检索结果-内蒙古大学图书馆

AutoImplant 2020-First MICCAI Challenge on Automatic Cranial Implant Design

IEEE TRANSACTIONS ON medICAL IMAGING 2021年第9期40卷 2329-2342页

作者： Li, Jianning Pimentel, Pedro Szengel, Angelika Ehlke, Moritz Lamecker, Hans Zachow, Stefan Estacio, Laura Doenitz, Christian Ramm, Heiko Shi, Haochen Chen, Xiaojun Matzkin, Franco Newcombe, Virginia Ferrante, Enzo Jin, Yuan Ellis, David G. Aizenberg, Michele R. Kodym, Oldrich Spanel, Michal Herout, Adam Mainprize, James G. Fishman, Zachary Hardisty, Michael R. Bayat, Amirhossein Shit, Suprosanna Wang, Bomin Liu, Zhi Eder, Matthias Pepe, Antonio Gsaxner, Christina Alves, Victor Zefferer, Ulrike von Campe, Gord Pistracher, Karin Schaefer, Ute Schmalstieg, Dieter Menze, Bjoern H. Glocker, Ben Egger, Jan Graz Univ Technol Inst Comp Graph & Vis A-8010 Graz Austria Comp Algorithms Med Lab Graz Austria 1000shapes GmbH D-12247 Berlin Germany Zuse Inst Berlin ZIB D-14195 Berlin Germany Univ Catolica San Pablo Dept Comp Sci Arequipa 04001 Peru Univ Med Ctr Regensburg Dept Neurosurg D-93053 Regensburg Germany Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Sch Mech Engn Shanghai 200240 Peoples R China Univ Nacl Litoral Inst Signals Syst & Computat Intelligence CONICET RA-3000 Santa Fe Argentina Univ Cambridge Univ Div Anaesthesia Cambridge CB2 0QQ England Univ Nebraska Med Ctr Dept Neurosurg Omaha NE 68198 USA Brno Univ Technol Dept Comp Graph & Multimedia Brno 61200 Czech Republic Sunnybrook Res Inst Toronto ON M4N 3M5 Canada Calavera Surg Design Inc Toronto ON M4N 3M5 Canada Univ Toronto Div Orthopaed Surg Toronto ON M5T 1P5 Canada Tech Univ Munich Dept Informat D-85748 Munich Germany Shandong Univ Sch Informat Sci & Engn Qingdao 266000 Peoples R China Med Univ Graz Dept Oral & Maxillofacial Surg A-8036 Graz Austria Univ Minho Ctr ALGORITMI P-4710057 Braga Portugal Med Univ Graz Res Unit Expt Neurotraumatol A-8036 Graz Austria Med Univ Graz Dept Neurosurg A-8036 Graz Austria Univ Zurich Dept Quantitat Biomed CH-8006 Zurich Switzerland Imperial Coll London Biomed Image Anal Grp Dept Comp London SW7 2AZ England

The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. The codes can be found at https://***/Jianningli/tmi.

关键词： Skull Shape Implants Three-dimensional displays Cranial Image reconstruction Biomedical imaging Volumetric shape completion shape inpainting skull reconstruction shape prior statistical shape model deep learning cranioplasty

来源：评论

学校读者我要写书评

暂无评论

k-strip: A novel segmentation algorithm in k-space for the application of skull stripping

引用

compUTER METHODS AND PROGRAMS IN BIOmedICINE 2024年 243卷 107912-107912页

作者： Rempe, Moritz Mentzel, Florian Pomykala, Kelsey L. Haubold, Johannes Nensa, Felix Kroeninger, Kevin Egger, Jan Kleesiek, Jens Univ Hosp Essen Inst AI Med IKIM Girardetstr 2 D-45131 Essen Germany Tech Univ Dortmund Dept Phys Otto-Hahn-Str 4a D-44227 Dortmund Germany Comp Algorithms Med Lab Graz Austria Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16 A-8010 Graz Austria Univ Med Essen Canc Res Ctr Cologne Essen CCCE Hufelandstr 55 D-45147 Essen Germany German Canc Consortium DKTK Partner Site Essen Hufelandstr 55 D-45147 Essen Germany Univ Hosp Essen Inst AI Med IKIM Girardetstr 2 D-45131 Essen Germany

Background and objective: We present a novel deep learning-based skull stripping algorithm for magnetic resonance imaging (MRI) that works directly in the information rich complex valued k-space. Methods: Using four datasets from different institutions with a total of around 200,000 MRI slices, we show that our network can perform skull-stripping on the raw data of MRIs while preserving the phase information which no other skull stripping algorithm is able to work with. For two of the datasets, skull stripping performed by HDBET (Brain Extraction Tool) in the image domain is used as the ground truth, whereas the third and fourth dataset comes with per-hand annotated brain segmentations. Results: All four datasets were very similar to the ground truth (DICE scores of 92 %-99 % and Hausdorff distances of under 5.5 pixel). Results on slices above the eye-region reach DICE scores of up to 99 %, whereas the accuracy drops in regions around the eyes and below, with partially blurred output. The output of k-Strip often has smoothed edges at the demarcation to the skull. Binary masks are created with an appropriate threshold. Conclusion: With this proof-of-concept study, we were able to show the feasibility of working in the k-space frequency domain, preserving phase information, with consistent results. Besides preserving valuable information for further diagnostics, this approach makes an immediate anonymization of patient data possible, already before being transformed into the image domain. Future research should be dedicated to discovering additional ways the k-space can be used for innovative image analysis and further workflows.

关键词： complex convolutional networks Deep learning k-space Magnetic resonance imaging (MRI) Skull stripping

来源：评论

学校读者我要写书评

暂无评论

Bioconda: sustainable and comprehensive software distribution for the life sciences

引用

NATURE METHODS 2018年第7期15卷 475-476页

作者： Gruening, Bjoern Dale, Ryan Sjoedin, Andreas Chapman, Brad A. Rowe, Jillian Tomkins-Tinch, Christopher H. Valieris, Renan Koester, Johannes Team, Bioconda Univ Freiburg Dept Comp Sci Bioinformat Grp Freiburg Germany NIDDK Lab Cellular & Dev Biol US Natl Inst Hlth Bethesda MD 20892 USA FOI Swedish Def Res Agcy Div CBRN Secur & Def Umea Sweden Umea Univ Dept Chem Computat Life Sci Cluster CLiC Umea Sweden Harvard TH Chan Sch Publ Hlth Boston MA USA NYU Abu Dhabi Ctr Genom & Syst Biol Genom Core Abu Dhabi U Arab Emirates Harvard Univ Dept Organism & Evolutionary Biol Cambridge MA 02138 USA Broad Inst MIT & Harvard Cambridge MA 02142 USA AC Camargo Canc Ctr Lab Bioinformat & Computat Biol Sao Paulo Brazil Univ Duisburg Essen Univ Hosp Essen Inst Human Genet Algorithms Reproducible Bioinformat Genome Inform Essen Germany Harvard Med Sch Dana Farber Canc Inst Med Oncol Boston MA 02115 USA

来源：评论

学校读者我要写书评

暂无评论

PSB 2019 Workshop on Text Mining and Visualization for Precision medicine 24

PSB 2019 Workshop on Text Mining and Visualization for Preci...

引用

24th Pacific Symposium on Biocomputing (PSB)

作者： Gonzalez-Hernandez, Graciela Lu, Zhiyong Leaman, Robert Weissenbacher, Davy Boland, Mary Regina Chen, Yong Du, Jingcheng Fluck, Juliane Greene, Casey S. Holmes, John Kashyap, Aditya Nielsen, Rikke Linnemann Ouyang, Zhengqing Schaaf, Sebastian Taroni, Jaclyn N. Tao, Cui Zhang, Yuping Liu, Hongfang Univ Penn Perelman Sch Med Dept Biostat Epidemiol & Informat Philadelphia PA 19104 USA NIH NCBI Natl Lib Med 8600 Rockville Pike Bethesda MD 20894 USA Mayo Clin Coll Med Div Biomed Stat & Informat Rochester MN USA Childrens Hosp Philadelphia Dept Biomed & Hlth Informat Philadelphia PA 19104 USA Univ Texas Hlth Sci Ctr Houston Sch Biomed Informat Houston TX 77030 USA ZB MED Informat Ctr Life Sci Bonn Germany Fraunhofer Inst Sci Comp & Algorithms SCAI Dept Bioinformat St Augustin Germany Univ Penn Perelman Sch Med Dept Syst Pharmacol & Translat Therapeut Philadelphia PA 19104 USA Alexs Lemonade Stand Fdn Childhood Canc Data Lab Philadelphia PA USA Univ Penn Data Sci Masters Program Philadelphia PA 19104 USA Tech Univ Denmark Dept Bio & Hlth Informat Lyngby Denmark Jackson Lab Genom Med Farmington CT USA Univ Connecticut Dept Stat Storrs CT USA Univ Bonn Inst Geodesy & Geoinformat Bonn Germany

ISBN: (纸本)9789813279827;9789813279810

Precision medicine, an approach for disease treatment and prevention that considers "individual variability in genes, environment, and lifestyle"(1) was endorsed by the National Institutes of Health, aided by the presidential Precision medicine Initiative (PMI), in 2016. PMI provided funding for cancer research and for building a national cohort of one million or more U.S. participants, now known as the "All of Us" Research Program, which aims to expand its impact to all diseases. PMI was the catalyst to a widespread effort around precision medicine, as evidenced by the more than 1000 grants funded by different NIH institutes in just the last two years. The data being generated by these efforts is growing exponentially, and becomes both the greatest treasure and the greatest challenge for researchers. This workshop is a continuation of a similar session in PSB 2018, providing a forum for researchers with strong background in text mining or natural language processing (NLP) and/or machine learning (ML) who are actively collaborating with bench scientists and clinicians to tackle the challenges brought about by this explosion of data.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Vertebral body segmentation with GrowCut: Initial experience, workflow and practical application

引用

SAGE OPEN medICINE 2017年 5卷 2050312117740984-2050312117740984页

作者： Egger, Jan Nimsky, Christopher Chen, Xiaojun Graz Univ Technol TUG Inst Comp Graph & Vis Inffeldgasse 16c-2 A-8010 Graz Austria BioTechMed Graz Graz Austria Univ Hosp Marburg Dept Neurosurg Marburg Germany Comp Algorithms Med Cafe Lab Graz Austria Shanghai Jiao Tong Univ Sch Mech Engn Dongchuan Rd 800 Shanghai 200240 Peoples R China

Objectives: Spinal diseases are very common;for example, the risk of osteoporotic fracture is 40% for White women and 13% for White men in the United States during their lifetime. Hence, the total number of surgical spinal treatments is on the rise with the aging population, and accurate diagnosis is of great importance to avoid complications and a reappearance of the symptoms. Imaging and analysis of a vertebral column is an exhausting task that can lead to wrong interpretations. The overall goal of this contribution is to study a cellular automata-based approach for the segmentation of vertebral bodies between the compacta and surrounding structures yielding to time savings and reducing interpretation errors. Methods: To obtain the ground truth, T2-weighted magnetic resonance imaging acquisitions of the spine were segmented in a slice-by-slice procedure by several neurosurgeons. Subsequently, the same vertebral bodies have been segmented by a physician using the cellular automata approach GrowCut. Results: Manual and GrowCut segmentations have been evaluated against each other via the Dice Score and the Hausdorff distance resulting in 82.99% +/- 5.03% and 18.91 +/- 7.2 voxel, respectively. Moreover, the times have been determined during the slice-by-slice and the GrowCut course of actions, indicating a significantly reduced segmentation time (5.77 +/- 0.73 min) of the algorithmic approach. Conclusion: In this contribution, we used the GrowCut segmentation algorithm publicly available in three-dimensional Slicer for three-dimensional segmentation of vertebral bodies. To the best of our knowledge, this is the first time that the GrowCut method has been studied for the usage of vertebral body segmentation. In brief, we found that the GrowCut segmentation times were consistently less than the manual segmentation times. Hence, GrowCut provides an alternative to a manual slice by-slice segmentation process.

关键词： Segmentation vertebral body GrowCut magnetic resonance imaging Dice Score

来源：评论

学校读者我要写书评

暂无评论

GAN-based generation of realistic 3D volumetric data: A systematic review and taxonomy

引用

medICAL IMAGE ANALYSIS 2024年 93卷 103100页

作者： Ferreira, Andre Li, Jianning Pomykala, Kelsey L. Kleesiek, Jens Alves, Victor Egger, Jan Univ Minho Ctr Algoritmi LASI P-4710057 Braga Portugal Comp Algorithms Med Lab Graz Austria Univ Med Essen Inst AI Med IKIM Girardetstr 2 D-45131 Essen Germany Univ Med Essen Canc Res Ctr Cologne Essen CCCE Hufelandstr 55 D-45147 Essen Germany German Canc Consortium DKTK Partner Site EssenHufelandstr 55 D-45147 Essen Germany Graz Univ Technol Inst Comp Graph & Vis Inffeldgasse 16 Graz 801 Austria TU Dortmund Univ Dept Phys Otto Hahn Str 4 D-44227 Dortmund Germany Univ Hosp RWTH Aachen Dept Oral & Maxillofacial Surg D-52074 Aachen Germany Univ Hosp RWTH Aachen Inst Med Informat D-52074 Aachen Germany

With the massive proliferation of data -driven algorithms, such as deep learning-based approaches, the availability of high-quality data is of great interest. Volumetric data is very important in medicine, as it ranges from disease diagnoses to therapy monitoring. When the dataset is sufficient, models can be trained to help doctors with these tasks. Unfortunately, there are scenarios where large amounts of data is unavailable. For example, rare diseases and privacy issues can lead to restricted data availability. In non-medical fields, the high cost of obtaining enough high-quality data can also be a concern. A solution to these problems can be the generation of realistic synthetic data using Generative Adversarial Networks (GANs). The existence of these mechanisms is a good asset, especially in healthcare, as the data must be of good quality, realistic, and without privacy issues. Therefore, most of the publications on volumetric GANs are within the medical domain. In this review, we provide a summary of works that generate realistic volumetric synthetic data using GANs. We therefore outline GAN-based methods in these areas with common architectures, loss functions and evaluation metrics, including their advantages and disadvantages. We present a novel taxonomy, evaluations, challenges, and research opportunities to provide a holistic overview of the current state of volumetric GANs.

关键词： Synthetic volumetric data Generative adversarial network Systematic review Volumetric GANs taxonomy

来源：评论

学校读者我要写书评

暂无评论

The Helmholtz Network for Bioinformatics:: an integrative web portal for bioinformatics resources

引用

BIOINFORMATICS 2004年第2期20卷 268-270页

作者： Crass, T Antes, I Basekow, R Bork, P Buning, C Christensen, M Claussen, H Ebeling, C Ernst, P Gailus-Durner, V Glatting, KH Gohla, R Gössling, F Grote, K Heidtke, K Herrmann, A O'Keeffe, S Kiesslich, O Kolibal, S Korbel, JO Lengauer, T Liebich, I van der Linden, M Luz, H Meissner, K von Mering, C Mevissen, HT Mewes, HW Michael, H Mokrejs, M Müller, T Pospisil, H Rarey, M Reich, JG Schneider, R Schomburg, D Schulze-Kremer, S Schwarzer, K Sommer, I Springstubbe, S Suhai, S Thoppae, G Vingron, M Warfsmann, J Werner, T Wetzler, D Wingender, E Zimmer, R Univ Gottingen Fac Med Dept Bioinformat D-37077 Gottingen Germany Max Planck Inst Informat Computat Biol & Appl Al D-66123 Saarbrucken Germany RZPD Deutsch Ressourcenzentrum Genomforsch GmbH D-14059 Berlin Germany European Mol Biol Lab Struct & Computat Biol Programme D-69117 Heidelberg Germany Max Delbruck Ctr Mol Med Dept Bioinformat D-13125 Berlin Germany Schloss Birlinghoven Fraunhofer Inst Algorithms & Sci Comp D-53754 St Augustin Germany Univ Cologne Inst Biochem D-50674 Cologne Germany German Canc Res Ctr Dept Mol Biophys D-69120 Heidelberg Germany Natl Res Ctr Environm & Hlth GSF Inst Bioinformat MIPS IBI D-85764 Neuherberg Germany German Biotechnol Res Ctr GBF Genome Anal Dept D-38124 Braunschweig Germany Max Planck Inst Mol Genet Bioinformat Dept D-14195 Berlin Germany Univ Munich Inst Informat Prakt Informat & Bioinformat D-80333 Munich Germany

The Helmholtz Network for Bioinformatics (HNB) is a joint venture of eleven German bioinformatics research groups that offers convenient access to numerous bioinformatics resources through a single web portal. The 'Guided Solution Finder' which is available through the HNB portal helps users to locate the appropriate resources to answer their queries by employing a detailed, tree-like questionnaire. Furthermore, automated complex tool cascades ('tasks'), involving resources located on different servers, have been implemented, allowing users to perform comprehensive data analyses without the requirement of further manual intervention for data transfer and re-formatting. Currently, automated cascades for the analysis of regulatory DNA segments as well as for the prediction of protein functional properties are provided.

关键词： algorithms* computational Biology/methods* computational Biology/organization & administration Database Management Systems* Germany Information Storage and Retrieval/methods* Interinstitutional Relations Internet* Sequence Analysis, DNA/methods* Sequence Analysis, Protein/methods* Software User-computer Interface*

来源：评论

学校读者我要写书评

暂无评论

Eleven grand challenges in single-cell data science

引用

GENOME BIOLOGY 2020年第1期21卷 1页

作者： Laehnemann, David Koester, Johannes Szczurek, Ewa McCarthy, Davis J. Hicks, Stephanie C. Robinson, Mark D. Vallejos, Catalina A. Campbell, Kieran R. Beerenwinkel, Niko Mahfouz, Ahmed Pinello, Luca Skums, Pavel Stamatakis, Alexandros Attolini, Camille Stephan-Otto Aparicio, Samuel Baaijens, Jasmijn Balvert, Marleen de Barbanson, Buys Cappuccio, Antonio Corleone, Giacomo Dutilh, Bas E. Florescu, Maria Guryev, Victor Holmer, Rens Jahn, Katharina Lobo, Thamar Jessurun Keizer, Emma M. Khatri, Indu Kielbasa, Szymon M. Korbel, Jan O. Kozlov, Alexey M. Kuo, Tzu-Hao Lelieveldt, Boudewijn P. F. Mandoiu, Ion I. Marioni, John C. Marschall, Tobias Moelder, Felix Niknejad, Amir Raczkowski, Lukasz Reinders, Marcel de Ridder, Jeroen Saliba, Antoine-Emmanuel Somarakis, Antonios Stegle, Oliver Theis, Fabian J. Yang, Huan Zelikovsky, Alex McHardy, Alice C. Raphael, Benjamin J. Shah, Sohrab P. Schonhuth, Alexander Univ Duisburg Essen Univ Hosp Essen Inst Human Genet Algorithms Reproducible BioinformatGenome Inform Essen Germany Heinrich Heine Univ Univ Hosp Fac Med Dept Paediat Oncol Haematol & Immunol Dusseldorf Germany Helmholtz Ctr Infect Res Computat Biol Infect Res Grp Braunschweig Germany Harvard Med Sch Dana Farber Canc Inst Med Oncol Boston MA 02115 USA Univ Warsaw Inst Informat Fac Math Informat & Mech Warsaw Poland St Vincents Inst Med Res Bioinformat & Cellular Genom Fitzroy Vic Australia Univ Melbourne Fac Sci Sch Math & Stat Melbourne Integrat GenomSch BioSci Melbourne Vic Australia Johns Hopkins Univ Dept Biostat Baltimore MD 21205 USA Univ Zurich Inst Mol Life Sci Zurich Switzerland Univ Zurich SIB Zurich Switzerland Univ Edinburgh Western Gen Hosp Inst Genet & Mol Med MRC Human Genet Unit Edinburgh Midlothian Scotland British Lib Alan Turing Inst London England Univ British Columbia Dept Stat Vancouver BC Canada BC Canc Agcy Dept Mol Oncol Vancouver BC Canada Univ British Columbia Data Sci Inst Vancouver BC Canada Swiss Fed Inst Technol Dept Biosyst Sci & Engn Basel Switzerland SIB Lausanne Switzerland Leiden Univ Med Ctr Leiden Computat Biol Ctr Leiden Netherlands Delft Univ Technol Fac Elect Engn Math & Comp Sci Delft Bioinformat Lab Delft Netherlands Massachusetts Gen Hosp Res Inst Mol Pathol Unit Charlestown MA USA Massachusetts Gen Hosp Res Inst Ctr Canc Res Charlestown MA USA Harvard Med Sch Dept Pathol Boston MA 02115 USA Broad Inst MIT & Harvard Cambridge MA 02142 USA Georgia State Univ Dept Comp Sci Atlanta GA 30303 USA Heidelberg Inst Theoret Studies Computat Mol Evolut Grp Heidelberg Germany Karlsruhe Inst Technol Inst Theoret Informat Karlsruhe Germany Barcelona Inst Sci & Technol Inst Res Biomed Barcelona Spain Univ British Columbia Dept Pathol & Lab Med Vancouver BC Canada Ctr Wiskunde & Informat Life Sci & Hlth Amsterdam Netherlands Univ Utrecht Theoret Biol & Bioinformat Sci Life Utr

The recent boom in microfluidics and combinatorial indexing strategies, combined with low sequencing costs, has empowered single-cell sequencing technology. Thousands-or even millions-of cells analyzed in a single experiment amount to a data revolution in single-cell biology and pose unique data science problems. Here, we outline eleven challenges that will be central to bringing this emerging field of single-cell data science forward. For each challenge, we highlight motivating research questions, review prior work, and formulate open problems. This compendium is for established researchers, newcomers, and students alike, highlighting interesting and rewarding problems for the coming years.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transparency and reproducibility in artificial intelligence

引用

NATURE 2020年第7829期586卷 E14-U7页

作者： Haibe-Kains, Benjamin Adam, George Alexandru Hosny, Ahmed Khodakarami, Farnoosh Shraddha, Thakkar Kusko, Rebecca Sansone, Susanna-Assunta Tong, Weida Wolfinger, Russ D. Mason, Christopher E. Jones, Wendell Dopazo, Joaquin Furlanello, Cesare Waldron, Levi Wang, Bo McIntosh, Chris Goldenberg, Anna Kundaje, Anshul Greene, Casey S. Broderick, Tamara Hoffman, Michael M. Leek, Jeffrey T. Korthauer, Keegan Huber, Wolfgang Brazma, Alvis Pineau, Joelle Tibshirani, Robert Hastie, Trevor Ioannidis, John P. A. Quackenbush, John Aerts, Hugo J. W. L. Univ Hlth Network Princess Margaret Canc Ctr Toronto ON Canada Univ Toronto Dept Med Biophys Toronto ON Canada Univ Toronto Dept Comp Sci Toronto ON Canada Ontario Inst Canc Res Toronto ON Canada Vector Inst Artificial Intelligence Toronto ON Canada Harvard Med Sch Brigham & Womens Hosp Artificial Intelligence Med AIM Program Boston MA 02115 USA Harvard Med Sch Radiat Oncol & Radiol Dana Farber Canc Inst Brigham & Womens Hosp Boston MA 02115 USA CUNY Grad Sch Publ Hlth & Hlth Policy Dept Epidemiol & Biostat New York NY 10021 USA CUNY Grad Sch Publ Hlth & Hlth Policy Inst Implementat Sci Populat Hlth New York NY 10021 USA Univ Hlth Network Peter Munk Cardiac Ctr Toronto ON Canada Univ Toronto Dept Lab Med & Pathobiol Toronto ON Canada SickKids Res Inst Toronto ON Canada CIFAR Child & Brain Dev Program Toronto ON Canada Stanford Univ Dept Genet Sch Med Stanford CA 94305 USA Stanford Univ Dept Comp Sci Stanford CA 94305 USA Univ Penn Perelman Sch Med Dept Syst Pharmacol & Translat Therapeut Philadelphia PA 19104 USA Alexs Lemonade Stand Fdn Childhood Canc Data Lab Philadelphia PA USA MIT Dept Elect Engn & Comp Sci Cambridge MA 02139 USA Johns Hopkins Bloomberg Sch Publ Hlth Dept Biostat Baltimore MD USA Univ British Columbia Dept Stat Vancouver BC Canada BC Childrens Hosp Res Inst Vancouver BC Canada European Mol Biol Lab Genome Biol Unit Heidelberg Germany EMBL EBI European Mol Biol Lab European Bioinformat Inst Hinxton England McGill Univ Montreal PQ Canada Montreal Inst Learning Algorithms Quebec City PQ Canada Stanford Univ Dept Stat Sch Humanities & Sci Stanford CA 94305 USA Stanford Univ Sch Med Dept Biomed Data Sci Stanford CA 94305 USA Stanford Univ Dept Med Sch Med Stanford CA 94305 USA Meta Res Innovat Ctr Stanford METRICS Stanford CA USA Stanford Univ Sch Med Dept Epidemiol & Populat Hlth Stanford CA 94305 USA Harvard TH Chan Sch Publ Hlth Dept Biostat Boston MA USA Brigham & Womens Hosp Channin

Scientific progress depends on the ability of independent researchers to scrutinize the results of a research study, to reproduce the study's main results using its materials, and to build on them in future studies (https://***/nature-research/editorial-policies/reporting-standards). Nuances in the computer code may have marked effects on the training and evaluation of results4, potentially leading to unintended consequences5. [...]transparency in the form of the actual computer code used to train a model and arrive at its final set of parameters is essential for research reproducibility. The many software dependencies of large-scale machine learning applications require appropriate control of the software environment, which can be achieved through package managers including Conda, as well as container and virtualization systems, including Code Ocean, Gigantum, Colaboratory and Docker. Sharing the fitted model (architecture along with learned parameters) should be simple aside from privacy concerns that the model may reveal sensitive information about the set of patients used to train it.

关键词： Diagnostic markers Translational research

来源：评论

学校读者我要写书评

暂无评论

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens

引用

GENOME BIOLOGY 2019年第1期20卷 1-23页

作者： Zhou, Naihui Jiang, Yuxiang Bergquist, Timothy R. Lee, Alexandra J. Kacsoh, Balint Z. Crocker, Alex W. Lewis, Kimberley A. Georghiou, George Nguyen, Huy N. Hamid, Md Nafiz Davis, Larry Dogan, Tunca Atalay, Volkan Rifaioglu, Ahmet S. Dalkiran, Alperen Atalay, Rengul Cetin Zhang, Chengxin Hurto, Rebecca L. Freddolino, Peter L. Zhang, Yang Bhat, Prajwal Supek, Fran Fernandez, Jose M. Gemovic, Branislava Perovic, Vladimir R. Davidovic, Radoslav S. Sumonja, Neven Veljkovic, Nevena Asgari, Ehsaneddin Mofrad, Mohammad R. K. Profiti, Giuseppe Savojardo, Castrense Martelli, Pier Luigi Casadio, Rita Boecker, Florian Schoof, Heiko Kahanda, Indika Thurlby, Natalie McHardy, Alice C. Renaux, Alexandre Saidi, Rabie Gough, Julian Freitas, Alex A. Antczak, Magdalena Fabris, Fabio Wass, Mark N. Hou, Jie Cheng, Jianlin Wang, Zheng Romero, Alfonso E. Paccanaro, Alberto Yang, Haixuan Goldberg, Tatyana Zhao, Chenguang Holm, Liisa Toronen, Petri medlar, Alan J. Zosa, Elaine Borukhov, Itamar Novikov, Ilya Wilkins, Angela Lichtarge, Olivier Chi, Po-Han Tseng, Wei-Cheng Linial, Michal Rose, Peter W. Dessimoz, Christophe Vidulin, Vedrana Dzeroski, Saso Sillitoe, Ian Das, Sayoni Lees, Jonathan Gill Jones, David T. Wan, Cen Cozzetto, Domenico Fa, Rui Torres, Mateo Vesztrocy, Alex Warwick Rodriguez, Jose Manuel Tress, Michael L. Frasca, Marco Notaro, Marco Grossi, Giuliano Petrini, Alessandro Re, Matteo Valentini, Giorgio Mesiti, Marco Roche, Daniel B. Reeb, Jonas Ritchie, David W. Aridhi, Sabeur Alborzi, Seyed Ziaeddin Devignes, Marie-Dominique Koo, Da Chen Emily Bonneau, Richard Gligorijevic, Vladimir Barot, Meet Fang, Hai Toppo, Stefano Lavezzo, Enrico Falda, Marco Berselli, Michele Tosatto, Silvio C. E. Carraro, Marco Piovesan, Damiano Rehman, Hafeez Ur Mao, Qizhong Zhang, Shanshan Vucetic, Slobodan Black, Gage S. Jo, Dane Suh, Erica Dayton, Jonathan B. Larsen, Dallas J. Omdahl, Ashton R. McGuffin, Liam J. Brackenridge, Danielle A. Babbitt, Patricia C. Yunes, Jeffrey M. Fontana, Paolo Zhang, Feng Zhu, Shanfeng You, Ronghui Zhang, Zihan Da Iowa State Univ Vet Microbiol & Prevent Med Ames IA USA Program Bioinformat & Computat Biol Ames IA USA Indiana Univ Bloomington Bloomington IN USA Univ Washington Dept Biomed Informat & Med Educ Seattle WA USA Univ Pennsylvania Dept Syst Pharmacol & Translat Therapeut Philadelphia PA USA Geisel Sch Med Hanover NH USA Dept Mol & Syst Biol Hanover NH USA Geisel Sch Med Dept Microbiol & Immunol Hanover NH USA European Bioinformat Inst EMBL EBI European Mol Biol Lab Hinxton England Program Comp Sci Ames IA USA Hacettepe Univ Dept Comp Engn Ankara Turkey Middle East Tech Univ METU Dept Comp Engn Ankara Turkey Iskenderun Tech Univ Dept Comp Engn Antakya Turkey Middle East Tech Univ Grad Sch Informat CanSyL Ankara Turkey Univ Michigan Dept Computat Med & Bioinformat Ann Arbor MI USA Univ Michigan Dept Biol Chem Ann Arbor MI 48109 USA Achira Labs Bangalore Karnataka India Inst Res Biomedicine IRB Barcelona Barcelona Spain Inst Catalana Recerca Estudis Avancats ICREA Barcelona Spain Barcelona Supercomput Ctr Dept Life Sci INB Coordinat Unit Barcelona Spain Spanish Natl Canc Res Ctr INB GN2 Struct & Computat Biol Programme Barcelona Spain Univ Belgrade Inst Nucl Sci VINCA Lab Bioinformat & Computat Chem Belgrade Serbia Univ Calif Berkeley Dept Bioengineering Mol Cell Biomechan Lab Berkeley CA USA Helmholtz Ctr Infect Res Computat Biol Infect Res Berkeley CA USA Dept Bioengn Berkeley CA USA Dept Mech Engn Berkeley CA USA Univ Bologna Dept Pharm & Biotechnol Bologna Biocomputing Grp Bologna Italy IBIOM Natl Res Council Bologna Italy Univ Bonn INRES Crop Bioinformat Bonn Germany Univ Bonn INRES Crop Bioinformat Bonn Germany Montana State Univ Gianforte Sch Comp Bozeman MT USA Univ Bristol Comp Sci Bristol Avon England Helmholtz Ctr Infect Res Computat Biol Infect Res Braunschweig ME Germany RESIST DFG Cluster Excellence 2155 Braunschweig ME Germany Univ Iibre Bruxelles Vrije Univ Brussel Interunivers Inst Bioinformat Brusse

Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. Results Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. Conclusion We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging;although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.

关键词： Protein function prediction Long-term memory Biofilm Critical assessment Community challenge

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：