Filters








1,159 Hits in 9.9 sec

Hierarchical boosting: a machine-learning framework to detect and classify hard selective sweeps in human populations

Marc Pybus, Pierre Luisi, Giovanni Marco Dall'Olio, Manu Uzkudun, Hafid Laayouni, Jaume Bertranpetit, Johannes Engelken
2015 Bioinformatics  
Results: We have developed a machine-learning classification framework that exploits the combined ability of some selection tests to uncover different polymorphism features expected under the hard sweep  ...  We calibrated and applied the method to three reference human populations from The 1000 Genome Project to generate a genome-wide classification map of hard selective sweeps.  ...  Methods The classification method described in this study is based on a machine-learning algorithm called boosting (from the mboost R package-Bü hlmann and Hothorn, 2008) .  ... 
doi:10.1093/bioinformatics/btv493 pmid:26315912 fatcat:2lwltpbmonbptjhojszjjko5bi

Is there adaptation in the human genome for taste perception and phase I biotransformation?

Begoña Dobon, Carla Rossell, Sandra Walsh, Jaume Bertranpetit
2019 BMC Evolutionary Biology  
A total of 91 genes (taste receptors and CYP450 superfamily) have been studied using Hierarchical Boosting, a powerful combination of different selection tests, to detect signatures of recent positive  ...  selection in three continental human populations: Northern Europeans (CEU), East Asians (CHB) and Africans (YRI).  ...  1.0 and the Hierarchical Boosting data, and in PopHuman, the Human population genomics browser website, https:// pophuman.uab.cat/.  ... 
doi:10.1186/s12862-019-1366-7 pmid:30704392 pmcid:PMC6357387 fatcat:uzil25zzq5bzvmd7v2by7eawdq

Localization of adaptive variants in human genomes using averaged one-dependence estimation

Lauren Alpert Sugden, Elizabeth G. Atkinson, Annie P. Fischer, Stephen Rong, Brenna M. Henn, Sohini Ramachandran
2018 Nature Communications  
Here, we introduce SWIF(r), a probabilistic method that detects selective sweeps by learning the distributions of multiple selection statistics under different evolutionary scenarios and calculating the  ...  SWIF(r) provides a transparent probabilistic framework for localizing beneficial mutations that is extensible to a variety of evolutionary scenarios.  ...  Acknowledgements We thank Dean Bobo, Barbara Engelhardt, Chris Gignoux, David Guertin, Erik Sudderth, Zachary Szpiech, Jeremy Mumford, Lorin Crawford, Paul Norman, and the Ramachandran Lab for helpful  ... 
doi:10.1038/s41467-018-03100-7 pmid:29459739 pmcid:PMC5818606 fatcat:xadvvke23zbrrcei3bnf65hqum

Supervised Machine Learning for Population Genetics: A New Paradigm

Daniel R. Schrider, Andrew D. Kern
2018 Trends in Genetics  
With such a model in hand, all one would need to do would be to estimate its parameters, and in so doing learn everything about the evolution of a given population.  ...  In this review we discuss a new paradigm that has emerged in computational population genomics: that of supervised machine learning (ML).  ...  We also thank Justin Blumenstiel and Lex Flagel for discussions about image classification in population genetics. D.R.S. was supported by National Institutes of Health (NIH) award K99HG008696.  ... 
doi:10.1016/j.tig.2017.12.005 pmid:29331490 pmcid:PMC5905713 fatcat:xzqm7666breqflmwtno5ntvxty

Machine Learning for Population Genetics: A New Paradigm [article]

Daniel R Schrider, Andrew D Kern
2017 bioRxiv   pre-print
In this review we discuss a new paradigm that has emerged in computational population genomics: that of supervised machine learning.  ...  We review the fundamentals of machine learning, discuss recent applications of supervised machine learning to population genetics that outperform competing methods, and describe promising future directions  ...  We also thank Justin Blumenstiel and Lex Flagel for discussions about image classification in population genetics. DRS was supported by NIH award no. K99HG008696. ADK was supported by NIH award no.  ... 
doi:10.1101/206482 fatcat:tv6mqnk7vjgutju7f47pa7cifm

Learning by imitation: a hierarchical approach

R W Byrne, A E Russon
1998 Behavioral and Brain Sciences  
Action level imitation is seldom observed in great ape skill learning, and may have a largely social role, even in humans.  ...  There is evidence that great apes suffer from a stricter capacity limit than humans in the hierarchical depth of planning.  ...  Novel frameworks could also be assembled on the basis of trial-and-error exploration, and no doubt in simple cases this is quite sufficient; but imitation confers benefit in boosting the rate of acquisition  ... 
pmid:10097023 fatcat:qieb6t76vfcj7fyvynrafi3zai

On the Optimum Architecture of the Biologically Inspired Hierarchical Temporal Memory Model Applied to the Hand-Written Digit Recognition

Svorad Štolc, Ivan Bajla
2010 Measurement Science Review  
In order to study effects of two substantial parameters of the architecture: the patch size and the overlap in more details, we have restricted ourselves to the single-level HTM networks.  ...  In the paper we describe basic functions of the Hierarchical Temporal Memory (HTM) network based on a novel biologically inspired model of the large-scale structure of the mammalian neocortex.The focus  ...  ACKNOWLEDGMENTS The research reported in this paper has been partially supported by the Slovak Grant Agency for Science (project No. 2/0019/10).  ... 
doi:10.2478/v10048-010-0008-4 fatcat:4y7vggyydjfpvodo22nosvwpea

Localization of adaptive variants in human genomes using averaged one-dependence estimation [article]

Lauren Alpert Sugden, Elizabeth G Atkinson, Annie P Fischer, Stephen Rong, Brenna M Henn, Sohini Ramachandran
2017 bioRxiv   pre-print
Here, we introduce SWIF(r), a probabilistic method that detects selective sweeps by learning the distributions of multiple selection statistics under different evolutionary scenarios and calculating the  ...  SWIF(r) provides a transparent probabilistic framework for localizing beneficial mutations that is extensible to a variety of evolutionary scenarios.  ...  Hierarchical boosting: a machine-learning framework to detect and classify hard selective sweeps in human populations. Bioinformatics btv493 (2015). 18. Schrider, D. R. & Kern, A. D.  ... 
doi:10.1101/229070 fatcat:zp3rmadbbzcjdore2m3uavtfey

Genomic analysis of Andamanese provides insights into ancient human migration into Asia and adaptation

Mayukh Mondal, Ferran Casals, Tina Xu, Giovanni M Dall'Olio, Marc Pybus, Mihai G Netea, David Comas, Hafid Laayouni, Qibin Li, Partha P Majumder, Jaume Bertranpetit
2016 Nature Genetics  
, but instead result from strong natural selection on genes 32 related to human body size. 33 34 Main Text: 35  ...  We show that all Asian and Pacific populations share a single origin 27 and expansion out of Africa, contradicting an earlier proposal of two independent waves 1-4 .  ...  Hierarchical boosting: a machine-learning framework to detect and classify hard 216 selective sweeps in human populations. Bioinformatics 31, btv493 (2015). 217 27. Becker, K. G., Barnes, K.  ... 
doi:10.1038/ng.3621 pmid:27455350 fatcat:6xcs7triz5gpnkwjveywgl25tu

Deep neural networks: a new framework for modelling biological vision and brain information processing [article]

Nikolaus Kriegeskorte
2015 bioRxiv   pre-print
With human-level performance no longer out of reach, we are entering an exciting new era, in which we will be able to build neurobiologically faithful feedforward and recurrent computational models of  ...  However, the current models are designed with engineering goals and not to model brain computations.  ...  Lowe 1999) forming the input to shallow machine learning classifiers, such as support vector machines.  ... 
doi:10.1101/029876 fatcat:lxuwpdhzrvhpdmtyzg33ogwncy

Survey of intrusion detection systems: techniques, datasets and challenges

Ansam Khraisat, Iqbal Gondal, Peter Vamplew, Joarder Kamruzzaman
2019 Cybersecurity  
The authors are grateful to the Centre for Informatics and Applied Optimization (CIAO) for their support.  ...  Availability of data and materials This manuscript has not been published and is not under consideration for publication elsewhere.  ...  The objective of using machine learning techniques is to create IDS with improved accuracy and less requirement for human knowledge.  ... 
doi:10.1186/s42400-019-0038-7 fatcat:x7gyb3vqhfcldehzmo5dnuvclq

Mid-level Representation for Visual Recognition [article]

Moin Nabi
2015 arXiv   pre-print
We investigate on discovering and learning a set of mid-level patches to be used for representing the images of an object category.  ...  In the case of image understanding, we focus on object detection/recognition task.  ...  Finally we feed all the positive and negative feature vectors to train SVM classifier (see Figure 2.1(a)). In detection phase, we will sweep the model over the image in a sliding window manner.  ... 
arXiv:1512.07314v1 fatcat:knmhkwxqk5aczis7ce6g2sv2wm

Evaluating Grayware Characteristics and Risks

Zhongqiang Chen, Zhanyan Liang, Yuan Zhang, Zhongrong Chen
2011 Journal of Computer Networks and Communications  
A grayware categorization framework is therefore proposed here to not only classify grayware according to diverse taxonomic features but also facilitate evaluations on grayware risk to cyberspace.  ...  The features used in learning models are selected with information gain and the high dimensionality of feature space is reduced by word stemming and stopword removal process.  ...  They are also indebted to Professors Alex Delis and Mema Roussopoulos at University of Athens for their suggestions on the draft of the paper.  ... 
doi:10.1155/2011/569829 fatcat:ka27b2npszgeniwptysdpo26ui

Large-scale data mining using genetics-based machine learning

Jaume Bacardit, Xavier Llorà
2013 Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery  
In the last decade, genetics-based machine learning methods have shown their competence in large-scale data mining tasks because of the scalability capacity that these techniques have demonstrated.  ...  This capacity goes beyond the innate massive parallelism of evolutionary computation methods by the proposal of a variety of mechanisms specifically tailored for machine learning tasks, including knowledge  ...  data mining because in most cases it is not possible to afford a full parameter sweep.  ... 
doi:10.1002/widm.1078 fatcat:3av5ue3zvranth3z7pvipcyz44

A/B Testing [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
impossible for a human to classify.  ...  Learning from Labeled and Unlabeled Data In the machine learning literature, the task of learning a classifier has traditionally been studied in the framework of supervised learning.  ...  However, most approaches to learning with onedependence classifiers perform model selection, a process that usually imposes substantial computational overheads and substantially increases variance relative  ... 
doi:10.1007/978-1-4899-7687-1_100507 fatcat:bg6sszljsrax5heho4glbcbicu
« Previous Showing results 1 — 15 out of 1,159 results