Determine data types to be processed

[ByroneCole-SageBionetworks]

• Look at the list of data types cohorts are collecting and determine existing nextflow/CWL workflows that exist for these data types
  • CyTOF: https://github.com/nf-core/imcyto?
  • Mass spec metabolomics: https://nf-co.re/metaboigniter
• Categorize the data types with and without existing workflows and prioritize the data types we potentially want to process and add to Cavatica.
• Bonus: Determine process of running nf-core workflows within Cavatica

Edit: Since we aren't so sure about the metadata available, this might be more helpful:

1. enumerate anticipated data types;
2. determine which data types we already have existing workflows to support;
3. determine which data types we already have models/schemas to collect metadata;
4. map out a plan to fill in any gaps for both data models and workflows (based on downstream use cases)

Internal JIRA tickets:

• https://sagebionetworks.jira.com/browse/IBCDPE-240

[thomasyu888]

@ByroneCole-SageBionetworks , @kjflynn . Thanks for setting this up, do you know who I should reach out to to find out the new genomic data types that are being supported in INCLUDE?

[kjflynn]

Hi @thomasyu888 do you mean for V3 or generally? probably for both actually start with @lopierra

[thomasyu888]

@kjflynn For V3 and just generally. Thanks!

[lopierra]

Did you mean new data types, or just new data? I don't think we have new genomic data types, just WGS and RNAseq as last time. We will have WGS from de Smith, Hakonarson, and HTP, and RNAseq from Hakonarson and HTP.

[thomasyu888]

Thanks @lopierra . I meant new data types.

[thomasyu888]

Had a discussion internally, and this is the summary:

• See here for a listof data types that cohorts are collecting. These are cohorts we've had intro calls with - we don't actually have data from most of them.

[thomasyu888]

I have some questions.

• Is there a difference between R01 metablomics and metablomics? If so, what is it?
• What is the difference between Flow Cytometry, CyTOF and Cytokine profiles?
• Did we have a list of the "other sequencing?"

[kjflynn]

Hey Tom, For your second question, these are three different immunological data types. Flow cytometry is sorted and counted fluorescently labeled cells. CyTOF is a higher dimension flow cytometry (often called mass cytometry) which uses heavy metal labeling to sort and count cells. Cytokine profiling is a measure of secreted immune-signaling proteins. I’ll let Pierrette answer the other two bullets.

…

On Sun, Feb 5, 2023 at 4:59 PM Thomas Yu ***@***.***> wrote: I have some questions. - Is there a difference between R01 metablomics and metablomics? If so, what is it? - What is the difference between Flow Cytometry, CyTOF and Cytokine profiles? - Did we have a list of the "other sequencing?" — Reply to this email directly, view it on GitHub <#28 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AASWIZLUR5LEWLXN72UAVD3WWBEIFANCNFSM6AAAAAATYMR6QE> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[thomasyu888]

Thanks! I took what was in this spreadsheet and I did a unique counts on the data_type column (minus the cognitive and clinical data_type_short) and got this count.

Data Type	# cohorts
Other sequencing (targeted, GWAS, DNA methylation, etc.)	6
Neuroimaging	4
Metabolomics/RO1 metablomics	4
Cytokine profiles	3
Proteomics	3
CyTOF	2
EEG	1
Head/neck MRI	1
Flow Cytometry	1
Pulse wave velocity	1
Sleep - summary, saturation, PSG, etc	1
Home & lab sleep apnea test (Nox A1)	1
sleep - Actigraphy, PSG	1

I'm thinking we could try to find nexflow or CWL workflows for those data types that don't have defined workflows as Cavatica applications to execute on the data. Some questions:

• Am I looking at the right spreadsheet for potential data types?
• Does it make sense to you all to focus on those data types that will have more than one cohort contributing data?
• We will start identifying those data types that have pre-existing written CWL/nextflow workflows, but will also identify those that don't. For the ones that don't is the thought that we would need to develop them?

[lopierra]

The Assays tab in that same spreadsheet is a little more granular on different types of sequencing, etc.

"R01 metabolomics" just means metabolomics data from a previous R01 grant.

I'm not sure we have enough metadata currently to start setting up workflows. Like there are numerous types of proteomics, and I'm not sure what each cohort has, and probably wouldn't ask for the details until they're actually ready to send data.

I'm also not sure if the plan is to import and harmonize all the actual data, or just make the files available. I guess it depends on the data type and whether multiple cohorts are doing comparable assays that could be analyzed together.