In modelling of individual red blood cells different bio-mechanical phenomena have to be taken into account. Besides the evident mechanical properties of the red blood cell membrane such as shear elasticity, viscosity ratio is sometimes omitted in the models. We present an approach for including the difference between the inner and the outer fluid of the cell into model. We analyze physical properties of protein hemoglobin that is responsible for higher viscosity of inner cytoplasm of the cell. To keep the computational complexity reasonable we build coarse-grained model of hemoglobin. We present initial proof-of-concept study using the validation test of cell’s behaviour in a shear flow.
{"title":"Proof-of-concept model of red blood cell with coarse-grained hemoglobin","authors":"Mariana Ondrusová, I. Cimrák","doi":"10.1145/3429210.3429228","DOIUrl":"https://doi.org/10.1145/3429210.3429228","url":null,"abstract":"In modelling of individual red blood cells different bio-mechanical phenomena have to be taken into account. Besides the evident mechanical properties of the red blood cell membrane such as shear elasticity, viscosity ratio is sometimes omitted in the models. We present an approach for including the difference between the inner and the outer fluid of the cell into model. We analyze physical properties of protein hemoglobin that is responsible for higher viscosity of inner cytoplasm of the cell. To keep the computational complexity reasonable we build coarse-grained model of hemoglobin. We present initial proof-of-concept study using the validation test of cell’s behaviour in a shear flow.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123528314","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}
Boris Velichkov, Simeon Gerginov, P. Panayotov, S. Vassileva, Gerasim Velchev, I. Koychev, S. Boytcheva
This paper presents an approach for the automatic association of diagnoses in Bulgarian language to ICD-10 codes. Since this task is currently performed manually by medical professionals, the ability to automate it would save time and allow doctors to focus more on patient care. The presented approach employs a fine-tuned language model (i.e. BERT) as a multi-class classification model. As there are several different types of BERT models, we conduct experiments to assess the applicability of domain and language specific model adaptation. To train our models we use a big corpora of about 350,000 textual descriptions of diagnosis in Bulgarian language annotated with ICD-10 codes. We conduct experiments comparing the accuracy of ICD-10 code prediction using different types of BERT language models. The results show that the MultilingualBERT model (Accuracy Top 1 - 81%; Macro F1 - 86%, MRR Top 5 - 88%) outperforms other models. However, all models seem to suffer from the class imbalance in the training dataset. The achieved accuracy of prediction in the experiments can be evaluated as very high, given the huge amount of classes and noisiness of the data. The result also provides evidence that the collected dataset and the proposed approach can be useful in building an application to help medical practitioners with this task and encourages further research to improve the prediction accuracy of the models. By design, the proposed approach strives to be language-independent as much as possible and can be easily adapted to other languages.
{"title":"Automatic ICD-10 codes association to diagnosis: Bulgarian case","authors":"Boris Velichkov, Simeon Gerginov, P. Panayotov, S. Vassileva, Gerasim Velchev, I. Koychev, S. Boytcheva","doi":"10.1145/3429210.3429224","DOIUrl":"https://doi.org/10.1145/3429210.3429224","url":null,"abstract":"This paper presents an approach for the automatic association of diagnoses in Bulgarian language to ICD-10 codes. Since this task is currently performed manually by medical professionals, the ability to automate it would save time and allow doctors to focus more on patient care. The presented approach employs a fine-tuned language model (i.e. BERT) as a multi-class classification model. As there are several different types of BERT models, we conduct experiments to assess the applicability of domain and language specific model adaptation. To train our models we use a big corpora of about 350,000 textual descriptions of diagnosis in Bulgarian language annotated with ICD-10 codes. We conduct experiments comparing the accuracy of ICD-10 code prediction using different types of BERT language models. The results show that the MultilingualBERT model (Accuracy Top 1 - 81%; Macro F1 - 86%, MRR Top 5 - 88%) outperforms other models. However, all models seem to suffer from the class imbalance in the training dataset. The achieved accuracy of prediction in the experiments can be evaluated as very high, given the huge amount of classes and noisiness of the data. The result also provides evidence that the collected dataset and the proposed approach can be useful in building an application to help medical practitioners with this task and encourages further research to improve the prediction accuracy of the models. By design, the proposed approach strives to be language-independent as much as possible and can be easily adapted to other languages.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126335540","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 paper, we applied EfficientNet, a scalable deep convolution neural network, with a custom data augmentation stage to a public protein crystallization image dataset called MARCO. The MARCO dataset has 493,214 protein crystallization images collected from several well-known institutions. In our experiments, EfficientNet outperformed the accuracies reported in the previous studies, and it reached an overall 96.71% testing and 91.33% validation accuracy on the dataset. Also, EfficientNet achieved 97.23% crystal detection accuracy in testing data, which is significant improvement over existing studies.
{"title":"Classification of Protein Crystallization Images using EfficientNet with Data Augmentation","authors":"David William Edwards II, I. Dinç","doi":"10.1145/3429210.3429220","DOIUrl":"https://doi.org/10.1145/3429210.3429220","url":null,"abstract":"In this paper, we applied EfficientNet, a scalable deep convolution neural network, with a custom data augmentation stage to a public protein crystallization image dataset called MARCO. The MARCO dataset has 493,214 protein crystallization images collected from several well-known institutions. In our experiments, EfficientNet outperformed the accuracies reported in the previous studies, and it reached an overall 96.71% testing and 91.33% validation accuracy on the dataset. Also, EfficientNet achieved 97.23% crystal detection accuracy in testing data, which is significant improvement over existing studies.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115408330","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}
Cassava (Manihot esculenta Crantz) is a staple crop that has a great impact on global food security. Cassava yield improvement has continuously been researched, resulting in various elite cultivars bred during last decades. To pursue a better yield, it requires deep insight into metabolic process underlying the assimilation and conversion of carbon substrates to storage root biomass. In this study, we employed E-Fmin analysis to model carbon metabolism in storage roots of cassava. The model was constructed based on primary metabolism of carbon assimilation pathway in non-photosynthetic cells and corresponding gene expression data. The model, namely rMeCBMx-EFmin, was able to mimic growth of storage roots measured from Kasetsart 50 (KU50). The rMeCBMx-EFmin highlighted the tentative metabolic flux distribution that carbon substrates were economically converted into cellular biomass of cassava storage roots. The small total flux (3.2749 mmol gDWSRs−1 day−1) with respect to the published model of cassava storage roots (4.4255 mmol gDWSRs−1 day−1) indicated metabolic frugality in the simulated root metabolism. The simulation also showed that alpha-D-glucose-6-phosphate (-D-Glc-6P) partitioned from respiration was a key carbon precursor imported to plastid for storage root biomass production. The knowledge gained would be beneficial for later experimental design of yield enhancement.
木薯(Manihot esculenta Crantz)是对全球粮食安全有重大影响的主要作物。近几十年来，人们对木薯产量的提高进行了不断的研究，培育出了各种优良品种。为了追求更好的产量，需要深入了解碳底物同化和转化为储存根生物量的代谢过程。在本研究中，我们采用E-Fmin分析来模拟木薯储存根的碳代谢。该模型基于非光合细胞碳同化途径的初级代谢和相应的基因表达数据构建。该模型，即rMeCBMx-EFmin，能够模拟从Kasetsart 50 (KU50)测量的储存根的生长。rMeCBMx-EFmin强调了碳基质经济转化为木薯储根细胞生物量的初步代谢通量分布。与已发表的木薯储存根模型(4.4255 mmol gDWSRs−1 day−1)相比，总通量(3.2749 mmol gDWSRs−1 day−1)较小，表明模拟根代谢的代谢节俭。模拟还表明，从呼吸中分离出来的α - d -葡萄糖-6-磷酸(- d -葡萄糖- 6p)是输入质体储存根生物量的关键碳前体。所获得的知识将有助于以后的增产试验设计。
{"title":"Modeling metabolic fluxes underlying cassava storage root growth through E-Fmin analysis","authors":"Ratchaprapa Kamsen, S. Kalapanulak, T. Saithong","doi":"10.1145/3429210.3429234","DOIUrl":"https://doi.org/10.1145/3429210.3429234","url":null,"abstract":"Cassava (Manihot esculenta Crantz) is a staple crop that has a great impact on global food security. Cassava yield improvement has continuously been researched, resulting in various elite cultivars bred during last decades. To pursue a better yield, it requires deep insight into metabolic process underlying the assimilation and conversion of carbon substrates to storage root biomass. In this study, we employed E-Fmin analysis to model carbon metabolism in storage roots of cassava. The model was constructed based on primary metabolism of carbon assimilation pathway in non-photosynthetic cells and corresponding gene expression data. The model, namely rMeCBMx-EFmin, was able to mimic growth of storage roots measured from Kasetsart 50 (KU50). The rMeCBMx-EFmin highlighted the tentative metabolic flux distribution that carbon substrates were economically converted into cellular biomass of cassava storage roots. The small total flux (3.2749 mmol gDWSRs−1 day−1) with respect to the published model of cassava storage roots (4.4255 mmol gDWSRs−1 day−1) indicated metabolic frugality in the simulated root metabolism. The simulation also showed that alpha-D-glucose-6-phosphate (-D-Glc-6P) partitioned from respiration was a key carbon precursor imported to plastid for storage root biomass production. The knowledge gained would be beneficial for later experimental design of yield enhancement.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122703469","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 affected humans worldwide, and we are in dire need of techniques to bring this situation within our control. Among the various approaches attempted by researchers, preliminary prediction of COVID-19 through chest X-ray images is proving to be quite beneficial and thus, is being explored thoroughly. In this paper, a novel combination of local binary pattern based feature selection along with a convolutional neural network is proposed which can predict positive and negative cases by analysing chest X-ray images. The model consists of a feature extraction process followed by various pooling and convolution layers systematically placed to give an optimal output. The proposed model has been trained and tested on a COVID-19 CXR images dataset, and it is seen that it achieves a significant improvement over the five other comparison methods.
{"title":"Convolutional neural network for prediction of COVID-19 from chest X-ray images","authors":"Debayan Goswami, Anwesha Law, Debasrita Chakraborty, Abhishek Dey","doi":"10.1145/3429210.3429219","DOIUrl":"https://doi.org/10.1145/3429210.3429219","url":null,"abstract":"The COVID-19 pandemic has affected humans worldwide, and we are in dire need of techniques to bring this situation within our control. Among the various approaches attempted by researchers, preliminary prediction of COVID-19 through chest X-ray images is proving to be quite beneficial and thus, is being explored thoroughly. In this paper, a novel combination of local binary pattern based feature selection along with a convolutional neural network is proposed which can predict positive and negative cases by analysing chest X-ray images. The model consists of a feature extraction process followed by various pooling and convolution layers systematically placed to give an optimal output. The proposed model has been trained and tested on a COVID-19 CXR images dataset, and it is seen that it achieves a significant improvement over the five other comparison methods.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125995269","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 late 2019, the first case of COVID-19 was confirmed in Wuhan, China. The number of cases has been rapidly growing since then. Molecular and antigen testing methods are very accurate for the diagnosis of COVID-19. However, with sudden increases of infected cases, laboratory-based molecular test and COVID-19 test kits are in short supply. Because the virus affects an infected patient’s lung, interpreting images obtained from Computed Tomography Scanners and Chest X-ray Radiography (CXR) machines can be an alternative for diagnosis. However CXR interpretation requires experts and the number of experts is limited. Therefore, automatic detection of COVID-19 from CXR images is required. We describe a system for automatic detection of COVID-19 from CXR images. It first segmented images to select only the lung. The segmented part was then fed into a multiclass classification module, which worked well with samples obtained from various sources, which had different aspect ratios, contrast and viewpoints. The system also handled the unbalanced dataset—only a small fraction of images showed COVID-19. Our system achieved 92% of F1-score and 88.1% Marco F1-score on the 3rd Deep Learning and AI Summer/Winter School Hackathon Phase 3—Multi-class COVID-19 Chest X-ray challenge public leaderboard.
{"title":"An Image Segment-based Classification for Chest X-Ray Image","authors":"Phongsathorn Kittiworapanya, Kitsuchart Pasupa","doi":"10.1145/3429210.3429227","DOIUrl":"https://doi.org/10.1145/3429210.3429227","url":null,"abstract":"In late 2019, the first case of COVID-19 was confirmed in Wuhan, China. The number of cases has been rapidly growing since then. Molecular and antigen testing methods are very accurate for the diagnosis of COVID-19. However, with sudden increases of infected cases, laboratory-based molecular test and COVID-19 test kits are in short supply. Because the virus affects an infected patient’s lung, interpreting images obtained from Computed Tomography Scanners and Chest X-ray Radiography (CXR) machines can be an alternative for diagnosis. However CXR interpretation requires experts and the number of experts is limited. Therefore, automatic detection of COVID-19 from CXR images is required. We describe a system for automatic detection of COVID-19 from CXR images. It first segmented images to select only the lung. The segmented part was then fed into a multiclass classification module, which worked well with samples obtained from various sources, which had different aspect ratios, contrast and viewpoints. The system also handled the unbalanced dataset—only a small fraction of images showed COVID-19. Our system achieved 92% of F1-score and 88.1% Marco F1-score on the 3rd Deep Learning and AI Summer/Winter School Hackathon Phase 3—Multi-class COVID-19 Chest X-ray challenge public leaderboard.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115194923","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 resistance threatens the effectiveness of treatments of infectious diseases, particularly on the global scale where mutation is rapid, mechanisms of resistance are developing or unknown, and limited data is available. Pathway activity inference is a dimensionality reduction method with proven effectiveness in classifying cancer types and drug responses based on transcription data. We propose a novel application of pathway activity inference to predict dihydroartemisinin resistance in the Plasmodium falciparum strain of malaria, a global infectious disease. Optimized pathway activity inference models outperform untransformed gene expression models in both in vitro regression (p = 0.03) and in vivo classification tasks (p = 2 × 10− 9). Optimal methods were found to be mostly ensemble (5 of 12) and/or kernel-based (7 of 12), providing the first evidence of the effectiveness of kernel methods for predicting drug resistance in infectious diseases. Performance metrics of the optimal in vitro model on in vivo data (accuracy , area under receiver operating characteristic curve = 0.63) affirmed the low empirical correlation between resistance measures in the two settings.
{"title":"Predicting Dihydroartemisinin Resistance in Plasmodium falciparum using Pathway Activity Inference","authors":"Nicola Lawford, Jonathan H. Chan","doi":"10.1145/3429210.3429215","DOIUrl":"https://doi.org/10.1145/3429210.3429215","url":null,"abstract":"Drug resistance threatens the effectiveness of treatments of infectious diseases, particularly on the global scale where mutation is rapid, mechanisms of resistance are developing or unknown, and limited data is available. Pathway activity inference is a dimensionality reduction method with proven effectiveness in classifying cancer types and drug responses based on transcription data. We propose a novel application of pathway activity inference to predict dihydroartemisinin resistance in the Plasmodium falciparum strain of malaria, a global infectious disease. Optimized pathway activity inference models outperform untransformed gene expression models in both in vitro regression (p = 0.03) and in vivo classification tasks (p = 2 × 10− 9). Optimal methods were found to be mostly ensemble (5 of 12) and/or kernel-based (7 of 12), providing the first evidence of the effectiveness of kernel methods for predicting drug resistance in infectious diseases. Performance metrics of the optimal in vitro model on in vivo data (accuracy , area under receiver operating characteristic curve = 0.63) affirmed the low empirical correlation between resistance measures in the two settings.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114144239","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}
Kritsada Sreebunpeng, Jonathan H. Chan, A. Meechai
In recent years, the increasing availability of cancer RNA-seq datasets has provided unprecedented information and opportunities for the discovery of biomarkers for cancer. In this study, we tested our previously published Gene Sub-Network-based Feature Selection (GSNFS) method to identify gene-subnetwork biomarkers with RNA-seq-based gene expression data of lung cancer. In addition, five different filter-based feature selection techniques were explored to rank identified subnetworks. We found that the majority of the top 10 ranked subnetworks were associated with cancer pathways such as the MAPK signalling pathway. With Support Vector Machine (SVM) as a classifier based on the Area Under Curve (AUC) of the Receiver Operating Characteristic (ROC) curve using 10-fold cross-validation and cross-dataset validation, we showed that gene subnetwork biomarkers obtained by RNA-seq-based GSNFS analysis had excellent classification performance. Additionally, when comparing the top-ranked subnetworks obtained from RNA-seq-based GSNFS analysis with those top-ranked subnetworks previously obtained from DNA microarray-based GSNFS analysis, we could categorize subnetworks and found unique pathways of cancer for each data-based analysis.
{"title":"Identification of Gene Subnetwork Biomarkers of Lung Cancer from RNA-seq Data","authors":"Kritsada Sreebunpeng, Jonathan H. Chan, A. Meechai","doi":"10.1145/3429210.3429212","DOIUrl":"https://doi.org/10.1145/3429210.3429212","url":null,"abstract":"In recent years, the increasing availability of cancer RNA-seq datasets has provided unprecedented information and opportunities for the discovery of biomarkers for cancer. In this study, we tested our previously published Gene Sub-Network-based Feature Selection (GSNFS) method to identify gene-subnetwork biomarkers with RNA-seq-based gene expression data of lung cancer. In addition, five different filter-based feature selection techniques were explored to rank identified subnetworks. We found that the majority of the top 10 ranked subnetworks were associated with cancer pathways such as the MAPK signalling pathway. With Support Vector Machine (SVM) as a classifier based on the Area Under Curve (AUC) of the Receiver Operating Characteristic (ROC) curve using 10-fold cross-validation and cross-dataset validation, we showed that gene subnetwork biomarkers obtained by RNA-seq-based GSNFS analysis had excellent classification performance. Additionally, when comparing the top-ranked subnetworks obtained from RNA-seq-based GSNFS analysis with those top-ranked subnetworks previously obtained from DNA microarray-based GSNFS analysis, we could categorize subnetworks and found unique pathways of cancer for each data-based analysis.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130295515","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 Huang, Madeline Diep, Kuk Jin Jang, E. Cherry, F. Fenton, R. Cleaveland, Mikael Lindvall, R. Mangharam, Adam Porter
The study of cardiac arrhythmias has spurred the development of models across a variety of formulations and scales and designed for different purposes, each with distinct configuration spaces. Nevertheless, these models should be able to exhibit equivalent behavior when their contexts overlap. Configuring models to both support this context equivalence and still exhibit intended behavioral characteristics can be challenging. Due to the complexity of this problem, automation can be desirable. We present a framework aimed at automating the comprehension and alignment of cardiac model behaviors. For model comprehension, we mine a set of properties (invariants) that a model with given configuration will exhibit when executed. Comprehension can be extended to model alignment: we perform comprehension of one model, and then mine a set of configurations for a second, each of which produces invariants aligned to the invariants of the first. The configuration spaces of the two models under study need not be related in any way; rather, the systems are compared by means of the system invariants that they each exhibit. We model system invariants as association rules, a well-studied representation used in the field of data mining. We apply our methodology to two one-dimensional models of cardiac tissue. One model is the well-known differential-equations-based Fenton-Karma model representing the electrophysiology of interconnected cardiac cells, while the other is a timed automaton representation of cardiac tissue designed to enable formal analysis. We demonstrate alignment of the models with respect to activation rates and path conductance. We expect this methodology can be generalized beyond cardiac models.
{"title":"Towards Automated Comprehension and Alignment of Cardiac Models at the System Invariant Level","authors":"Samuel Huang, Madeline Diep, Kuk Jin Jang, E. Cherry, F. Fenton, R. Cleaveland, Mikael Lindvall, R. Mangharam, Adam Porter","doi":"10.1145/3429210.3429225","DOIUrl":"https://doi.org/10.1145/3429210.3429225","url":null,"abstract":"The study of cardiac arrhythmias has spurred the development of models across a variety of formulations and scales and designed for different purposes, each with distinct configuration spaces. Nevertheless, these models should be able to exhibit equivalent behavior when their contexts overlap. Configuring models to both support this context equivalence and still exhibit intended behavioral characteristics can be challenging. Due to the complexity of this problem, automation can be desirable. We present a framework aimed at automating the comprehension and alignment of cardiac model behaviors. For model comprehension, we mine a set of properties (invariants) that a model with given configuration will exhibit when executed. Comprehension can be extended to model alignment: we perform comprehension of one model, and then mine a set of configurations for a second, each of which produces invariants aligned to the invariants of the first. The configuration spaces of the two models under study need not be related in any way; rather, the systems are compared by means of the system invariants that they each exhibit. We model system invariants as association rules, a well-studied representation used in the field of data mining. We apply our methodology to two one-dimensional models of cardiac tissue. One model is the well-known differential-equations-based Fenton-Karma model representing the electrophysiology of interconnected cardiac cells, while the other is a timed automaton representation of cardiac tissue designed to enable formal analysis. We demonstrate alignment of the models with respect to activation rates and path conductance. We expect this methodology can be generalized beyond cardiac models.","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122508357","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":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","authors":"","doi":"10.1145/3429210","DOIUrl":"https://doi.org/10.1145/3429210","url":null,"abstract":"","PeriodicalId":164790,"journal":{"name":"CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114902028","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：