Dataset Information

PySeqLab: an open source Python package for sequence labeling and segmentation.

ABSTRACT: Motivation:Text and genomic data are composed of sequential tokens, such as words and nucleotides that give rise to higher order syntactic constructs. In this work, we aim at providing a comprehensive Python library implementing conditional random fields (CRFs), a class of probabilistic graphical models, for robust prediction of these constructs from sequential data. Results:Python Sequence Labeling (PySeqLab) is an open source package for performing supervised learning in structured prediction tasks. It implements CRFs models, that is discriminative models from (i) first-order to higher-order linear-chain CRFs, and from (ii) first-order to higher-order semi-Markov CRFs (semi-CRFs). Moreover, it provides multiple learning algorithms for estimating model parameters such as (i) stochastic gradient descent (SGD) and its multiple variations, (ii) structured perceptron with multiple averaging schemes supporting exact and inexact search using 'violation-fixing' framework, (iii) search-based probabilistic online learning algorithm (SAPO) and (iv) an interface for Broyden-Fletcher-Goldfarb-Shanno (BFGS) and the limited-memory BFGS algorithms. Viterbi and Viterbi A* are used for inference and decoding of sequences. Using PySeqLab, we built models (classifiers) and evaluated their performance in three different domains: (i) biomedical Natural language processing (NLP), (ii) predictive DNA sequence analysis and (iii) Human activity recognition (HAR). State-of-the-art performance comparable to machine-learning based systems was achieved in the three domains without feature engineering or the use of knowledge sources. Availability and implementation:PySeqLab is available through https://bitbucket.org/A_2/pyseqlab with tutorials and documentation. Contact:ahmed.allam@yale.edu or michael.krauthammer@yale.edu. Supplementary information:Supplementary data are available at Bioinformatics online.

SUBMITTER: Allam A

PROVIDER: S-EPMC5872256 | biostudies-literature | 2017 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

PySeqLab: an open source Python package for sequence labeling and segmentation.

Allam Ahmed A Krauthammer Michael M

Bioinformatics (Oxford, England) 20171101 21

<h4>Motivation</h4>Text and genomic data are composed of sequential tokens, such as words and nucleotides that give rise to higher order syntactic constructs. In this work, we aim at providing a comprehensive Python library implementing conditional random fields (CRFs), a class of probabilistic graphical models, for robust prediction of these constructs from sequential data.<h4>Results</h4>Python Sequence Labeling (PySeqLab) is an open source package for performing supervised learning in structu ...[more]

PMID: 29036277

Similar Datasets

Project description:IntroductionIn smoking cessation clinical trials, timeline followback (TLFB) interviews are widely used to track daily cigarette consumption. However, there are no standard tools for calculating abstinence based on TLFB data. Individual research groups have to develop their own calculation tools, which is not only time- and resource-consuming but might also lead to variability in the data processing and calculation procedures.Aims and methodsTo address these issues, we developed a novel open-source Python package named abstcal to calculate abstinence using TLFB data. This package provides data verification, duplicate and outlier detection, missing-data imputation, integration of biochemical verification data, and calculation of a variety of definitions of abstinence, including continuous, point-prevalence, and prolonged abstinence.ResultsWe verified the accuracy of the calculator using data derived from a clinical smoking cessation study. To improve the package's accessibility, we have made it available as a free web app.ConclusionsThe abstcal package is a reliable abstinence calculator with open-source access, providing a shared validated online tool to the addiction research field. We expect that this open-source abstinence calculation tool will improve the rigor and reproducibility of smoking and addiction research by standardizing TLFB-based abstinence calculation.ImplicationsAbstinence calculation is an essential task in any smoking intervention study. However, there have not been standard open-source tools available to the researchers. This commentary describes a Python-based package called abstcal that can calculate abstinence from TLFB data, a common methodology to collect smoking consumption data in research settings. The package supports the calculation of point-prevalence, prolonged, and continuous abstinence. Importantly, the package has a web app interface that allows researchers to use the tool without any coding experience. This tool will facilitate smoking research by providing a standardized and easy-to-use abstinence calculation tool.

Dataset Information

PySeqLab: an open source Python package for sequence labeling and segmentation.

Publications

PySeqLab: an open source Python package for sequence labeling and segmentation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets