Harnessing the human genome to personalise health care

By Jane Allman
Thursday, 05 August, 2021

Harnessing the human genome to personalise health care

Genomic sequencing is a valuable tool that can be wielded to improve health outcomes, and it holds great promise for the future of medicine. In recent months we have seen its ability to rapidly identify transmission pathways of COVID-19, which has been vital in our ability to manage outbreaks and track variants. But analysis of the human genome has a bright future in a whole host of medical applications, giving specialists better tools to make treatment decisions for individual patients.

Melbourne-based company GMDx Genomics is blazing pathways towards the future of personalised medicine and the next generation of health care. By extracting valuable information from the whole human genome to obtain a deeper understanding of a particular individual’s immune system, GMDx is translating data into clinical utility.

The company’s clinical-grade analytics platform — backed by big data, powered by Oracle Cloud Infrastructure (OCI) and driven by artificial intelligence — was designed on the foundation of a decade of research and development conducted by Co-founder and Chief Scientific Officer Robyn Lindley.

GMDx CEO Bernie Romanin explained that the platform applies a validated algorithm to extracted subsets of metrics to monitor the Innate Immune Fitness (IIF) of individual patients. Analysis of an individual’s IIF can identify if that person is capable of mounting an effective adaptive immune response.

GMDx’s core technology is built on a platform developed by partner Applied Precision Medicine and, in association with that platform, the company uses OCI for the intensive data processing required to create each IIF profile.

GMDx CTO Richard Rendell said that the company also uses the OCI-based Oracle Autonomous Data Warehouse to capture and analyse the data it accumulates, which he estimates to be in the range of 10 to 12 terabytes. Rendell anticipates that GMDx will eventually hold about a terabyte of data per individual it profiles.

Given the volumes of sensitive data GMDx collects and distributes to partners, the company places great value on Oracle’s expertise to help address data security and regulatory compliance requirements.

Predicting treatment response

Romanin described a collaborative study with The Alfred Hospital Melbourne, which is demonstrating the platform’s ability to reveal why some patients with melanoma respond to immunotherapy when others don’t.

GMDx is in the early stages of similar work with the University of Kansas Medical Center in Kansas City in the area of bladder cancer.

Immunotherapies — invented about a decade ago to treat certain forms of cancer — can cost up to $100,000 per patient, but only have a 10–40% chance of working, depending on the cancer being treated. For this reason, insurers tend to use these therapies only when a patient is in a late stage of the disease. So, by the time immunotherapy is considered, patients have likely already undergone several rounds of chemotherapy, leaving their immune system in a less-than-ideal state.

The ability to identify which patients are unlikely to respond to immunotherapy could spare patients the false hope and enormous expense of a gruelling, potentially toxic series of treatments, and enable doctors to focus on providing them with more productive care alternatives.

“Having the ability to determine which patients will respond to treatment is invaluable to doctors. If they know — from a patient’s genetic profile — that a patient will tolerate and respond well to a particular immunotherapy, they may be able to administer the treatment much earlier, as a first- or second-line treatment, before the disease progresses,” Romanin explained.

Predicting relapse and remission

Cancer progression-associated signatures indicate the likelihood of disease relapsing, meaning that patients at higher risk of disease progression can be monitored closely.

In a study published in Oncotarget, a panel of 142 mutation-signature-associated metrics (P142) successfully predicted progression-free survival (PFS) in patients from a ‘TCGA PanCancer Atlas’ cohort with certain cancer types. Machine learning models were employed to determine PFS, categorising patients as ‘High PFS’ or ‘Low PFS’, with up to 100% predictive accuracy for 11 cancer types.

Early detection of sarcoma

In collaboration with the Garvan Institute of Medical Research, GMDx’s platform is being studied in the early detection of sarcoma. The study will look to identify individuals most likely to contract sarcoma, before signs are evident. The research has revealed that patients diagnosed with the disease display ‘dysregulation’ of a particular group of mutagenic enzymes early on. Monitoring these enzymes using GMDx’s IIF analytics could enable doctors to intervene early.

Future scope

While oncology has been a key focus for GMDx in recent years, the company is making waves in other therapy areas, namely in the field of cognitive impairment and Alzheimer’s disease. In the case of mild cognitive impairment, cognitive changes can occur 15–20 years before the presentation of symptoms. Assessing the genetic predictors for cognitive impairment could provide the tools needed to identify, assess and prevent disease progression — an invaluable weapon in what will be one of our ageing society’s greatest challenges.

GMDx plans to partner with diagnostics providers and pharmaceutical companies, using analytics to examine different treatment populations and inform selection for clinical trials. Among the applications GMDx is developing are those to help pharma companies pre-screen clinical trial participants, gauge potential adverse drug reactions and understand why some patients are resistant to certain kinds of drugs.

Romanin highlighted the high cost of drug development, adding that pharma companies can spend up to one billion dollars investing in research and development of a particular drug.

“If pharma companies find that, at phase 2 and 3, they are not meeting clinical endpoints, they might seek tools to re-evaluate their treatment cohorts and find subsets that did meet clinical endpoints. They can go back and re-analyse the data, and may be able to get an indication for a subset — a better outcome than no indication,” he said.

GMDx has made significant investments in intellectual property, with an extensive patent profile giving them serious commercial clout. The company is striving to forge partnerships to take the platform’s capability across as many spectrums of disease as possible.

Image credit: ©stock.adobe.com/au/Good Studio

Related Articles

Opinion: How do we do no harm with AI in health care?

AI is poised to play a significant role in the delivery of health care for all Australians, but...

Four steps to robust clinical cybersecurity

Healthcare providers must pay careful attention to their cyber hygiene or find themselves facing...

The role of telehealth in modern health care

In recent years teleconsultations have played a growing role in the delivery of healthcare and...

  • All content Copyright © 2022 Westwick-Farrow Pty Ltd