Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995043
Guoxing Yang, Xiaohong Liu, Jianyu Shi, Xianchao Zhang, Guangyu Wang
Lung cancer is one of the leading causes of death worldwide. Early diagnosis through cancer screening can significantly improve lung cancer patients’ survival. Recently, deep learning based diagnostic systems for nodule detection have shown great potential in assisting radiologists to screen cancer more efficiently. However, studies have found that deep learning models lack robustness against imperceptible crafted adversarial attacks and few studied improving the robustness of pulmonary nodule detection. Therefore, making pulmonary nodule detection models robust remains challenges. Moreover, traditional adversarial training methods either hurt the natural generalization or need expensive computational cost. To address these challenges, here we propose a novel adversarial training method called, Adaptive Iteration Adversarial Training (AIAT). AIAT generates adversarial samples by adding adversarial noise with an adaptive iteration strategy, so that it can stably and fast train models with improving robustness. Extensive experiments on the LUNA 16 dataset show that AIAT improves robustness for pulmonary nodule detection without compromising the natural generalization, and largely reduces training time.
{"title":"AIAT: Adaptive Iteration Adversarial Training for Robust Pulmonary Nodule Detection","authors":"Guoxing Yang, Xiaohong Liu, Jianyu Shi, Xianchao Zhang, Guangyu Wang","doi":"10.1109/BIBM55620.2022.9995043","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995043","url":null,"abstract":"Lung cancer is one of the leading causes of death worldwide. Early diagnosis through cancer screening can significantly improve lung cancer patients’ survival. Recently, deep learning based diagnostic systems for nodule detection have shown great potential in assisting radiologists to screen cancer more efficiently. However, studies have found that deep learning models lack robustness against imperceptible crafted adversarial attacks and few studied improving the robustness of pulmonary nodule detection. Therefore, making pulmonary nodule detection models robust remains challenges. Moreover, traditional adversarial training methods either hurt the natural generalization or need expensive computational cost. To address these challenges, here we propose a novel adversarial training method called, Adaptive Iteration Adversarial Training (AIAT). AIAT generates adversarial samples by adding adversarial noise with an adaptive iteration strategy, so that it can stably and fast train models with improving robustness. Extensive experiments on the LUNA 16 dataset show that AIAT improves robustness for pulmonary nodule detection without compromising the natural generalization, and largely reduces training time.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128230364","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995300
Yuqi Chen, Juan Liu, Peng Jiang, Jing Feng, Dehua Cao, Baochuan Pang
Lots of researchers have studied for classifying histopathological whole slide images (WSIs). Since a WSI is too large to be processed directly, researchers usually cut it into many small-sized patches and then integrate the discriminative features extracted from the patches to obtain a slide-level feature of the WSI. The integration strategy generating the slide-level features is crucial for the WSI classification model. Lots of attention-based methods have been proposed for such purpose. However, most attention-based methods do not take the patches relationship into consideration, which affects the classification performance of the models. In this work, we propose a novel Context-Guided attention (CGattention) method to integrate the patch-level features, which constructs a context vector to simulate the global context information of the whole WSI and implicitly characterizes the relationship between patches in the WSI. When evaluated on two publicly available datasets, the CGattention based model obtained the better performance than other attention-based models.
{"title":"A Context-Guided Attention Method for Integrating Features of Histopathological Patches","authors":"Yuqi Chen, Juan Liu, Peng Jiang, Jing Feng, Dehua Cao, Baochuan Pang","doi":"10.1109/BIBM55620.2022.9995300","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995300","url":null,"abstract":"Lots of researchers have studied for classifying histopathological whole slide images (WSIs). Since a WSI is too large to be processed directly, researchers usually cut it into many small-sized patches and then integrate the discriminative features extracted from the patches to obtain a slide-level feature of the WSI. The integration strategy generating the slide-level features is crucial for the WSI classification model. Lots of attention-based methods have been proposed for such purpose. However, most attention-based methods do not take the patches relationship into consideration, which affects the classification performance of the models. In this work, we propose a novel Context-Guided attention (CGattention) method to integrate the patch-level features, which constructs a context vector to simulate the global context information of the whole WSI and implicitly characterizes the relationship between patches in the WSI. When evaluated on two publicly available datasets, the CGattention based model obtained the better performance than other attention-based models.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129943795","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995330
Hang Wei, Xiayue Fan, Shuai Wu
Circular RNAs (circRNAs) are severing as important regulators for various physiological and pathological life activities. Identifying associations between circRNAs and diseases can help uncover the disease mechanism, and promote the diagnosis and treatment of human diseases. To provide assisting guidance and optimize biological experiments, some computational methods have been proposed to predict circRNA-disease associations. However, most predictors focus on identifying missing associations for known circRNA and diseases. It is still challenging to effectively detect potential circRNA-disease association pattern because of their limited generation ability and insufficient pair representation. In this regard, we propose a novel computational method named iCircDA-ENR for identifying circRNA-disease associations based on ensemble network representation. Different from other predictors, iCircDA-ENR is a ranking method. Multiple biological information and meta-paths are introduced to construct heterogeneous relation network, and then different network representation algorithms are incorporated into ranking framework to capture informative network features. The learned ranking predictor prioritizes the candidate diseases for query circRNAs according to their relevance degree. Experimental results illustrate that iCircDA-ENR achieves better performance and wider applicability, benefited from its sufficient representation and effective learning.
{"title":"iCircDA-ENR: identification of circRNA-disease associations based on ensemble network representation","authors":"Hang Wei, Xiayue Fan, Shuai Wu","doi":"10.1109/BIBM55620.2022.9995330","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995330","url":null,"abstract":"Circular RNAs (circRNAs) are severing as important regulators for various physiological and pathological life activities. Identifying associations between circRNAs and diseases can help uncover the disease mechanism, and promote the diagnosis and treatment of human diseases. To provide assisting guidance and optimize biological experiments, some computational methods have been proposed to predict circRNA-disease associations. However, most predictors focus on identifying missing associations for known circRNA and diseases. It is still challenging to effectively detect potential circRNA-disease association pattern because of their limited generation ability and insufficient pair representation. In this regard, we propose a novel computational method named iCircDA-ENR for identifying circRNA-disease associations based on ensemble network representation. Different from other predictors, iCircDA-ENR is a ranking method. Multiple biological information and meta-paths are introduced to construct heterogeneous relation network, and then different network representation algorithms are incorporated into ranking framework to capture informative network features. The learned ranking predictor prioritizes the candidate diseases for query circRNAs according to their relevance degree. Experimental results illustrate that iCircDA-ENR achieves better performance and wider applicability, benefited from its sufficient representation and effective learning.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130127720","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995251
Shilin Zhang, Qingcheng Zhang
Emotion recognition is an important component of human-computer interaction (HCI) systems. However, current emotion recognition methods have some drawbacks such as inconsistency in brain network size, lack of effective mining of features in different dimensions. In this paper, we propose a multidimensional feature extraction method based on MSTBN and EEMD-WPT for emotion recognition. Firstly, the wavelet packet transform (WPT) is utilized to decompose the pre-processed electroencephalography (EEG) signals into four frequency bands ($theta,alpha,beta$, and $gamma$), and phase locking value (PLV) is used to construct multi-band connectivity matrix. Secondly, to remove redundant information, the minimum spanning tree based brain network (MSTBN) is established and MSTBN features are extracted including global features and local features. Thirdly, ensemble empirical mode decomposition (EEMD) and WPT (EEMD-WPT) are applied to EEG signals for a more refined decomposition of modes and bands. Then, the modified multi-scale sample entropy (MMSE) and fractal dimension (FD) are extracted to capture the neural activity processes in the brain. Finally, the MSTBN features are fused with the nonlinear features MMSE and FD, which are input into random forest (RF) to identify emotions. Experimental results on DEAP dataset indicate that the accuracy is 87.24% and 89.84% for valance and arousal. Experimental analysis reveals that MSTBN of negative emotions is more divergent and emotional information is transmitted more rapidly in the brain. Women are more susceptible to emotional perception than men. The proposed multidimensional feature extraction method has potential to be applied to HCI systems.
情感识别是人机交互(HCI)系统的重要组成部分。然而,目前的情绪识别方法存在脑网络大小不一致、缺乏对不同维度特征的有效挖掘等缺点。本文提出了一种基于MSTBN和EEMD-WPT的情感识别多维特征提取方法。首先,利用小波包变换(WPT)将预处理后的脑电图信号分解为4个频段($theta,alpha,beta$、$gamma$),并利用锁相值(PLV)构建多频段连接矩阵;其次,为了去除冗余信息,建立基于最小生成树的脑网络(MSTBN),提取MSTBN特征,包括全局特征和局部特征;第三,将集成经验模态分解(EEMD)和WPT (EEMD-WPT)技术应用于脑电信号中,得到更精细的模态和频带分解。然后,提取改进的多尺度样本熵(MMSE)和分形维数(FD)来捕捉大脑的神经活动过程;最后,将MSTBN特征与非线性特征MMSE和FD融合,输入到随机森林(RF)中进行情绪识别。在DEAP数据集上的实验结果表明,该方法的准确率为87.24% and 89.84% for valance and arousal. Experimental analysis reveals that MSTBN of negative emotions is more divergent and emotional information is transmitted more rapidly in the brain. Women are more susceptible to emotional perception than men. The proposed multidimensional feature extraction method has potential to be applied to HCI systems.
{"title":"A Multidimensional Feature Extraction Method Based on MSTBN and EEMD-WPT for Emotion Recognition from EEG Signals","authors":"Shilin Zhang, Qingcheng Zhang","doi":"10.1109/BIBM55620.2022.9995251","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995251","url":null,"abstract":"Emotion recognition is an important component of human-computer interaction (HCI) systems. However, current emotion recognition methods have some drawbacks such as inconsistency in brain network size, lack of effective mining of features in different dimensions. In this paper, we propose a multidimensional feature extraction method based on MSTBN and EEMD-WPT for emotion recognition. Firstly, the wavelet packet transform (WPT) is utilized to decompose the pre-processed electroencephalography (EEG) signals into four frequency bands ($theta,alpha,beta$, and $gamma$), and phase locking value (PLV) is used to construct multi-band connectivity matrix. Secondly, to remove redundant information, the minimum spanning tree based brain network (MSTBN) is established and MSTBN features are extracted including global features and local features. Thirdly, ensemble empirical mode decomposition (EEMD) and WPT (EEMD-WPT) are applied to EEG signals for a more refined decomposition of modes and bands. Then, the modified multi-scale sample entropy (MMSE) and fractal dimension (FD) are extracted to capture the neural activity processes in the brain. Finally, the MSTBN features are fused with the nonlinear features MMSE and FD, which are input into random forest (RF) to identify emotions. Experimental results on DEAP dataset indicate that the accuracy is 87.24% and 89.84% for valance and arousal. Experimental analysis reveals that MSTBN of negative emotions is more divergent and emotional information is transmitted more rapidly in the brain. Women are more susceptible to emotional perception than men. The proposed multidimensional feature extraction method has potential to be applied to HCI systems.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128951512","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995586
R. D. Luca, Marco Carfora, Gonzalo Blanco, A. Mastropietro, M. Petti, P. Tieri
The possibility to computationally prioritize candidate disease genes capitalizing on existing information has led to a speedup in the discovery of new methods. Many gene discovery techniques exploit network data, like protein-protein interactions (PPIs), in order to extract knowledge from the network structure relying on several network metrics. We here present PROCONSUL, a method that builds on top of the concept of connectivity significance (CS) and exploits the idea of probabilistic exploration of the space of putative disease genes. We show that our methodology is able to outperform the state-of-the-art tool based on CS in several settings, and propose different, effective gene discovery strategies according to specific disease network properties.
{"title":"PROCONSUL: PRObabilistic exploration of CONnectivity Significance patterns for disease modULe discovery","authors":"R. D. Luca, Marco Carfora, Gonzalo Blanco, A. Mastropietro, M. Petti, P. Tieri","doi":"10.1109/BIBM55620.2022.9995586","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995586","url":null,"abstract":"The possibility to computationally prioritize candidate disease genes capitalizing on existing information has led to a speedup in the discovery of new methods. Many gene discovery techniques exploit network data, like protein-protein interactions (PPIs), in order to extract knowledge from the network structure relying on several network metrics. We here present PROCONSUL, a method that builds on top of the concept of connectivity significance (CS) and exploits the idea of probabilistic exploration of the space of putative disease genes. We show that our methodology is able to outperform the state-of-the-art tool based on CS in several settings, and propose different, effective gene discovery strategies according to specific disease network properties.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129150079","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995052
Guohua Hu, Jianxiu Jin, Zhen Song, Shibin Wu, Lin Shu, Junan Xie, Jianlin Ou, Zhuoming Chen, Xiangmin Xu
Falling is characterized by high incidence and great harm among the elderly. Timely assessing falling risk in daily life is helpful for reducing the occurrence of severe health outcomes. Establishing dataset for falling risk assessment based on wearable devices in the elderly is important work. However, current existing datasets might not reflect the natural gait of the subject due to the discomfort in wearing. Relevant data processing methods based on these datasets have limited practicability and might not be applied to real scenes in daily life. To make daily falling risk assessment possible, we proposed a novel approach to set up a continuous and wearable plantar pressure dataset of 48 older adults along with falling risk labels. The dataset was collected by plantar pressure monitoring shoes which were suitable for daily living spaces. Moreover, the Conv-LSTM algorithm was applied on the dataset, and the average classification result was up to 95.57%, reflecting the effectiveness of this dataset. The dataset is helpful for the studies of falling risk assessment and health monitoring among the elderly.
{"title":"A Dataset for Falling Risk Assessment of the Elderly using Wearable Plantar Pressure","authors":"Guohua Hu, Jianxiu Jin, Zhen Song, Shibin Wu, Lin Shu, Junan Xie, Jianlin Ou, Zhuoming Chen, Xiangmin Xu","doi":"10.1109/BIBM55620.2022.9995052","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995052","url":null,"abstract":"Falling is characterized by high incidence and great harm among the elderly. Timely assessing falling risk in daily life is helpful for reducing the occurrence of severe health outcomes. Establishing dataset for falling risk assessment based on wearable devices in the elderly is important work. However, current existing datasets might not reflect the natural gait of the subject due to the discomfort in wearing. Relevant data processing methods based on these datasets have limited practicability and might not be applied to real scenes in daily life. To make daily falling risk assessment possible, we proposed a novel approach to set up a continuous and wearable plantar pressure dataset of 48 older adults along with falling risk labels. The dataset was collected by plantar pressure monitoring shoes which were suitable for daily living spaces. Moreover, the Conv-LSTM algorithm was applied on the dataset, and the average classification result was up to 95.57%, reflecting the effectiveness of this dataset. The dataset is helpful for the studies of falling risk assessment and health monitoring among the elderly.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130585245","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995592
C. Leung, Evan W. R. Madill, N. D. Tran, Christine Y. Zhang
Nowadays, very large amounts of data are generating at a fast rate from a wide variety of rich data sources. Valuable information and knowledge embedded in these big data can be discovered by data science, data mining and machine learning techniques. Biomedical records are examples of the big data. With the technological advancements, more healthcare practice has gradually been supported by electronic processes and communication. This enables health informatics, in which computer science meets the healthcare sector to address healthcare and medical problems. As a concrete example, there have been more than 635 millions cumulative cases of coronavirus disease 2019 (COVID-19) worldwide over the past 3 years since COVID-19 has declared as a pandemic. Hence, effective strategies, solutions, tools and methods—such as artificial intelligence (AI) and/or big data approaches—to tackle the COVID-19 pandemic and possible future pandemics are in demand. In this paper, we present models to analyze big COVID-19 pandemic data and make predictions via N-shot learning. Specifically, our binary model predicts whether patients are COVID-19 or not. If so, the model predicts whether they require hospitalization or not, whereas our multi-class model predicts severity and thus the corresponding levels of hospitalization required by the patients. Our models uses N-shot learning with autoencoders. Evaluation results on real-life pandemic data demonstrate the practicality of our models towards effective allocation of resources (e.g., hospital facilities, staff). These showcase the benefits of AI and/or big data approaches in tackling the pandemic.
{"title":"Health Informatics on Big COVID-19 Pandemic Data via N-Shot Learning","authors":"C. Leung, Evan W. R. Madill, N. D. Tran, Christine Y. Zhang","doi":"10.1109/BIBM55620.2022.9995592","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995592","url":null,"abstract":"Nowadays, very large amounts of data are generating at a fast rate from a wide variety of rich data sources. Valuable information and knowledge embedded in these big data can be discovered by data science, data mining and machine learning techniques. Biomedical records are examples of the big data. With the technological advancements, more healthcare practice has gradually been supported by electronic processes and communication. This enables health informatics, in which computer science meets the healthcare sector to address healthcare and medical problems. As a concrete example, there have been more than 635 millions cumulative cases of coronavirus disease 2019 (COVID-19) worldwide over the past 3 years since COVID-19 has declared as a pandemic. Hence, effective strategies, solutions, tools and methods—such as artificial intelligence (AI) and/or big data approaches—to tackle the COVID-19 pandemic and possible future pandemics are in demand. In this paper, we present models to analyze big COVID-19 pandemic data and make predictions via N-shot learning. Specifically, our binary model predicts whether patients are COVID-19 or not. If so, the model predicts whether they require hospitalization or not, whereas our multi-class model predicts severity and thus the corresponding levels of hospitalization required by the patients. Our models uses N-shot learning with autoencoders. Evaluation results on real-life pandemic data demonstrate the practicality of our models towards effective allocation of resources (e.g., hospital facilities, staff). These showcase the benefits of AI and/or big data approaches in tackling the pandemic.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130620948","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995264
Xuan Yang, Keqin Li, Yang Zhang, Xi Yu, Junli Deng, Jianxiao Liu
Proposing a more effective and accurate epistatic loci detection method is of great significance in improving crop quality, disease treatment, etc. Due to the characteristics of high accuracy and processing non-linear relationship, Bayesian network (BN) has been widely used in constructing the network of SNPs and phenotypes and thus to mine epistasis. However, the shortcoming of BN is that the search space is too large and unable to process large-scale SNPs. In this work, we propose a kind of epistasis mining method using Markov Chain Monte Carlo (MCMC) sampling optimizing Bayesian network (EpiMCBN). Firstly, we use the space of node order composed of SNPs and phenotype to replace the space of network structure. Then MCMC algorithm is used to do sampling to generate multiple different initial orders in linear space or partial space. We use Markov state transition matrix to transfer the initial samples along the Markov chain, thus obtaining multiple order samples. Then we use the $alpha$-BICBN scoring function to score the Bayesian networks corresponding to these node orders. Through estimating the probability of edge occurrence in the Bayesian networks, we get an approximate Bayesian network of SNPs and phenotype, then obtain the epistatic loci affecting phenotype. Finally, we compare EpiMCBN with the current popular epistasis mining algorithms using both simulated and real age-related macular disease (AMD) datasets. Experiment results show that EpiMCBN has better epistasis detection accuracy, lower false positive rate, and higher F1-score compared to other methods. Availability and implementation: Source code and dataset are available at: http://122.205.95.139/EpiMCBN/.
{"title":"EpiMCBN: A Kind of Epistasis Mining Approach Using MCMC Sampling Optimizing Bayesian Network","authors":"Xuan Yang, Keqin Li, Yang Zhang, Xi Yu, Junli Deng, Jianxiao Liu","doi":"10.1109/BIBM55620.2022.9995264","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995264","url":null,"abstract":"Proposing a more effective and accurate epistatic loci detection method is of great significance in improving crop quality, disease treatment, etc. Due to the characteristics of high accuracy and processing non-linear relationship, Bayesian network (BN) has been widely used in constructing the network of SNPs and phenotypes and thus to mine epistasis. However, the shortcoming of BN is that the search space is too large and unable to process large-scale SNPs. In this work, we propose a kind of epistasis mining method using Markov Chain Monte Carlo (MCMC) sampling optimizing Bayesian network (EpiMCBN). Firstly, we use the space of node order composed of SNPs and phenotype to replace the space of network structure. Then MCMC algorithm is used to do sampling to generate multiple different initial orders in linear space or partial space. We use Markov state transition matrix to transfer the initial samples along the Markov chain, thus obtaining multiple order samples. Then we use the $alpha$-BICBN scoring function to score the Bayesian networks corresponding to these node orders. Through estimating the probability of edge occurrence in the Bayesian networks, we get an approximate Bayesian network of SNPs and phenotype, then obtain the epistatic loci affecting phenotype. Finally, we compare EpiMCBN with the current popular epistasis mining algorithms using both simulated and real age-related macular disease (AMD) datasets. Experiment results show that EpiMCBN has better epistasis detection accuracy, lower false positive rate, and higher F1-score compared to other methods. Availability and implementation: Source code and dataset are available at: http://122.205.95.139/EpiMCBN/.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130747733","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995075
J. Shang, Yijun Gu, Y. Sun, Feng Li, Jin-Xin Liu, Boxin Guan
In the genome-wide association studies (GWAS), epistasis detection is of great significance to study the pathogenesis of complex diseases. Epistasis refers to the effect of interactions between multiple single nucleotide polymorphisms (SNPs) on complex diseases. In this paper, an artificial bee colony algorithm based on self-adjusting random grouping (ABC-SRG) is proposed for high-order epistasis detection. ABC-SRG adopts a new self-adjusting random grouping strategy, which realizes the division of the original data according to the fitness value of each grouping. In addition, a variance-based adaptive iteration strategy is proposed, which implements the adaptive iteration through the variance of the fitness value of each iteration of the algorithm. To demonstrate the effectiveness of the algorithm, the experiments on simulated data and real data were conducted. In the simulation experiments, ABC-SRG was compared with the other five methods for second-order and third-order SNP interaction detection. Age-related macular degeneration (AMD) data were selected for the real data experiment, and most of the SNP interactions detected in the experiment have been confirmed to be related to the AMD disease. Therefore, ABC-SRG is an effective method to detect high-order epistasis.
{"title":"Artificial bee colony algorithm based on self-adjusting random grouping for high-order epistasis detection","authors":"J. Shang, Yijun Gu, Y. Sun, Feng Li, Jin-Xin Liu, Boxin Guan","doi":"10.1109/BIBM55620.2022.9995075","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995075","url":null,"abstract":"In the genome-wide association studies (GWAS), epistasis detection is of great significance to study the pathogenesis of complex diseases. Epistasis refers to the effect of interactions between multiple single nucleotide polymorphisms (SNPs) on complex diseases. In this paper, an artificial bee colony algorithm based on self-adjusting random grouping (ABC-SRG) is proposed for high-order epistasis detection. ABC-SRG adopts a new self-adjusting random grouping strategy, which realizes the division of the original data according to the fitness value of each grouping. In addition, a variance-based adaptive iteration strategy is proposed, which implements the adaptive iteration through the variance of the fitness value of each iteration of the algorithm. To demonstrate the effectiveness of the algorithm, the experiments on simulated data and real data were conducted. In the simulation experiments, ABC-SRG was compared with the other five methods for second-order and third-order SNP interaction detection. Age-related macular degeneration (AMD) data were selected for the real data experiment, and most of the SNP interactions detected in the experiment have been confirmed to be related to the AMD disease. Therefore, ABC-SRG is an effective method to detect high-order epistasis.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131954702","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}
Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995247
Yanglin Huang, Donghui Tan, Yuan Zhang, Xuanya Li, Kai Hu
Learning how to fully extract global representations and local features is a key factor in improving the performance of polyp segmentation. In this paper, we explore the potential of combined techniques of Transformers and convolutional neural networks (CNNs) to address the challenges of polyp segmentation. Specifically, we present TransMixer, a hybrid interaction fusion architecture of the Transformer branch and the CNN branch, which is able to enhance the local details of global representations and the global context awareness of local features. To achieve this, we first bridge the semantic gap between the Transformer branch and the CNN branch through the Interaction Fusion Module (IFM), and then make full use of both respective properties to enhance polyp feature representations. After that, we further propose the Hierarchical Attention Module (HAM) to collect polyp semantic information from high-level features to gradually guide the recovery of polyp spatial information in low-level features. Quantitative and qualitative results show that the proposed model is more robust to various complex situations compared to existing methods, and achieves state-of-the-art performance in polyp segmentation.
{"title":"TransMixer: A Hybrid Transformer and CNN Architecture for Polyp Segmentation","authors":"Yanglin Huang, Donghui Tan, Yuan Zhang, Xuanya Li, Kai Hu","doi":"10.1109/BIBM55620.2022.9995247","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995247","url":null,"abstract":"Learning how to fully extract global representations and local features is a key factor in improving the performance of polyp segmentation. In this paper, we explore the potential of combined techniques of Transformers and convolutional neural networks (CNNs) to address the challenges of polyp segmentation. Specifically, we present TransMixer, a hybrid interaction fusion architecture of the Transformer branch and the CNN branch, which is able to enhance the local details of global representations and the global context awareness of local features. To achieve this, we first bridge the semantic gap between the Transformer branch and the CNN branch through the Interaction Fusion Module (IFM), and then make full use of both respective properties to enhance polyp feature representations. After that, we further propose the Hierarchical Attention Module (HAM) to collect polyp semantic information from high-level features to gradually guide the recovery of polyp spatial information in low-level features. Quantitative and qualitative results show that the proposed model is more robust to various complex situations compared to existing methods, and achieves state-of-the-art performance in polyp segmentation.","PeriodicalId":210337,"journal":{"name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131972200","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}