Calypr: Computation Analysis and Learning Yielding Predictions and Reports

Challenge: Data Silos + Duplications + Interoperability

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

 .  .  .

lab A

lab Z

Data Lake

UI interface

Search API UI

Clark et al. AI-readiness for Biomedical Data Bridge2AI Recommendations

Management

ETL

Standards

Data Science Garage: Data Standards + ETL + management

Calypr : Extending Gen3 with Microservices for Bioinformatics Data Storage, Querying & Management

Modular microservises

  • Gen3 User: Build cohort and download
  • Gen3 Developer: build + integrate micorservises
  • Gen3 operator: Spinup an instance + configure data + costumize frontend

BMEG Iceberg + FHIR graph schema

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Gene

Allele

Protein

Transcript

Pathway

Calypr: Data Ingestion + Integration

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Calypr: Landing and Main App Page 

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

  • ​Data Explorer​ 
  • Storage Manager​
  • Custom Report Pages​
  • Data Viewer​
  •  Interactive Computation​
  •  Graph Queries​
  •  Project Management​​

Calypr: Discovery and Summary Reports page    

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Calypr: File Viewer App

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Calypr: Data Explorer - Cohort Builder

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Calypr: Data Explorer - Temporal Data Tracking

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Calypr: Image Viewer  

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Calypr:  Connecting Applications 

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.

Nasim Sanati 
Computational Biologist
@teslajoy

Quinn Wai Wong 
Research Software Eng.
@quinnwai

Kyle Ellrott 
PI + Associate Professor 
@kellrott

Liam Beckman
Research Software Eng.
@lbeckman314

Brian Walsh 
Sr. Research Software Eng.
@bwalsh

Jordan Tagle 
Computational Biologist
@jordan2lee

Matthew Peterkort 
Research Software Eng.
@matthewpeterkort

Data Science Garage Team + Creason's Team

Allison Creason 
Sr. Computational Biologist

Jay Egger
Computational Biologist
 

Code + Stunning Sunrise + Local Coffee + Great Team

Extra Slides

HTAN: Bidirectional Transformer between FHIR and HTAN schema.   

 

GRIP & FHIR

Querying TCGA BRCA Data with subtype labels for classification

Subtype Classification with Neural Networks

ML modeling and Shapley Feature Extraction

Pathway Enrichment Analysis

Extracting Biological Insights from Gene Set Results

Where We Work

Knight Cancer Research Building @ South Waterfront

Across from OMSI and right by Tilikum Crossing

Scientific Problem

How can we find actionable insights in a disease as complex as cancer?

Scientific Problem

How do we integrate data to extract meaningful insights?

  • ETL (Extract, Transform, Load)

    • FHIRizer – Transforms GDC, Cellosaurus, HTAN data into FHIR graph representation.

    • Snakemake & Airflow – Automate and orchestrate ETL workflows.

Bringing It All Together with Python

Data Standards, ETL, and Management

  • Management

    • GRaph Integration Platform (GRIP) - a powerful  graph query engine designed to span across multiple database backends.

    • Gen3 – Data commons for storage, querying, and management.

  • Standards

    • Pydantic – Validates and enforces FHIR schema.

    • GA4GH (Global Alliance for Genomics & Health) – Establishes global       standards for genomic data interoperability.

    • Pathway Databases (Pathway Commons, Reactome) – Structure & standardize biological context through molecular interaction graphs.

Data Science Garage team 

Bringing it all together with data standards + extract transform load (ETL) + management  

Management

ETL

Standards

Calypr: Data Explorer - Cohort Builder

Data can become fragmented locked in silos, duplicated unnecessarily, and difficult to integrate.