Understanding impact of genetic factors in SARS-CoV-2 infection development

Our client partnered with Neurons Lab as part of a research program focused on understanding genetic factors and their variations with respect to the SARS-CoV-2 infection development.

Partner Overview

Our client is a genomics service company focused on general NGS and microarray research with a proprietary technology platform.

Challenge

Our client started a research program to understand genetic factors and their variations with respect to the SARS-CoV-2 infection development. The main focus was on sequencing patients’ data and identification of the genetic factors that may cause or correlate with disease outcomes.

Technologically, the company collected WGS data and performed viral genome sequencing, which allowed host respectability analysis, disease severity, host-virus interactions, and other factors.

Massive datasets and a need to test several research hypotheses in parallel and quickly were the biggest challenge at the beginning of the project. Of course, cost-effective and secure storage alongside the ability to make fast queries over the research data were also among the requirements.

Solution

A fusion of ML-based and physics based models.

Since the high load was the biggest challenge, we focused on cloud platform development. To allow parallel task processing we built a workflow orchestrator that automatically schedules, monitors, and scales processing.

All the results from the analytics queries ran on separate VMs and were stored in a cloud object storage which is scalable with respect to the amount of data and protects results from unauthorized access with encryption features and access management tools.

Cost-effectiveness was met with data lifecycle policies and automatic workflow orchestration. The OLAP data warehouse provided fast analytical queries on structured data.

Results

Before:

• Unstructured WGS datasets were stored in an on-premise ecosystem with an analytics speed bottleneck that became a critical pain point in relation to data growth.
• An inability to analyze host susceptibility, clinical outcomes, severity of the disease, and host-virus interactions based on the WGS data.

After:

• A secure cloud platform tailored for parallel data processing running in production and supporting hundreds of simultaneous analytical tasks processing.
• A human-friendly UX interface for fast analytical queries.

About Neurons Lab

Neurons Lab is an AI service provider that partners with fast-growing companies to co-create disruptive AI solutions, empowering them to gain a competitive edge in their industries.

Our goal is to help businesses to unlock the full potential of AI technologies with support from our diverse and highly skilled team, made up of applied scientists and PhDs, industry experts, data scientists, AI developers, cloud specialists, user design experts and business strategists with international expertise from across a variety of industries.