DIAG-NOSE MEDICAL (APR – 2344)

Multi-omics Data Platform Internship

Medical, Biological and other Sciences

ABOUT THE INDUSTRY PARTNER

Chronic respiratory diseases often present with substantial symptomatic overlap, yet each is driven by distinct underlying biology that varies between patients. This heterogeneity is a central problem in respiratory medicine: clinicians prescribe costly biologic and small-molecule therapies with no objective, biology-based way to predict which patients will respond.

Diag-Nose.io is closing that gap with a first-in-class platform: a nasal microsampling device paired with a multi-biomarker algorithm that reads out disease activity and likely treatment response directly from the underlying biology, rather than from clinical guesswork or trial-and-error prescribing. Our mission is simple: the right therapy for the right patient, the first time

WHAT’S IN IT FOR YOU?

• Work on a real platform, not a teaching dataset: You will build core components of the data platform underpinning a commercial diagnostics pipeline. Your work will be used by our science team and clinical collaborators, with pharmaceutical companies as our target end user.
• Multi-omics and data engineering skills that transfer anywhere: You will gain hands-on experience across complex datasets, quality control, multiomics modelling and integration and database design. This is one of the most in-demand skill sets in biotech, and it is difficult to acquire outside a project with real multi-omic data at scale.
•  Genuine industry experience inside a growing medtech: Diag-Nose.io is a Melbourne-based diagnostics company built around a TGA- and FDA-listed nasal microsampling device. You will be embedded in a small, fast-moving science team, with visibility into how research decisions become product decisions, weighing up data governance, regulatory strategy, IP, and commercialisation.
• Scope to publish: While the commercial platform itself is protected, there is genuine scope for a publishable output, for example a methods or benchmarking paper, or an analysis built on open, published datasets, that showcases your contribution without exposing internal IP.
• A pathway, not just a placement: You will finish with a demonstrable technical portfolio, a strong reference, and a professional network across Australia’s diagnostics sector. Strong performers may have opportunities to continue working with us beyond the placement.

RESEARCH TO BE CONDUCTED

Diag-Nose.io has developed a nasal microsampling device that collects undiluted nasal fluid. Nasal fluid is an information-rich but under-exploited biofluid, carrying signals relevant to a broad range of respiratory diseases, including inflammatory or obstructive airways disease, rare and genetic lung disease, and mucosal and innate immune responses to respiratory infection. Characterising nasal fluid at a multi-omics level requires infrastructure. This project contributes to the internal data platform that takes multi-omic data generated from nasal sample cohorts and makes it structured, comparable, and analysable at scale, while meeting the privacy and governance standards expected of clinical and commercial health data.

Depending on the candidate’s strengths and interests, the work will focus on one or more of:

• Data architecture: designing schemas and metadata standards so that results remain comparable across cohorts, assay platforms and studies.
• Database and data management: developing the infrastructure to catalogue, index and clean large volumes of multi-omics data, so it can be reliably queried and compared across studies.
• Integrative analysis: applying statistical and machine learning methods to identify structure and candidate signatures across omics layers.
• Processing pipelines: building reproducible workflows to harmonise data generated on different analytical platforms.

Scope will be finalised with the successful candidate. Further detail on the platform and methods will be shared under confidentiality during the application process.

SKILLS WISH LIST

If you’re a postgraduate research student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:

Disease background is not a barrier. We are looking for computational and analytical capability, not respiratory expertise, so candidates from oncology, immunology, neuroscience, microbiology or any other data-rich field are equally welcome. We would rather recruit a strong data scientist and teach them the biology than the reverse. Candidates meeting most of the essential criteria are encouraged to apply.

Essential skills:

• Programming in R and/or Python for data analysis; comfort at the command line.
• Sound grounding in statistics and experience with multivariate methods, dimensionality reduction, multiple-testing correction, and handling large, messy biological or health datasets.
• Ability to produce reproducible, documented analyses (Git, R Markdown / Jupyter, environment management).
• Understanding of database design (SQL, relational schemas) or data engineering concepts
• Strong written communication and the ability to work independently in a small team.

Highly desirable:

• Experience with one or more omics data types such as LC-MS proteomics, metabolomics or lipidomics, NGS transcriptomics or genomics, or microbiome data.
• Familiarity with integrative or multi-omics methods.
• Experience with workflow/pipeline tools (e.g. Snakemake, Nextflow) for building reproducible processing pipelines.
• Experience working with clinical or cohort data and its associated metadata.

RESEARCH OUTCOMES

By the end of the placement we expect to have delivered:

•  A documented, versioned data model: A schema and metadata standard that allows multi-omic findings from nasal samples to be compared across cohorts, assay platforms and studies rather than remaining locked to individual experiments.
• Reproducible processing pipelines: Version-controlled, documented code that ingests and harmonises multi-omic data, benchmarked against reference datasets or controls where available.
• A validated analytical workflow: A demonstration analysis on real cohort data, establishing which integration and modelling approaches perform best on these dataset.
• A foundation for discovery: Outcomes will directly enable Diag-Nose.io’s biomarker discovery programs and inform the company’s technical and commercial strategy. Where appropriate, a component of this work, a methods benchmark or an open-data analysis, may be developed toward a publication or conference presentation.

ADDITIONAL DETAILS

The intern will receive $3,300 per month of the internship, usually in the form of scholarship payments.

It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

Please note, applications are reviewed regularly and this internship may be filled prior to the advertised closing date if a suitable applicant is identified. Early submissions are encouraged.

INTERNSHIP CONTACT

CONNECT WITH APR.INTERN