Aashish Bhandari

Good work by @aashishbhandari.com

#digitalhealth #missingdata #machinelearning #predictivemodeling #AIforHealth

Genome language modeling (GLM): a beginner’s cheat sheet Abstract. Integrating genomics with diverse data modalities has the potential to revolutionize personalized medicine. However, this integration poses signi

New publication from the lab @tyagilab.bsky.social

Applications of linguistics in genome language modeling

academic.oup.com/biomethods/a...

Navigating the Multiverse: a Hitchhiker’s guide to selecting harmonization methods for multimodal biomedical data Abstract. The application of machine learning (ML) techniques in predictive modelling has greatly advanced our comprehension of biological systems. There i

New publication from the lab @tyagilab.bsky.social academic.oup.com/biomethods/a...

#multimidaldata #biomedicaldata #dataharmonisation #tyagilab

Research published in 2024 by our lab member @naimavahab.bsky.social and continue to use this for future work on elucidating biological regulatory pathways.

DM us for online meeting link

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

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...

Advancing non-coding RNA annotation with RNA sequence foundation models: structure and function perspectives - BMC Artificial Intelligence Noncoding RNAs (ncRNAs) form the major part of the expressed transcriptome. These are critical in regulating gene expression and contributing to disease mechanisms, primarily through their complex sec...

Our latest review explores how RNA foundation models are reshaping predictions of ncRNA structure & function.

We highlight key architectures, training strategies, and open challenges to guide the next phase of RNA-AI research.

Read here 👉 link.springer.com/article/10.1...

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....

🩺 Missing medical data isn't just something to fill in or ignore!
EHRs often have missing values. Common fix? Imputation. But filling gaps can mislead predictions.
We explore ML approaches to handle missingness while preserving the original data distribution.
📜 www.researchsquare.com/article/rs-6...