Pub Date : 2022-12-06DOI: 10.1109/BIBM55620.2022.9995712
Poulami Samaddar, K. Gopalakrishnan, Priyanka Anvekar, Poushali Samadder, I. C. I. Sa, Rachel Bayer, Sunil Gaddam, Dipankar Mitra, Sayan Roy, P. Hirsova, S. P. Arunachalam
Non-Alcoholic Steatohepatitis (NASH) is known as the key cause of cirrhosis in adults. As the name suggests, NASH is described as the excessive fat accumulation in the nonalcoholics. The genomic components play a vital role in the development and progression of the NASH. The existing imaging modalities have limited use in the diagnosis of NASH leading to delayed presentation of the disease. Owing to this, risk of hepatocellular carcinoma and the need for liver transplant is on a rising trend in patients with NASH. Even with the advent of new diagnostic techniques, biopsy is still considered the fundamental tool for confirming NASH. However, due to the highly invasive nature of the biopsy, its broad application becomes very difficult. Therefore, it is important to validate a tool which will identify the detection and progression of steatohepatitis and help in the timely diagnosis of the disease. Dielectric spectroscopy can be used to measure the dielectric properties of the tissue as a function of the frequency. This work introduces a feasibility study to classify between murine healthy liver and liver affected by two types of diets including nonalcoholic steatohepatitis using dielectric property of liver tissue as a biomarker. Multiclass classification using different machine learning models is performed. Among them, K-Nearest Neighbors Classifier and Random Forest Classifier showed good accuracy i.e., 89% and 90% respectively.
{"title":"Multiclass Classification of Nonalcoholic Steatohepatitis Mouse Models Using Dielectric Properties as Disease Biomarker","authors":"Poulami Samaddar, K. Gopalakrishnan, Priyanka Anvekar, Poushali Samadder, I. C. I. Sa, Rachel Bayer, Sunil Gaddam, Dipankar Mitra, Sayan Roy, P. Hirsova, S. P. Arunachalam","doi":"10.1109/BIBM55620.2022.9995712","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995712","url":null,"abstract":"Non-Alcoholic Steatohepatitis (NASH) is known as the key cause of cirrhosis in adults. As the name suggests, NASH is described as the excessive fat accumulation in the nonalcoholics. The genomic components play a vital role in the development and progression of the NASH. The existing imaging modalities have limited use in the diagnosis of NASH leading to delayed presentation of the disease. Owing to this, risk of hepatocellular carcinoma and the need for liver transplant is on a rising trend in patients with NASH. Even with the advent of new diagnostic techniques, biopsy is still considered the fundamental tool for confirming NASH. However, due to the highly invasive nature of the biopsy, its broad application becomes very difficult. Therefore, it is important to validate a tool which will identify the detection and progression of steatohepatitis and help in the timely diagnosis of the disease. Dielectric spectroscopy can be used to measure the dielectric properties of the tissue as a function of the frequency. This work introduces a feasibility study to classify between murine healthy liver and liver affected by two types of diets including nonalcoholic steatohepatitis using dielectric property of liver tissue as a biomarker. Multiclass classification using different machine learning models is performed. Among them, K-Nearest Neighbors Classifier and Random Forest Classifier showed good accuracy i.e., 89% and 90% respectively.","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":"133471837","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/BIBM55620.2022.9995089
Mengxu Zhu, Kongyan Li, Hong Yan
Covid-19 has become a world pandemic for years. With the appearance of mutations, immune escape has become a problem, reducing the effectiveness of vaccines and antibodies. To reveal the mechanism of immune escape, we analyze the geometrical properties of the receptor-binding domain in the SARS-CoV-2 spike protein, which plays a vital role in the immune reaction. Several important variants are taken as examples, and the wild type model is prepared as a reference. The computational method is applied to simulate the behaviors of the models, and alpha shape algorithm is employed to extract geometrical data of the protein surface. Average moving distance of the surface atoms is used to quantify their activity. Our results show that the mutations changed the properties of the protein. The variants have different distributions of active sites, which may change the specific antigenicity and influence the binding abilities of drugs and antibodies. This study explains the mechanism of immune escape of SARS-CoV-2, and provides a geometrical method to find potential new target sites for the design of drugs and vaccines.
{"title":"Computational Analysis of Receptor-Binding Domains of SARS-CoV-2 to Reveal the Mechanism of Immune Escape","authors":"Mengxu Zhu, Kongyan Li, Hong Yan","doi":"10.1109/BIBM55620.2022.9995089","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995089","url":null,"abstract":"Covid-19 has become a world pandemic for years. With the appearance of mutations, immune escape has become a problem, reducing the effectiveness of vaccines and antibodies. To reveal the mechanism of immune escape, we analyze the geometrical properties of the receptor-binding domain in the SARS-CoV-2 spike protein, which plays a vital role in the immune reaction. Several important variants are taken as examples, and the wild type model is prepared as a reference. The computational method is applied to simulate the behaviors of the models, and alpha shape algorithm is employed to extract geometrical data of the protein surface. Average moving distance of the surface atoms is used to quantify their activity. Our results show that the mutations changed the properties of the protein. The variants have different distributions of active sites, which may change the specific antigenicity and influence the binding abilities of drugs and antibodies. This study explains the mechanism of immune escape of SARS-CoV-2, and provides a geometrical method to find potential new target sites for the design of drugs and vaccines.","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":"132046407","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/BIBM55620.2022.9995111
Jun Huang, He Xiao, Qingfeng Wang, Zhiqin Liu, Bo Chen, Yaobin Wang, Ping Zhang, Ying Zhou
The detection of breast masses and calcified clusters on mammograms is critical for early diagnosis and treatment to improve the survivals of breast cancer patients. In this study, we propose a local-whole-focus pipeline to automatically identify breast masses and calcified clusters on full-size mammograms, from local breast tissues to the whole mammograms, and then focusing on the lesion areas. We first train a deep model to learn the fine features of breast masses and calcified clusteres on local breast tissues, and then transfer the well-trained deep model to identify breast masses and calcified clusteres on full-size mammograms with image-level annotations. We also highlight the areas of the breast masses and calcified clusteres in mammograms to visualize the identification results. We evaluated the proposed local-whole-focus pipeline on a public dataset CBIS-DDSM (Curated Breast Imaging Subset of Digital Database for Screening Mammography) and a private dataset MY-Mammo (Mianyang central hospital mammograms). The experiment results showed the DenseNet embedded with squeeze-and-excitation (SE) blocks achieved competitive results on the identification of breast masses and calcified clusteres on full-size mammograms. The highlight areas of the breast masses and calcified clusteres on the entire mammograms could also explain model decision making, which are important in practical medical applications. Index Terms–Breast mass, calcified cluster, local breast tissue, full-size mammogram, automatic identification.
{"title":"Local-Whole-Focus: Identifying Breast Masses and Calcified Clusters on Full-Size Mammograms","authors":"Jun Huang, He Xiao, Qingfeng Wang, Zhiqin Liu, Bo Chen, Yaobin Wang, Ping Zhang, Ying Zhou","doi":"10.1109/BIBM55620.2022.9995111","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995111","url":null,"abstract":"The detection of breast masses and calcified clusters on mammograms is critical for early diagnosis and treatment to improve the survivals of breast cancer patients. In this study, we propose a local-whole-focus pipeline to automatically identify breast masses and calcified clusters on full-size mammograms, from local breast tissues to the whole mammograms, and then focusing on the lesion areas. We first train a deep model to learn the fine features of breast masses and calcified clusteres on local breast tissues, and then transfer the well-trained deep model to identify breast masses and calcified clusteres on full-size mammograms with image-level annotations. We also highlight the areas of the breast masses and calcified clusteres in mammograms to visualize the identification results. We evaluated the proposed local-whole-focus pipeline on a public dataset CBIS-DDSM (Curated Breast Imaging Subset of Digital Database for Screening Mammography) and a private dataset MY-Mammo (Mianyang central hospital mammograms). The experiment results showed the DenseNet embedded with squeeze-and-excitation (SE) blocks achieved competitive results on the identification of breast masses and calcified clusteres on full-size mammograms. The highlight areas of the breast masses and calcified clusteres on the entire mammograms could also explain model decision making, which are important in practical medical applications. Index Terms–Breast mass, calcified cluster, local breast tissue, full-size mammogram, automatic identification.","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":"132453943","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/BIBM55620.2022.9995298
Piyush Basia, Tae-Hyuk Ahn, Myoungkyu Song
Modeling in machine learning (ML) is critical for software systems in practice. ML applications are required to validate their models and implementations but quality validation is a challenging and time-consuming process for developers. To address this limitation, we present a novel validation technique for ML applications to help developers or researchers (e.g., bioengineering domain) inspect (1) software code (ML API usages) and (2) ML model (extracted features).
{"title":"An IDE Support for Validating Machine Learning Applications in Bioengineering Text Corpora","authors":"Piyush Basia, Tae-Hyuk Ahn, Myoungkyu Song","doi":"10.1109/BIBM55620.2022.9995298","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995298","url":null,"abstract":"Modeling in machine learning (ML) is critical for software systems in practice. ML applications are required to validate their models and implementations but quality validation is a challenging and time-consuming process for developers. To address this limitation, we present a novel validation technique for ML applications to help developers or researchers (e.g., bioengineering domain) inspect (1) software code (ML API usages) and (2) ML model (extracted features).","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":"132634129","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/BIBM55620.2022.9995216
Gang Cao, Liying Yang, Pei Ni
The use of Electroencephalogram(EEG) for emotion recognition has tremendous potential across psychology and biomedicine. However, how the brain generates emotions remains unclear. Inspired by neuroscience and psychology, this paper puts forward the individual frontal asymmetry hypothesis and three methods of Electroencephalogram(EEG) emotion recognition based on this potential hypothesis are introduced, which recognizes and classifies the individual’s emotion effectively with signals from only four channels out of the total 32 channels. First, all EEG signals are filtered according to the EEG frequency band. Then, taking the filtered left and right frontal lobe signal differences as the input, three different models are used for classification with leave-one-out cross-validation. For each subject, one film is used for testing and the remaining films are used for training. We verify our idea on the public database DEAP, and recognition accuracy reaches 75.39% in the valence dimension and 68.13% in the arousal dimension, respectively. Since only four EEG channels were used, it greatly improves the operation efficiency and saves the running time. This work might be a demonstration that emotion recognition using individual frontal asymmetry hypothesis is effective, and it provides a potential direction for emotion recognition using portable EEG acquisition devices.
{"title":"Electroencephalogram Emotion Recognition Based on Individual Frontal Asymmetry Hypothesis","authors":"Gang Cao, Liying Yang, Pei Ni","doi":"10.1109/BIBM55620.2022.9995216","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995216","url":null,"abstract":"The use of Electroencephalogram(EEG) for emotion recognition has tremendous potential across psychology and biomedicine. However, how the brain generates emotions remains unclear. Inspired by neuroscience and psychology, this paper puts forward the individual frontal asymmetry hypothesis and three methods of Electroencephalogram(EEG) emotion recognition based on this potential hypothesis are introduced, which recognizes and classifies the individual’s emotion effectively with signals from only four channels out of the total 32 channels. First, all EEG signals are filtered according to the EEG frequency band. Then, taking the filtered left and right frontal lobe signal differences as the input, three different models are used for classification with leave-one-out cross-validation. For each subject, one film is used for testing and the remaining films are used for training. We verify our idea on the public database DEAP, and recognition accuracy reaches 75.39% in the valence dimension and 68.13% in the arousal dimension, respectively. Since only four EEG channels were used, it greatly improves the operation efficiency and saves the running time. This work might be a demonstration that emotion recognition using individual frontal asymmetry hypothesis is effective, and it provides a potential direction for emotion recognition using portable EEG acquisition devices.","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":"132677311","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/BIBM55620.2022.9995161
Zongheng Cai, J. Lei, Junli Deng, Jianxiao Liu
How to construct accurate gene regulatory networks $(GRN)$ has important significance for the research of functional genomics. Several existing gene regulatory network construction methods have the problems of low accuracy and unable to handle large scale network effectively. In order to solve the above problems, this work proposes a gene regulatory network construction method based on k-tree sampling and decomposition (KtreeGRN). It transforms the problem of gene network construction into generating codes. Firstly, it constructs the k-tree structure of the gene regulatory network through sampling dandelion codes uniformly. Then, the k-tree is decomposed into several k-cliques using the tree decomposition algorithm based on the minimum degree selection. It constructs the sub-networks for the genes in each k-clique using the mixed entropy optimizing mutual information method. Finally, it obtains the whole gene regulatory network through merging all the sub-networks. It repeats the above operations (k-tree generation, k-tree decomposition, network generation) several times and gets the final gene regulatory network according to the frequency of edges. Experimental results show that KtreeGRN performs better than other several kinds of gene network construction methods on the simulated dataset of DREAM challenge and two real datasets of Escherichia-coil (E. coli SOS pathway network, E. coli SOS DNA repair network).
{"title":"KtreeGRN: A Method of Gene Regulatory Network Construction Based on k-tree Sampling and Decomposition","authors":"Zongheng Cai, J. Lei, Junli Deng, Jianxiao Liu","doi":"10.1109/BIBM55620.2022.9995161","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995161","url":null,"abstract":"How to construct accurate gene regulatory networks $(GRN)$ has important significance for the research of functional genomics. Several existing gene regulatory network construction methods have the problems of low accuracy and unable to handle large scale network effectively. In order to solve the above problems, this work proposes a gene regulatory network construction method based on k-tree sampling and decomposition (KtreeGRN). It transforms the problem of gene network construction into generating codes. Firstly, it constructs the k-tree structure of the gene regulatory network through sampling dandelion codes uniformly. Then, the k-tree is decomposed into several k-cliques using the tree decomposition algorithm based on the minimum degree selection. It constructs the sub-networks for the genes in each k-clique using the mixed entropy optimizing mutual information method. Finally, it obtains the whole gene regulatory network through merging all the sub-networks. It repeats the above operations (k-tree generation, k-tree decomposition, network generation) several times and gets the final gene regulatory network according to the frequency of edges. Experimental results show that KtreeGRN performs better than other several kinds of gene network construction methods on the simulated dataset of DREAM challenge and two real datasets of Escherichia-coil (E. coli SOS pathway network, E. coli SOS DNA repair network).","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":"128830690","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 compressed sensing (CS) method can reconstruct images with a small amount of under-sampling data, which is an effective method for fast magnetic resonance imaging (MRI). As the traditional optimization-based models for MRI suffered from non-adaptive sampling and shallow” representation ability, they were unable to characterize the rich patterns in MRI data. In this paper, we propose a CS MRI method based on iterative shrinkage threshold algorithm (ISTA) and adaptive sparse sampling, called DSLS-ISTA-Net. Corresponding to the sampling and reconstruction of the CS method, the network framework includes two folders: the sampling sub-network and the improved ISTA reconstruction sub-network which are coordinated with each other through end-to-end training in an unsupervised way. The sampling sub-network and ISTA reconstruction sub-network are responsible for the implementation of adaptive sparse sampling and deep sparse representation respectively. In the testing phase, we investigate different modules and parameters in the network structure, and perform extensive experiments on MR images at different sampling rates to obtain the optimal network. Due to the combination of the advantages of the model-based method and the deep learning-based method in this method, and taking both adaptive sampling and deep sparse representation into account, the proposed networks significantly improve the reconstruction performance compared to the art-of-state CS-MRI approaches.
{"title":"ISTA-based Adaptive Sparse Sampling Network for Compressive Sensing MRI Reconstruction","authors":"Wenwei Huang, Chunhong Cao, Sixia Hong, Xieping Gao","doi":"10.1109/BIBM55620.2022.9994954","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9994954","url":null,"abstract":"The compressed sensing (CS) method can reconstruct images with a small amount of under-sampling data, which is an effective method for fast magnetic resonance imaging (MRI). As the traditional optimization-based models for MRI suffered from non-adaptive sampling and shallow” representation ability, they were unable to characterize the rich patterns in MRI data. In this paper, we propose a CS MRI method based on iterative shrinkage threshold algorithm (ISTA) and adaptive sparse sampling, called DSLS-ISTA-Net. Corresponding to the sampling and reconstruction of the CS method, the network framework includes two folders: the sampling sub-network and the improved ISTA reconstruction sub-network which are coordinated with each other through end-to-end training in an unsupervised way. The sampling sub-network and ISTA reconstruction sub-network are responsible for the implementation of adaptive sparse sampling and deep sparse representation respectively. In the testing phase, we investigate different modules and parameters in the network structure, and perform extensive experiments on MR images at different sampling rates to obtain the optimal network. Due to the combination of the advantages of the model-based method and the deep learning-based method in this method, and taking both adaptive sampling and deep sparse representation into account, the proposed networks significantly improve the reconstruction performance compared to the art-of-state CS-MRI approaches.","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":"128894920","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/BIBM55620.2022.9995176
Alexander Gerniers, P. Dupont
Identifying rare subpopulations in single-cell data is a key aspect when analyzing its heterogeneity. With large datasets now commonly generated, the focus went to scalability when designing rare cell mining methods, often relying on univariate approaches. Yet, MicroCellClust, an approach based on a multivariate optimization problem, has proven effective to jointly identify rare cells and specific genes in small-scale data. The proposed solver had a quadratic complexity, posing a practical limit to analyzing small or middle-scale data. Here, we present a new approach that scales MicroCellClust to larger datasets. It first performs a beam search among cells that are identified as rare to find an initial approximation. Then it uses simulated annealing, a classical derivative-free optimization algorithm which efficiently approaches the optimal solution. MicroCellClust 2 has a linear complexity in terms of the number of cells, which makes it scalable to large data (typically containing over 100000 cells). Our experiments report the identification of rare megakaryocytes within 68000 PBMCs, and rare ependymal cells within 160000 mouse brain cells. These results show that MicroCellClust 2 is more effective at identifying a subpopulation as a whole than typical alternatives, demonstrating the usefulness of jointly selecting cells and genes as opposed to other approaches.
{"title":"MicroCellClust 2: a hybrid approach for multivariate rare cell mining in large-scale single-cell data","authors":"Alexander Gerniers, P. Dupont","doi":"10.1109/BIBM55620.2022.9995176","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995176","url":null,"abstract":"Identifying rare subpopulations in single-cell data is a key aspect when analyzing its heterogeneity. With large datasets now commonly generated, the focus went to scalability when designing rare cell mining methods, often relying on univariate approaches. Yet, MicroCellClust, an approach based on a multivariate optimization problem, has proven effective to jointly identify rare cells and specific genes in small-scale data. The proposed solver had a quadratic complexity, posing a practical limit to analyzing small or middle-scale data. Here, we present a new approach that scales MicroCellClust to larger datasets. It first performs a beam search among cells that are identified as rare to find an initial approximation. Then it uses simulated annealing, a classical derivative-free optimization algorithm which efficiently approaches the optimal solution. MicroCellClust 2 has a linear complexity in terms of the number of cells, which makes it scalable to large data (typically containing over 100000 cells). Our experiments report the identification of rare megakaryocytes within 68000 PBMCs, and rare ependymal cells within 160000 mouse brain cells. These results show that MicroCellClust 2 is more effective at identifying a subpopulation as a whole than typical alternatives, demonstrating the usefulness of jointly selecting cells and genes as opposed to other approaches.","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":"131876607","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/BIBM55620.2022.9995535
Yu Zhang, Lin Tong, Guangkun Chen, Xiang Li, Hongtao Li
Objective: To explore and analyze the medication rule of Chinese medicine master Yu Ying-ao in the treatment of primary epilepsy, hoping to provide reference for the clinical treatment of primary epilepsy. Methods: Mining and analysis primary epilepsy Outpatient records of Chinese medicine master Yu Ying-ao, extracted the traditional Chinese medicine(TCM) diagnosis and treatment data in the medical cases, standardized the obtained TCM diagnosis and treatment data, and used the data mining function integrated by the ancient and modern medical case cloud platform V2.3.5 to carry out frequency statistics, cluster analysis, association analysis and complex network analysis on the diagnosis and treatment data, the common medicines used by Chinese medicine master Yu Ying-ao in the treatment of primary epilepsy, properties and classifications of commonly used medicines, therapeutic principle and method and coreprescriptions were obtained. Results: A total of 70 cases, 213 medical records and 231 prescriptions data of TCM were included. A total of 120 Chinese medicines were involved, and the total frequency of medication was 3388. The core prescription groups mined through the complex network method are: Raw Concha Ostreae(Shengmuli), Radix Curcumae(Yujin), Alum(Baifan), longchi, Salvia miltiorrhiza(Danshen), Caulis Bambusae in Taenia(Zhuru), Semen armeniacae amarum(Kuxingren), Semen Persicae(Taoren), Arisaema cum Bile(Dannanxing) and Amber(Hupo). In the prescription, Raw Concha Ostreae(Shengmuli) and Radix Curcumae(Yujin) were king medicines and also high-frequency medicines, all of which were cold medicines. Yu Ying-ao's clinical dosage of Alum(Baifan) was between $1.5 sim 3mathrm{g}$, and the curative effect was enhanced by decocting it first to remove its great fire. Yu Ying-ao's clinical high-frequency medicines are: Raw Concha Ostreae(Shengmuli), Radix Curcumae(Yujin), Alum(Baifan), Salvia miltiorrhiza(Danshen), Longchi, Semen armeniacae amarum(Kuxingren), Semen Persicae(Taoren) and Arisaema cum Bile(Dannanxing). Most of the high-frequency medicines were cold medicines (such as Shengmuli, Yujin, Baifan, Kuxingren, etc.), The specific drugs were mild cold drugs (827 times). The most common distribution of the five flavors of traditional Chinese medicine was bitter medicine (1678 times), the meridian of returning to the liver (2214 times) was the most common. The top three efficacy of 120 traditional Chinese medicines were moistening bowels (529 times), promoting blood circulation and removing blood stasis (436 times), clearing heat and resolving phlegm (385 times).Conclusion: Chinese medicine master Yu Ying-ao takes the principle of purging excess and tonifying deficiency, and purging more than tonifying. To calm the mind, invigorate the spleen, regulate the liver, moisten the internal organs, reconcile the middle, and invigorate the qi, and harmonizing lung, heart, spleen and large intestine.
目的:探讨和分析中医大师余应饶治疗原发性癫痫的用药规律,希望为临床治疗原发性癫痫提供参考。方法:挖掘分析中医大师余应敖的癫痫初级门诊病历,提取病例中的中医诊疗数据,对获得的中医诊疗数据进行标准化,利用古今医疗案例云平台V2.3.5集成的数据挖掘功能,对诊疗数据进行频次统计、聚类分析、关联分析和复杂网络分析。获得中医大师余应傲治疗原发性癫痫的常用药物、常用药物的性质、分类、治疗原理、方法及配方。结果:共纳入70例病例,病历213份,中药处方资料231份。共涉及120种中药,总用药频次为3388种。通过复杂网络方法挖掘的核心处方群为:生木耳、姜黄、白矾、龙池、丹参、竹如、苦杏仁、桃仁、丹参胆汁、虎坡琥珀。方剂中生木耳、郁金为王药,也是高频药,均为感冒药。余应敖的白矾临床用量在1.5 μ m ~ 3 μ m之间,先煎除其大火,疗效更佳。余应傲的临床高频用药有:生木耳、姜黄、白矾、丹参、龙池、苦杏仁、桃仁、丹参胆。高频药以感冒药(如生木里、玉金、白凡、苦杏仁等)居多,特异药以轻度感冒药居多(827次)。中医五味分布最常见的是苦药(1678次)、归肝经(2214次)。120种中药功效排名前三的分别是润肠(529次)、活血化瘀(436次)、清热化痰(385次)。结论:余应傲中医大师以清亢补虚为主,清大于补。平心静气,健脾,调肝,润脏腑,调和中脉,补气,调和肺、心、脾、大肠。
{"title":"Study on the treatment rules of primary epilepsy of treated by National TCM Master Yu Ying-ao","authors":"Yu Zhang, Lin Tong, Guangkun Chen, Xiang Li, Hongtao Li","doi":"10.1109/BIBM55620.2022.9995535","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9995535","url":null,"abstract":"Objective: To explore and analyze the medication rule of Chinese medicine master Yu Ying-ao in the treatment of primary epilepsy, hoping to provide reference for the clinical treatment of primary epilepsy. Methods: Mining and analysis primary epilepsy Outpatient records of Chinese medicine master Yu Ying-ao, extracted the traditional Chinese medicine(TCM) diagnosis and treatment data in the medical cases, standardized the obtained TCM diagnosis and treatment data, and used the data mining function integrated by the ancient and modern medical case cloud platform V2.3.5 to carry out frequency statistics, cluster analysis, association analysis and complex network analysis on the diagnosis and treatment data, the common medicines used by Chinese medicine master Yu Ying-ao in the treatment of primary epilepsy, properties and classifications of commonly used medicines, therapeutic principle and method and coreprescriptions were obtained. Results: A total of 70 cases, 213 medical records and 231 prescriptions data of TCM were included. A total of 120 Chinese medicines were involved, and the total frequency of medication was 3388. The core prescription groups mined through the complex network method are: Raw Concha Ostreae(Shengmuli), Radix Curcumae(Yujin), Alum(Baifan), longchi, Salvia miltiorrhiza(Danshen), Caulis Bambusae in Taenia(Zhuru), Semen armeniacae amarum(Kuxingren), Semen Persicae(Taoren), Arisaema cum Bile(Dannanxing) and Amber(Hupo). In the prescription, Raw Concha Ostreae(Shengmuli) and Radix Curcumae(Yujin) were king medicines and also high-frequency medicines, all of which were cold medicines. Yu Ying-ao's clinical dosage of Alum(Baifan) was between $1.5 sim 3mathrm{g}$, and the curative effect was enhanced by decocting it first to remove its great fire. Yu Ying-ao's clinical high-frequency medicines are: Raw Concha Ostreae(Shengmuli), Radix Curcumae(Yujin), Alum(Baifan), Salvia miltiorrhiza(Danshen), Longchi, Semen armeniacae amarum(Kuxingren), Semen Persicae(Taoren) and Arisaema cum Bile(Dannanxing). Most of the high-frequency medicines were cold medicines (such as Shengmuli, Yujin, Baifan, Kuxingren, etc.), The specific drugs were mild cold drugs (827 times). The most common distribution of the five flavors of traditional Chinese medicine was bitter medicine (1678 times), the meridian of returning to the liver (2214 times) was the most common. The top three efficacy of 120 traditional Chinese medicines were moistening bowels (529 times), promoting blood circulation and removing blood stasis (436 times), clearing heat and resolving phlegm (385 times).Conclusion: Chinese medicine master Yu Ying-ao takes the principle of purging excess and tonifying deficiency, and purging more than tonifying. To calm the mind, invigorate the spleen, regulate the liver, moisten the internal organs, reconcile the middle, and invigorate the qi, and harmonizing lung, heart, spleen and large intestine.","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":"127384355","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/BIBM55620.2022.9994959
Shoujia Zhang, Wei Li, Weidong Xie, Linjie Wang
In recent decades, the rapid development of gene sequencing and computer technology has increased the growth of high-dimensional microarray data. Some machine learning methods have been successfully applied to it to help classify cancer. In most cases, high dimensionality and the small sample size of microarray data restricted the performance of cancer classification. This problem usually issolved bysome feature selection methods. However, most of them neglect the exploitation of relations among genes. This paper proposes a novel feature selection method by fusing multiple gene relation network information based on community detection (MGRCD). The proposed method divides all genes into different communities. Then, the genes most associated with cancer classification are selected from each community. The proposed method satisfies both maximum relevances gene with cancer and minimum redundancy among genes for the selected optimal feature subset. The experiment results show that the proposed gene selection method can effectively improve classification performance.
{"title":"Feature Selection for Microarray Data via Community Detection Fusing Multiple Gene Relation Networks Information","authors":"Shoujia Zhang, Wei Li, Weidong Xie, Linjie Wang","doi":"10.1109/BIBM55620.2022.9994959","DOIUrl":"https://doi.org/10.1109/BIBM55620.2022.9994959","url":null,"abstract":"In recent decades, the rapid development of gene sequencing and computer technology has increased the growth of high-dimensional microarray data. Some machine learning methods have been successfully applied to it to help classify cancer. In most cases, high dimensionality and the small sample size of microarray data restricted the performance of cancer classification. This problem usually issolved bysome feature selection methods. However, most of them neglect the exploitation of relations among genes. This paper proposes a novel feature selection method by fusing multiple gene relation network information based on community detection (MGRCD). The proposed method divides all genes into different communities. Then, the genes most associated with cancer classification are selected from each community. The proposed method satisfies both maximum relevances gene with cancer and minimum redundancy among genes for the selected optimal feature subset. The experiment results show that the proposed gene selection method can effectively improve classification performance.","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":"114877097","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}