检索结果-内蒙古大学图书馆

A Penalized Shared-parameter Algorithm for Estimating Optimal Dynamic Treatment Regimens

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ghosh, Palash Wang, Xinru Nalamada, Trikay Agarwal, Shruti Jahja, Maria Chakraborty, Bibhas Department of Mathematics Indian Institute of Technology Assam Guwahati India Centre for Quantitative Medicine Duke-NUS Medical School National University of Singapore Singapore Singapore Department of Statistics North Carolina State University NC United States Department of Statistics and Data Science National University of Singapore Singapore Singapore Department of Biostatistics and Bioinformatics Duke University DurhamNC United States

A dynamic treatment regimen (DTR) is a set of decision rules to personalize treatments for an individual using their medical history. The Q-learning-based Q-shared algorithm has been used to develop DTRs that involve decision rules shared across multiple stages of intervention. We show that the existing Q-shared algorithm can suffer from non-convergence due to the use of linear models in the Q-learning setup, and identify the condition under which Q-shared fails. We develop a penalized Q-shared algorithm that not only converges in settings that violate the condition, but can outperform the original Q-shared algorithm even when the condition is satisfied. We give evidence for the proposed method in a real-world application and several synthetic simulations. © 2021, CC BY-NC-SA.

关键词： Consensus algorithm

Prediction of Driver Gene Matching in Lung Cancer NOG/PDX Models Based on Artificial Intelligence

学校读者我要写书评

暂无评论

Engineering 2022年第8期8卷 102-114页

作者： Yayi He Haoyue Guo Li Diao Yu Chen Junjie Zhu Hiran C.Fernando Diego Gonzalez Rivas Hui Qi Chunlei Dai Xuzhen Tang Jun Zhu Jiawei Dai Kan He Dan Chan Yang Yang School of Medicin5 Tongji UniversityShanghai 200092China Department of Medical Oncology Shanghai Pulmonary HospitalSchool of Medicin5Tongji UniversityShanghai 200433China Department of Automation School of Electronic Information and Electrical Engineerin7Shanghai Jiao Tong UniversityShanghai 200240China Spine Center Orthopedic DepartmentShanghai Changzheng HospitalShanghai 200003China Department of Thoracic Surgery Shanghai Pulmonary HospitalSchool of Medicin5Tongji UniversityShanghai 200433China School of Materials Science and Engineerin7 Tongji UniversityShanghai 201804China Department of Thoracic Surgery Allegheny General HospitalPittsburg8PA 15212USA Department of Thoracic Surgery and Minimally Invasive Thoracic Surgery Unit(UCTMI) Coruna University HospitalCoruna 15006Spain Oncology and Immunology BU Research Service DivisionWuXi Appte3Shanghai 200131China SJTU–Yale Joint Center for Biostatistics and Data Scienc5 Department of Bioinformatics and BiostatisticsSchool of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghai 200240China Division of Medical Oncology Department of Medicin5University of Colorado Anschutz Medical CampusAuror1CO 80045USA

Patient-derived tumor xenografts(PDXs)are a powerful tool for drug discovery and screening in ***,current studies have led to little understanding of genotype mismatches in PDXs,leading to massive economic ***,we established PDX models from 53 lung cancer patients with a genotype matching rate of 79.2%(42/53).Furthermore,17 clinicopathological features were examined and input in stepwise logistic regression(LR)models based on the lowest Akaike information criterion(AIC),least absolute shrinkage and selection operator(LASSO)-LR,support vector machine(SVM)recursive feature elimination(SVM-RFE),extreme gradient boosting(XGBoost),gradient boosting and categorical features(Cat Boost),and the synthetic minority oversampling technique(SMOTE).Finally,the performance of all models was evaluated by the accuracy,area under the receiver operating characteristic curve(AUC),and F1 score in 100 testing *** multivariable LR models revealed that age,number of driver gene mutations,epidermal growth factor receptor(EGFR)gene mutations,type of prior chemotherapy,prior tyrosine kinase inhibitor(TKI)therapy,and the source of the sample were powerful ***,Cat Boost(mean accuracy=0.960;mean AUC=0.939;mean F1 score=0.908)and the eight-feature SVM-RFE(mean accuracy=0.950;mean AUC=0.934;mean F1 score=0.903)showed the best performance among the ***,application of the SMOTE improved the predictive capability of most models,except Cat *** on the SMOTE,the ensemble classifier of single models achieved the highest accuracy(mean=0.975),AUC(mean=0.949),and F1 score(mean=0.938).In conclusion,we established an optimal predictive model to screen lung cancer patients for non-obese diabetic(NOD)/Shi-scid,interleukin-2 receptor(IL-2R)γ^(null)(NOG)/PDX models and offer a general approach for building predictive models.

关键词： Machine learning Patient-derived tumor xenografts NOG mice

Shapley variable importance clouds for interpretable machine learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ning, Yilin Ong, Marcus Eng Hock Chakraborty, Bibhas Goldstein, Benjamin Alan Ting, Daniel Shu Wei Vaughan, Roger Liu, Nan Centre for Quantitative Medicine Duke-NUS Medical School Singapore Singapore Programme in Health Services and Systems Research Duke-NUS Medical School Singapore Singapore Health Services Research Centre Singapore Health Services Singapore Singapore Department of Emergency Medicine Singapore General Hospital Singapore Singapore Department of Statistics and Data Science National University of Singapore Singapore Singapore Department of Biostatistics and Bioinformatics Duke University DurhamNC United States SingHealth Ai Health Program Singapore Health Services Singapore Singapore Institute of Data Science National University of Singapore Singapore Singapore

Interpretable machine learning has been focusing on explaining final models that optimize performance. The current state-of-the-art is the Shapley additive explanations (SHAP) that locally explains variable impact on individual predictions, and it is recently extended for a global assessment across the dataset. Recently, Dong and Rudin proposed to extend the investigation to models from the same class as the final model that are "good enough", and identified a previous overclaim of variable importance based on a single model. However, this method does not directly integrate with existing Shapley-based interpretations. We close this gap by proposing a Shapley variable importance cloud that pools information across good models to avoid biased assessments in SHAP analyses of final models, and communicate the findings via novel visualizations. We demonstrate the additional insights gain compared to conventional explanations and Dong and Rudin's method using criminal justice and electronic medical records data. © 2021, CC BY.

关键词： Medical computing

Gene set correlation enrichment analysis for interpreting and annotating gene expression profiles

学校读者我要写书评

暂无评论

Nucleic Acids Research 2024年第3期52卷 E17页

作者： Chang, Lan-Yun Lee, Meng-Zhan Wu, Yujia Lee, Wen-Kai Ma, Chia-Liang Chang, Jun-Mao Chen, Ciao-Wen Huang, Tzu-Chun Lee, Chia-Hwa Lee, Jih-Chin Tseng, Yu-Yao Lin, Chun-Yu Institute of Bioinformatics and Systems Biology National Yang Ming Chiao Tung University Hsinchu 300 Taiwan School of Medical Laboratory Science and Biotechnology College of Medical Science and Technology Taipei Medical University New Taipei City 235 Taiwan Center for Intelligent Drug Systems and Smart Bio-devices (IDS2B) National Yang Ming Chiao Tung University Hsinchu 300 Taiwan TMU Research Center of Cancer Translational Medicine Taipei Medical University Taipei 110 Taiwan Ph.D. Program in Medical Biotechnology College of Medical Science and Technology Taipei Medical University New Taipei City 235 Taiwan Department of Otolaryngology-Head and Neck Surgery Tri-Service General Hospital National Defense Medical Center Taipei 110 Taiwan Department of Food Science Nutrition and Nutraceutical Biotechnology Shih Chien University Taipei 104 Taiwan Department of Biological Science and Technology National Yang Ming Chiao Tung University Hsinchu 300 Taiwan Cancer and Immunology Research Center National Yang Ming Chiao Tung University Taipei 112 Taiwan Institute of Data Science and Engineering National Yang Ming Chiao Tung University Hsinchu 300 Taiwan School of Dentistry Kaohsiung Medical University Kaohsiung 807 Taiwan

Pathway analysis, including nontopology-based (non-TB) and topology-based (TB) methods, is widely used to interpret the biological phenomena underlying differences in expression data between two phenotypes. By considering dependencies and interactions between genes, TB methods usually perform better than non-TB methods in identifying pathways that include closely relevant or directly causative genes for a given phenotype. However, most TB methods may be limited by incomplete pathway data used as the reference network or by difficulties in selecting appropriate reference networks for different research topics. Here, we propose a gene set correlation enrichment analysis method, Gscore, based on an expression dataset-derived coexpression network to examine whether a differentially expressed gene (DEG) list (or each of its DEGs) is associated with a known gene set. Gscore is better able to identify target pathways in 89 human disease expression datasets than eight other state-of-the-art methods and offers insight into how disease-wide and pathway-wide associations reflect clinical outcomes. When applied to RNA-seq data from COVID-19-related cells and patient samples, Gscore provided a means for studying how DEGs are implicated in COVID-19-related pathways. In summary, Gscore offers a powerful analytical approach for annotating individual DEGs, DEG lists, and genome-wide expression profiles based on existing biological knowledge. © 2024 Oxford University Press. All rights reserved.

关键词：

Worm Perturb-Seq: massively parallel whole-animal RNAi and RNA-seq

学校读者我要写书评

暂无评论

Nature Communications 2025年第1期16卷 1-21页

作者： Zhang, Hefei Li, Xuhang Song, Dongyuan Yukselen, Onur Nanda, Shivani Kucukural, Alper Li, Jingyi Jessica Garber, Manuel Walhout, Albertha J. M. Department of Systems Biology University of Massachusetts Chan Medical School Worcester MA United States Bioinformatics Interdepartmental Ph.D. Program University of California Los Angeles CA United States Via Scientific Inc. Cambridge MA United States Department of Genomics and Computational Biology University of Massachusetts Chan Medical School Worcester MA United States Department of Statistics and Data Science Department of Biostatistics Department of Computational Medicine and Department of Human Genetics University of California Los Angeles CA United States Department of Genetics and Genome Sciences University of Connecticut Health Center Farmington CT United States Pathology Beth Israel Deaconess Medical Center Harvard Medical School Boston MA United States

Transcriptomes provide highly informative molecular phenotypes that, combined with gene perturbation, can connect genotype to phenotype. An ultimate goal is to perturb every gene and measure transcriptome changes, however, this is challenging, especially in whole animals. Here, we present ‘Worm Perturb-Seq (WPS)’, a method that provides high-resolution RNA-sequencing profiles for hundreds of replicate perturbations at a time in living animals. WPS introduces multiple experimental advances combining strengths of Caenhorhabditis elegans genetics and multiplexed RNA-sequencing with a novel analytical framework, EmpirDE. EmpirDE leverages the unique power of large transcriptomic datasets and improves statistical rigor by using gene-specific empirical null distributions to identify DEGs. We apply WPS to 103 nuclear hormone receptors (NHRs) and find a striking ‘pairwise modularity’ in which pairs of NHRs regulate shared target genes. We envision the advances of WPS to be useful not only for C. elegans, but broadly for other models, including human cells. © The Author(s) 2025.

关键词：

Feature Pyramid Networks for Crowd Counting

学校读者我要写书评

暂无评论

Procedia Computer science 2019年 157卷 175-182页

作者： Tjeng Wawan Cenggoro Ayu Hidayah Aslamiah Ardian Yunanto Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480

In this paper, we propose the use of Feature Pyramid Networks (FPN) for Crowd Counting problem. FPN previously has been used for retinanet, the state-of-the-art model for object detection. By using FPN, our proposed crowd counting model achieved a state-of-the-art performance for UCF CC 50 dataset with MAE 136.4 and MSE 223.6. The proposed model is also achieved a state-of-the-art MSE value of 7.6 for ShanghaiTech Part B dataset. The code can be accessed at https: //***/wawancenggoro/fpncc.

关键词： Crowd Counting Scale-Aware Deep Learning Feature Pyramid Networks

Weisfeiler and Leman go Machine Learning: The Story so far

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Morris, Christopher Lipman, Yaron Maron, Haggai Rieck, Bastian Kriege, Nils M. Grohe, Martin Fey, Matthias Borgwardt, Karsten Department of Computer Science RWTH Aachen University Aachen Germany Meta AI Research Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel NVIDIA Research Tel Aviv Israel AIDOS Lab Institute of AI for Health Helmholtz Zentrum München and Technical University of Munich Munich Germany Faculty of Computer Science University of Vienna Vienna Austria Research Network Data Science University of Vienna Vienna Austria Kumo.AI Mountain ViewCA United States Machine Learning & Computational Biology Lab Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland

In recent years, algorithms and neural architectures based on the Weisfeiler–Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm’s use in a machine-learning setting, focusing on the supervised regime. We discuss the theoretical background, show how to use it for supervised graph and node representation learning, discuss recent extensions, and outline the algorithm’s connection to (permutation-)equivariant neural architectures. Moreover, we give an overview of current applications and future directions to stimulate further research. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Relative Timing Information and Orthology in Evolutionary Scenarios

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Schaller, David Hartmann, Tom Lafond, Manuel Wieseke, Nicolas Stadler, Peter F. Hellmuth, Marc Bioinformatics Group Department of Computer Science Interdisciplinary Center for Bioinformatics Universität Leipzig Härtelstraße 16–18 LeipzigD-04107 Germany Max Planck Institute for Mathematics in the Sciences Inselstraße 22 LeipzigD-04103 Germany Department of Computer Science Université de Sherbrooke 2500 boul. de l’Université SherbrookeQCJ1K 2R1 Canada Halle-Jena-Leipzig Competence Center for Scalable Data Services and Solutions Dresden-Leipzig Leipzig Research Center for Civilization Diseases Centre for Biotechnology and Biomedicine Leipzig University Universität Leipzig Germany Institute for Theoretical Chemistry University of Vienna Währingerstrasse 17 WienA-1090 Austria Facultad de Ciencias Universidad National de Colombia Sede Bogotá Colombia Santa Fe Insitute 1399 Hyde Park Rd. Santa FeNM87501 United States Swarm Intelligence and Complex Systems Group Department of Computer Science Leipzig University Augustusplatz 10 LeipzigD-04109 Germany Department of Mathematics Faculty of Science Stockholm University StockholmSE - 106 91 Sweden

Evolutionary scenarios describing the evolution of a family of genes within a collection of species comprise the mapping of the vertices of a gene tree T to vertices and edges of a species tree S. The relative timing of the last common ancestors of two extant genes (leaves of T) and the last common ancestors of the two species (leaves of S) in which they reside is indicative of horizontal gene transfers (HGT) and ancient duplications. Orthologous gene pairs, on the other hand, require that their last common ancestors coincides with a corresponding speciation event. The relative timing information of gene and species divergences is captured by three colored graphs that have the extant genes as vertices and the species in which the genes are found as vertex colors: the equal-divergence-time (EDT) graph, the later-divergence-time (LDT) graph and the prior-divergence-time (PDT) graph, which together form an edge partition of the complete graph. Here we give a complete characterization in terms of informative and forbidden triples that can be read off the three graphs and provide a polynomial time algorithm for constructing an evolutionary scenario that explains the graphs, provided such a scenario exists. While both LDT and PDT graphs are cographs, this is not true for the EDT graph in general. We show that every EDT graph is perfect. While the information about LDT and PDT graphs is necessary to recognize EDT graphs in polynomial-time for general scenarios, this extra information can be dropped in the HGT-free case. However, recognition of EDT graphs without knowledge of putative LDT and PDT graphs is NP-complete for general scenarios. In contrast, PDT graphs can be recognized in polynomial-time. We finally connect the EDT graph to the alternative definitions of orthology that have been proposed for scenarios with horizontal gene transfer. With one exception, the corresponding graphs are shown to be colored cographs. © 2022, CC BY.

关键词： Genes

Learning management system for oil palm smallholder-owned plantations

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2594卷

作者： E. Firmansyah D. Nurjannah S. I. Dinarti D. Sudigyo T. Suparyanto B. Pardamean Department of Agrotechnology Institute of Agriculture STIPER Yogyakarta Indonesia 55281 Departement of Agricultural Economics Institute of Agriculture STIPER Yogyakarta Indonesia 55281 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Departement of Agriculture Engineering Institute of Agriculture STIPER Yogyakarta Indonesia 55281 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

The production gap between oil palm smallholder-owned plantations and corporations shows a real problem in the national palm oil industry. To reduce the gap, user-friendly assistance for smallholder-owned plantations is needed for the cultivation of sustainable palm oil production. Android-based software can be a platform for bridging the transfer of knowledge and technology, transfer of problems, and transfer of solutions between planters and experts. The platform development was formulated in five stages which began with Learning Management System (LMS) application development, identification of Good Agricultural Practices (GAP) and Best Management Practices (BMP) materials, development of digital contents, uploading the digital content to the LMS server, and dissemination. The curriculum in the application platform was prepared based on the needs of the growers according to the identification results of the farmers' profiles. The curriculum consists of GAP and BMP material blocks. Each block was divided into discussion topics. The digital contents related to GAP and BMP were set in the LMS, which was built using Moodle platform.

关键词：