Skip to content

Commit

Permalink
Merge pull request #24 from jhudsl/add-workspaces
Browse files Browse the repository at this point in the history
Add workspaces for each track
  • Loading branch information
ehumph authored Nov 8, 2024
2 parents cf05133 + 684ad80 commit 7bd51b0
Show file tree
Hide file tree
Showing 4 changed files with 33 additions and 5 deletions.
10 changes: 5 additions & 5 deletions prs-analysis.Rmd
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@ Led by: Matthew Lebo, Harvard Medical School

AnVIL Outreach coordinator: Elizabeth Humphries

About This Track


## About

This track, run by the AnVIL Clinical Resource team, will consist of both an overview and a hands-on workshop to provide individuals with an understanding of polygenic scores and how to run and evaluate them in AnVIL. First, we will level-set by providing an overview of the current state of polygenic analysis, with a focus on polygenic risk scores (PRS). Next, we will jointly work with participants to run PRS analyses in AnVIL using the WDL framework. These tasks will increase in complexity in terms of analytical components of the workflow, with the goal of enabling users to run the WDL on their own. We will also engage with participants to get feedback and create user-friendly documents to enable processing of this workflow once published to the broader community. Finally, we will work with more advanced users to generate a new WDL focused on the evaluation of PRS among a cohort of individuals.


Participants are not required to supply their own data, as publicly available data and an AnVIL workspace will be provided as part of the CoFest! track. Users who are interested in running the analyses on their own data are welcome, but should have their own workspace in which to run the analyses.

## Workspace

Participants are not required to supply their own data, as publicly available data and an AnVIL workspace will be provided as part of the CoFest track. Users who are interested in running the analyses on their own data are welcome, but should have their own workspace in which to run the analyses.
The workspace for this track can be found at [https://anvil.terra.bio/#workspaces/mgb-lmm-clinical/AnVIL_CoFest2024_PRS_Analysis](https://anvil.terra.bio/#workspaces/mgb-lmm-clinical/AnVIL_CoFest2024_PRS_Analysis). This is a private workspace, so you will have to be given permission in order to view it. Participants in this tract should contact Elizabeth Humphries if they cannot access the workspace.
10 changes: 10 additions & 0 deletions resources/dictionary.txt
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
acc
ACC
Anshul
AnVIL
Expand All @@ -10,11 +11,14 @@ bioinformatics
biomedical
BIPOC
Bloomberg
BPNet
callout
Callout
Carpinteyro
ChIP
ChromBPNet
Cliffe
cofest
CoFest
cofests
CoFests
Expand All @@ -24,6 +28,7 @@ CoV
customizations
dex
dexamethasone
DNase
dropdown
galaxyproject
GDSCN
Expand All @@ -42,8 +47,10 @@ Jupyter
Kundaje
Lebo
limma
lmm
MDS
mentorship
mgb
NCI
NHGRI
NHGRI's
Expand All @@ -68,9 +75,12 @@ RStudio
Scalable
seqr
skillset
terra
timeframe
underserved
Vivek
Vivekanandan
wdl
WDL
wip
workspaces
Expand Down
7 changes: 7 additions & 0 deletions scalable-ml.Rmd
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,13 @@ AnVIL Outreach coordinator: Kate Isaac

The "Deploying, Training, and Interpreting Deep Learning Models for Regulatory Genomics in AnVIL" CoFests! track at the AnVIL Community Conference offers hands-on training for users and developers interested in applying deep learning to regulatory genomics. This track aims to demonstrate how deep learning models can be utilized for functional genomics datasets, such as ChIP-seq and ATAC-seq, at scale via AnVIL. Participants will develop a comprehensive understanding of the steps involved in deploying, training, and interpreting these models, including the available input options and how to leverage the resulting outputs to address various biological questions.

## Workspaces

The workspaces that will be used for this CoFest! are used to train and analyze base pair resolution neural network models on Transcription factor ChIP-seq datasets (BPNet) and to process train and analyze ChromBPNet style models on ATAC and DNase datasets.

- [BPNet workspace](https://anvil.terra.bio/#workspaces/terra-billing-vir/BPNet)
- [ChromBPNet workspace](https://anvil.terra.bio/#workspaces/terra-billing-vir/ChromBPNet)

## Report Out

At the conclusion of the CoFest!, we will spend some time to collaboratively develop a user guide for utilizing these deep learning workspaces. This user guide will be published on GitHub.
11 changes: 11 additions & 0 deletions wrap-tool.Rmd
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,17 @@ AnVIL Outreach coordinator: Javier Carpinteyro-Ponce

Workflow Description Language (WDL) not in your programming skillset? No problem! Learn to wrap your pipelining tool in WDL and run it in an AnVIL workspace in this CoFest! session. We’ll go over WDL basics and how to run pipelines in AnVIL, then walk through how to run your own Unix/Python/R script. Along the way, you’ll write a WDL and build a custom Docker to run it with. Come and wrap a tool of interest! All experience levels are welcome. We’ll brainstorm and, if time allows, we’ll create resources (tutorials? AnVIL book? Cheat sheet?) for others to use to run their non-WDL tool in AnVIL.

## Workspace

The workspace for this topic can be found at [https://anvil.terra.bio/#workspaces/acc2024-cofest-wdl/AnVIL_CoFest2024_Wrap-a-tool-in-WDL](https://anvil.terra.bio/#workspaces/acc2024-cofest-wdl/AnVIL_CoFest2024_Wrap-a-tool-in-WDL).

## Prep work

Participants on this topics should:

1. Download the Dockstore desktop app from [https://www.docker.com/products/docker-desktop/](https://www.docker.com/products/docker-desktop/).
2. Register for a DockerHub account at [https://hub.docker.com/](https://hub.docker.com/).

## Schedule

### Tuesday Nov 12, 2024 (2.5 hours)
Expand Down

0 comments on commit 7bd51b0

Please sign in to comment.