Compi: a framework for portable and reproducible pipelines

López-Fernández, Hugo; Graña‐Castro, Osvaldo; Nogueira-Rodríguez, Alba; Reboiro-Jato, Miguel; Glez-Peña, Daniel

doi:10.7717/peerj-cs.593

Cited by 11 publications

(10 citation statements)

References 15 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MyBrain-Seq is a Compi [ 39 , 40 ] pipeline to automatically analyze miRNA-Seq data in a highly reproducible way. It helps to find a profile of differentially expressed miRNAs between two conditions, assesses its potential classification power using hierarchical clustering analysis and aids in the discovery of biological pathways potentially affected by the conditions.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MyBrain-Seq: A Pipeline for MiRNA-Seq Data Analysis in Neuropsychiatric Disorders

2023

Self Cite

View full text Add to dashboard Cite

High-throughput sequencing of small RNA molecules such as microRNAs (miRNAs) has become a widely used approach for studying gene expression and regulation. However, analyzing miRNA-Seq data can be challenging because it requires multiple steps, from quality control and preprocessing to differential expression and pathway-enrichment analyses, with many tools and databases available for each step. Furthermore, reproducibility of the analysis pipeline is crucial to ensure that the results are accurate and reliable. Here, we present myBrain-Seq, a comprehensive and reproducible pipeline for analyzing miRNA-Seq data that incorporates miRNA-specific solutions at each step of the analysis. The pipeline was designed to be flexible and user-friendly, allowing researchers with different levels of expertise to perform the analysis in a standardized and reproducible manner, using the most common and widely used tools for each step. In this work, we describe the implementation of myBrain-Seq and demonstrate its capacity to consistently and reproducibly identify differentially expressed miRNAs and enriched pathways by applying it to a real case study in which we compared schizophrenia patients who responded to medication with treatment-resistant schizophrenia patients to obtain a 16-miRNA treatment-resistant schizophrenia profile.

show abstract

Section: Methodsmentioning

confidence: 99%

“…MyBrain-Seq is implemented as a Compi pipeline [ 39 , 40 ] and distributed as a Docker image that allows running it effortlessly. All external dependencies ( Table 1 ) are satisfied using Docker images from the pegi3s Bioinformatics Docker images Project [ 62 ] ( ).…”

Section: Methodsmentioning

confidence: 99%

MyBrain-Seq: A Pipeline for MiRNA-Seq Data Analysis in Neuropsychiatric Disorders

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compi 17 is a framework to not only build and run workflows, but also deploy the workflows as commandline applications or containerised as Docker containers [74]. That is, once a domain expert has built a workflow, Compi packages the workflow and its dependencies can be easily shared to other domain experts to use as a command-line application.…”

Section: Markup or Domain-specific Languagementioning

confidence: 99%

“…That is, once a domain expert has built a workflow, Compi packages the workflow and its dependencies can be easily shared to other domain experts to use as a command-line application. Compi uses the markup language XML to define the workflows as the creators López-Fernández et al argue that a DSL for defining workflows is "less interoperable, being difficult to produce or consume from languages other than the one on which the DSL is based", and that XML is "easy to validate syntactically and semantically through schemas" [74]. A repository of Compi workflows is available through the Compi hub project 18 which aims to provide community exploration of the workflow, including automatic visualisation of the workflow tasks and links to sample input data [84].…”

Section: Markup or Domain-specific Languagementioning

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

“…In this work, pipelines used for model development and evaluation were implemented with Compi [65]. Compi is a framework for the development of pipeline-based, command-line applications, which provides developers with several useful features, such as the automatic generation of the user interface, the packaging of applications together with their dependencies in Docker images, or an easy way to distribute applications through the public Compi Hub repository [66].…”

Section: Pipeline Developmentmentioning

confidence: 99%

Real-time polyp detection model using convolutional neural networks

Nogueira-Rodríguez

Domínguez-Carbajales

Campos-Tato

et al. 2021

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Colorectal cancer is a major health problem, where advances towards computer-aided diagnosis (CAD) systems to assist the endoscopist can be a promising path to improvement. Here, a deep learning model for real-time polyp detection based on a pre-trained YOLOv3 (You Only Look Once) architecture and complemented with a post-processing step based on an object-tracking algorithm to reduce false positives is reported. The base YOLOv3 network was fine-tuned using a dataset composed of 28,576 images labelled with locations of 941 polyps that will be made public soon. In a frame-based evaluation using isolated images containing polyps, a general F1 score of 0.88 was achieved (recall = 0.87, precision = 0.89), with lower predictive performance in flat polyps, but higher for sessile, and pedunculated morphologies, as well as with the usage of narrow band imaging, whereas polyp size < 5 mm does not seem to have significant impact. In a polyp-based evaluation using polyp and normal mucosa videos, with a positive criterion defined as the presence of at least one 50-frames-length (window size) segment with a ratio of 75% of frames with predicted bounding boxes (frames positivity), 72.61% of sensitivity (95% CI 68.99–75.95) and 83.04% of specificity (95% CI 76.70–87.92) were achieved (Youden = 0.55, diagnostic odds ratio (DOR) = 12.98). When the positive criterion is less stringent (window size = 25, frames positivity = 50%), sensitivity reaches around 90% (sensitivity = 89.91%, 95% CI 87.20–91.94; specificity = 54.97%, 95% CI 47.49–62.24; Youden = 0.45; DOR = 10.76). The object-tracking algorithm has demonstrated a significant improvement in specificity whereas maintaining sensitivity, as well as a marginal impact on computational performance. These results suggest that the model could be effectively integrated into a CAD system.

show abstract

Compi: a framework for portable and reproducible pipelines

Cited by 11 publications

References 15 publications

MyBrain-Seq: A Pipeline for MiRNA-Seq Data Analysis in Neuropsychiatric Disorders

MyBrain-Seq: A Pipeline for MiRNA-Seq Data Analysis in Neuropsychiatric Disorders

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

Real-time polyp detection model using convolutional neural networks

Contact Info

Product

Resources

About