Galaxy-ML: An accessible, reproducible, and scalable machine learning toolkit for biomedicine

Gu, Qiang; Kumar, Anup; Bray, Simon; Creason, Allison; Khanteymoori, Alireza; Jalili, Vahid; Grüning, Björn; Goecks, Jeremy

doi:10.1371/journal.pcbi.1009014

Cited by 16 publications

(17 citation statements)

References 25 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Galaxy-ML ( 16 ) (Figure 4 ) is a new toolkit for Galaxy that features a large and general-purpose suite of supervised machine learning tools. With Galaxy’s web-based user interface, an entire machine learning pipeline from normalization, feature selection, model definition, hyperparameter optimization and cross-fold evaluation can be created and applied to large datasets using only a web browser.…”

Section: Scientific Applications and Usesmentioning

confidence: 99%

The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update

Ostrovsky¹,

Mahmoud²,

Lonie³

et al. 2022

Nucleic Acids Research

Self Cite

586

232

View full text Add to dashboard Cite

Galaxy is a mature, browser accessible workbench for scientific computing. It enables scientists to share, analyze and visualize their own data, with minimal technical impediments. A thriving global community continues to use, maintain and contribute to the project, with support from multiple national infrastructure providers that enable freely accessible analysis and training services. The Galaxy Training Network supports free, self-directed, virtual training with >230 integrated tutorials. Project engagement metrics have continued to grow over the last 2 years, including source code contributions, publications, software packages wrapped as tools, registered users and their daily analysis jobs, and new independent specialized servers. Key Galaxy technical developments include an improved user interface for launching large-scale analyses with many files, interactive tools for exploratory data analysis, and a complete suite of machine learning tools. Important scientific developments enabled by Galaxy include Vertebrate Genome Project (VGP) assembly workflows and global SARS-CoV-2 collaborations.

show abstract

Section: Scientific Applications and Usesmentioning

confidence: 99%

The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update

Ostrovsky¹,

Mahmoud²,

Lonie³

et al. 2022

Nucleic Acids Research

Self Cite

586

232

View full text Add to dashboard Cite

show abstract

“…Whereas many MTI and general-purpose analysis platforms are focused specifically on image analysis, Galaxy-ME tools can be connected with more than 8,500 other tools available in Galaxy to create analyses that extend far beyond imaging. For instance, Galaxy machine learning tools 40 can be used to develop predictive models that use features derived from MTI datasets to predict clinical attributes such as overall survival or response to therapy. The Galaxy community has developed tool suites and workflows for processing bulk and single cell omics data [41][42][43][44] , enabling integration of Galaxy-ME tools with these other tool suites to do sophisticated multimodal analyses.…”

Section: Discussionmentioning

confidence: 99%

A Web-based Software Resource for Interactive Analysis of Multiplex Tissue Imaging Datasets

Creason

Watson

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Highly multiplexed tissue imaging (MTI) is accomplished by applying powerful antibody-based spatial proteomics technologies that characterize tissues in situ at single-cell and potentially subcellular resolution and enable the creation of two-dimensional tissue maps. Example MTI methods include cyclic immunofluorescence (CyCIF), multiplex immunohistochemistry, Co-Detection by Indexing (CODEX), imaging mass cytometry, and multiplex ion beam imaging (MIBI). Analysis and visualization of MTI datasets is challenging and requires tens of analysis tools to be applied to datasets that are often hundreds of gigabytes in size. To make analysis of MTI datasets both broadly accessible and interactive, we have developed Galaxy-ME, a web-based software hub for interactive end-to-end analysis of MTI datasets. Galaxy-ME includes all tools and visualization platforms needed for analysis of MTI datasets, and the hub infrastructure enables both scalable and reproducible analyses. We have used the Galaxy-ME hub to process and visualize datasets from three different MTI assays to characterize both normal and cancerous tissue samples totaling 2.1 million cells. The Galaxy-ME hub is a publicly available open-source web resource that anyone can use to analyze their own MTI datasets.

show abstract

“…We highlight three recent DS specialisations of Galaxy which are publicly available online. Vandenbrouck et al developed a Galaxy instance for proteomics research [109], Tekman et al provide one for "single cell omics" [104], and Gu et al offer a ML focus [49]. These specialisations each offer targeted DS tools, workflows, and computational resources, allowing domain experts to quickly develop workflows.…”

Section: Graphicalmentioning

confidence: 99%

“…That is, they provide a website for domain experts to search for a workflow which suits their needs 48 . We also point to the impressive Collective Knowledge framework [40] for a repository focusing on AI, ML, and system research 49 .…”

Section: Providing a Solution Workflow For A Ds And/or ML Problemmentioning

confidence: 99%

Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-Practice

Oakes¹,

Famelis²,

Sahraoui³

2022

Preprint

View full text Add to dashboard Cite

Domain experts are increasingly employing machine learning to solve their domain-specific problems. This article presents six key challenges that a domain expert faces in transforming their problem into a computational workflow, and then into an executable implementation. These challenges arise out of our conceptual framework which presents the "route" of options that a domain expert may choose to take while developing their solution.To ground our conceptual framework in the stateof-the-practice, this article discusses a selection of available textual and graphical workflow systems and their support for these six challenges. Case studies from the literature in various domains are also examined to highlight the tools used by the domain experts as well as a classification of the domain-specificity and machine learning usage of their problem, workflow, and implementation.The state-of-the-practice informs our discussion of the six key challenges, where we identify which challenges are not sufficiently addressed by available tools. We also suggest possible research directions for software engineering researchers to increase the automation of these tools and disseminate best-practice techniques between software engineering and various scientific domains.

show abstract

Galaxy-ML: An accessible, reproducible, and scalable machine learning toolkit for biomedicine

Cited by 16 publications

References 25 publications

The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update

The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update

A Web-based Software Resource for Interactive Analysis of Multiplex Tissue Imaging Datasets

Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-Practice

Contact Info

Product

Resources

About