Filters








12 Hits in 9.1 sec

Multiclass Disease Classification from Microbial Whole-Community Metagenomes

Saad Khan, Libusha Kelly
2020 Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing  
We compared three different machine learning models: random forests, deep neural nets, and a novel graph convolutional architecture which exploits the graph structure of phylogenetic trees as its input  ...  We show that the graph convolutional model outperforms deep neural nets in terms of accuracy (achieving 75% average test-set accuracy), receiver-operator-characteristics (92.1% average area-under-ROC (  ...  Models We implemented three types of classifiers for comparison: a feed-forward deep neural network (DNN), a graph convolutional neural network (GCN), and a random forest (RF).  ... 
pmid:31797586 pmcid:PMC7120658 fatcat:nvmoyhcn7vgxfbdb25pwohuyva

Applications of Machine Learning in Human Microbiome Studies: A Review on Feature Selection, Biomarker Identification, Disease Prediction and Treatment

Laura Judith Marcos-Zambrano, Kanita Karaduzovic-Hadziabdic, Tatjana Loncar Turukalo, Piotr Przymus, Vladimir Trajkovik, Oliver Aasmets, Magali Berland, Aleksandra Gruca, Jasminka Hasic, Karel Hron, Thomas Klammsteiner, Mikhail Kolev (+17 others)
2021 Frontiers in Microbiology  
The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit  ...  This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics.  ...  ACKNOWLEDGMENTS The authors are grateful to all COST Action CA18131 "Statistical and machine learning techniques in human microbiome studies" members for their contribution in discussion about evaluation  ... 
doi:10.3389/fmicb.2021.634511 pmid:33737920 pmcid:PMC7962872 fatcat:wbun4lkwwjen5ccdy4zb7mnz3q

Machine Learning Approaches for Epidemiological Investigations of Food-Borne Disease Outbreaks

Baiba Vilne, Irēna Meistere, Lelde Grantiņa-Ieviņa, Juris Ķibilds
2019 Frontiers in Microbiology  
genomics, and inference of phylogeny or phylogenomics.  ...  As genotyping using whole-genome sequencing (WGS) is becoming more accessible and affordable, it is increasingly used as a routine tool for the detection of pathogens, and has the potential to differentiate  ...  Most recently, Suvorov et al. (2019) has proposed an approach that uses convolutional neural networks (CNNs) for phylogenetic inference.  ... 
doi:10.3389/fmicb.2019.01722 pmid:31447800 pmcid:PMC6691741 fatcat:3kuz7hgocrepjemyb5gb7mg7my

Algorithmic complexity in computational biology: basics, challenges and limitations [article]

Davide Cirillo, Miguel Ponce-de-Leon, Alfonso Valencia
2021 arXiv   pre-print
The importance of defining the computational complexity of computational biology algorithms is a topic rarely surveyed for broad audiences of bioinformaticians and users of bioinformatics tools.  ...  However, recognizing the underlying complexity of any algorithm is essential for understanding their potential and limitations.  ...  Acknowledgements The authors wish to acknowledge the advice and support provided by José María Fernández and Miguel Vázquez on this work.  ... 
arXiv:1811.07312v2 fatcat:f6qnbrilnrh3zomveqptsjbbju

A survey of biodiversity informatics: Concepts, practices, and challenges [article]

Luiz M. R. Gadelha Jr., Pedro C. de Siracusa, Artur Ziviani, Eduardo Couto Dalcin, Helen Michelle Affe, Marinez Ferreira de Siqueira, Luís Alexandre Estevão da Silva, Douglas A. Augusto, Eduardo Krempser, Marcia Chame, Raquel Lopes Costa, Pedro Milet Meirelles (+1 others)
2020 arXiv   pre-print
The transformation of this raw data into synthesized information that is fit for use requires going through many refinement steps.  ...  Across the world, countries are concerned about the growing resource consumption and the capacity of ecosystems to provide them.  ...  Acknowledgements The work is partially supported by CAPES, CNPq, and FAPERJ.  ... 
arXiv:1810.00224v2 fatcat:6yidjdczrrdyrjbg7odj2bpvmu

An Online Bioinformatics Curriculum

David B. Searls, Fran Lewitter
2012 PLoS Computational Biology  
Special emphasis will be given to unifying the different approaches to the subject coming from statistics, function approximation, optimization, pattern recognition, and neural networks.''  ...  The author is aware of at least one graduatelevel course in bioinformatics that is in preparation for one of the major online venues, but is as yet unannounced. Provider description.  ...  Independent Study Even in a university environment, it is not unusual for the classes that are necessary or desirable for a given course of study to be unavailable when needed.  ... 
doi:10.1371/journal.pcbi.1002632 pmid:23028269 pmcid:PMC3441465 fatcat:n2ckzvbcf5fqfnw6vm4t7p3goi

Globally Consistent Quantitative Observations of Planktonic Ecosystems

Fabien Lombard, Emmanuel Boss, Anya M. Waite, Meike Vogt, Julia Uitz, Lars Stemmann, Heidi M. Sosik, Jan Schulz, Jean-Baptiste Romagnan, Marc Picheral, Jay Pearlman, Mark D. Ohman (+29 others)
2019 Frontiers in Marine Science  
In this paper we review the technologies available to make globally quantitative observations of particles in general-and plankton in particular-in the world oceans, and for sizes varying from sub-microns  ...  Some of these technologies have been available for years while others have only recently emerged.  ...  It uses machine learning, combining classical approaches and Convolutional Neural Networks in a user-friendly way, to help ecologists, even those with no computer-science background, classify large numbers  ... 
doi:10.3389/fmars.2019.00196 fatcat:ygrsqx5njfhktfzspogae4ye24

D1.11- Annual work plan for the fourth year [article]

ANSES
2021 Zenodo  
The existing models in this domain reply on probabilistic models such as Support Vector Machines (SVM) or Deep Learning models such as deep convolutional neural networks.  ...  For this purpose, the efficacy of RNASeq and 16S metagenomics for the detection of Brucella in clinical samples will be compared.  ... 
doi:10.5281/zenodo.4897080 fatcat:sle543ekvrhp5fitnkygqerg64

Investigations into Distributional Semantics for Cognate Detection and Phylogenetics

Diptesh Kanojia
2021
We also generate typological trees for Indian languages and, additionally, propose the division of the text into meaningful functional units which aid phylogenetic tree generation.  ...  This thesis investigates distributional semantics for cognate detection, false friends' detection and computational phylogenetics to present the insights drawn from our research, for 14 Indian languages  ...  We train neural networks to establish a baseline for cognate detection. 4. We validate the importance of Wordnets as a resource to perform cognate detection. 5.  ... 
doi:10.26180/14870082.v1 fatcat:w66zzisj35h7zgzzozssovneqy

Proceedings of the 10th International Conference on Ecological Informatics: translating ecological data into knowledge and decisions in a rapidly changing world: ICEI 2018

International Conference On Ecological Informatics, Thüringer Universitäts- Und Landesbibliothek Jena, Jitendra Gaikwad
2018
The Conference Proceedings are an impressive display of the current scope of Ecological Informatics.  ...  of complementing monitoring technologies including DNA-barcoding, • sophisticated pattern recognition by deep learning, • advanced exploration of valuable information in 'big data' by means of machine  ...  Using a NASNet deep convolutional neural network trained on 860k taxon-labelled plant images we can presently achieve a 82% top-1 prediction accuracy.  ... 
doi:10.22032/dbt.37846 fatcat:abpbnzmatncp7piugi3udxzcxu

Proceedings of the 10th International Conference on Ecological Informatics: translating ecological data into knowledge and decisions in a rapidly changing world: ICEI 2018

International Conference On Ecological Informatics, Thüringer Universitäts- Und Landesbibliothek Jena, Jitendra Gaikwad
2019
The Conference Proceedings are an impressive display of the current scope of Ecological Informatics.  ...  of complementing monitoring technologies including DNA-barcoding, • sophisticated pattern recognition by deep learning, • advanced exploration of valuable information in 'big data' by means of machine  ...  Using a NASNet deep convolutional neural network trained on 860k taxon-labelled plant images we can presently achieve a 82% top-1 prediction accuracy.  ... 
doi:10.22032/dbt.38375 fatcat:qwx5h42r4zdibdhwjxtpcia6oe

50th Anniversary Conference Ecology Science in Transition, Science for Transition, 30th August – 1st September 2021, Braunschweig: Book of Abstracts

:None, Universitätsbibliothek Braunschweig
2021
setups. 07-O-07 -Automated plant cover prediction with convolutional neural networks Here, we propose an approach using convolutional neural networks (CNNs) to identify species and analyze the plant  ...  We use convolutional neural networks (e.g. ResNet50) and finetune them for binary classification tasks ("bird", "no bird"), while forcing the model to respect temporal smoothness along frames.  ... 
doi:10.24355/dbbs.084-202108120758-0 fatcat:rhobu4e35zb23i3dfvgqu5mukq