Ian Simpson

New machine learning method for automated extraction of gene-disease relationships from the literature using @gene2phenotype.bsky.social - should make future curation much faster, easier and more comprehensive, see preprint: www.medrxiv.org/content/10.1...

Domain-wide Mapping of Peer-reviewed Literature for Genetic Developmental Disorders using Machine Learning and Gene2Phenotype https://www.medrxiv.org/content/10.1101/2025.11.24.25340871v1

🧬 & 🖥️

🧬 & 🖥️

Where we demonstrate the value of including biological priors when performing batch correction tasks as part of molecular data integration. (2/2)

The significance of molecular heterogeneity in breast cancer batch correction and dataset integration Breast cancer research benefits from a substantial collection of gene expression datasets that are commonly integrated to increase analytical power. Gene expression batch effects arising between exper...

…and another pre-print - “The Significance of Molecular Heterogeneity in Breast Cancer Batch Correction and Dataset Integration” - www.medrxiv.org/content/10.1...

(1/2)

We demonstrate the value of integrating clinical text data into our explainable multi-modal MOGDx framework to improve patient stratification in Parkinson’s Disease.

Combining Clinical Embeddings with Multi-Omic Features for Improved Patient Classification and Interpretability in Parkinson’s Disease This study demonstrates the integration of Large Language Model (LLM)-derived clinical text embeddings from the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) questionn...

Our latest pre-print just out - “Combining Clinical Embeddings with Multi-Omic Features for Improved Patient Classification and Interpretability in Parkinson’s Disease” - www.medrxiv.org/content/10.1.... (1/2)

SIDB are partnering with the School of Informatics, University of Edinburgh to offer studentships that will use AI methods to improve our understanding of autism & neurodevelopmental conditions.

Find a project that interests you: www.ai4biomed.io/research/pro...

We have fully-funded PhD opportunities combining AI & Autism Research!

Find out more & apply by 20th Jan >> www.ai4biomed.io/research/pro...

@tisimpson.bsky.social #healthinformatics #biomedicalengineering #biomedicalimaging #genomicmedicine #ExtraordinaryEdinburgh

🙋🏼‍♂️

🙋🏼‍♂️

Congratulations 🎉

This is a great piece of research on the state of scientific publishing and I’d say essential reading. It’s not sustainable and it’s incredibly damaging to our reputation as a community. Many thanks to the authors for shining a light on this issue and backing it up with quantitative evidence.

Absolutely delighted to be partnering with SIDB; combining AI and Autism Research to improve our understanding of ASDs. We have a very exciting collection of PhD projects open for applications - www.ai4biomed.io/research/pro... closing 8th January.

SIDB has partnered with The UKRI AI CDT in Biomedical Innovation. Our PhD studentships have a strong translational focus and seek to develop & apply AI approaches to biomedical domains.

Find out more & apply by 20th Jan >> www.ai4biomed.io/research/pro...

@tisimpson.bsky.social

👋

We’ve also prepared what we hope is a useful tutorial/notebook to help you try it out - biomedicalinformaticsgroup.github.io/MOGDxBook/Ex...

Multi-Omic Graph Diagnosis (MOGDx): A data integration tool to perform classification tasks for heterogeneous diseases AbstractMotivation. Heterogeneity in human diseases presents challenges in diagnosis and treatments due to the broad range of manifestations and symptoms.

Our MOGDx method now out in Bioinformatics. If you’re interested in multi-modal integration you might find this useful. academic.oup.com/bioinformati...

📢 Latest MOGDx pre-print, this time for Parkinson’s Disease.

Ryan B, Marioni RE, Simpson TI. An Integrative Network Approach for Longitudinal Stratification in Parkinson’s Disease. medRxiv 2024 - doi.org/10.1101/2024.0…

Congratulations Barry Ryan @BioMedAI_CDT

Very much looking forward to be hosting our first tutorial at #ISMB24 iscb.org/ismb2024/ this summer in Montreal with @BioMedAI_CDT students Barry Ryan, Sebestyén Kamp.

“Modelling Multi-Modal Biomedical Data Using Networks “ - iscb.org/ismb2024/progr…

A manifesto on explainability for artificial intelligence in medicine The rapid increase of interest in, and use of, artificial intelligence (AI) in computer applications has raised a parallel concern about its ability (…

Our comprehensive 2022 paper on explainable AI www.sciencedirect.com/science/arti... #artificialintelligence #machinelearning #datascience #bioinformatics #XAI

I'm delighted to release the first half of my new textbook in human genetics:
web.stanford.edu/group/pritch...

"An Owner's Guide to the Human Genome: an introduction to human population genetics, variation and disease"

Multi-Omic Graph Diagnosis (MOGDx) : A data integration tool to perform classification tasks for het... medRxiv - The Preprint Server for Health Sciences

Our latest preprint ➡️ Omics network integration and GNNs for patient class prediction. Multi-Omic Graph Diagnosis (MOGDx) : A data integration tool to perform classification tasks for heterogeneous diseases - www.medrxiv.org/content/10.1... #gnn #networks #dataintegration #omics