AskBeacon-performing genomic data exchange and analytics with natural language

Anuradha Wickramarachchi; Shakila Tonni; Sonali Majumdar; Sarvnaz Karimi; Sulev Kõks; Brendan Hosking; Jordi Rambla; Natalie A Twine; Yatish Jain; Denis C Bauer

doi:10.1093/bioinformatics/btaf079

Back

AskBeacon-performing genomic data exchange and analytics with natural language

Journal article

Open access

Peer reviewed

AskBeacon-performing genomic data exchange and analytics with natural language

Anuradha Wickramarachchi, Shakila Tonni, Sonali Majumdar, Sarvnaz Karimi, Sulev Kõks, Brendan Hosking, Jordi Rambla, Natalie A Twine, Yatish Jain and Denis C Bauer

Bioinformatics (Oxford, England), Vol.41(3), btaf079

2025

DOI: https://doi.org/10.1093/bioinformatics/btaf079

PMID: 39985504

Files and links (1)

pdf

Published1.95 MBDownload View

CC BY V4.0, Open Access

Abstract

Databases, Genetic

Female

Genomics - methods

Humans

Male

Natural Language Processing

Parkinson Disease - genetics

Software

Enabling clinicians and researchers to directly interact with global genomic data resources by removing technological barriers is vital for medical genomics. AskBeacon enables large language models (LLMs) to be applied to securely shared cohorts via the Global Alliance for Genomics and Health Beacon protocol. By simply "asking" Beacon, actionable insights can be gained, analyzed, and made publication-ready. In the Parkinson's Progression Markers Initiative (PPMI), we use natural language to ask whether the sex-differences observed in Parkinson's disease are due to X-linked or autosomal markers. AskBeacon returns a publication-ready visualization showing that for PPMI the autosomal marker occurred 1.4 times more often in males with Parkinson's disease than females, compared to no differences for the X-linked marker. We evaluate commercial and open-weight LLM models, as well as different architectures to identify the best strategy for translating research questions to Beacon queries. AskBeacon implements extensive safety guardrails to ensure that genomic data is not exposed to the LLM directly, and that generated code for data extraction, analysis and visualization process is sanitized and hallucination resistant, so data cannot be leaked or falsified. AskBeacon is available at https://github.com/aehrc/AskBeacon.

Details

Title: AskBeacon-performing genomic data exchange and analytics with natural language
Authors/Creators: Anuradha Wickramarachchi - Australian e-Health Research Centre
Shakila Tonni - Commonwealth Scientific and Industrial Research Organisation
Sonali Majumdar - Commonwealth Scientific and Industrial Research Organisation
Sarvnaz Karimi - Commonwealth Scientific and Industrial Research Organisation
Sulev Kõks - Murdoch University, Centre for Molecular Medicine and Innovative Therapeutics
Brendan Hosking - Australian e-Health Research Centre
Jordi Rambla - Centre for Genomic Regulation
Natalie A Twine - Australian e-Health Research Centre
Yatish Jain - Australian e-Health Research Centre
Denis C Bauer - Australian e-Health Research Centre
Publication Details: Bioinformatics (Oxford, England), Vol.41(3), btaf079
Publisher: Oxford University Press.
Number of pages: 4
Grant note: CSIRO
Identifiers: 991005752728207891
Murdoch Affiliation: Centre for Molecular Medicine and Innovative Therapeutics
Language: English
Resource Type: Journal article

Metrics

134 File views/ downloads

17 Record Views

1 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 6 Social Sciences; 6.238 Bibliometrics, Scientometrics & Research Integrity; 6.238.2805 Cultural Narratives
Web Of Science research areas: Biochemical Research Methods; Biotechnology & Applied Microbiology; Computer Science, Interdisciplinary Applications; Mathematical & Computational Biology; Statistics & Probability
ESI research areas: Biology & Biochemistry