Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering最新文献

{"title":"Informative gene identification for Single-Cell RNA-Seq Data with Mutual Information based Firefly Algorithm","authors":"Yiyao Dou, Hao Jiang","doi":"10.1145/3502871.3502881","DOIUrl":"https://doi.org/10.1145/3502871.3502881","url":null,"abstract":"Single-cell RNA-seq data are characterized by high dimensionality, large data volume, and noise. It is of critical importance for identifying marker genes to achieve dimensionality reduction and target the corresponding informative markers. In this paper, we perform supervised gene selection method based on firefly algorithm that integrates mutual information and information gain. Distinguished from the standard binary firefly algorithm, a novel move strategy and update strategy was proposed, which saves computational resources and enhances the capability of the algorithm. Numerical experiments on several single-cell RNA sequencing datasets are conducted and compared with state-of-the-art intelligent algorithms, gene function analysis was also performed for representative genes and the results also verify the effectiveness of the method in this paper.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121669673","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":"Arrhythmia Classification with Continuous Wavelet Transform and Convolutional Neural Network on ECG","authors":"J. Kim","doi":"10.1145/3502871.3502889","DOIUrl":"https://doi.org/10.1145/3502871.3502889","url":null,"abstract":"Electrocardiogram (ECG) is an electric signal recorded from the heart which is used to monitor conditions in the cardiovascular systems of hospitalized patients. For many years, there have been efforts to accurately determine cardiovascular conditions represented by ECG. This paper proposes a four-step method integrating continuous wavelet transform (CWT) and convolutional neural network (CNN) to classify arrhythmia into five distinct classes. First, the ECG signals are preprocessed for improved data quality. Second, continuous wavelet transform with the Complex Morlet wavelet is applied on the data to return image representations of the signals over the time-frequency domains. Third, a lightweight CNN is trained to classify the five different arrhythmia classes based on the images obtained via wavelet transform. Finally, the network is used to predict the class of each ECG signal from the test dataset. The results derived using this method reveal an average F1 score of 90% and a weighted F1 score of 98%.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125927951","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":"Active Learning for Microarray based Leukemia Classification","authors":"Kecheng Zhu","doi":"10.1145/3502871.3502884","DOIUrl":"https://doi.org/10.1145/3502871.3502884","url":null,"abstract":"In machine learning, data labeling is assumed to be easy and cheap. However, in real word cases especially clinical field, data sets are rare and expensive to obtain. Active learning is an approach that can query the most informative data for the training. This leads to an alternative to deal with the concern mentioned above. The Sampling method is one of the key parts in active learning because it minimizes the training cost of the classifier. By different query method, models with considerable difference could be produced. The difference in model could lead to significant difference in training cost and final accuracy outcome. The approaches that were used to in this experiment is uncertainty sampling, diversity sampling and query by committee. In the experiment, active learning is applied on the microarray data with improving results. The classification on two types leukemia (acute myeloid leukemia and acute lymophoblastic leukemia) indicates a boost in accuracy with the same number of samples compared to passive machine learning. The experiments leads to the conclusion that with small number of samples with randomness in the field of leukemia classification, active learning produce an more active model. Additionally, active learning with query by committee finds the most informative sample with fewest trials.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124697404","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":"A Novel Bci Paradigm Combining Visual Imagery and Emotion: A Pilot Study","authors":"Long Chen, Chenghui Tang, Chang-Lin Li, Wanping Qiu, Zhongpeng Wang, Xin Zhang, Dong Ming","doi":"10.1145/3502871.3502894","DOIUrl":"https://doi.org/10.1145/3502871.3502894","url":null,"abstract":"Visual imagery (VI) has become a research hotspot with the development of brain-computer Interface (BCI). But it's very difficult to decode the electroencephalogram (EEG) during the VI task because of the lack of effective classification features. However, the classification of emotion-based EEG now can achieve a very high accuracy. We proposed a new BCI paradigm in which emotions would be integrated into VI to improve the performance. To verify the feasibility of our paradigm, we designed a two-session EEG acquisition experiment. We designed three kinds of emotions and three kinds of semantic correspondence i.e., negative animal, positive human and neutral thing. Sixteen subjects were asked to observe and imagine three pictures selected by subjects in visual observation (VO) and VI session, respectively. Then, we used power spectral density (PSD), common spatial pattern (CSP) and Riemann tangent space three features with SVM to analysis the EEG during three statements. The classification results show that the Riemann features obtain the highest average accuracies which are 84.36% and 67.36% for VO and VI, respectively. All the three types of features can exceed chance level on all the subjects. The results prove that our VI integrating emotion is a promising paradigm.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130888443","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":"Identification of Gene Modules and Key Genes Associated with Atrial Fibrillation Based on Gene Co-expression Network Analysis","authors":"Felix K. Biwott, Cheng-Si Luo, X. Lv, Han Zhang, N. Rao","doi":"10.1145/3502871.3502879","DOIUrl":"https://doi.org/10.1145/3502871.3502879","url":null,"abstract":"Atrial fibrillation (AF) is the most frequent cardiac arrhythmia worldwide. However, its molecular pathogenesis remains unclear. Herein, by integrated bioinformatics analysis, we identified the key gene module and potential genes responsible for AF. The gene expression profile of AF was analyzed using the bioinformatics framework. Firstly, we identified differentially expressed genes (DEGs), then gene co-expression network (GCN) was constructed. Gene modules were then mined with five different community detection algorithms. Subsequently, correlation analysis between gene modules and clinical traits was carried out. Gene ontology analysis was performed to annotate the biological pathways of the genes in the key module. The key genes were identified using cytohubba plug-in algorithms. A total of 379 DEGs were identified between the AF and sinus rhythm groups. The constructed GCN contains 286 genes and 3554 interaction pairs, where a multi-level algorithm that had the highest modularity divide the GCN into five gene modules, in which the gene module and key genes were identified. Association analysis between the modules and clinical indicators showed that the modules were associated with AF, and the biological functions of the genes in the key module play vital roles in AF pathogenesis. The identified key genes could be potential biomarkers for AF pathogenesis and might improve the understanding of the underlying mechanisms of AF, and opens up avenues to further explore these novel key genes paving the way towards AF diagnosis and therapy.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114055001","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":"Comprehensive Identification of Potential Lung Cancer Biomarkers That are Applicable in Both Diagnosis and Prognosis","authors":"B. Zheng","doi":"10.1145/3502871.3502888","DOIUrl":"https://doi.org/10.1145/3502871.3502888","url":null,"abstract":"Lung cancer continually led all cancers in patient deaths, and lung adenocarcinoma and lung squamous cell carcinoma are two of the most common lung cancer subtypes. Given the steep increase in patient survival rate as lung cancer tumor progresses from the early to later stages, it is pivotal to develop diagnostic and prognostic strategies using biomarkers to ensure a better chance of survival for the patients. In this study, we performed a comprehensive analysis on the poly-A tail selected RNA-sequencing datasets in lung cancer. We firstly performed differential expression analysis to identify genes having different expression profiles between tumor and healthy patients. We then confirmed the biological impacts for these differential genes by observing their co-expression patterns and connectivity within the co-activation modules in tumor patients. Certain limitations exist with using RNA biomarkers in a clinical setting, due to RNA being a single-stranded structure that is likely to break down in an extract patient fluid sample and has inadequately abundant expression signal. Thus, we further applied epigenetic annotation data to associate our RNA gene list with methylation level and transcription factor binding signal. At last, with the annotated featured gene list serving as the basis, we developed a predictive model using Support Vector Machine (SVM) and showed that the selected featured genes not only possess biological significance but also a decent prognostic predictive power in distinguish early stage tumors. We further showed that they can be applicable to other endodermal cancers.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131214601","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":"Tracking Mesenchymal Stromal Cells In Vivo Using A Sensitive Bioluminescence Method","authors":"Qiu-Li Yu","doi":"10.1145/3502871.3502885","DOIUrl":"https://doi.org/10.1145/3502871.3502885","url":null,"abstract":"Akaluc can achieve cell tracking at the single-cell level, so this paper hypothesized that the bioluminescence of Akaluc could be used to tracking MSC in vivo. A newly discovered imaging platform of bioluminescence which based on a red-shifted and highly deliverable luciferin analog Akaluc was used to evaluate the safety and distribution of mesenchymal stromal cells)MSCs( in vivo. After intravenous infusion in immune-deficient Nude mice with gene modified Akaluc MSC which was established by lentivirus mVenus-Akaluc infection, we tracked the MSCs in real time. Therefore, we could assess the safety of MSCs in vivo and their biodistribution and finally determine whether MSCs are suitable for further research and experiment. We genetically-engineered MSCs with Akaluc lentivirus infection and puromycine screening named Akaluc MSCs. In vitro, the Akaluc activity of Akaluc MSCs reached 6300 per 104 cells. Signals can also be observed in more than 10 cells through in vivo imaging. Within 1-5 days after injection, the cells are mainly concentrated in the lungs. A part of the cells was observed to transfer to liver on the fifth day and was mainly spread in liver after 7 days. The cells were observed to survive for 14 to 21 days in vivo. In the meantime, the nude mice behave normally, and the mesenchymal stem cells disappear after 21 days. After continuous observation over one year, no tumorigenesis and no death wea observed in the mice. Former researches showed that cells were trapped in lungs and disappeared after 7 days. In this study, we observed MSCs live for over 14 days by the tracking using Akaluc. Akaluc was proven to be more effective than other enzymes in visualizing the biodistribution of mesenchymal stem cells, and it was proven to be not having tumorigenicity, because no sign of tumorigenesis was observed in vivo after one year.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116998907","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":"Insight into Plant Grafting and Its Regulation","authors":"Kexin Wang","doi":"10.1145/3502871.3502904","DOIUrl":"https://doi.org/10.1145/3502871.3502904","url":null,"abstract":"Grafting is an ancient agricultural technique, which is based on plant regeneration, has become an important and effective plant breeding technique in agricultural production. However, the understanding of tissue regeneration at grafting junctions is still not deep. The grafting regeneration includes wound healing, tissue conjoin and vascular re-connection. In recent years, some progress has been made in studying the mechanism of rootstock and scion regeneration using model plant Arabidopsis thaliana. In this paper, the graft regeneration signal perception, cells regeneration, vascular bundles reconnect, the roles of phytohormones were analyzed and summarized, in order to provide references understanding of the mechanism of grafting in regeneration.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126873385","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":"A New Medical Image Fusion Approach Using Spatial Attention and Weighted Local Energy","authors":"F. Hu, Chuan Hu, Wenying Du, Guixia Kang, Ying Han","doi":"10.1145/3502871.3502872","DOIUrl":"https://doi.org/10.1145/3502871.3502872","url":null,"abstract":"∗Medical image fusion technology has become a powerful tool for assisting physicians in diagnosing diseases and locating lesions since it can integrate various pathological information given by single modal medical images. This paper proposes a novel multi-modality medical image fusion approach in generalized rieszwavelet transform (GRWT) domain. Two source images are deconstructed by GRWT into low-frequency sub-band and highfrequency sub-band. Then a spatial attention based fusion rule and a weighted local energy (WLE) fusion rule are adopted for low-frequency sub-band and high-frequency sub-band respectively. After performing the inverse GRWT, final fused image is obtained. The proposed method is tested on two cases of MRI-CT group and MRI-PET group. Qualitative analysis and quantitative evaluations are performed on the proposed method with better performance in AG,Q_NCIE,PSNR,SF and RMSE. The results suggest that our ∗Corresponding author: YingHan, Biomedical Engineering Institute, Hainan University, Haikou, China 570228; Department of Neurology, Xuanwu Hospital of Capital Medical University, Beijing, China 100053; Center of Alzheimer’s Disease, Beijing Institute for Brain Disorders, Beijing, China 100053; hanying@xwh.ccmu.edu.cn. †Corresponding author: Guixia Kang, Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China; gxkang@bupt.edu.cn. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. ICBBE ’21, November 12–15, 2021, Kyoto, Japan © 2021 Association for Computing Machinery. ACM ISBN 978-1-4503-8507-7/21/11. . . $15.00 https://doi.org/10.1145/3502871.3502872 method is an effective and valuable approach to help clinicians to diagnose diseases.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134535700","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":"Drug Analysis and Omics Study of Neurodegenerative Diseases","authors":"Haoran Zhang","doi":"10.1145/3502871.3502901","DOIUrl":"https://doi.org/10.1145/3502871.3502901","url":null,"abstract":"Neurodegenerative diseases, such as Alzheimer's disease, Parkinson's disease and etc, affect humans’ body effectively. As the previous study showed that human still do not know what cause those kinds of diseases and how to cure them. This paper tries to do the drug analysis of the medicine that can curb the symptoms of neurodegenerative diseases by gas chromatography (GC), liquid chromatographic (LC), and mass spectrometry (MS). With those methods, we can make sure that the drug has no harm to neither humans or environment. As the experiment goes deeper, we begin to analyze Ding-Zhi-Xiao-Wan, a well-known Chinese medical formula used to treat Alzheimer's disease. By doing control experiment with four white rats, Ding-Zhi-Xiao-Wan is an effective treatment to Alzheimer's disease. However, it is hard to tell which is the active ingredient. End but not least, the research also focuses on the change of Protein S-nitrosylation in the brain by using the methods, such as the biotin switch, his-tag switch, and 2-D DIGE, 2-D differential gel electrophoresis. The analysis shows that the decline of Protein S-nitrosylation is one of the reasons which cause Alzheimer's disease.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122337118","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}