In this paper, the effectiveness of two deep learning models was tested and the significance of 62 different electroencephalogram (EEG) channels were explored on covert speech classification tasks using time series EEG signals. Experiments were done on the classification between the words “in” and “cooperate” from the ASU dataset and the classification between 11 different prompts from the KaraOne dataset. The types of deep learning models used are the 1D convolutional neural network (CNN) and the graphical neural network (GNN). Overall, the CNN model showed decent performance with an accuracy of around 80% on the classification between “in” and “cooperate”, while the GNN seemed to be unsuitable for time series data. By examining the accuracy of the CNN model trained on different EEG channels, the prefrontal and frontal regions appeared to be the most relevant to the performance of the model. Although this finding is noticeably different from various previous works, it could provide possible insights into the cortical activities behind covert speech.
{"title":"Testing the Effectiveness of CNN and GNN and Exploring the Influence of Different Channels on Decoding Covert Speech from EEG Signals: CNN and GNN on Decoding Covert Speech from EEG Signals","authors":"Serena Liu, Jonathan H. Chan","doi":"10.1145/3486713.3486733","DOIUrl":"https://doi.org/10.1145/3486713.3486733","url":null,"abstract":"In this paper, the effectiveness of two deep learning models was tested and the significance of 62 different electroencephalogram (EEG) channels were explored on covert speech classification tasks using time series EEG signals. Experiments were done on the classification between the words “in” and “cooperate” from the ASU dataset and the classification between 11 different prompts from the KaraOne dataset. The types of deep learning models used are the 1D convolutional neural network (CNN) and the graphical neural network (GNN). Overall, the CNN model showed decent performance with an accuracy of around 80% on the classification between “in” and “cooperate”, while the GNN seemed to be unsuitable for time series data. By examining the accuracy of the CNN model trained on different EEG channels, the prefrontal and frontal regions appeared to be the most relevant to the performance of the model. Although this finding is noticeably different from various previous works, it could provide possible insights into the cortical activities behind covert speech.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117020146","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}
Samuel Buchet, F. Carbone, M. Magnin, M. Ménager, O. Roux
Single cell sequencing technologies represent a unique opportunity to appreciate all the heterogeneity of gene expressions within specific biological cell types. While these data are sparse and especially noisy, it remains possible to perform multiple analysis tasks such as identifying sub cellular types and biological markers. Beyond revealing distinct sub cell populations, single cell gene expressions usually involve complex gene interactions, which may often be interpreted as an underlying gene network. In this context, logical computational approaches are particularly attractive as they provide models that are easy to interpret and verify. However, the noise is especially important in single cell sequencing data. This may appear as a limit for symbolic methods as they usually fail in addressing the statistical aspect necessary to handle efficiently such noise. In this work, we propose a computational approach based on symbolic modeling to identify gene connections from single cell RNA sequencing data. Our algorithm, LOLH, is based on Inductive Logic Programming, and intends to rapidly identify potential gene interactions by formulating discrete classification problems, which are solved through discrete optimization. By combining symbolic modeling with optimization techniques, we aim to provide an interpretable model that still fits properly on sparse and noisy data. We apply our method to the unsupervised inference of a gene correlation network from a concrete single cell dataset. We show that the output of our algorithm can be interpreted by using the data itself, and we use additional biological knowledge to validate the approach.
{"title":"Inference of Gene Networks from Single Cell Data through Quantified Inductive Logic Programming","authors":"Samuel Buchet, F. Carbone, M. Magnin, M. Ménager, O. Roux","doi":"10.1145/3486713.3486746","DOIUrl":"https://doi.org/10.1145/3486713.3486746","url":null,"abstract":"Single cell sequencing technologies represent a unique opportunity to appreciate all the heterogeneity of gene expressions within specific biological cell types. While these data are sparse and especially noisy, it remains possible to perform multiple analysis tasks such as identifying sub cellular types and biological markers. Beyond revealing distinct sub cell populations, single cell gene expressions usually involve complex gene interactions, which may often be interpreted as an underlying gene network. In this context, logical computational approaches are particularly attractive as they provide models that are easy to interpret and verify. However, the noise is especially important in single cell sequencing data. This may appear as a limit for symbolic methods as they usually fail in addressing the statistical aspect necessary to handle efficiently such noise. In this work, we propose a computational approach based on symbolic modeling to identify gene connections from single cell RNA sequencing data. Our algorithm, LOLH, is based on Inductive Logic Programming, and intends to rapidly identify potential gene interactions by formulating discrete classification problems, which are solved through discrete optimization. By combining symbolic modeling with optimization techniques, we aim to provide an interpretable model that still fits properly on sparse and noisy data. We apply our method to the unsupervised inference of a gene correlation network from a concrete single cell dataset. We show that the output of our algorithm can be interpreted by using the data itself, and we use additional biological knowledge to validate the approach.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114375423","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}
Corneal ulcer is a common corneal symptom that, upon infection, can lead to destruction of the corneal tissues, resulting in corneal blindness. To ease the corneal ulcer screening process, this paper introduces a deep transfer learning architecture based on various backbone networks to help identify two severity levels of the symptom: early stage and advanced stage. The total of 15 well-known deep convolutional neural networks are used as the base model. The proposed transfer learning-based architectures are trained, validated, and tested on 426, 143, and 143 fluorescein staining slit-lamp images from the public SUSTech-SYSU dataset. The experimental results show that ResNet50 is the best model achieving the best accuracy, sensitivity, F1 score, and Cohen’s kappa of 95.10%, 94.37%, 95.04%, and 0.9021, respectively, on the blind test set of the cropped corneal images. This model is further evaluated on an external dataset and its prediction is also explained using Integrated Gradients to provide an insight into its generalization performance.
{"title":"Deep learning-based approach for corneal ulcer screening","authors":"Kasemsit Teeyapan","doi":"10.1145/3486713.3486734","DOIUrl":"https://doi.org/10.1145/3486713.3486734","url":null,"abstract":"Corneal ulcer is a common corneal symptom that, upon infection, can lead to destruction of the corneal tissues, resulting in corneal blindness. To ease the corneal ulcer screening process, this paper introduces a deep transfer learning architecture based on various backbone networks to help identify two severity levels of the symptom: early stage and advanced stage. The total of 15 well-known deep convolutional neural networks are used as the base model. The proposed transfer learning-based architectures are trained, validated, and tested on 426, 143, and 143 fluorescein staining slit-lamp images from the public SUSTech-SYSU dataset. The experimental results show that ResNet50 is the best model achieving the best accuracy, sensitivity, F1 score, and Cohen’s kappa of 95.10%, 94.37%, 95.04%, and 0.9021, respectively, on the blind test set of the cropped corneal images. This model is further evaluated on an external dataset and its prediction is also explained using Integrated Gradients to provide an insight into its generalization performance.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122854523","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}
Gatis Melkus, Kārlis Čerāns, Kārlis Freivalds, Lelde Lace, Darta Zajakina, Juris Viksna
We present hybrid system based gene regulatory network models for lambda, HK022 and Mu bacteriophages and analysis of dynamics and possible stable behaviours of the modelled networks. Lambda phage model LPH2 is the result of further development of an earlier LPH1 model taking into account more recent biological assumptions about the underlying biological gene regulatory mechanism. HK022 and Mu phage models are new. All three models provide accurate representations of lytic and lysogenic behavioural cycles, and, importantly, allow to conclude that lysis and lysogeny are the only stable behaviours that can occur in the modelled networks. Along with these models we describe also some new analysis techniques for hybrid system model state spaces. The models also allow to derive switching conditions that irrevocably lead to one of these two stable behaviours (these are consistent with proposed biological models) and also constraints on binding site affinities that are required for biologically feasible lysis and lysogeny processes. One of the derived constraints in LPH2 model is required for lambda lysis cycle feasibility and places conditions on cro protein binding site affinities. This is consistent with the constraint obtained previously for LPH1 model, although parts of state spaces that describe lysis in these models are different. Another constraint on protein cI binding affinities that is required for biologically feasible lysogeny cycle is new (and likely has been overlooked earlier). At the same time dynamics of HK022 model (which, notably, lacks N antitermination protein) turns out to be independent of both these constraints, although the involved genes and binding their sites are very similar. The used HSM system framework also allows to reproduce biologically different lysis-lysogeny switching mechanisms that are used by Mu phage. In general the results show that HSM hybrid system framework can be successfully applied to modelling small gene regulatory networks (with up to ∼ 20 genes) and for comprehensive analysis of model state space stability regions.
{"title":"Analysis of Dynamics and Stability of Hybrid System Models of Gene Regulatory Networks","authors":"Gatis Melkus, Kārlis Čerāns, Kārlis Freivalds, Lelde Lace, Darta Zajakina, Juris Viksna","doi":"10.1145/3486713.3486727","DOIUrl":"https://doi.org/10.1145/3486713.3486727","url":null,"abstract":"We present hybrid system based gene regulatory network models for lambda, HK022 and Mu bacteriophages and analysis of dynamics and possible stable behaviours of the modelled networks. Lambda phage model LPH2 is the result of further development of an earlier LPH1 model taking into account more recent biological assumptions about the underlying biological gene regulatory mechanism. HK022 and Mu phage models are new. All three models provide accurate representations of lytic and lysogenic behavioural cycles, and, importantly, allow to conclude that lysis and lysogeny are the only stable behaviours that can occur in the modelled networks. Along with these models we describe also some new analysis techniques for hybrid system model state spaces. The models also allow to derive switching conditions that irrevocably lead to one of these two stable behaviours (these are consistent with proposed biological models) and also constraints on binding site affinities that are required for biologically feasible lysis and lysogeny processes. One of the derived constraints in LPH2 model is required for lambda lysis cycle feasibility and places conditions on cro protein binding site affinities. This is consistent with the constraint obtained previously for LPH1 model, although parts of state spaces that describe lysis in these models are different. Another constraint on protein cI binding affinities that is required for biologically feasible lysogeny cycle is new (and likely has been overlooked earlier). At the same time dynamics of HK022 model (which, notably, lacks N antitermination protein) turns out to be independent of both these constraints, although the involved genes and binding their sites are very similar. The used HSM system framework also allows to reproduce biologically different lysis-lysogeny switching mechanisms that are used by Mu phage. In general the results show that HSM hybrid system framework can be successfully applied to modelling small gene regulatory networks (with up to ∼ 20 genes) and for comprehensive analysis of model state space stability regions.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124300278","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}
Hannes Klarner, Elisa Tonello, L. Fontanals, F. Janody, C. Chaouiya, H. Siebert
Motivation: Capturing the molecular diversity of living cells is not straightforward. One approach is to measure molecular markers that serve as indicators of specific biological conditions or phenotypes. This is particularly relevant in modern medicine to provide precise diagnostics and pinpoint the best treatment for each patient. The challenge is to select a minimal set of markers whose activity patterns are in correspondence with the phenotypes of interest. Results: This article approaches the marker detection problem in the context of discrete phenotypes which arise, for example, from Boolean models of cellular networks. Mathematically this poses a combinatorial optimization problem with many answers. We propose a solution to this optimization problem that is based on the modelling language answer set programming (ASP). A case study of a death cell receptor network illustrates the methodology. Discussion and code: For code, discussions and reporting errors visit https://github.com/hklarner/detection_of_markers_for_discrete_phenotypes.
{"title":"Detection of markers for discrete phenotypes","authors":"Hannes Klarner, Elisa Tonello, L. Fontanals, F. Janody, C. Chaouiya, H. Siebert","doi":"10.1145/3486713.3486729","DOIUrl":"https://doi.org/10.1145/3486713.3486729","url":null,"abstract":"Motivation: Capturing the molecular diversity of living cells is not straightforward. One approach is to measure molecular markers that serve as indicators of specific biological conditions or phenotypes. This is particularly relevant in modern medicine to provide precise diagnostics and pinpoint the best treatment for each patient. The challenge is to select a minimal set of markers whose activity patterns are in correspondence with the phenotypes of interest. Results: This article approaches the marker detection problem in the context of discrete phenotypes which arise, for example, from Boolean models of cellular networks. Mathematically this poses a combinatorial optimization problem with many answers. We propose a solution to this optimization problem that is based on the modelling language answer set programming (ASP). A case study of a death cell receptor network illustrates the methodology. Discussion and code: For code, discussions and reporting errors visit https://github.com/hklarner/detection_of_markers_for_discrete_phenotypes.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131858627","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}
{"title":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","authors":"","doi":"10.1145/3486713","DOIUrl":"https://doi.org/10.1145/3486713","url":null,"abstract":"","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128528179","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}
Pulmonary embolism (PE) is a preventable life-threatening disease that is among the top three most common causes of cardiovascular deaths. Producing an accurate diagnosis can be challenging. Nowadays, computer-aided diagnosis has proven itself to be a useful tool for physicians. However, computers need to recognize the relevant human anatomy as accurately as possible. In case of PE, pulmonary artery is the structure in which the lesion manifests. Segmentation of the structure is required to define the area to search for emboli. In this study, we proposed a segmentation algorithm that accurately identifies voxels occupied by pulmonary artery in computed tomography angiography (CTA) images. The output could directly be used to create the 3D visualization of the pulmonary artery network for the PE diagnosis. The algorithm consists of three parts: lung mask extraction, pulmonary artery detection, and pulmonary artery connection. The technique involves several conventional image processing methods such as morphological operations and thresholding to separate the vessels from the background. The pulmonary artery connection further refined the preliminary vessel contours and improved the accuracy. We evaluated our method with the dataset from a publicly available FUMPE (Ferdowsi University of Mashhad's PE) dataset. The resulting Dice similarity coefficients against the ground truth created by human experts was about 81% ± 1%. The visualizations created by the automatic algorithm was also very similar to that created by human experts. Future works building upon our study may contribute to the better diagnosis of PE.
{"title":"Pulmonary Artery Visualization for Computed Tomography Angiography Data of Pulmonary Embolism","authors":"Patiwet Wuttisarnwattana, Annop Krasaesin, Poommetee Ketson","doi":"10.1145/3486713.3486737","DOIUrl":"https://doi.org/10.1145/3486713.3486737","url":null,"abstract":"Pulmonary embolism (PE) is a preventable life-threatening disease that is among the top three most common causes of cardiovascular deaths. Producing an accurate diagnosis can be challenging. Nowadays, computer-aided diagnosis has proven itself to be a useful tool for physicians. However, computers need to recognize the relevant human anatomy as accurately as possible. In case of PE, pulmonary artery is the structure in which the lesion manifests. Segmentation of the structure is required to define the area to search for emboli. In this study, we proposed a segmentation algorithm that accurately identifies voxels occupied by pulmonary artery in computed tomography angiography (CTA) images. The output could directly be used to create the 3D visualization of the pulmonary artery network for the PE diagnosis. The algorithm consists of three parts: lung mask extraction, pulmonary artery detection, and pulmonary artery connection. The technique involves several conventional image processing methods such as morphological operations and thresholding to separate the vessels from the background. The pulmonary artery connection further refined the preliminary vessel contours and improved the accuracy. We evaluated our method with the dataset from a publicly available FUMPE (Ferdowsi University of Mashhad's PE) dataset. The resulting Dice similarity coefficients against the ground truth created by human experts was about 81% ± 1%. The visualizations created by the automatic algorithm was also very similar to that created by human experts. Future works building upon our study may contribute to the better diagnosis of PE.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"488 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134410541","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 COVID-19 pandemic has impacted many countries around the world resulting in the need to develop quick and effective screening methods to ease the burden and overcome the limitations of varying healthcare capacities. Given the nature of the disease, the use of Chest X-ray (CXR) medical imaging has proven to be very useful which has prompted the exploration of computer-aided diagnosis tools to augment and assist radiologists. However, recent reports have deemed many of the proposed methods to be impractical for use in real-life applications due to models with poor generalization capabilities, an issue closely related to the quality of current datasets in the CXR domain. Typically, deep convolutional neural network (CNN) based classification systems utilize transfer learning techniques when data is limited. We suggest first training models on publicly available large-scale and CXR specific datasets, such as CheXpert, and using these pretrained weights when initializing the final model. Compared with a CNN pretrained on the more general ImageNet dataset, pretraining on large-scale domain specific data increased the model's ability to generalize to unseen data.
{"title":"The Effect of PreTraining Thoracic Disease Detection Systems on Large-Scale Chest X-Ray Domain Datasets","authors":"Shafinul Haque, Jonathan H. Chan","doi":"10.1145/3486713.3486735","DOIUrl":"https://doi.org/10.1145/3486713.3486735","url":null,"abstract":"The COVID-19 pandemic has impacted many countries around the world resulting in the need to develop quick and effective screening methods to ease the burden and overcome the limitations of varying healthcare capacities. Given the nature of the disease, the use of Chest X-ray (CXR) medical imaging has proven to be very useful which has prompted the exploration of computer-aided diagnosis tools to augment and assist radiologists. However, recent reports have deemed many of the proposed methods to be impractical for use in real-life applications due to models with poor generalization capabilities, an issue closely related to the quality of current datasets in the CXR domain. Typically, deep convolutional neural network (CNN) based classification systems utilize transfer learning techniques when data is limited. We suggest first training models on publicly available large-scale and CXR specific datasets, such as CheXpert, and using these pretrained weights when initializing the final model. Compared with a CNN pretrained on the more general ImageNet dataset, pretraining on large-scale domain specific data increased the model's ability to generalize to unseen data.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131063309","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}
Authoritative thesauri in the form of web ontologies offer a sound representation of domain knowledge and can act as a reference point for automated semantic tagging. On the other hand, current language models achieve to capture contextualized semantics of text corpora and can be leveraged towards this goal. We present an approach for injecting subject annotations using query term expansion against such ontologies in the biomedical domain. For the user to have an indication of the usefulness of these suggestions we further propose an online method for validating the quality of annotations using NLI models such as BART and XLM-R. To circumvent training barriers posed by very large label sets and scarcity of data we rely on zero-shot classification and show that semantic matching can contribute above-average thematic annotations. Also, a web-based validation service can be attractive for human curators vs. the overhead of pretraining large, domain-tailored classification models.
{"title":"Validating Ontology-based Annotations of Biomedical Resources using Zero-shot Learning","authors":"Dimitrios A. Koutsomitropoulos","doi":"10.1145/3486713.3486730","DOIUrl":"https://doi.org/10.1145/3486713.3486730","url":null,"abstract":"Authoritative thesauri in the form of web ontologies offer a sound representation of domain knowledge and can act as a reference point for automated semantic tagging. On the other hand, current language models achieve to capture contextualized semantics of text corpora and can be leveraged towards this goal. We present an approach for injecting subject annotations using query term expansion against such ontologies in the biomedical domain. For the user to have an indication of the usefulness of these suggestions we further propose an online method for validating the quality of annotations using NLI models such as BART and XLM-R. To circumvent training barriers posed by very large label sets and scarcity of data we rely on zero-shot classification and show that semantic matching can contribute above-average thematic annotations. Also, a web-based validation service can be attractive for human curators vs. the overhead of pretraining large, domain-tailored classification models.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"543 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133236059","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}
Partial differential equations play an important role in mathematical modeling of nephrons. The finite difference solution methods exhibit regular, period doubling and irregular oscillations. In this paper, a single nephron model with transport mechanism and autoregulatory mechanism has been developed using cellular automata framework for a rigid tubule. Cellular automata framework captures the emergent behavior of the system. The importance of cellular automata approach of studying a dynamical system emanates from its ability to capture new behavior not easily shown by numerical analysis. The governing equations of a single nephron model are converted to cellular automata local rules using ultradiscretization. The emergent properties from the local cellular automata rules have been compared with the reported experimental findings. It has been shown that cellular automata framework with ultradiscretization is a promising approach to model macrolevel behaviors of physiological systems.
{"title":"Spatio-Temporal Evolution of Cellular Automata based Single Nephron Rigid Tubular Model","authors":"Siva Manohar Reddy Kesu, Hariharan Ramasangu","doi":"10.1145/3486713.3486744","DOIUrl":"https://doi.org/10.1145/3486713.3486744","url":null,"abstract":"Partial differential equations play an important role in mathematical modeling of nephrons. The finite difference solution methods exhibit regular, period doubling and irregular oscillations. In this paper, a single nephron model with transport mechanism and autoregulatory mechanism has been developed using cellular automata framework for a rigid tubule. Cellular automata framework captures the emergent behavior of the system. The importance of cellular automata approach of studying a dynamical system emanates from its ability to capture new behavior not easily shown by numerical analysis. The governing equations of a single nephron model are converted to cellular automata local rules using ultradiscretization. The emergent properties from the local cellular automata rules have been compared with the reported experimental findings. It has been shown that cellular automata framework with ultradiscretization is a promising approach to model macrolevel behaviors of physiological systems.","PeriodicalId":268366,"journal":{"name":"The 12th International Conference on Computational Systems-Biology and Bioinformatics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116545061","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：