scholarly journals seagull: lasso, group lasso and sparse-group lasso regularisation for linear regression models via proximal gradient descent

2020 ◽  
Author(s):  
Jan Klosa ◽  
Noah Simon ◽  
Pål O. Westermark ◽  
Volkmar Liebscher ◽  
Dörte Wittenburg
Keyword(s):  
Gradient Descent ◽  
Goodness Of Fit ◽  
Linear Models ◽  
R Package ◽  
Group Lasso ◽  
Linear Regression Models ◽  
Step Size ◽  
Link Type ◽  
Sparse Group Lasso ◽  
Proximal Gradient Descent

SummaryStatistical analyses of biological problems in life sciences often lead to high-dimensional linear models. To solve the corresponding system of equations, penalisation approaches are often the methods of choice. They are especially useful in case of multicollinearity which appears if the number of explanatory variables exceeds the number of observations or for some biological reason. Then, the model goodness of fit is penalised by some suitable function of interest. Prominent examples are the lasso, group lasso and sparse-group lasso. Here, we offer a fast and numerically cheap implementation of these operators via proximal gradient descent. The grid search for the penalty parameter is realised by warm starts. The step size between consecutive iterations is determined with backtracking line search. Finally, the package produces complete regularisation paths.Availability and implementationseagull is an R package that is freely available on the Comprehensive R Archive Network (CRAN; https://CRAN.R-project.org/package=seagull; vignette included). The source code is available on https://github.com/jklosa/[email protected]

scholarly journals Seagull: lasso, group lasso and sparse-group lasso regularization for linear regression models via proximal gradient descent

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Jan Klosa ◽  
Noah Simon ◽  
Pål Olof Westermark ◽  
Volkmar Liebscher ◽  
Dörte Wittenburg
Keyword(s):  
Linear Regression ◽  
Regression Models ◽  
Gradient Descent ◽  
Methylation Status ◽  
R Package ◽  
Group Lasso ◽  
High Dimensional ◽  
Linear Regression Models ◽  
Sparse Group Lasso ◽  
Proximal Gradient Descent

Abstract Background Statistical analyses of biological problems in life sciences often lead to high-dimensional linear models. To solve the corresponding system of equations, penalization approaches are often the methods of choice. They are especially useful in case of multicollinearity, which appears if the number of explanatory variables exceeds the number of observations or for some biological reason. Then, the model goodness of fit is penalized by some suitable function of interest. Prominent examples are the lasso, group lasso and sparse-group lasso. Here, we offer a fast and numerically cheap implementation of these operators via proximal gradient descent. The grid search for the penalty parameter is realized by warm starts. The step size between consecutive iterations is determined with backtracking line search. Finally, seagull -the R package presented here- produces complete regularization paths. Results Publicly available high-dimensional methylation data are used to compare seagull to the established R package SGL. The results of both packages enabled a precise prediction of biological age from DNA methylation status. But even though the results of seagull and SGL were very similar (R2 > 0.99), seagull computed the solution in a fraction of the time needed by SGL. Additionally, seagull enables the incorporation of weights for each penalized feature. Conclusions The following operators for linear regression models are available in seagull: lasso, group lasso, sparse-group lasso and Integrative LASSO with Penalty Factors (IPF-lasso). Thus, seagull is a convenient envelope of lasso variants.

scholarly journals AB0210 ACREULAR: AN R PACKAGE FOR THE CALCULATION AND VISUALISATION OF ACR/EULAR RELATED RHEUMATOID ARTHRITIS MEASURES

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 1405.1-1406
Author(s):  
F. Morton ◽  
J. Nijjar ◽  
C. Goodyear ◽  
D. Porter
Keyword(s):  
Rheumatoid Arthritis ◽  
Functional Status ◽  
Rheumatic Diseases ◽  
Web Application ◽  
R Package ◽  
Diagnostic Classification ◽  
Microsoft Excel ◽  
Link Type ◽  
Large Joint ◽  
Programming Skills

Background:The American College of Rheumatology (ACR) and the European League Against Rheumatism (EULAR) individually and collaboratively have produced/recommended diagnostic classification, response and functional status criteria for a range of different rheumatic diseases. While there are a number of different resources available for performing these calculations individually, currently there are no tools available that we are aware of to easily calculate these values for whole patient cohorts.Objectives:To develop a new software tool, which will enable both data analysts and also researchers and clinicians without programming skills to calculate ACR/EULAR related measures for a number of different rheumatic diseases.Methods:Criteria that had been developed by ACR and/or EULAR that had been approved for the diagnostic classification, measurement of treatment response and functional status in patients with rheumatoid arthritis were identified. Methods were created using the R programming language to allow the calculation of these criteria, which were incorporated into an R package. Additionally, an R/Shiny web application was developed to enable the calculations to be performed via a web browser using data presented as CSV or Microsoft Excel files.Results:acreular is a freely available, open source R package (downloadable fromhttps://github.com/fragla/acreular) that facilitates the calculation of ACR/EULAR related RA measures for whole patient cohorts. Measures, such as the ACR/EULAR (2010) RA classification criteria, can be determined using precalculated values for each component (small/large joint counts, duration in days, normal/abnormal acute-phase reactants, negative/low/high serology classification) or by providing “raw” data (small/large joint counts, onset/assessment dates, ESR/CRP and CCP/RF laboratory values). Other measures, including EULAR response and ACR20/50/70 response, can also be calculated by providing the required information. The accompanying web application is included as part of the R package but is also externally hosted athttps://fragla.shinyapps.io/shiny-acreular. This enables researchers and clinicians without any programming skills to easily calculate these measures by uploading either a Microsoft Excel or CSV file containing their data. Furthermore, the web application allows the incorporation of additional study covariates, enabling the automatic calculation of multigroup comparative statistics and the visualisation of the data through a number of different plots, both of which can be downloaded.Figure 1.The Data tab following the upload of data. Criteria are calculated by the selecting the appropriate checkbox.Figure 2.A density plot of DAS28 scores grouped by ACR/EULAR 2010 RA classification. Statistical analysis has been performed and shows a significant difference in DAS28 score between the two groups.Conclusion:The acreular R package facilitates the easy calculation of ACR/EULAR RA related disease measures for whole patient cohorts. Calculations can be performed either from within R or by using the accompanying web application, which also enables the graphical visualisation of data and the calculation of comparative statistics. We plan to further develop the package by adding additional RA related criteria and by adding ACR/EULAR related measures for other rheumatic disorders.Disclosure of Interests:Fraser Morton: None declared, Jagtar Nijjar Shareholder of: GlaxoSmithKline plc, Consultant of: Janssen Pharmaceuticals UK, Employee of: GlaxoSmithKline plc, Paid instructor for: Janssen Pharmaceuticals UK, Speakers bureau: Janssen Pharmaceuticals UK, AbbVie, Carl Goodyear: None declared, Duncan Porter: None declared

scholarly journals Adverse childhood experiences and depression among women in rural Pakistan

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Katherine LeMasters ◽  
Lisa M. Bates ◽  
Esther O. Chung ◽  
John A. Gallis ◽  
Ashley Hagaman ◽  
...  
Keyword(s):  
Mental Health ◽  
Symptom Severity ◽  
Adverse Childhood Experiences ◽  
Linear Regression Models ◽  
Childhood Experiences ◽  
Link Type ◽  
Rural Pakistan ◽  
Adverse Childhood ◽  
Major Depressive Episodes ◽  
Depressive Episodes

Abstract Background Adverse Childhood Experiences (ACEs) are a common pathway to adult depression. This pathway is particularly important during the perinatal period when women are at an elevated risk for depression. However, this relationship has not been explored in South Asia. This study estimates the association between ACEs and women’s (N = 889) depression at 36 months postpartum in rural Pakistan. Method Data come from the Bachpan Cohort study. To capture ACEs, an adapted version of the ACE-International Questionnaire was used. Women’s depression was measured using both major depressive episodes (MDE) and depressive symptom severity. To assess the relationship between ACEs and depression, log-Poisson models were used for MDE and linear regression models for symptom severity. Results The majority (58%) of women experienced at least one ACE domain, most commonly home violence (38.3%), followed by neglect (20.1%). Women experiencing four or more ACEs had the most pronounced elevation of symptom severity (β = 3.90; 95% CL = 2.13, 5.67) and MDE (PR = 2.43; 95% CL = 1.37, 4.32). Symptom severity (β = 2.88; 95% CL = 1.46, 4.31), and MDE (PR = 2.01; 95% CL = 1.27, 3.18) were greater for those experiencing community violence or family distress (β = 2.04; 95%; CL = 0.83, 3.25) (PR = 1.77; 95% CL = 1.12, 2.79). Conclusions Findings suggest that ACEs are substantively distinct and have unique relationships to depression. They signal a need to address women’s ACEs as part of perinatal mental health interventions and highlight women’s lifelong experiences as important factors to understanding current mental health. Trial registration NCT02111915. Registered 11 April 2014. NCT02658994. Registered 22 January 2016. Both trials were prospectively registered.

scholarly journals kataegis: an R package for identification and visualization of the genomic localized hypermutation regions using high-throughput sequencing

BMC Genomics ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Xue Lin ◽  
Yingying Hua ◽  
Shuanglin Gu ◽  
Li Lv ◽  
Xingyu Li ◽  
...  
Keyword(s):  
High Throughput ◽  
High Throughput Sequencing ◽  
Somatic Mutations ◽  
R Package ◽  
Frequency Of Occurrence ◽  
Link Type ◽  
Genomic Landscape ◽  
One Step ◽  
Flanking Regions

Abstract Background Genomic localized hypermutation regions were found in cancers, which were reported to be related to the prognosis of cancers. This genomic localized hypermutation is quite different from the usual somatic mutations in the frequency of occurrence and genomic density. It is like a mutations “violent storm”, which is just what the Greek word “kataegis” means. Results There are needs for a light-weighted and simple-to-use toolkit to identify and visualize the localized hypermutation regions in genome. Thus we developed the R package “kataegis” to meet these needs. The package used only three steps to identify the genomic hypermutation regions, i.e., i) read in the variation files in standard formats; ii) calculate the inter-mutational distances; iii) identify the hypermutation regions with appropriate parameters, and finally one step to visualize the nucleotide contents and spectra of both the foci and flanking regions, and the genomic landscape of these regions. Conclusions The kataegis package is available on Bionconductor/Github (https://github.com/flosalbizziae/kataegis), which provides a light-weighted and simple-to-use toolkit for quickly identifying and visualizing the genomic hypermuation regions.

scholarly journals Meta-Descent for Online, Continual Prediction

2019 ◽  
Vol 33 ◽  
pp. 3943-3950
Author(s):  
Andrew Jacobsen ◽  
Matthew Schlegel ◽  
Cameron Linke ◽  
Thomas Degris ◽  
Adam White ◽  
...  
Keyword(s):  
Gradient Descent ◽  
Large Scale ◽  
Time Series Prediction ◽  
Real Data ◽  
Second Order ◽  
Stochastic Gradient Descent ◽  
Step Size ◽  
Vector Approximation ◽  
Prediction Problems ◽  
Stationary Problems

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update—a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the stepsize parameters to minimize prediction error. These metadescent strategies are promising for non-stationary problems, but have not been as extensively explored as quasi-second order methods. We first derive a general, incremental metadescent algorithm, called AdaGain, designed to be applicable to a much broader range of algorithms, including those with semi-gradient updates or even those with accelerations, such as RMSProp. We provide an empirical comparison of methods from both families. We conclude that methods from both families can perform well, but in non-stationary prediction problems the meta-descent methods exhibit advantages. Our method is particularly robust across several prediction problems, and is competitive with the state-of-the-art method on a large-scale, time-series prediction problem on real data from a mobile robot.

Inverse Sparse Group Lasso Model for Robust Object Tracking

2017 ◽  
Vol 19 (8) ◽  
pp. 1798-1810 ◽  
Author(s):  
Yun Zhou ◽  
Jianghong Han ◽  
Xiaohui Yuan ◽  
Zhenchun Wei ◽  
Richang Hong
Keyword(s):  
Object Tracking ◽  
Group Lasso ◽  
Sparse Group Lasso
Sign in / Sign up

Export Citation Format

Share Document