects lipid conformation and membrane phase unlike other alkali ions, with consequences for membrane permeability, buffer property and excitability, and ideas for further research in microbiology and drug development are discussed.
{"title":"A physical perspective on lithium therapy","authors":"Dana Kamp","doi":"arxiv-2409.04455","DOIUrl":"https://doi.org/arxiv-2409.04455","url":null,"abstract":"Lithium salts have strong medical properties in neurological disorders such\u0000as bipolar disorder and primary headaches, and has recently gathered attention\u0000due to its preventive effect on viral attacks. Though the therapeutic effect of\u0000lithium was documented by Cade already in the late 1940s, the underlying\u0000mechanism of action is still disputed. Acute lithium exposure has an activating\u0000effect on excitable organic tissue and organisms, and is highly toxic. The\u0000therapeutic effect is achieved through long-term exposure to lower doses, where\u0000it, opposite to acute doses, alleviates excessive cellular activity, and\u0000induces a strong metabolic response in the organism, with large changes in\u0000phospholipid and cholesterol expression. This review investigates how lithium ions affect membrane composition and\u0000function, and how lithium response might in fact be the body's attempt to\u0000counteract the physical presence of lithium ions at cell level. The presence of\u0000lithium ions strongly affects lipid conformation and membrane phase unlike\u0000other alkali ions, with consequences for membrane permeability, buffer property\u0000and excitability, and ideas for further research in microbiology and drug\u0000development are discussed.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213354","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}
This work presents the INBD network proposed by Gillert et al. in CVPR-2023 and studies its application for delineating tree rings in RGB images of Pinus taeda cross sections captured by a smartphone (UruDendro dataset), which are images with different characteristics from the ones used to train the method. The INBD network operates in two stages: first, it segments the background, pith, and ring boundaries. In the second stage, the image is transformed into polar coordinates, and ring boundaries are iteratively segmented from the pith to the bark. Both stages are based on the U-Net architecture. The method achieves an F-Score of 77.5, a mAR of 0.540, and an ARAND of 0.205 on the evaluation set. The code for the experiments is available at https://github.com/hmarichal93/mlbrief_inbd.
{"title":"A Brief Analysis of the Iterative Next Boundary Detection Network for Tree Rings Delineation in Images of Pinus taeda","authors":"Henry Marichal, Gregory Randall","doi":"arxiv-2408.14343","DOIUrl":"https://doi.org/arxiv-2408.14343","url":null,"abstract":"This work presents the INBD network proposed by Gillert et al. in CVPR-2023\u0000and studies its application for delineating tree rings in RGB images of Pinus\u0000taeda cross sections captured by a smartphone (UruDendro dataset), which are\u0000images with different characteristics from the ones used to train the method.\u0000The INBD network operates in two stages: first, it segments the background,\u0000pith, and ring boundaries. In the second stage, the image is transformed into\u0000polar coordinates, and ring boundaries are iteratively segmented from the pith\u0000to the bark. Both stages are based on the U-Net architecture. The method\u0000achieves an F-Score of 77.5, a mAR of 0.540, and an ARAND of 0.205 on the\u0000evaluation set. The code for the experiments is available at\u0000https://github.com/hmarichal93/mlbrief_inbd.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"104 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213384","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}
Regulation of cell growth and division is essential to achieve cell-size homeostasis. Recent advances in imaging technologies, such as ``mother machines" for bacteria or yeast, have allowed long-term tracking of cell-size dynamics across many generations, and thus have brought major insights into the mechanisms underlying cell-size control. However, understanding the governing rules of cell growth and division within a quantitative dynamical-systems framework remains a major challenge. Here, we implement and apply a framework that makes it possible to infer stochastic differential equation (SDE) models with Poisson noise directly from experimentally measured time series for cellular growth and divisions. To account for potential nonlinear memory effects, we parameterize the Poisson intensity of stochastic cell division events in terms of both the cell's current size and its ancestral history. By applying the algorithm to experimentally measured cell size trajectories, we are able to quantitatively evaluate the linear one-step memory hypothesis underlying the popular ``sizer",``adder", and ``timer" models of cell homeostasis. For Escherichia coli and Bacillus subtilis bacteria, Schizosaccharomyces pombe yeast and Dictyostelium discoideum amoebae, we find that in many cases the inferred stochastic models have a substantial nonlinear memory component. This suggests a need to reevaluate and generalize the currently prevailing linear-memory paradigm of cell homeostasis. More broadly, the underlying inference framework is directly applicable to identify quantitative models for stochastic jump processes in a wide range of scientific disciplines.
{"title":"Nonlinear memory in cell division dynamics across species","authors":"Shijie Zhang, Chenyi Fei, Jörn Dunkel","doi":"arxiv-2408.14564","DOIUrl":"https://doi.org/arxiv-2408.14564","url":null,"abstract":"Regulation of cell growth and division is essential to achieve cell-size\u0000homeostasis. Recent advances in imaging technologies, such as ``mother\u0000machines\" for bacteria or yeast, have allowed long-term tracking of cell-size\u0000dynamics across many generations, and thus have brought major insights into the\u0000mechanisms underlying cell-size control. However, understanding the governing\u0000rules of cell growth and division within a quantitative dynamical-systems\u0000framework remains a major challenge. Here, we implement and apply a framework\u0000that makes it possible to infer stochastic differential equation (SDE) models\u0000with Poisson noise directly from experimentally measured time series for\u0000cellular growth and divisions. To account for potential nonlinear memory\u0000effects, we parameterize the Poisson intensity of stochastic cell division\u0000events in terms of both the cell's current size and its ancestral history. By\u0000applying the algorithm to experimentally measured cell size trajectories, we\u0000are able to quantitatively evaluate the linear one-step memory hypothesis\u0000underlying the popular ``sizer\",``adder\", and ``timer\" models of cell\u0000homeostasis. For Escherichia coli and Bacillus subtilis bacteria,\u0000Schizosaccharomyces pombe yeast and Dictyostelium discoideum amoebae, we find\u0000that in many cases the inferred stochastic models have a substantial nonlinear\u0000memory component. This suggests a need to reevaluate and generalize the\u0000currently prevailing linear-memory paradigm of cell homeostasis. More broadly,\u0000the underlying inference framework is directly applicable to identify\u0000quantitative models for stochastic jump processes in a wide range of scientific\u0000disciplines.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213329","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}
Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evolutionary studies. Addressing the inherent complexities, we introduce a new approach to annotating enzymes based on their catalyzed reactions. This method provides detailed insights into specific reactions and is adaptable to newly discovered reactions, diverging from traditional classifications by protein family or expert-derived reaction classes. We employ machine learning algorithms to analyze enzyme reaction datasets, delivering a much more refined view on the functionality of enzymes. Our evaluation leverages the largest enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases with entries up to January 8, 2024. We frame the enzyme-reaction prediction as a retrieval problem, aiming to rank enzymes by their catalytic ability for specific reactions. With our model, we can recruit proteins for novel reactions and predict reactions in novel proteins, facilitating enzyme discovery and function annotation.
{"title":"Reactzyme: A Benchmark for Enzyme-Reaction Prediction","authors":"Chenqing Hua, Bozitao Zhong, Sitao Luan, Liang Hong, Guy Wolf, Doina Precup, Shuangjia Zheng","doi":"arxiv-2408.13659","DOIUrl":"https://doi.org/arxiv-2408.13659","url":null,"abstract":"Enzymes, with their specific catalyzed reactions, are necessary for all\u0000aspects of life, enabling diverse biological processes and adaptations.\u0000Predicting enzyme functions is essential for understanding biological pathways,\u0000guiding drug development, enhancing bioproduct yields, and facilitating\u0000evolutionary studies. Addressing the inherent complexities, we introduce a new\u0000approach to annotating enzymes based on their catalyzed reactions. This method\u0000provides detailed insights into specific reactions and is adaptable to newly\u0000discovered reactions, diverging from traditional classifications by protein\u0000family or expert-derived reaction classes. We employ machine learning\u0000algorithms to analyze enzyme reaction datasets, delivering a much more refined\u0000view on the functionality of enzymes. Our evaluation leverages the largest\u0000enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases\u0000with entries up to January 8, 2024. We frame the enzyme-reaction prediction as\u0000a retrieval problem, aiming to rank enzymes by their catalytic ability for\u0000specific reactions. With our model, we can recruit proteins for novel reactions\u0000and predict reactions in novel proteins, facilitating enzyme discovery and\u0000function annotation.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213585","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}
Drug repurposing offers a promising avenue for accelerating drug development by identifying new therapeutic potentials of existing drugs. In this paper, we propose a multi-agent framework to enhance the drug repurposing process using state-of-the-art machine learning techniques and knowledge integration. Our framework comprises several specialized agents: an AI Agent trains robust drug-target interaction (DTI) models; a Knowledge Graph Agent utilizes the drug-gene interaction database (DGIdb), DrugBank, Comparative Toxicogenomics Database (CTD), and Search Tool for Interactions of Chemicals (STITCH) to systematically extract DTIs; and a Search Agent interacts with biomedical literature to annotate and verify computational predictions. By integrating outputs from these agents, our system effectively harnesses diverse data sources, including external databases, to propose viable repurposing candidates. Preliminary results demonstrate the potential of our approach in not only predicting drug-disease interactions but also in reducing the time and cost associated with traditional drug discovery methods. This paper highlights the scalability of multi-agent systems in biomedical research and their role in driving innovation in drug repurposing. Our approach not only outperforms existing methods in predicting drug repurposing potential but also provides interpretable results, paving the way for more efficient and cost-effective drug discovery processes.
{"title":"DrugAgent: Explainable Drug Repurposing Agent with Large Language Model-based Reasoning","authors":"Yoshitaka Inoue, Tianci Song, Tianfan Fu","doi":"arxiv-2408.13378","DOIUrl":"https://doi.org/arxiv-2408.13378","url":null,"abstract":"Drug repurposing offers a promising avenue for accelerating drug development\u0000by identifying new therapeutic potentials of existing drugs. In this paper, we\u0000propose a multi-agent framework to enhance the drug repurposing process using\u0000state-of-the-art machine learning techniques and knowledge integration. Our\u0000framework comprises several specialized agents: an AI Agent trains robust\u0000drug-target interaction (DTI) models; a Knowledge Graph Agent utilizes the\u0000drug-gene interaction database (DGIdb), DrugBank, Comparative Toxicogenomics\u0000Database (CTD), and Search Tool for Interactions of Chemicals (STITCH) to\u0000systematically extract DTIs; and a Search Agent interacts with biomedical\u0000literature to annotate and verify computational predictions. By integrating\u0000outputs from these agents, our system effectively harnesses diverse data\u0000sources, including external databases, to propose viable repurposing\u0000candidates. Preliminary results demonstrate the potential of our approach in\u0000not only predicting drug-disease interactions but also in reducing the time and\u0000cost associated with traditional drug discovery methods. This paper highlights\u0000the scalability of multi-agent systems in biomedical research and their role in\u0000driving innovation in drug repurposing. Our approach not only outperforms\u0000existing methods in predicting drug repurposing potential but also provides\u0000interpretable results, paving the way for more efficient and cost-effective\u0000drug discovery processes.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"77 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213332","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}
Jeungeun Park, Yongsam Kim, Wanho Lee, Veronika Pfeifer, Valeriia Muraveva, Carsten Beta, Sookkyung Lim
We present a mathematical model of lophotrichous bacteria, motivated by Pseudomonas putida, which swim through fluid by rotating a cluster of multiple flagella extended from near one pole of the cell body. Although the flagella rotate individually, they are typically bundled together, enabling the bacterium to exhibit three primary modes of motility: push, pull, and wrapping. One key determinant of these modes is the coordination between motor torque and rotational direction of motors. The computational variations in this coordination reveal a wide spectrum of dynamical motion regimes, which are modulated by hydrodynamic interactions between flagellar filaments. These dynamic modes can be categorized into two groups based on the collective behavior of flagella, i.e., bundled and unbundled configurations. For some of these configurations, experimental examples from fluorescence microscopy recordings of swimming P. putida cells are also presented. Furthermore, we analyze the characteristics of stable bundles, such as push and pull, and investigate the dependence of swimming behaviors on the elastic properties of the flagella.
{"title":"Bundling instability of lophotrichous bacteria","authors":"Jeungeun Park, Yongsam Kim, Wanho Lee, Veronika Pfeifer, Valeriia Muraveva, Carsten Beta, Sookkyung Lim","doi":"arxiv-2408.12907","DOIUrl":"https://doi.org/arxiv-2408.12907","url":null,"abstract":"We present a mathematical model of lophotrichous bacteria, motivated by\u0000Pseudomonas putida, which swim through fluid by rotating a cluster of multiple\u0000flagella extended from near one pole of the cell body. Although the flagella\u0000rotate individually, they are typically bundled together, enabling the\u0000bacterium to exhibit three primary modes of motility: push, pull, and wrapping.\u0000One key determinant of these modes is the coordination between motor torque and\u0000rotational direction of motors. The computational variations in this\u0000coordination reveal a wide spectrum of dynamical motion regimes, which are\u0000modulated by hydrodynamic interactions between flagellar filaments. These\u0000dynamic modes can be categorized into two groups based on the collective\u0000behavior of flagella, i.e., bundled and unbundled configurations. For some of\u0000these configurations, experimental examples from fluorescence microscopy\u0000recordings of swimming P. putida cells are also presented. Furthermore, we\u0000analyze the characteristics of stable bundles, such as push and pull, and\u0000investigate the dependence of swimming behaviors on the elastic properties of\u0000the flagella.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213355","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}
AnnaElaine L. Rosengart, Amanda L. Bidwell, Marlene K. Wolfe, Alexandria B. Boehm, F. William Townes
Since the start of the coronavirus-19 pandemic, the use of wastewater-based epidemiology (WBE) for disease surveillance has increased throughout the world. Because wastewater measurements are affected by external factors, processing WBE data typically includes a normalization step in order to adjust wastewater measurements (e.g. viral RNA concentrations) to account for variation due to dynamic population changes, sewer travel effects, or laboratory methods. Pepper mild mottle virus (PMMoV), a plant RNA virus abundant in human feces and wastewater, has been used as a fecal contamination indicator and has been used to normalize wastewater measurements extensively. However, there has been little work to characterize the spatio-temporal variability of PMMoV in wastewater, which may influence the effectiveness of PMMoV for adjusting or normalizing WBE measurements. Here, we investigate its variability across space and time using data collected over a two-year period from sewage treatment plants across the United States. We find that most variation in PMMoV measurements can be attributed to longitude and latitude followed by site-specific variables. Further research into cross-geographical and -temporal comparability of PMMoV-normalized pathogen concentrations would strengthen the utility of PMMoV in WBE.
{"title":"Spatio-Temporal Variability of the Pepper Mild Mottle Virus Biomarker in Wastewater","authors":"AnnaElaine L. Rosengart, Amanda L. Bidwell, Marlene K. Wolfe, Alexandria B. Boehm, F. William Townes","doi":"arxiv-2408.12012","DOIUrl":"https://doi.org/arxiv-2408.12012","url":null,"abstract":"Since the start of the coronavirus-19 pandemic, the use of wastewater-based\u0000epidemiology (WBE) for disease surveillance has increased throughout the world.\u0000Because wastewater measurements are affected by external factors, processing\u0000WBE data typically includes a normalization step in order to adjust wastewater\u0000measurements (e.g. viral RNA concentrations) to account for variation due to\u0000dynamic population changes, sewer travel effects, or laboratory methods. Pepper\u0000mild mottle virus (PMMoV), a plant RNA virus abundant in human feces and\u0000wastewater, has been used as a fecal contamination indicator and has been used\u0000to normalize wastewater measurements extensively. However, there has been\u0000little work to characterize the spatio-temporal variability of PMMoV in\u0000wastewater, which may influence the effectiveness of PMMoV for adjusting or\u0000normalizing WBE measurements. Here, we investigate its variability across space\u0000and time using data collected over a two-year period from sewage treatment\u0000plants across the United States. We find that most variation in PMMoV\u0000measurements can be attributed to longitude and latitude followed by\u0000site-specific variables. Further research into cross-geographical and -temporal\u0000comparability of PMMoV-normalized pathogen concentrations would strengthen the\u0000utility of PMMoV in WBE.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213358","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}
Introduction: Electrical impedance spectroscopy (EIS) has recently developed as a novel diagnostic device for screening and evaluating cervical dysplasia, prostate cancer, breast cancer and basal cell carcinoma. The current study aimed to validate and evaluate bioimpedance as a diagnostic tool for tobacco-induced oral lesions. Methodology: The study comprised 50 OSCC and OPMD tissue specimens for in-vitro study and 320 subjects for in vivo study. Bioimpedance device prepared and calibrated. EIS measurements were done for the habit and control groups and were compared. Results: The impedance value in the control group was significantly higher compared to the OPMD and OSCC groups. Diagnosis based on BIS measurements has a sensitivity of 95.9% and a specificity of 86.7%. Conclusion: Bioimpedance device can help in decision-making for differentiating OPMD and OSCC cases and their management, especially in primary healthcare settings. Keywords: Impedance, Cancer, Diagnosis, Device, Community
导言：电阻抗光谱（EIS）是最近发展起来的一种新型诊断设备，可用于筛查和评估宫颈发育不良、前列腺癌、乳腺癌和基底细胞癌。本研究旨在验证和评估生物阻抗作为烟草引起的口腔病变的诊断工具。研究方法：生物阻抗装置的准备和校准。准备并校准了生物阻抗装置，对习惯组和对照组进行了 EIS 测量并进行了比较。结果：基于 BIS 测量的诊断灵敏度为 95.9%，特异度为 86.7%。结论生物阻抗仪有助于对OPMD和OSCC病例进行鉴别和管理，尤其是在基层医疗机构。关键词阻抗 癌症 诊断 设备 社区
{"title":"Bioimpedance a Diagnostic Tool for Tobacco Induced Oral Lesions: a Mixed Model cross-sectional study","authors":"Vaibhav Gupta, Poonam Goel, Usha Agrawal, Neena Chaudhary, Garima Jain, Deepak Gupta","doi":"arxiv-2408.11886","DOIUrl":"https://doi.org/arxiv-2408.11886","url":null,"abstract":"Introduction: Electrical impedance spectroscopy (EIS) has recently developed\u0000as a novel diagnostic device for screening and evaluating cervical dysplasia,\u0000prostate cancer, breast cancer and basal cell carcinoma. The current study\u0000aimed to validate and evaluate bioimpedance as a diagnostic tool for\u0000tobacco-induced oral lesions. Methodology: The study comprised 50 OSCC and OPMD\u0000tissue specimens for in-vitro study and 320 subjects for in vivo study.\u0000Bioimpedance device prepared and calibrated. EIS measurements were done for the\u0000habit and control groups and were compared. Results: The impedance value in the\u0000control group was significantly higher compared to the OPMD and OSCC groups.\u0000Diagnosis based on BIS measurements has a sensitivity of 95.9% and a\u0000specificity of 86.7%. Conclusion: Bioimpedance device can help in\u0000decision-making for differentiating OPMD and OSCC cases and their management,\u0000especially in primary healthcare settings. Keywords: Impedance, Cancer, Diagnosis, Device, Community","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213357","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}
Guy Lutsker, Gal Sapir, Anastasia Godneva, Smadar Shilo, Jerry R Greenfield, Dorit Samocha-Bonet, Shie Mannor, Eli Meirom, Gal Chechik, Hagai Rossman, Eran Segal
Recent advances in self-supervised learning enabled novel medical AI models, known as foundation models (FMs) that offer great potential for characterizing health from diverse biomedical data. Continuous glucose monitoring (CGM) provides rich, temporal data on glycemic patterns, but its full potential for predicting broader health outcomes remains underutilized. Here, we present GluFormer, a generative foundation model on biomedical temporal data based on a transformer architecture, and trained on over 10 million CGM measurements from 10,812 non-diabetic individuals. We tokenized the CGM training data and trained GluFormer using next token prediction in a generative, autoregressive manner. We demonstrate that GluFormer generalizes effectively to 15 different external datasets, including 4936 individuals across 5 different geographical regions, 6 different CGM devices, and several metabolic disorders, including normoglycemic, prediabetic, and diabetic populations, as well as those with gestational diabetes and obesity. GluFormer produces embeddings which outperform traditional CGM analysis tools, and achieves high Pearson correlations in predicting clinical parameters such as HbA1c, liver-related parameters, blood lipids, and sleep-related indices. Notably, GluFormer can also predict onset of future health outcomes even 4 years in advance. We also show that CGM embeddings from pre-intervention periods in Randomized Clinical Trials (RCTs) outperform other methods in predicting primary and secondary outcomes. When integrating dietary data into GluFormer, we show that the enhanced model can accurately generate CGM data based only on dietary intake data, simulate outcomes of dietary interventions, and predict individual responses to specific foods. Overall, we show that GluFormer accurately predicts health outcomes which generalize across different populations metabolic conditions.
{"title":"From Glucose Patterns to Health Outcomes: A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis","authors":"Guy Lutsker, Gal Sapir, Anastasia Godneva, Smadar Shilo, Jerry R Greenfield, Dorit Samocha-Bonet, Shie Mannor, Eli Meirom, Gal Chechik, Hagai Rossman, Eran Segal","doi":"arxiv-2408.11876","DOIUrl":"https://doi.org/arxiv-2408.11876","url":null,"abstract":"Recent advances in self-supervised learning enabled novel medical AI models,\u0000known as foundation models (FMs) that offer great potential for characterizing\u0000health from diverse biomedical data. Continuous glucose monitoring (CGM)\u0000provides rich, temporal data on glycemic patterns, but its full potential for\u0000predicting broader health outcomes remains underutilized. Here, we present\u0000GluFormer, a generative foundation model on biomedical temporal data based on a\u0000transformer architecture, and trained on over 10 million CGM measurements from\u000010,812 non-diabetic individuals. We tokenized the CGM training data and trained\u0000GluFormer using next token prediction in a generative, autoregressive manner.\u0000We demonstrate that GluFormer generalizes effectively to 15 different external\u0000datasets, including 4936 individuals across 5 different geographical regions, 6\u0000different CGM devices, and several metabolic disorders, including\u0000normoglycemic, prediabetic, and diabetic populations, as well as those with\u0000gestational diabetes and obesity. GluFormer produces embeddings which\u0000outperform traditional CGM analysis tools, and achieves high Pearson\u0000correlations in predicting clinical parameters such as HbA1c, liver-related\u0000parameters, blood lipids, and sleep-related indices. Notably, GluFormer can\u0000also predict onset of future health outcomes even 4 years in advance. We also\u0000show that CGM embeddings from pre-intervention periods in Randomized Clinical\u0000Trials (RCTs) outperform other methods in predicting primary and secondary\u0000outcomes. When integrating dietary data into GluFormer, we show that the\u0000enhanced model can accurately generate CGM data based only on dietary intake\u0000data, simulate outcomes of dietary interventions, and predict individual\u0000responses to specific foods. Overall, we show that GluFormer accurately\u0000predicts health outcomes which generalize across different populations\u0000metabolic conditions.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"94 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213356","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}
Models of reaction networks within interacting compartments (RNIC) are a generalization of stochastic reaction networks. It is most natural to think of the interacting compartments as ``cells'' that can appear, degrade, split, and even merge, with each cell containing an evolving copy of the underlying stochastic reaction network. Such models have a number of parameters, including those associated with the internal chemical model and those associated with the compartment interactions, and it is natural to want efficient computational methods for the numerical estimation of sensitivities of model statistics with respect to these parameters. Motivated by the extensive work on computational methods for parametric sensitivity analysis in the context of stochastic reaction networks over the past few decades, we provide a number of methods in the RNIC setting. Provided methods include the (unbiased) Girsanov transformation method (also called the Likelihood Ratio method) and a number of coupling methods for the implementation of finite differences. We provide several numerical examples and conclude that the method associated with the ``Split Coupling'' provides the most efficient algorithm. This finding is in line with the conclusions from the work related to sensitivity analysis of standard stochastic reaction networks. We have made all of the Matlab code used to implement the various methods freely available for download.
{"title":"Parametric Sensitivity Analysis for Models of Reaction Networks within Interacting Compartments","authors":"David F. Anderson, Aidan S. Howells","doi":"arxiv-2408.09208","DOIUrl":"https://doi.org/arxiv-2408.09208","url":null,"abstract":"Models of reaction networks within interacting compartments (RNIC) are a\u0000generalization of stochastic reaction networks. It is most natural to think of\u0000the interacting compartments as ``cells'' that can appear, degrade, split, and\u0000even merge, with each cell containing an evolving copy of the underlying\u0000stochastic reaction network. Such models have a number of parameters, including\u0000those associated with the internal chemical model and those associated with the\u0000compartment interactions, and it is natural to want efficient computational\u0000methods for the numerical estimation of sensitivities of model statistics with\u0000respect to these parameters. Motivated by the extensive work on computational\u0000methods for parametric sensitivity analysis in the context of stochastic\u0000reaction networks over the past few decades, we provide a number of methods in\u0000the RNIC setting. Provided methods include the (unbiased) Girsanov\u0000transformation method (also called the Likelihood Ratio method) and a number of\u0000coupling methods for the implementation of finite differences. We provide\u0000several numerical examples and conclude that the method associated with the\u0000``Split Coupling'' provides the most efficient algorithm. This finding is in\u0000line with the conclusions from the work related to sensitivity analysis of\u0000standard stochastic reaction networks. We have made all of the Matlab code used\u0000to implement the various methods freely available for download.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":"94 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213365","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：