1
|
Wang T, Yan Z, Zhang Y, Lou Z, Zheng X, Mai D, Wang Y, Shang X, Xiao B, Peng J, Chen J. postGWAS: A web server for deciphering the causality post the genome-wide association studies. Comput Biol Med 2024; 171:108108. [PMID: 38359659 DOI: 10.1016/j.compbiomed.2024.108108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 01/23/2024] [Accepted: 02/04/2024] [Indexed: 02/17/2024]
Abstract
While genome-wide association studies (GWAS) have unequivocally identified vast disease susceptibility variants, a majority of them are situated in non-coding regions and are in high linkage disequilibrium (LD). To pave the way of translating GWAS signals to clinical drug targets, it is essential to identify the underlying causal variants and further causal genes. To this end, a myriad of post-GWAS methods have been devised, each grounded in distinct principles including fine-mapping, co-localization, and transcriptome-wide association study (TWAS) techniques. Yet, no platform currently exists that seamlessly integrates these diverse post-GWAS methodologies. In this work, we present a user-friendly web server for post-GWAS analysis, that seamlessly integrates 9 distinct methods with 12 models, categorized by fine-mapping, colocalization, and TWAS. The server mainly helps users decipher the causality hindered by complex GWAS signals, including casual variants and casual genes, without the burden of computational skills and complex environment configuration, and provides a convenient platform for post-GWAS analysis, result visualization, facilitating the understanding and interpretation of the genome-wide association studies. The postGWAS server is available at http://g2g.biographml.com/.
Collapse
Affiliation(s)
- Tao Wang
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China; Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi'an, 710072, China
| | - Zhihao Yan
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China; Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi'an, 710072, China
| | - Yiming Zhang
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China
| | - Zhuofei Lou
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China
| | - Xiaozhu Zheng
- Department of Anesthesiology, The People's Hospital of Yubei District, Chongqing, 401120, China
| | - DuoDuo Mai
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China; Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi'an, 710072, China
| | - Yongtian Wang
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China; Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi'an, 710072, China
| | - Xuequn Shang
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China; Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi'an, 710072, China
| | - Bing Xiao
- School of Automation, Northwestern Polytechnical University, Xi'an, 710072, China
| | - Jiajie Peng
- School of Computer Science, Northwestern Polytechnical University, Xi'an, 710072, China; Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi'an, 710072, China
| | - Jing Chen
- School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, 710048, China.
| |
Collapse
|
2
|
Sun Y, Guo J, Liu Y, Wang N, Xu Y, Wu F, Xiao J, Li Y, Wang X, Hu Y, Zhou Y. METnet: A novel deep learning model predicting MET dysregulation in non-small-cell lung cancer on computed tomography images. Comput Biol Med 2024; 171:108136. [PMID: 38367451 DOI: 10.1016/j.compbiomed.2024.108136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Revised: 01/24/2024] [Accepted: 02/12/2024] [Indexed: 02/19/2024]
Abstract
BACKGROUND Mesenchymal epithelial transformation (MET) is a key molecular target for diagnosis and treatment of non-small cell lung cancer (NSCLC). The corresponding molecularly targeted therapeutics have been approved by Food and Drug Administration (FDA), achieving promising results. However, current detection of MET dysregulation requires biopsy and gene sequencing, which is invasive, time-consuming and difficult to obtain tumor samples. METHODS To address the above problems, we developed a noninvasive and convenient deep learning (DL) model based on Computed tomography (CT) imaging data for prediction of MET dysregulation. We introduced the unsupervised algorithm RK-net for automated image processing and utilized the MedSAM large model to achieve automated tissue segmentation. Based on the processed CT images, we developed a DL model (METnet). The model based on the grouped convolutional block. We evaluated the performance of the model over the internal test dataset using the area under the receiver operating characteristic curve (AUROC) and accuracy. We conducted subgroup analysis on the basis of clinical data of the lung cancer patients and compared the performance of the model in different subgroups. RESULTS The model demonstrated a good discriminative ability over the internal test dataset. The accuracy of METnet was 0.746 with an AUC value of 0.793 (95% CI 0.714-0.871). The subgroup analysis revealed that the model exhibited similar performance across different subgroups. CONCLUSIONS METnet realizes prediction of MET dysregulation in NSCLC, holding promise for guiding precise tumor diagnosis and treatment at the molecular level.
Collapse
Affiliation(s)
- Yige Sun
- Department of Radiology, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, 150010, Heilongjiang, P.R. China; Genomics Research Center (Key Laboratory of Gut Microbiota and Pharmacogenomics of Heilongjiang Province, State-Province Key Laboratory of Biomedicine-Pharmaceutics of China), College of Pharmacy, Harbin Medical University, Harbin, 150081, China
| | - Jirui Guo
- Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, 150001, China
| | - Yang Liu
- Department of Radiology, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, 150010, Heilongjiang, P.R. China
| | - Nan Wang
- Beidahuang Industry Group General Hospital, Harbin, 150088, China
| | - Yanwei Xu
- Beidahuang Group Neuropsychiatric Hospital, Jiamusi, 154000, China
| | - Fei Wu
- The Second Affiliated Hospital of Harbin Medical University, Harbin Medical University, 150001, Harbin, Heilongjiang, China
| | - Jianxin Xiao
- Department of Radiology, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, 150010, Heilongjiang, P.R. China
| | - Yingpu Li
- Department of Oncological Surgery, Harbin Medical University Cancer Hospital, Harbin, Heilongjiang Province, 150000, China
| | - Xinxin Wang
- Department of Radiology, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, 150010, Heilongjiang, P.R. China
| | - Yang Hu
- Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, 150001, China.
| | - Yang Zhou
- Department of Radiology, Harbin Medical University Cancer Hospital, 150 Haping Road, Harbin, 150010, Heilongjiang, P.R. China.
| |
Collapse
|
3
|
O'Brien CL, Summers KM, Martin NM, Carter-Cusack D, Yang Y, Barua R, Dixit OVA, Hume DA, Pavli P. The relationship between extreme inter-individual variation in macrophage gene expression and genetic susceptibility to inflammatory bowel disease. Hum Genet 2024; 143:233-261. [PMID: 38421405 PMCID: PMC11043138 DOI: 10.1007/s00439-024-02642-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Accepted: 01/14/2024] [Indexed: 03/02/2024]
Abstract
The differentiation of resident intestinal macrophages from blood monocytes depends upon signals from the macrophage colony-stimulating factor receptor (CSF1R). Analysis of genome-wide association studies (GWAS) indicates that dysregulation of macrophage differentiation and response to microorganisms contributes to susceptibility to chronic inflammatory bowel disease (IBD). Here, we analyzed transcriptomic variation in monocyte-derived macrophages (MDM) from affected and unaffected sib pairs/trios from 22 IBD families and 6 healthy controls. Transcriptional network analysis of the data revealed no overall or inter-sib distinction between affected and unaffected individuals in basal gene expression or the temporal response to lipopolysaccharide (LPS). However, the basal or LPS-inducible expression of individual genes varied independently by as much as 100-fold between subjects. Extreme independent variation in the expression of pairs of HLA-associated transcripts (HLA-B/C, HLA-A/F and HLA-DRB1/DRB5) in macrophages was associated with HLA genotype. Correlation analysis indicated the downstream impacts of variation in the immediate early response to LPS. For example, variation in early expression of IL1B was significantly associated with local SNV genotype and with subsequent peak expression of target genes including IL23A, CXCL1, CXCL3, CXCL8 and NLRP3. Similarly, variation in early IFNB1 expression was correlated with subsequent expression of IFN target genes. Our results support the view that gene-specific dysregulation in macrophage adaptation to the intestinal milieu is associated with genetic susceptibility to IBD.
Collapse
Affiliation(s)
- Claire L O'Brien
- Centre for Research in Therapeutics Solutions, Faculty of Science and Technology, University of Canberra, Canberra, ACT, Australia
- Inflammatory Bowel Disease Research Group, Canberra Hospital, Canberra, ACT, Australia
| | - Kim M Summers
- Mater Research Institute-University of Queensland, Translational Research Institute, Brisbane, QLD, Australia
| | - Natalia M Martin
- Inflammatory Bowel Disease Research Group, Canberra Hospital, Canberra, ACT, Australia
| | - Dylan Carter-Cusack
- Mater Research Institute-University of Queensland, Translational Research Institute, Brisbane, QLD, Australia
| | - Yuanhao Yang
- Mater Research Institute-University of Queensland, Translational Research Institute, Brisbane, QLD, Australia
| | - Rasel Barua
- Inflammatory Bowel Disease Research Group, Canberra Hospital, Canberra, ACT, Australia
| | - Ojas V A Dixit
- Centre for Research in Therapeutics Solutions, Faculty of Science and Technology, University of Canberra, Canberra, ACT, Australia
| | - David A Hume
- Mater Research Institute-University of Queensland, Translational Research Institute, Brisbane, QLD, Australia.
| | - Paul Pavli
- Inflammatory Bowel Disease Research Group, Canberra Hospital, Canberra, ACT, Australia.
- School of Medicine and Psychology, College of Health and Medicine, Australian National University, Canberra, ACT, Australia.
| |
Collapse
|
4
|
Jiang F, Hu SY, Tian W, Wang NN, Yang N, Dong SS, Song HM, Zhang DJ, Gao HW, Wang C, Wu H, He CY, Zhu DL, Chen XF, Guo Y, Yang Z, Yang TL. A landscape of gene expression regulation for synovium in arthritis. Nat Commun 2024; 15:1409. [PMID: 38360850 PMCID: PMC10869817 DOI: 10.1038/s41467-024-45652-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Accepted: 01/29/2024] [Indexed: 02/17/2024] Open
Abstract
The synovium is an important component of any synovial joint and is the major target tissue of inflammatory arthritis. However, the multi-omics landscape of synovium required for functional inference is absent from large-scale resources. Here we integrate genomics with transcriptomics and chromatin accessibility features of human synovium in up to 245 arthritic patients, to characterize the landscape of genetic regulation on gene expression and the regulatory mechanisms mediating arthritic diseases predisposition. We identify 4765 independent primary and 616 secondary cis-expression quantitative trait loci (cis-eQTLs) in the synovium and find that the eQTLs with multiple independent signals have stronger effects and heritability than single independent eQTLs. Integration of genome-wide association studies (GWASs) and eQTLs identifies 84 arthritis related genes, revealing 38 novel genes which have not been reported by previous studies using eQTL data from the GTEx project or immune cells. We further develop a method called eQTac to identify variants that could affect gene expression by affecting chromatin accessibility and identify 1517 regions with potential regulatory function of chromatin accessibility. Altogether, our study provides a comprehensive synovium multi-omics resource for arthritic diseases and gains new insights into the regulation of gene expression.
Collapse
Affiliation(s)
- Feng Jiang
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Shou-Ye Hu
- Department of Joint Surgery, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi, 710054, P.R. China
| | - Wen Tian
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Nai-Ning Wang
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Ning Yang
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Shan-Shan Dong
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Hui-Miao Song
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Da-Jin Zhang
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Hui-Wu Gao
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Chen Wang
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Hao Wu
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Chang-Yi He
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Dong-Li Zhu
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Xiao-Feng Chen
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Yan Guo
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China
| | - Zhi Yang
- Department of Joint Surgery, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi, 710054, P.R. China.
| | - Tie-Lin Yang
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Biomedical Informatics & Genomics Center, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, P.R. China.
| |
Collapse
|
5
|
Nguyen DT. An integrative pipeline for circular RNA quantitative trait locus discovery with application in human T cells. Bioinformatics 2023; 39:btad667. [PMID: 37929995 PMCID: PMC10636286 DOI: 10.1093/bioinformatics/btad667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 10/25/2023] [Accepted: 10/30/2023] [Indexed: 11/07/2023] Open
Abstract
MOTIVATION Molecular quantitative trait locus (QTL) mapping has proven to be a powerful approach for prioritizing genetic regulatory variants and causal genes identified by genome-wide association studies. Recently, this success has been extended to circular RNA (circRNA), a potential group of RNAs that can serve as markers for the diagnosis, prognosis, or therapeutic targets of various human diseases. However, a well-developed computational pipeline for circRNA QTL (circQTL) discovery is still lacking. RESULTS We introduce an integrative method for circQTL mapping and implement it as an automated pipeline based on Nextflow, named cscQTL. The proposed method has two main advantages. Firstly, cscQTL improves the specificity by systematically combining outputs of multiple circRNA calling algorithms to obtain highly confident circRNA annotations. Secondly, cscQTL improves the sensitivity by accurately quantifying circRNA expression with the help of pseudo references. Compared to the single method approach, cscQTL effectively identifies circQTLs with an increase of 20%-100% circQTLs detected and recovered all circQTLs that are highly supported by the single method approach. We apply cscQTL to a dataset of human T cells and discover genetic variants that control the expression of 55 circRNAs. By colocalization tests, we further identify circBACH2 and circYY1AP1 as potential candidates for immune disease regulation. AVAILABILITY AND IMPLEMENTATION cscQTL is freely available at: https://github.com/datngu/cscQTL and https://doi.org/10.5281/zenodo.7851982.
Collapse
Affiliation(s)
- Dat Thanh Nguyen
- Centre for Integrative Genetics, Faculty of Biosciences, Norwegian University of Life Sciences, 1432 Ås, Norway
| |
Collapse
|
6
|
Arlt C, Wachtmeister T, Köhrer K, Stich B. Affordable, accurate and unbiased RNA sequencing by manual library miniaturization: A case study in barley. PLANT BIOTECHNOLOGY JOURNAL 2023; 21:2241-2253. [PMID: 37593840 PMCID: PMC10579711 DOI: 10.1111/pbi.14126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Revised: 05/12/2023] [Accepted: 07/01/2023] [Indexed: 08/19/2023]
Abstract
We present an easy-to-reproduce manual miniaturized full-length RNA sequencing (RNAseq) library preparation workflow that does not require the upfront investment in expensive lab equipment or long setup times. With minimal adjustments to an established commercial protocol, we were able to manually miniaturize the RNAseq library preparation by a factor of up to 1:8. This led to cost savings for miniaturized library preparation of up to 86.1% compared to the gold standard. The resulting data were the basis of a rigorous quality control analysis that inspected: sequencing quality metrics, gene body coverage, raw read duplications, alignment statistics, read pair duplications, detected transcripts and sequence variants. We also included a deep dive data analysis identifying rRNA contamination and suggested ways to circumvent these. In the end, we could not find any indication of biases or inaccuracies caused by the RNAseq library miniaturization. The variance in detected transcripts was minimal and not influenced by the miniaturization level. Our results suggest that the workflow is highly reproducible and the sequence data suitable for downstream analyses such as differential gene expression analysis or variant calling.
Collapse
Affiliation(s)
- Christopher Arlt
- Institute of Quantitative Genetics and Genomics of PlantsHeinrich Heine University DuesseldorfDuesseldorfGermany
| | - Thorsten Wachtmeister
- Genomics & Transcriptomics Laboratory, Biological and Medical Research Centre (BMFZ)Heinrich Heine University DuesseldorfDuesseldorfGermany
| | - Karl Köhrer
- Genomics & Transcriptomics Laboratory, Biological and Medical Research Centre (BMFZ)Heinrich Heine University DuesseldorfDuesseldorfGermany
| | - Benjamin Stich
- Institute of Quantitative Genetics and Genomics of PlantsHeinrich Heine University DuesseldorfDuesseldorfGermany
- Cluster of Excellence on Plant Sciences (CEPLAS)DuesseldorfGermany
- Max Planck Institute for Plant Breeding ResearchCologneGermany
- Present address:
Institute for Breeding Research on Agricultural CropsJulius Kühn Institute (JKI) ‐ Federal Research Centre for Cultivated PlantsSanitzGermany
| |
Collapse
|
7
|
Vigorito E, Barton A, Pitzalis C, Lewis MJ, Wallace C. BBmix: a Bayesian beta-binomial mixture model for accurate genotyping from RNA-sequencing. Bioinformatics 2023; 39:btad393. [PMID: 37338536 PMCID: PMC10318392 DOI: 10.1093/bioinformatics/btad393] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Revised: 05/15/2023] [Accepted: 06/19/2023] [Indexed: 06/21/2023] Open
Abstract
MOTIVATION While many pipelines have been developed for calling genotypes using RNA-sequencing (RNA-Seq) data, they all have adapted DNA genotype callers that do not model biases specific to RNA-Seq such as allele-specific expression (ASE). RESULTS Here, we present Bayesian beta-binomial mixture model (BBmix), a Bayesian beta-binomial mixture model that first learns the expected distribution of read counts for each genotype, and then deploys those learned parameters to call genotypes probabilistically. We benchmarked our model on a wide variety of datasets and showed that our method generally performed better than competitors, mainly due to an increase of up to 1.4% in the accuracy of heterozygous calls, which may have a big impact in reducing false positive rate in applications sensitive to genotyping error such as ASE. Moreover, BBmix can be easily incorporated into standard pipelines for calling genotypes. We further show that parameters are generally transferable within datasets, such that a single learning run of less than 1 h is sufficient to call genotypes in a large number of samples. AVAILABILITY AND IMPLEMENTATION We implemented BBmix as an R package that is available for free under a GPL-2 licence at https://gitlab.com/evigorito/bbmix and https://cran.r-project.org/package=bbmix with accompanying pipeline at https://gitlab.com/evigorito/bbmix_pipeline.
Collapse
Affiliation(s)
- Elena Vigorito
- MRC Biostatistics Unit, University of Cambridge, Cambridge CB2 0SR, United Kingdom
| | - Anne Barton
- Division of Musculoskeletal and Dermatological Sciences, University of Manchester, Manchester M13 9PL, United Kingdom
| | - Costantino Pitzalis
- Centre for Experimental Medicine and Rheumatology, William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London EC1M 6BQ, United Kingdom
| | - Myles J Lewis
- Centre for Experimental Medicine and Rheumatology, William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London EC1M 6BQ, United Kingdom
| | - Chris Wallace
- MRC Biostatistics Unit, University of Cambridge, Cambridge CB2 0SR, United Kingdom
- Cambridge Institute of Therapeutic Immunology & Infectious Disease (CITIID), Jeffrey Cheah Biomedical Centre, Cambridge Biomedical Campus, University of Cambridge, Cambridge CB2 0AW, United Kingdom
| |
Collapse
|
8
|
Cui X, Chen N, Zhao C, Li J, Zheng X, Liu C, Yang J, Li X, Yu C, Liu J, Liu X. An Adaptive Weighted Attention-Enhanced Deep Convolutional Neural Network for Classification of MRI images of Parkinson's Disease. J Neurosci Methods 2023:109884. [PMID: 37207799 DOI: 10.1016/j.jneumeth.2023.109884] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 05/05/2023] [Accepted: 05/16/2023] [Indexed: 05/21/2023]
Abstract
BACKGROUND Parkinson's disease (PD) is the second prevalent neurological diseases with a significant growth rate in incidence. Convolutional neural networks using structural magnetic resonance images (sMRI) are widely used for PD classification. However, the areas of change in the patient's MRI images are small and unfixed. Thus, capturing the features of the areas accurately where the lesions changed became a problem. METHOD We propose a deep learning framework that combines multi-scale attention guidance and multi-branch feature processing modules to diagnose PD by learning sMRI T2 slice features. In this scheme, firstly, to achieve effective feature transfer and gradient descent, a deep convolutional neural network framework based on dense block is designed. Next, an Adaptive Weighted Attention algorithm is proposed, whose pursers is to extract multi branch and even diverse features. Finally, Dropout layer and SoftMax layer are added to the network structure to obtain good classification results and rich and diverse feature information. The Dropout layer is used to reduce the number of intermediate features to increase the orthogonality between features of each layer. The activation function SoftMax increases the flexibility of the neural network by increasing the degree of fitting to the training set and converting linear to nonlinear. RESULTS The best performance of the proposed method an accuracy of 92%, a sensitivity of 94%, specificity of 90% and a F1 score of 95% respectively for identifying PD and HC. CONCLUSION Experiments show that the proposed method can successfully distinguish PD and NC. Good classification results were obtained in PD diagnosis classification task and compared with advanced research methods.
Collapse
Affiliation(s)
- Xinchun Cui
- School of Computer Science, Qufu Normal University @ Rizhao, 276826, Rizhao, China; School of Foundational Education, University of Health and Rehabilitation Sciences, 266071, Qingdao, China; Qingdao Municipal Hospital, University of Health and Rehabilitation Sciences, 266011, Qingdao, China; Guangxi Key Laboratory of Cryptography and Information Security, Guilin University of Electronic Technology@Huajiang, 541004, Guilin, China
| | - Ningning Chen
- School of Computer Science, Qufu Normal University @ Rizhao, 276826, Rizhao, China
| | - Chao Zhao
- School of Computer Science, Qufu Normal University @ Rizhao, 276826, Rizhao, China; Department of Neurosurgery, the Affiliated Rizhao People's Hospital of Jining Medical University, 276800, Rizhao, Shandong, China
| | - Jianlong Li
- School of Computer Science, Qufu Normal University @ Rizhao, 276826, Rizhao, China; Department of Radiology, The Affiliated Rizhao People's Hospital of Jining Medical University, 276800, Rizhao, Shandong, China
| | - Xiangwei Zheng
- School of Information Science and Engineering, Shandong Normal University, 250358, Ji'nan, China
| | - Caixia Liu
- Nursing Department, Zhejiang Hospital,310013, Hangzhou, China.
| | - Jiahu Yang
- Department of Radiology, Zhejiang Hospital,310013, Hangzhou, China.
| | - Xiuli Li
- School of Foundational Education, University of Health and Rehabilitation Sciences, 266071, Qingdao, China
| | - Chao Yu
- School of Foundational Education, University of Health and Rehabilitation Sciences, 266071, Qingdao, China
| | - Jinxing Liu
- School of Computer Science, Qufu Normal University @ Rizhao, 276826, Rizhao, China
| | - Xiaoli Liu
- Department of Neurology, Zhejiang Hospital,310013, Hangzhou, China.
| |
Collapse
|
9
|
Zhang C, Cui X, Lian S, Xiao R, Qiao H, Li S, Lou Y, Feng Y, Zhuang L, Du J, Liu X. Intelligent algorithm for dynamic functional brain network complexity from CN to AD. INT J INTELL SYST 2022. [DOI: 10.1002/int.22737] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Affiliation(s)
- Chenghui Zhang
- School of Computer Science Qufu Normal University Rizhao China
- Department of Psychology and Behavioral Sciences Zhejiang University Hangzhou China
| | - Xinchun Cui
- School of Computer Science Qufu Normal University Rizhao China
- Guangxi Key Laboratory of Cryptography and Information Security Guilin China
| | - Shujun Lian
- School of Management Qufu Normal University Rizhao China
| | - Ruyi Xiao
- School of Computer Science Qufu Normal University Rizhao China
| | - Hong Qiao
- School of Business Shandong Normal University Jinan China
| | - Shancang Li
- Department of Computer Science University of the West of England Bristol UK
| | - Yue Lou
- Department of Neurology Zhejiang Hospital Hangzhou China
| | - Yue Feng
- Department of Radiology Zhejiang Hospital Hangzhou China
| | - Liying Zhuang
- Department of Neurology Zhejiang Hospital Hangzhou China
| | - Jianzong Du
- Respiratory Medicine Zhejiang Hospital Hangzhou China
| | - Xiaoli Liu
- Department of Neurology Zhejiang Hospital Hangzhou China
| |
Collapse
|
10
|
Liu H, Wang Z, Li H, Li M, Han B, Qi Y, Wang H, Gao J. Label-free Quantitative Proteomic Analysis of Cerebrospinal Fluid and Serum in Patients With Relapse-Remitting Multiple Sclerosis. Front Genet 2022; 13:892491. [PMID: 35571066 PMCID: PMC9092947 DOI: 10.3389/fgene.2022.892491] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2022] [Accepted: 04/05/2022] [Indexed: 11/13/2022] Open
Abstract
Background: The lack of effective serum and cerebrospinal fluid (CSF) biomarkers remains a barrier to early diagnosis and treatment of multiple sclerosis (MS). The study is to identify the diagnostic biomarkers of serum and CSF in patients who suffered MS. Methods: At first, we performed differential analysis of CSF and serum proteomics on control and relapse-remitting multiple sclerosis (RRMS) patients. Secondly, CSF and serum’s differential proteins were compared, in order to identify the significative proteins. Finally, Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) analysis were performed on the differential proteins in serum and CSF respectively to clarify their common biological functions and pathways. Results: At the first step, in CSF, 73 proteins were significantly differentially expressed in the RRMS set compared with the controls. In serum, 22 proteins were differentially expressed. Secondly, we found MMP2 C8G and CFH were the same high expression trend in CSF and serum. Finally, we found the differential proteins in serum and CSF are mostly participated in biological processes: immuno-inflammatory response, neuronal development, cell adhesion and signaling. Conclusion: MMP2, C8G and CFH may participate in the pathogenesis of RRMS, which are the potential diagnostic biomarkers of the disease.
Collapse
Affiliation(s)
- Haijie Liu
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Ziwen Wang
- Department of Neurology, Baoding No. 1 Central Hospital, Baoding, China
| | - He Li
- Department of Automation, College of Information Science and Engineering, Tianjin Tianshi College, Tianjin, China
| | - Meijie Li
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Bo Han
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Yuan Qi
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Huailu Wang
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Juan Gao
- Department of Neurology, Baoding No. 1 Central Hospital, Baoding, China
| |
Collapse
|
11
|
Chen J, Li H, Ma L, Soong F. DEEMD-SPP: A Novel Framework for Emotion Recognition Based on EEG Signals. Front Psychiatry 2022; 13:885120. [PMID: 35573327 PMCID: PMC9091650 DOI: 10.3389/fpsyt.2022.885120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/27/2022] [Accepted: 04/01/2022] [Indexed: 11/13/2022] Open
Abstract
Electroencephalography (EEG) is one of the most widely-used biosignal capturing technology for investigating brain activities, cognitive diseases, and affective disorders. To understand the underlying principles of brain activities and affective disorders using EEG data, one of the fundamental tasks is to accurately identify emotions from EEG signals, which has attracted huge attention in the field of affective computing. To improve the accuracy and effectiveness of emotion recognition based on EEG data, previous studies have successfully developed numerous feature extraction methods and classifiers. Among them, ensemble empirical mode decomposition (EEMD) is an efficient signal decomposition technique for extracting EEG features. It can alleviate the mode-mixing problem by adding white noise to the source signal. However, there remain some issues when applying this method to recognition tasks. As the added noise cannot be filtered completely, spurious modes are generated due to the residual noise. Therefore, it is crucial to perform intrinsic mode function (IMF) selection to find the most valuable IMF components that represent brain activities. Furthermore, the number of decomposed IMFs is various to different original signals, thus how to unify feature dimensions needs better solutions. To solve these issues, we propose a novel forecasting framework, named DEEMD-SPP, to identify emotions from EEG signals, based on the combination of denoising ensemble empirical mode decomposition (DEEMD) and Spatial Pyramid Pooling Network (SPP-Net). First, DEEMD is proposed to decompose the EEG signals, which effectively eliminates residual noise in the IMFs and selects the most valuable IMFs. Second, time-domain and frequency-domain features are extracted from the selected IMFs. Finally, SPP-net is employed as the classifier to recognize emotions, which can effectively transform various-sized feature maps into fixed-sized feature vectors through the pyramid pooling layer. The experimental results demonstrate that our proposed DEEMD-SPP framework can effectively reduce the effect of spike-in white noise, accurately extract EEG features, and significantly improve the performance of emotion recognition.
Collapse
Affiliation(s)
- Jing Chen
- School of Computer Science and Technology, Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Haifeng Li
- School of Computer Science and Technology, Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Lin Ma
- School of Computer Science and Technology, Faculty of Computing, Harbin Institute of Technology, Harbin, China
| | - Frank Soong
- School of Computer Science and Technology, Faculty of Computing, Harbin Institute of Technology, Harbin, China.,Speech Group, Microsoft Research Asia, Beijing, China
| |
Collapse
|
12
|
Du J, Lin D, Yuan R, Chen X, Liu X, Yan J. Graph Embedding Based Novel Gene Discovery Associated With Diabetes Mellitus. Front Genet 2021; 12:779186. [PMID: 34899863 PMCID: PMC8657768 DOI: 10.3389/fgene.2021.779186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2021] [Accepted: 10/20/2021] [Indexed: 11/25/2022] Open
Abstract
Diabetes mellitus is a group of complex metabolic disorders which has affected hundreds of millions of patients world-widely. The underlying pathogenesis of various types of diabetes is still unclear, which hinders the way of developing more efficient therapies. Although many genes have been found associated with diabetes mellitus, more novel genes are still needed to be discovered towards a complete picture of the underlying mechanism. With the development of complex molecular networks, network-based disease-gene prediction methods have been widely proposed. However, most existing methods are based on the hypothesis of guilt-by-association and often handcraft node features based on local topological structures. Advances in graph embedding techniques have enabled automatically global feature extraction from molecular networks. Inspired by the successful applications of cutting-edge graph embedding methods on complex diseases, we proposed a computational framework to investigate novel genes associated with diabetes mellitus. There are three main steps in the framework: network feature extraction based on graph embedding methods; feature denoising and regeneration using stacked autoencoder; and disease-gene prediction based on machine learning classifiers. We compared the performance by using different graph embedding methods and machine learning classifiers and designed the best workflow for predicting genes associated with diabetes mellitus. Functional enrichment analysis based on Human Phenotype Ontology (HPO), KEGG, and GO biological process and publication search further evaluated the predicted novel genes.
Collapse
Affiliation(s)
| | | | | | | | | | - Jing Yan
- Zhejiang Hospital, Hangzhou, China.,Zhejiang Provincial Key Lab of Geriatrics, Zhejiang Hospital, Hangzhou, China
| |
Collapse
|