检索结果-内蒙古大学图书馆

PDGNet: Predicting Disease Genes Using a Deep Neural Network With Multi-View Features

ieee-ACM TRANSACTIONS ON computational biology AND bioinformatics 2022年第1期19卷 575-584页

作者： Yang, Kuo Zheng, Yi Lu, Kezhi Chang, Kai Wang, Ning Shu, Zixin Yu, Jian Liu, Baoyan Gao, Zhuye Zhou, Xuezhong Beijing Jiaotong Univ Sch Comp & Informat Technol Inst Med Intelligence Beijing 100044 Peoples R China Tsinghua Univ BNRIST Dept Automat Beijing 10084 Peoples R China Beijing Jiaotong Univer Sity Beijing Key Lab Traff Data Anal & Min Sch Comp & Informat Technol Beijing 100044 Peoples R China China Acad Chinese Med Sci Data Ctr Tradit Chinese Med Beijing 100700 Peoples R China China Acad China Acad Chinese Med Sci Xiyuan Hosp Beijing 100091 Peoples R China

The knowledge of phenotype-genotype associations is crucial for the understanding of disease mechanisms. Numerous studies have focused on developing efficient and accurate computing approaches to predict disease genes. However, owing to the sparseness and complexity of medical data, developing an efficient deep neural network model to identify disease genes remains a huge challenge. Therefore, we develop a novel deep neural network model that fuses the multi-view features of phenotypes and genotypes to identify disease genes (termed PDGNet). Our model integrated the multi-view features of diseases and genes and leveraged the feedback information of training samples to optimize the parameters of deep neural network and obtain the deep vector features of diseases and genes. The evaluation experiments on a large data set indicated that PDGNet obtained higher performance than the state-of-the-art method (precision and recall improved by 9.55 and 9.63 percent). The analysis results for the candidate genes indicated that the predicted genes have strong functional homogeneity and dense interactions with known genes. We validated the top predicted genes of Parkinson's disease based on external curated data and published medical literatures, which indicated that the candidate genes have a huge potential to guide the selection of causal genes in the 'wet experiment'. The source codes and the data of PDGNet are available at https://***/yangkuoone/PDGNet.

关键词： Disease gene prediction deep neural network multi-view features

来源：评论

学校读者我要写书评

暂无评论

To Improve Prediction of Binding Residues With DNA, RNA, Carbohydrate, and Peptide Via Multi-Task Deep Neural Networks

引用

ieee-ACM TRANSACTIONS ON computational biology AND bioinformatics 2022年第6期19卷 3735-3743页

作者： Sun, Zhe Zheng, Shuangjia Zhao, Huiying Niu, Zhangming Lu, Yutong Pan, Yi Yang, Yuedong Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510000 Guangdong Peoples R China Sun Yat Sen Univ Sun Yat Sen Mem Hosp Guangzhou 510000 Guangdong Peoples R China Aladdin Healthcare Technol Ltd London EC1Y 1AA England Georgia State Univ Dept Comp Sci Atlanta GA 30303 USA Sun Yat Sen Univ Key Lab Machine Intelligence & Adv Comp MOE Guangzhou 510000 Guangdong Peoples R China

Motivation: The interactions of proteins with DNA, RNA, peptide, and carbohydrate play key roles in various biological processes. The studies of uncharacterized protein-molecules interactions could be aided by accurate predictions of residues that bind with partner molecules. However, the existing methods for predicting binding residues on proteins remain of relatively low accuracies due to the limited number of complex structures in databases. As different types of molecules partially share chemical mechanisms, the predictions for each molecular type should benefit from the binding information with other molecule types. Results: In this study, we employed a multiple task deep learning strategy to develop a new sequence-based method for simultaneously predicting binding residues/sites with multiple important molecule types named MTDsite. By combining four training sets for DNA, RNA, peptide, and carbohydrate-binding proteins, our method yielded accurate and robust predictions with AUC values of 0.852, 0836, 0.758, and 0.776 on their respective independent test sets, which are 0.52 to 6.6% better than other state-of-the-art methods. To my best knowledge, this is the first method using multi-task framework to predict multiple molecular binding sites simultaneously.

关键词： Proteins RNA DNA Training Feature extraction Peptides Hidden Markov models Protein binding sites nucleic acid molecule carbohydrate peptide LSTM Multi-task Sequence-based approach

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate LSTM Meta-modeling of TNF-induced Tumor Resistance In Vitro

Fast and Accurate LSTM Meta-modeling of TNF-induced Tumor Re...

引用

ieee International conference on bioinformatics and Biomedicine (BIBM)

作者： Marco P. Abrate Riccardo Smeriglio Roberta Bardini Alessandro Savino Stefano Di Carlo Dept. of Cell and Developmental Biology University College London London UK Dept. of Control and Computer Engineering Politecnico di Torino Turin Italy

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Multi-level, hybrid models and simulations, among other methods, are essential to enable predictions and hypothesis generation in systems biology research. However, the computational complexity of these models poses a bottleneck, limiting the applicability of methodologies relying on large number of simulations, such as the Optimization via Simulation (OvS) of complex biological processes. Meta-models based on approximate surrogate models simplify multi-level simulations, maintaining accuracy while reducing computational costs. Among Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM) networks are well suited to handle sequential data, which often characterizes biological simulations. This paper presents an LSTM-based surrogate modeling approach for multi-level simulations of complex biological processes. Validation relies on the simulation of Tumor Necrosis Factor (TNF) administration to a 3T3 mouse fibroblasts tumor spheroid based on PhysiBoSS 2.0, a hybrid agent-based multi-level modeling framework. Results show that the proposed LSTM meta-model is accurate and fast compared with the simulator. In fact, it infers simulated behavior with an average relative error of 7.5%. Moreover, it is at least five orders of magnitude faster. Even considering the cost of training, this approach provides a faster, more accurate, and reusable surrogate of multi-scale simulations in computationally complex tasks, such as model-based OvS of biological processes.

关键词： Training Accuracy Biological system modeling computational modeling Biological processes Metamodeling Predictive models Data models Long short term memory Tumors

来源：评论

学校读者我要写书评

暂无评论

Oral Health Parameter-Based Mini-Mental State Examination Indication Using Machine Learning

Oral Health Parameter-Based Mini-Mental State Examination In...

引用

ieee International conference on bioinformatics and computational biology (ICBCB)

作者： Johan Flyborg Alper Idrisoglu Peter Anderberg Stefan Renvert Johan Sanmartin Berglund Department of Health Blekinge Institute of Technology Karlskrona Sweden University of Skövde School of Health Science Skövde Sweden Department of Oral Health Faculty of Health Science Kristianstad University Kristianstad Sweden

ISBN: (数字)9798350375749

ISBN: (纸本)9798350375756

Among the growing elderly population, the number of people with neurocognitive disease increases, highlighting the need for early diagnosis. Mini-Mental State Examination (MMSE) is one of the tools used to diagnose neurocognitive disease. The existence of a relationship between degraded oral health and decreased MMSE scores is known. Using machine Learning (ML) techniques, the present study aimed to study the potential of using oral health and demographic examination data to indicate the level of MMSE score. Data from a study evaluating oral health over time and data from an ongoing study evaluating the general health in an elderly population were used as inputs to ML models Random Forest (RF), Support Vektor Machine (SVM), and Catboost (CB) for the binary indication of MMSE score 30 or MMSE score 26 or lower was used to find the best classification performance to distinguish between MMSE low and healthy control (HC) groups. The classifiers were trained using the nested cross-validation (nCV) method to mitigate the risk of overfiting. CB and RF achieved the highest classification accuracy of 80%. However, the CB classifier outperformed other classifiers with 76.4 average accuracies over all the nCV combinations. The oral health parameters and demographics used as input to the ML classifiers carry enough information to distinguish between MMSE low and HC groups. This study suggests that oral health examination might provide information that can be used with the help of Machine Learning (ML) to indicate lowered MMSE scores.

关键词： Support vector machines Accuracy Data models Older adults bioinformatics Random forests Diseases Classification tree analysis computational biology

来源：评论

学校读者我要写书评

暂无评论

DeepIII: Predicting Isoform-Isoform Interactions by Deep Neural Networks and Data Fusion

引用

ieee-ACM TRANSACTIONS ON computational biology AND bioinformatics 2022年第4期19卷 2177-2187页

作者： Wang, Jun Zhang, Long Zeng, An Xia, Dawen Yu, Jiantao Yu, Guoxian Shandong Univ Joint SDU NTU Ctr Artificial Intelligence Res Jinan 250101 Shandong Peoples R China Alibaba Grp Hangzhou 310000 Peoples R China Guangdong Univ Technol Sch Comp Guangzhou 510006 Peoples R China Guizhou Minzu Univ Coll Data Sci & Informat Engn Guiyang 550025 Peoples R China Northwest A&F Univ Coll Informat Engn Yangling 712100 Shaanxi Peoples R China

Alternative splicing enables a gene translating into different isoforms and into the corresponding proteoforms, which actually accomplish various biological functions of a living body. Isoform-isoform interactions (IIIs) provide a higher resolution interactome to explore the cellular processes and disease mechanisms than the canonically studied protein-protein interactions (PPIs), which are often recorded at the coarse gene level. The knowledge of IIIs is critical to map pathways, understand protein complexity and functional diversity, but the known IIIs are very scanty. In this paper, we propose a deep learning based method called DeepIII to systematically predict genome-wide IIIs by integrating diverse data sources, including RNA-seq datasets of different human tissues, exon array data, domain-domain interactions (DDIs) of proteins, nucleotide sequences and amino acid sequences. Particularly, DeepIII fuses these data to learn the representation of isoform pairs with a four-layer deep neural networks, and then performs binary classification on the learnt representation to achieve the prediction of IIIs. Experimental results show that DeepIII achieves a superior prediction performance to the state-of-the-art solutions and the III network constructed by DeepIII gives more accurate isoform function prediction. Case studies further confirm that DeepIII can differentiate the individual interaction partners of different isoforms spliced from the same gene. The code and datasets of DeepIII are available at http://***/***?name=DeepIII.

关键词： Proteins Feature extraction Amino acids Standards Arrays Neurons Location awareness Isoform-isoform interactions deep neural networks data fusion RNA-seq datasets nucleotide sequences amino acid sequences

来源：评论

学校读者我要写书评

暂无评论

WSI2ML - An Open-Source Whole Slide Image Annotation Software for Machine Learning Applications 23

WSI2ML - An Open-Source Whole Slide Image Annotation Softwar...

引用

29th Brazilian Symposium on Multimedia and the Web, WebMedia 2023

作者： Martins, Luan V. C. Bueno, Adriana Passos Defelicibus, Alexandre Drummond, Rodrigo D. Valieris, Renan Zhu, Yu-Tao Da Silva, Israel Tojal Zhao, Liang São Carlos Brazil Laboratory of Computational Biology Bioinformatics CIPE/A.C. Camargo Cancer Center São Paulo Brazil China Branch of BRICS Institute of Future Networks ShenZhen China Ribeirão Preto Brazil

ISBN: (纸本)9798400709081

Machine learning (ML) has emerged as a powerful tool for improving the clinical pathology routine;however, developing novel ML research requires a complex multidisciplinary team effort. Therefore, a software for tackling the challenges of effectively annotating, building, and validating ML models is desirable. In this work we present WSI2ML, a web-based platform that provides a friendly interface suited for ML computational pathology research to be easily performed. Compared to similar tools currently available, the proposed software provides a complete toolset for each stage of ML workflow. We demonstrate the usefulness and functionality of WSI2ML by analyzing the performance results obtained in a tissue recognition task using a novel gastric cancer research dataset that is currently being developed with the tool. The software, documentation, installation instructions and related annotation handling library is freely available at https://***/WSI2ML/. © 2023 ACM.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Sequence to Graph Alignment Using Gap-Sensitive Co-linear Chaining 27th

Sequence to Graph Alignment Using Gap-Sensitive Co-linear C...

引用

27th International conference on Research in computational Molecular biology, RECOMB 2023

作者： Chandra, Ghanshyam Jain, Chirag Department of Computational and Data Sciences Indian Institute of Science KA Bangalore560012 India

ISBN: (纸本)9783031291180

Co-linear chaining is a widely used technique in sequence alignment tools that follow seed-filter-extend methodology. It is a mathematically rigorous approach to combine short exact matches. For co-linear chaining between two sequences, efficient subquadratic-time chaining algorithms are well-known for linear, concave and convex gap cost functions [Eppstein et al. JACM’92]. However, developing extensions of chaining algorithms for directed acyclic graphs (DAGs) has been challenging. Recently, a new sparse dynamic programming framework was introduced that exploits small path cover of pangenome reference DAGs, and enables efficient chaining [Makinen et al. TALG’19, RECOMB’18]. However, the underlying problem formulation did not consider gap cost which makes chaining less effective in practice. To address this, we develop novel problem formulations and optimal chaining algorithms that support a variety of gap cost functions. We demonstrate empirically the ability of our provably-good chaining implementation to align long reads more precisely in comparison to existing aligners. For mapping simulated long reads from human genome to a pangenome DAG of 95 human haplotypes, we achieve precision while leaving reads unmapped. Implementation: https://***/at-cg/minichain. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

On the Accuracy of Eikonal Approximations in Cardiac Electrophysiology in the Presence of Fibrosis 12th

On the Accuracy of Eikonal Approximations in Cardiac Elec...

引用

Functional Imaging and Modeling of the Heart - 12th International conference, FIMH 2023, Proceedings

作者： Gander, Lia Krause, Rolf Weiser, Martin Sahli Costabal, Francisco Pezzuto, Simone Center for Computational Medicine in Cardiology Euler Institute Università della Svizzera italiana Lugano Switzerland FernUni Brig Switzerland Zuse Institute Berlin Berlin Germany Department of Mechanical and Metallurgical Engineering School of Engineering and Institute for Biological and Medical Engineering Schools of Engineering Medicine and Biological Sciences Pontificia Universidad Católica de Chile Santiago Chile Laboratory of Mathematics for Biology and Medicine Department of Mathematics University of Trento Trento Italy

ISBN: (纸本)9783031353017

Fibrotic tissue is one of the main risk factors for cardiac arrhythmias. It is therefore a key component in computational studies. In this work, we compare the monodomain equation to two eikonal models for cardiac electrophysiology in the presence of fibrosis. We show that discontinuities in the conductivity field, due to the presence of fibrosis, introduce a delay in the activation times. The monodomain equation and eikonal-diffusion model correctly capture these delays, contrarily to the classical eikonal equation. Importantly, a coarse space discretization of the monodomain equation amplifies these delays, even after accounting for numerical error in conduction velocity. The numerical discretization may also introduce artificial conduction blocks and hence increase propagation complexity. Therefore, some care is required when comparing eikonal models to the discretized monodomain equation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

A Distance Geometry Procedure Using the Levenberg-Marquardt Algorithm and with Applications in biology but Not only 9th

A Distance Geometry Procedure Using the Levenberg-Marquardt ...

引用

9th International Work-conference on bioinformatics and Biomedical Engineering (IWBBIO)

作者： Goncalves, Douglas S. Mucherino, Antonio Univ Fed Santa Catarina Dept Math Florianopolis SC Brazil Univ Rennes IRISA Rennes France

ISBN: (纸本)9783031078026;9783031078019

We revisit a simple, yet capable to provide good solutions, procedure for solving the Distance Geometry Problem (DGP). This procedure combines two main components: the first one identifying an initial approximated solution via semidefinite programming, which is thereafter projected to the target dimension via PCA;and another component where this initial solution is refined by locally minimizing the Smooth STRESS function. In this work, we propose the use of the projected Levenberg-Marquart algorithm for this second step. In spite of the simplicity, as well as of its heuristic character, our experiments show that this procedure is able to exhibit good performances in terms of quality of the solutions for most of the instances we have selected for our experiments. Moreover, it seems to be promising not only for the DGP application arising in structural biology, which we considered in our computational experiments, but also in other ongoing studies related to the DGP and its applications: we finally provide a general discussion on how extending the presented ideas to other applications.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Impacts of Behavioral Biases on Active Learning Strategies 4

Impacts of Behavioral Biases on Active Learning Strategies

引用

4th International conference on Artificial intelligence in Information and Communication, ICAIIC 2022

作者： Agarwal, Deepesh Covarrubias-Zambrano, Obdulia Bossmann, Stefan Natarajan, Balasubramaniam Kansas State University Department of Electrical and Computer Engineering ManhattanKS United States The University of Kansas Medical Center Department of Cancer Biology Kansas CityKS United States

ISBN: (纸本)9781665458184

Cyber-Physical-Human Systems (CPHS) interconnect humans, physical plants and cyber infrastructure across space and time. Industrial processes, electromechanical systems operations and medical diagnosis are some examples where one can see the intersection of humans, physical and cyber components. Emergence of Artificial intelligence (AI) based computational models, controllers and decision support engines have improved the efficiency and cost effectiveness of such systems and processes. These CPHS typically involve a collaborative decision environment, comprising of AI-based models and human experts. Active Learning (AL) is a category of AI algorithms which aims to learn an efficient decision model by combining domain expertise of the human expert and computational capabilities of the AI model. Given the indispensable role of humans and lack of understanding about human behavior in collaborative decision environments, modeling and prediction of behavioral biases is a critical need. This paper, for the first time, introduces different behavioral biases within an AL context and investigates their impacts on the performance of AL strategies. The modelling of behavioral biases is demonstrated using experiments conducted on a real-world pancreatic cancer dataset. It is observed that classification accuracy of the decision model reduces by at least 20% in case of all the behavioral biases. © 2022 ieee.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：