Sonika Tyagi
banner
tsonika.bsky.social
Sonika Tyagi
@tsonika.bsky.social
Academic @RMIT University Melbourne Australia

#computationalbiology #digitalhealth #MachineLearning #AI #LLM #genomics #data4diversity #aiforsocialgood #equityDiversityInclusion
Pinned
#repost in your network.

Postdoctoral Fellowship with @tyagilab.bsky.social and Barcelona Supercomputing Centre.
🔈 *** Deadline extended to 26 Jan 2026 **** 🔈

Applications are now open for the second call of the Australia-Spain Network for Innovation and Research Excellence (AuSpire), a postdoctoral network co-funded by the European Union.

🔗 More details on the project: lnkd.in/gZgg7PVm
#MultiOmics data #integration using #MachineLearning.

A book chapter co-authored with PhD student Samitha Amarapathy.
A book chapter from the lab:

This chapter explores multi-omics integrative studies enabled by machine learning, presenting an overview of state-of-the-art methodologies and the foundational background. Suitable for both beginners & advanced bioinformaticians
www.sciencedirect.com/science/chap...
Multi‐omics applications in health and diseases
Multi-omics research has transformed our ability to study biological systems by capturing information across multiple molecular layers, including geno…
www.sciencedirect.com
January 30, 2026 at 10:17 PM
Deadline extended to 3 Feb 2026

#Spreadtheword
#repost in your network.

Postdoctoral Fellowship with @tyagilab.bsky.social and Barcelona Supercomputing Centre.
🔈 *** Deadline extended to 26 Jan 2026 **** 🔈

Applications are now open for the second call of the Australia-Spain Network for Innovation and Research Excellence (AuSpire), a postdoctoral network co-funded by the European Union.

🔗 More details on the project: lnkd.in/gZgg7PVm
January 21, 2026 at 8:12 PM
‼️ New Publicaiton alert ‼️

Delighted to share the publication of our article “A comparative evaluation of handling missing data points and modalities in electronic health records” accepted in the International Journal of Medical Informatics.

www.sciencedirect.com/science/arti...
A comparative evaluation of handling missing data points and modalities in electronic health records
Background: Healthcare data, generally available as electronic health records (EHR), provide rich insight for predictive modelling. A common challenge…
www.sciencedirect.com
January 21, 2026 at 8:08 PM
‼️ New Publicaiton alert ‼️

Delighted to share the publication of our article “A comparative evaluation of handling missing data points and modalities in electronic health records” accepted in the International Journal of Medical Informatics.

www.sciencedirect.com/science/arti...
A comparative evaluation of handling missing data points and modalities in electronic health records
Background: Healthcare data, generally available as electronic health records (EHR), provide rich insight for predictive modelling. A common challenge…
www.sciencedirect.com
January 21, 2026 at 8:06 PM
Client Challenge
www.nature.com
January 13, 2026 at 8:38 PM
#repost in your network.

Postdoctoral Fellowship with @tyagilab.bsky.social and Barcelona Supercomputing Centre.
🔈 *** Deadline extended to 26 Jan 2026 **** 🔈

Applications are now open for the second call of the Australia-Spain Network for Innovation and Research Excellence (AuSpire), a postdoctoral network co-funded by the European Union.

🔗 More details on the project: lnkd.in/gZgg7PVm
January 13, 2026 at 8:23 PM
Thank you 🙏🏼
December 19, 2025 at 4:21 AM
Conference diary Dec 2025
December 18, 2025 at 6:25 AM
November 20, 2025 at 1:55 AM
Reposted by Sonika Tyagi
Our lab head, @tsonika.bsky.social, presented at the 2025 Victorian Affiliation of Research Nurses Inc. Conference on the applications of AI in clinical trials.
The session sparked a great exchange of ideas with delegates, highlighting the excitement and opportunities in this rapidly evolving field.
October 21, 2025 at 12:37 AM
Preprint from the lab.
Our latest paper presents EHR-QC 2.0, a major upgrade to our open-source pipeline for preparing and standardising biomedical & genomic EHR data for machine learning.

🔍 What’s new:

LLM-enabled clinical vocabulary mapping

Support for FHIR

A web-based interface

🔗 papers.ssrn.com/sol3/papers....
<span>An accessible pipeline for LLM-driven medical concept mapping, automated OMOP and FHIR conversion</span>
Background:Our previous work introduced the open-source EHR-QC pipeline. This pipeline implements extraction, transform and load (ETL), pre-processing and quali
papers.ssrn.com
October 15, 2025 at 1:37 AM
Our invited editorial in BMC Artificial Intelligence along with @naimavahab.bsky.social
October 14, 2025 at 9:45 PM
New publication from the lab
Our latest paper combines multi-omics integration with genome-scale NLP models trained on DNA to uncover how S. aureus regulates infection, metabolism, and antibiotic resistance.

This unique organism agnostic method offers a new lens for systems-level biology.

🔗 www.nature.com/articles/s41...
Understanding the regulatory grammar of sepsis-causing Staphylococcus aureus bacteria using contexualised DNA language models - Scientific Reports
Scientific Reports - Understanding the regulatory grammar of sepsis-causing Staphylococcus aureus bacteria using contexualised DNA language models
www.nature.com
October 14, 2025 at 9:13 PM
Reposted by Sonika Tyagi
Nice there’s another ML standards case study in this #IDW2025 “long-tail of supplemental data” session, Slava Tykhonov presenting on Croissant ML docs.google.com/presentation...
croissant-deem-slides
Croissant: A Metadata Format for ML-Ready Datasets June 9, 2024 8th Workshop on Data Management for End-to-End Machine Learning (DEEM) 2024 SIGMOD/PODS 2024 Mubashara Akhtar, Omar Benjelloun, Costanza...
docs.google.com
October 14, 2025 at 2:07 AM
Our Digital Health and AI applications reading group is on this week. Join in.
📢 Join us for the next Digital Health Reading Group!

We’ll be diving into fairness, bias, and ethics in AI for healthcare from the book - Fairness and Machine Learning: Limitations and Opportunities.

🗓️ Thu, 16 Oct 2025
🕧 12:30–1:30 pm
📍 Room 014.10.035A, RMIT University, Melbourne + online (Teams)
October 13, 2025 at 10:27 AM
Reposted by Sonika Tyagi
The pre-print of our #SIGIRAP2025 paper titled "ISMIE: A Framework to Characterize Information Seeking in Modern Information Environments" is now available arxiv.org/abs/2510.07644

@shuoqisun.bsky.social @danulah.bsky.social @admscentre.org.au @rmitcomputing.bsky.social
ISMIE: A Framework to Characterize Information Seeking in Modern Information Environments
The modern information environment (MIE) is increasingly complex, shaped by a wide range of techniques designed to satisfy users' information needs. Information seeking (IS) models are effective mecha...
arxiv.org
October 10, 2025 at 5:56 AM
Reposted by Sonika Tyagi
@ewanbirney.bsky.social on the new version of Alphafold at the @emblebi.bsky.social
www.ebi.ac.uk/about/news/t...
AlphaFold has been a transformation not just in structural biology but also - due to its ability to be applied to all proteins - to molecular biology as a whole.
EMBL-EBI and Google DeepMind renew partnership and release update to AlphaFold Database
Deeper collaboration between EMBL-EBI and Google DeepMind brings updates to the AlphaFold Database.
www.ebi.ac.uk
October 8, 2025 at 10:38 AM
Reposted by Sonika Tyagi
My colleagues and I here at UVA are looking to hire a skilled #Rstats developer. You'll be working with me on the project. Here's the posting: jobs.virginia.edu/us/en/job/R0...
Epidemiologist / Research Data Scientist; Infectious Diseases and International Health in Charlottesville, Virginia, United States of America | Information Management, Services & Technology at Univers...
Apply for Epidemiologist / Research Data Scientist; Infectious Diseases and International Health job with University of Virginia in Charlottesville, Virginia, United States of America. Information Man...
jobs.virginia.edu
October 8, 2025 at 2:17 PM
Reposted by Sonika Tyagi
ChatGPT scores up to 97% on medical facts — yet fails to read symptoms. Experts like Ahmed Abdeen Hamed and Dr Andrew Thornton warn: AI can inform, not diagnose. The real challenge now? Using it responsibly in healthcare. #healthcare
AI performs well on facts, but fails when it comes to symptoms | ICT&health Global
An important explanation lies in the nature of the language ChatGPT uses. Even more worrying is that it does not indicate when it does not know something.
www.icthealth.org
October 8, 2025 at 9:28 AM
Reposted by Sonika Tyagi
"Your best defense isn’t your eyes — it’s your brain. Keep practicing media and digital literacy..."

#discover
#MedSky
#MentalHealth
#AI

www.medscape.com/viewarticle/...
Deepfake Doctors: How AI Spreads Medical Disinformation
AI-generated doctors, some fabricated and some mimicking well-known physicians, sell sketchy products and bad medical advice on social media. Here’s how it works.
www.medscape.com
October 3, 2025 at 1:09 AM
Reposted by Sonika Tyagi
Discover how AI can help creators beat creative block, visualize ideas, and craft standout portfolios—without replacing human creativity. #DataScience #AI #ArtificialIntelligence opendatascience.com/the-ai-advan...
The AI Advantage: How Creators Can Use AI to Generate Portfolio Concepts
The creative industry is rapidly evolving, and a new co-pilot has entered the studio: artificial intelligence. Creators across fields—graphic designers, photographers, illustrators, writers—often face...
opendatascience.com
October 2, 2025 at 10:56 AM
Reposted by Sonika Tyagi
A solemn day as we pay our respects to Dr Jane Goodall and her extraordinary legacy. Vale, Jane, we promise to keep fighting for all that you loved and fought for too!

theconversation.com/only-if-we-h... With @drkyliesoanes.bsky.social, Marissa Parrott, @drvanessapirotta.bsky.social & Zara Bending.
‘Only if we help shall all be saved’: Jane Goodall showed we can all be part of the solution
Jane Goodall showed tremendous courage in charting her own course as a pioneering researcher – and working to spread hope wherever she went.
theconversation.com
October 2, 2025 at 6:24 AM
Reposted by Sonika Tyagi
A versatile machine learning pipeline to find co-regulatory modules (CRMs) in DNA.
Check it out and explore: doi.org/10.1016/j.co...

#Genomics #Epigenomics #MachineLearning #CardiacResearch #OpenScience

@tyagilab.bsky.social @tsonika.bsky.social
September 25, 2025 at 4:22 AM