brainhackorg / brainhack_cloud Goto Github PK
View Code? Open in Web Editor NEWHome Page: https://brainhack.org/brainhack_cloud/
License: Creative Commons Attribution 4.0 International
Home Page: https://brainhack.org/brainhack_cloud/
License: Creative Commons Attribution 4.0 International
Ressource request MLOPsZoomCamp
yes
Both for the purpose of checking out the platform and because I am participating in the MlOpsZoomCamp, (https://github.com/DataTalksClub/mlops-zoomcamp) I'd like to request some ressources (see below). Also trying to figure out whether this might be a good way to teach people the usage of the cloud
https://github.com/likeajumprope/mlops-zoomcamp
Virtual Machines, Object Storage
I guess I COULD just create this project myself as admin, but thought I'd better go the traditional way..
watts_up_compute
no
Nikhil Bhagwat, nikhil153, [email protected]
Johanna Bayer, likeajumprope, https://www.linkedin.com/in/johanna-bayer
Sebastian Urchs, surchs, [email protected]
This is an ongoing project by the Sustainability and Environmental Action group (SEA-SIG) at the Organisation for Human Brain Mapping (OHBM). In this project we aim at better understanding the environmental costs of commonly used research pipelines and develop tools to help reduce them.
Recently there have been several projects that track cpu/gpu "power draws" incurred during a compute task. These statistics can then be translated into carbon-footprint based on your location and time of processing.
https://github.com/nikhil153/fmriprep/blob/carbon-trackers/singularity/carbon_trackers_readme.md
HPC
No response
Benchmark denoising strategies on fMRIPrep output
yes
Hao-Ting Wang @htwangtw [email protected]
The project is a continuation of load_confounds. The aim is to evaluate the impact of denoising strategy on functional connectivity data, using output processed by fMRIPrep LTS.
The main tool is now a part of nilearn.
https://github.com/SIMEXP/fmriprep-denoise-benchmark
HPC
No response
tunel: apps for high performance computing
no
@vsoch (email provided to sbollmann_MRI on Twitter
HPC
I only require access to a login node and a worker node, not even anything substantially impressive in terms of memory or compute!
The Oracle team would like to know which resources we need for the brainhack in which geo-regions (GPUs need to be requested in advance so they are available in the right data centres)
This is a test during the maintenance/update of the HPC module. This module currently reflects computeCA exclusively and will be supplemented by information about the Brainhack Cloud. In order to document the procedure properly I need to apply the process a student would have to run and access to the Brainhack Cloud to test what parameters need changing, if any. Maybe you Brainhack Cloud admins can pitch in? In the best case the only thing that's different is the ssh connection?
yes
Thomas S. Hartmann
[email protected]
@thecyclingcyclopse on GH
school-brainhack/school-brainhack.github.io#167 (comment)
HPC
Actually I don't really require HPC, nor will the students require extensive compute power, but for the exercise it would be nice to have them access a cluster as intended by the exercise's creator.
edit:
minor typo
Hi all.
In the Policies doc under the Admins subpage of the Brainhack Cloud website, we have a mention of Policy for Cloud Shell Acess that gives rights to the user to access the Cloud shell. However such group is missing from the lists under Identity> Groups.
I understand from the Oracle's Cloud Shell documents that we do not need to create a specific group but when we create the group it is enough to give them the cloud shell access rights with
allow group <GROUP-NAME> to use cloud-shell in tenancy
is just enough.
I wonder if this is the recommended way of doing for us too? If so I will append the document and delete the group indication instead will indicate to type that line of rule for the shell access policy.
Finding a way to plot weight maps from the outputs of non-linear decoder
yes
Shima Rastegarni
https://github.com/user_name/my_awesome_project
GPU resources
No response
This project aims at testing things
yes
Steffen Bollmann, @stebo85, [email protected]
Virtual Machines, Object Storage, other
no
The Oracle logo on the github Readme.md is made for dark mode and almost not visible in light mode.
Potential solutions:
Easily accessible seed to voxel correlation and machine learning program in Python with high performance computer (HPC) and Docker.
yes
Claudéric DeRoy (Github user : neurok8050)
https://github.com/brainhack-school2022/deroy_project
HPC
No response
The Oracle team would like to provide help by a cloud architect for the brainhack event and they asked if that person should be on-site in glasgow, virtual or both and how many support people we could need?
No response
No response
No response
No response
NeuroCausal: an open source platform for the storage, sharing, synthesis and meta-analysis of neuropsychological data.
No response
Project leads
@vborghe Valentina Borghesani
@Sladja13 Sladjana Lukic
@pinheirochagas Pedro PINHEIRO-CHAGAS
@complexbrains Isil Bilgin
will send the emails separately.
We are working with clinicians, neuroimagers, and software developers to develop an open source platform for the storage, sharing, synthesis and meta-analysis of human clinical data to the service of the clinical and cognitive neuroscience community so that the future of neuropsychology can be transdiagnostic, open, and FAIR.
https://github.com/neurocausal
HPC
We require access to a login & worker node and ~500 GB memory with internet access that will allow us to download/scrap papers using PubMed API and process/analyze the metadata
It might be nice to have a tutorial for folks on how to run NeuroDesk on the cloud
Deep learning for fMRI
yes
https://github.com/user_name/my_awesome_project
GPU resources
No response
Real-time shared data visualisation on the web with NiiVue
yes
I'm not listing emails of collaborators without their consent, but I have linked to their public GitHub profiles.
The primary aim of NiiVue is to translate the features of the widely used native desktop applications (MRIcroGL, Surfice) to their web-based equivalents. This will enable other researchers and developers to build cloud-based medical imaging tools with a powerful viewer that can operate on any device (desktop, tablet, mobile).
We are requesting resources to facilitate one of our goals: Real-time, shared visualisation in the browser. Specifically, a cloud VM will be used to host a WebSocket server that allows multiple NiiVue clients to share data with each other securely, and enable research collaboration and synchronisation in real-time across the globe.
https://github.com/niivue/niivue
Virtual Machines
No response
A Uniform Environment for Cloud and HPC-based Neuroimaging Research Education for Novice Users
yes
John Absher, jrabsher, [email protected], [email protected]
Grigori Yourganov, grigori-yourganov, [email protected]
Taylor Hanayik, hanayik, [email protected]
Chris Rorden, neurolabusc, [email protected]
Introduction
Neuroimaging research education for novice users typically requires a graphical user interface, because novice users lack familiarity with the command line. Meanwhile, the field of neuroimaging research increasingly utilizes cloud-based computing resources, data storage structures, and high performance computing environments. Along with these formidable technical challenges, there is increasing awareness of the need for reproducible data science, to assure that data, code, analysis and results are susceptible to peer review and scientific scrutiny. We believe that novice neuroimaging research students (from high school through professional levels of education) who utilize the same interface (e.g., NeuroDesk) in both a cloud-based learning/collaboration environment and an HPC production environment will be able to spend more time focusing on neuroscience/neuroimaging, and less time struggling with the technical complexities of these environments.
Background
For the past 5 years, the Structured Neuroimaging-Intensive Research Program (SNIRP) has introduced students to basic aspects of neuroimaging research. The program began with 2 undergraduate students and has grown to 21 students in the 2022 summer program. A seed grant has been obtained to study whether novice users benefit from a rudimentary graphical "front end" to neuroimaging tools such as MRIcroGL, FSL, SPM, Surfice, FSLeyes, and Matlab. By examining the user experience through the lens of "user-centered design" we hope to learn how to best enhance the learning experience for novice students. We begin this journey by observing students as they engage in tutorials designed to teach them neuroimaging research procedures, starting with FSL tutorials. Ultimately, we hope to engage the developers of open-source neuroimaging research tools (Freesurfer, SPM, AFNI, etc), related collaboration websites (e.g., github, NITRC), and data repositories (e.g., UK Biobank, ida.loni.usc.edu) in the curation of tutorials that novice users could easily access within a comprehensive cloud-based learning and collaboration environment housed on Oracle Cloud.
Methods
This project relies on https://github.com/NeuroDesk
/
neurodesk.github.io
Virtual Machines, Object Storage, GPU resources, HPC, other
As a practicing neurologist, my expertise is primarily in neuroimaging and neuroscience, rather than HPC, coding/scripting, and these highly technical areas. In fact, a prime motivation for pursuing this project is my own experience, facing the challenges of learning these skills over the past 3+ decades.
Therefore, I humbly request the ability to add a few collaborators to this project, people who can do many of the things that are difficult or impossible for me to do, or that are too time consuming for my immediate colleagues to add to their considerable lists of priorities.
Thank you for considering this project request.
Sincerly,
John R. Absher, MD
Github Actions runner for macapype package validation
yes
@davidmeunier79 @BastienCagna @oliviercoulon @kepkee
Macapype is a python package for segmentation of non-human primate anatomical MRI images; It runs on github, with unittests and PEP8 check on PR; For pre-relsease / release, we would like to validate full pipeline runs with some example data. However, the github server are limited in memory size availble for Github Actions, and for some stedp of the validation (namely using FSL fnirt) requires up to 30 Gb of RAM. Hence my request to add brainhack_cloud ressources to run on release validation with github actions.
https://github.com/Macatools/macapype
https://macatools.github.io/macapype/
Virtual Machines
No response
BrainHack School project to do some freesurfer analysis on 3D MRI structural images
yes
[email protected] (@Andjelaaaa)
https://github.com/Andjelaaaa/dimitrijevic_project
Virtual Machines, Object Storage, GPU resources, HPC
If this could be approved quickly that would be great! Thanks in advance,
Andjela Dimitrijevic
I'm working on the NARPS project at BrainHack. I'm on a M1 macbook and having a hard time downloading data and installing required packages so I'd very much appreciate access to the cloud.
No response
https://github.com/Inria-Empenn/narps_open_pipelines
Virtual Machines, Object Storage, HPC
No response
Participation in the ATLAS R2.0 - Anatomical Tracings of Lesions After Stroke Grand Challenge
No response
Sina Mansour L.
Niousha Dehestani
We will be developing various machine learning models for stroke lesion segmentation which we started working on during the OHBM brainhack in this brainhack project.
We'd require remote Linux servers (preferably with GPUs) to train various ML models for the challenge.
We have not yet created a git repo, but will create one before completing the challenge and make it publicly available after the challenge here.
Virtual Machines, Object Storage, GPU resources
We would like to host a remote Linux server with ssh access. Here's a ballpark estimate of the required system specs:
We'll be able to configure the server to host a jupyter lab environment.
Bayes on the brain in python
No response
Preethom Pal @Pregon [email protected]
Megan Campbell @meganEJcampbell [email protected]
Isabella Orlando @isabellaorlando [email protected]
Darin @dsleiter [email protected]
Adam @a-manoogian [email protected]
Kelly Garner @kel-github [email protected]
https://github.com/crnolan/pyrba
Virtual Machines, Object Storage, GPU resources, HPC
No response
We can see on some figures where we need to click but it's unintuitive.
eg, https://brainhack.org/brainhack_cloud/admins/admins/#create-a-new-admin
No response
Additional instruction mentioning the link and the steps.
No response
Big Linear Mixed Models
This is the first time we have posted it here. But it is a few years old.
Thomas Maullin-Sapey @TomMaullin [email protected]
Thomas Nichols @nicholst [email protected]
Vicente Ferrer @vinferrer [email protected]
Large-scale, shared datasets are becoming increasingly commonplace in fMRI, challenging existing tools both in terms of overall scale and complexity of the study designs. As sample sizes grow, new opportunities arise to detect and account for grouping factors and covariance structures present in large experimental designs. To facilitate large sample analysis, we have created two Python toolboxes for use on HPC clusters:
At present, both tools are functioning and can be used for the analysis of tens of thousands of fMRI images. However, there is plenty that could be improved. Some current goals include:
https://github.com/TomMaullin/BLMM
HPC
I believe we shouldn't need a virtual machine but as I am still learning how to use github actions (which we plan to use for continuous integration testing), this may change in future.
I think it would be good to add the bookmarking link https://cloud.oracle.com/?region=eu-frankfurt-1&tenant=brainhack to the cloud the website so that people can re-sign in more easily via the cloud website.
Hi,
I'm actually wondering at this point if I am allowed to use the brainhack cloud or not for the data I plan to use.
The participant consent for the data I want to use goes as follows:
"Individual identifying information will be kept confidential and only authorized personnel will have access to it. However, the Research Ethics Board or Quality Assurance Officers duly authorized by it may access study data. Data will be coded (identifying information replaced by a code) and the code key will be kept in a separate secure location. The data from the study will be maintained in a secure database, and used for purposes of analysis and comparison with other data, and for scientific dissemination and publication in the Principal Investigator’s lab and collaborating labs."
What are your thoughts would there be any confidentiality breach in using the brainhack cloud?
Project plan:
For my dataset, I'm want to use data I collected at the MNI during my Master's (~5 GB in size). I have received the raw data on my computer already and there are about 50 children with autism who followed a music intervention with pre-post scans for 10 minutes of rsFMRI and a T1. There has already been a publication on it for auditory-motor networks: https://www.nature.com/articles/s41398-018-0287-3
So I would like to see if I can associate changes in resting-state functional connectivity with networks related to joint attention using the brain imaging data set. My plan would be to convert it to NIFTY and BIDS and then get it preprocessed by Beluga. I don't know exactly how many resources are necessary but I'm guessing 1 node is enough.
Thanks for any help!
Hi, I'm co-hosting BrainHackHFX 2023 in Halifax, Nova Scotia and hoping to try out the BrainHack Cloud Computing resources. https://neural-data-science-hackathon.github.io/BrainHackHFX_global2023/
yes
Carl Helmick, affilliation="Dalhousie University, Psychiatry Dept", GitHubID="hfxcarl", email="[email protected]".
I am co-hosting a smallish (30-50 people) brain hackathon in Halifax, NS. I'm looking for some cloud computing resources that will allow running simultaneous hacker code on relatively small datasets for the 3-day event.
https://neural-data-science-hackathon.github.io/BrainHackHFX_global2023/
Virtual Machines, Object Storage, GPU resources, HPC
Assuming there would be options for running Jupyter notebooks in either the HPC or VM?
Hi @stebo85 ,
I tried testing out the neurodesk to use the freesurfer tool via the link you supplied and there seems to be a license issue. Do I need to add another license file as indicated ? Here is the shown error message below
ERROR: FreeSurfer license file /usr/local/freesurfer/.license not found. If you are outside the NMR-Martinos Center, go to http://surfer.nmr.mgh.harvard.edu/registration.html to get a valid license file (it's free). If you are inside the NMR-Martinos Center, make sure to source the standard environment. A path to an alternative license file can also be specified with the FS_LICENSE environmental variable.
The project requires usage of a docker container to extract time stamps of subtitles of a show to be aligned with the fMRI data.
yes
Isil Bilgin
https://github.com/user_name/my_awesome_project
Virtual Machines
No response
Twin normative modelling
yes
I'd need a notebook resource for the brainhack school 22 to do normative modelling on a twin data set
https://github.com/likeajumprope/normative_twins_project
Virtual Machines, HPC
No response
feels more appropriate for documentation, no?
Identifying Neuropsychiatric Diagnoses using fMRI Connectivity Data.
yes
Peter Brotherwood ([email protected])
https://github.com/brainhack-school2022/brotherwood_project
HPC
No response
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.