This document provides a detailed explanation of all the workflows, including their functionalities, problems they address, advantages, disadvantages, implementation requirements, and open points for future versions.
Creator: Daniel Marchan
Submitter: Daniel Marchan
Evaluation of Swin Transformer and knowledge transfer for denoising of super-resolution structured illumination microscopy data
In recent years, convolutional neural network (CNN)-based methods have shown remarkable performance in the denoising and reconstruction of super-resolved structured illumination microscopy (SR-SIM) data. Therefore, CNN-based architectures have been the main focus of existing studies. Recently, however, an alternative and highly competitive deep learning architecture, ...
MMV Im2Im Transformation
A generic python package for deep learning based image-to-image transformation in biomedical applications
The main branch will be further developed in order to be able to use the latest state of the art techniques and methods in the future. To reproduce the results of our manuscript, we refer to the branch ...
The ultimate-level complexity workflow is one among a collection of workflows designed to address tasks up to CTF estimation. In addition to the functionalities provided by layer 0 and 1 workflows, this workflow aims to enhance the quality of both acquisition images and processing.
Quality control protocols
Combination of methods
- CTF consensus
- New methods to compare ctf estimations
- CTF xmipp criteria (richer parameters i.e. ice detection)
- Control of ...
The second-level complexity workflow is one among a collection of workflows designed to address tasks up to CTF estimation. In addition to the functionalities provided by the layer 0 workflow, this workflow aims to enhance the quality of acquisition images using quality protocols.
Quality control protocols
Movie max shift: automatic reject those movies whose frames move more than a given threshold.
Tilt analysis: quality score based in the Power Spectrum Density (astigmatism and ...
The simplest workflow among a collection of workflows intended to solve tasks up to CTF estimation.
Basic processing pipeline
Movie alignment (recommended 2 GPUs)
- Monitor summary protocol:
- Monitor basic parameters (item counts, drift, resolution, astigmatism, defocus, etc.)
- Raise alarms (mail setting available)
- Provides information of the basic steps (html report)
Workflow for tracking objects in Cell Profiler: https://training.galaxyproject.org/training-material/topics/imaging/tutorials/object-tracking-using-cell-profiler/tutorial.html
- Read data to analyse from an object store.
- Analyse data in parallel using Dask.
- Show how to use public resources to train neural network.
- Load labels associated to the original data
- Compare results with ground truth.
The authors of the PLOS Biology paper, "Nessys: A new set of tools for the automated detection of nuclei within intact tissues and dense 3D cultures" published in August 2019: https://doi.org/10.1371/journal.pbio.3000388, considered several image ...
This workflow has been created as part of Demonstrator 6 of the project EOSC-Life (within WP3) and is focused on reusing publicly available RNAi screens to gain insights into the nucleolus biology. The workflow downloads images from the Image Data Resource (IDR), performs object segmentation (of nuclei and nucleoli) and feature extraction of the images and objects identified.
A set of generic and automatic workflows designed to:
Run on-the-fly and unattended.
Maintain robust stability for a wide range of samples.
Covers steps from movies to CTF estimation (for the moment).
Monitor the acquisition process and provide user feedback.
Comprise three proposed workflows, each with an additional layer of complexity.