mcp-ui demo showing a description of the aim of the demo
Finally I can properly explore the mcp-ui pattern. Pretty interesting how the development of new components (especially complex ones) will change dramatically in how data is loaded into them. Exiting times🔥 building a demo using @opentargets.org components.
Ref: mcpui.dev
Locus-to-Gene widget in the Open Targets Platform showing the Shapley values for features contributing to the prioritisation of two genes in a credible set.
In cooperative game theory, Shapley values help determine how to distribute rewards among players who contribute unequally to a team’s success
By implementing Shapley value-based explanations for L2G scores in the Platform, we provide a measure of which features contribute most to a given score
In the Open Targets Platform, the Locus-to-Gene (L2G) algorithm uses a number of predictive features to prioritise potentially causal genes for disease-associated GWAS signals
But how can we determine which of these features most influenced the final score?
A poker player lifts the corner of their cards on a table strewn with chips and playing cards, revealing a pair of kings.
What does game theory have to do with gene predictions?
Irene Lopez explains how we apply Shapley value-based explanations for Locus-to-Gene scores in the Open Targets Platform, addressing a common concern of machine learning models: explainability 🧬🖥️
blog.opentargets.org/how-we-impro...
Prior to 2015, this evidence would often become available after approval
This could be attributed to the increasing availability of relevant data, and intentional changes in how it's used in the pharmaceutical industry, with an increasing reliance on public data for target validation
Do you agree?
🧬🖥️ Our latest publication reveals a shift in strategies to discover novel drug targets over the past 20 years:
after 2015, biomedical evidence supporting a target-disease indication increasingly appears before the approval year
www.nature.com/articles/s41...
Where to access Open Targets Platform data? Web interface, API and API playgrounds, Data downloads, Google BigQuery public dataset, Microsoft Azure Open Dataset, and new: AWS Open Data
Open Targets Platform data is now available on @amazonwebservices.bsky.social through the Open Data Program!
registry.opendata.aws/opentargets/
🔬New Perturbation Catalogue update!
With a redesigned interface, richer datasets and powerful analysis workflows, it’s now easier than ever to explore genetic perturbation data. www.ebi.ac.uk/perturbation...
#Bioinformatics #FunctionalGenomics
@training.ebi.embl.org @opentargets.org
The team have already curated and ingested 11 Perturb-seq, 1197 CRISPR and 4 MAVE datasets. Following extensive user testing of the beta version, the portal design has been completely rethought and rebuilt, with improved search functionality and analysis workflows.
Perturbation Catalogue home page showing key metrics
The Perturbation Catalogue is live! 🧬🔎🖥️
It aims to bring genetic perturbation data into one curated, harmonised, and discoverable platform.
Take a look! www.ebi.ac.uk/perturbation...
🧬🖥️ "This integration is a great example of bringing leading AI to platforms and data that are already widely used across the industry.” — Jonah Cool, Head of Life Sciences Partnerships, Anthropic
Find out more about the Open Targets Platform MCP server: blog.opentargets.org/official-ope...
The needle in the haystack problem: spotting novel drug targets among redundant evidence.
Our solution? A time-series novelty metric for Open Targets Platform associations.
Thanks to Coté Falaguera & @opentargets.org partners for making this happen.
This method tracks the evolution of target-disease association scores over time, and provides a way to identify novel drug target opportunities as increasingly more genetics, literature, expression, pathway data, and other supportive biomedical evidence become publicly available.
In the past decade, 1/5 of new drugs are first-in-class.
Therapies against such novel targets are a bigger risk to develop compared to well-known targets, but are often indicated for diseases with an unmet clinical need, and may significantly impact patients’ lives
Out now in Nature Communications! 🧬🖥️
An Open Targets team developed a metric for the novelty of a target in the context of a disease, according to current available knowledge.
This allows drug discovery scientists to easily identify potentially novel targets
www.nature.com/articles/s41...
Out now! 🧬
Loss of CHD1 and MAP3K7 creates an acquired cancer vulnerability, highlighting these genes as potential biomarkers of immune checkpoint blockade response
Find out more: www.cell.com/cell-reports...
New biomarkers for cancer immunotherapy have been identified. 🔎
Researchers found that loss of two genes, CHD1 and MAP3K7, makes tumours more likely to respond to immunotherapy.
The findings could help support more personalised cancer treatment 👇
bit.ly/4sMBTq2
➡ Lotfollahi (senior) Postdoc Fellow in Computational Biology and ML
Contribute to transformative projects that integrate single-cell genomics, spatial transcriptomics, and generative AI to build models for understanding tissue biology and cellular dynamics
£38,000-£49,156
Apply by 1 February
➡ Bayraktar Technical Specialist in Neurodegenerative Disease Spatial Transcriptomics
Join a new project to create comparative cell atlases of ALS, Alzheimer’s and Parkinson’s diseases. Coordinate experiments for single nucleus RNA-sequencing of patient samples
£40,523-£48,143
Apply by 8 February
➡ Anderson Postdoc:
Lead the analysis of one of the largest long-read single-cell RNA-seq studies aimed at elucidating the cellular and molecular mechanisms underpinning isoform usage dysregulation in Inflammatory Bowel Disease
£38,000-£49,156
Apply by 1 February
We're recruiting 3 roles through @sangerinstitute.bsky.social 👩🔬🧬💻
NEW:
➡ Postdoc with @carlanderson.bsky.social
➡ Technical Specialist with @bayraktarlab.bsky.social
ALSO:
➡ (Senior) Postdoc in Mo Lotfollahi’s lab
More information in the thread
See all available jobs: opentargets.org/jobs
🚀 Announcing the Official @opentargets.org MCP!
We've partnered with @anthropic.com to give AI seamless access to high-quality genetic and target-discovery data. Open for the entire community to accelerate therapeutic development.
Read more at blog.opentargets.org/official-ope...
Introducing the official Open Targets Platform Model Context Protocol 🧬🖥️
In partnership with @anthropic.com, we’ve created an MCP server making Open Targets Platform data accessible to AI-powered tools and agents
Try it out and watch out for future releases: mcp.platform.opentargets.org/mcp
A brightly lit Christmas tree at night, with a building in the background. Pathways leading to the building are illuminated with lights dotted on each side.
The Wellcome Genome Campus lit up for the holidays ✨
📸 Helena Cornu
NEW: NLP data scientists/scientific data engineers at @ebi.embl.org
Develop a comprehensive open source side effect resource and standardised AI/ML training sets to improve early identification of safety liabilities
Apply by 11 January
embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
Open Targets Platform 25.12 is out now!
Thanks to a GWAS Catalog update including 3 major studies using UK Biobank data, we now have over 1.4 million GWAS credible sets in the Platform.
Discover the data, feature, and technical updates in this release: blog.opentargets.org/open-targets... 🧬🖥️
NEW: multiple (senior) postdoctoral fellow roles in Mo Lotfollahi's group at @sangerinstitute.bsky.social
There are many research focus areas available, including Open Targets translational AI projects
Apply now: sanger.wd103.myworkdayjobs.com/en-US/Wellco...
Congratulations to the whole team at Open Targets, past and present — here’s to another ten years! 🥂
None of that would have been possible without the contributions of all our team members, the input and feedback from our partners, collaborators, and data providers, and of course, our community of users
The Platform was created as an open source resource for the systematic identification and prioritisation of targets for drug discovery. In the past decade, we've been going from strength to strength, with considerable changes and refinements to the data, analyses, and interface
