Reposting for the Monday morning crowd: We call her little Polly Prompt Injection. My riff on the classic @xkcd.com comic -> xkcd.com/327/

The UK countryside is full of interdimensional portals. You just have to know where to look. I've decided to make a thread here of some of the best ones I've found on walks. 1. JRR Tolkien's Psychedelic Lime Kiln.

Excited to partner with Anthropic on using AI for #RareDisease, and grateful for support on building the @monarchinitiative.bsky.social DisMech pathomechanism knowledge base! #MedSky #GeneSky

Anthropic {bot}@anthropicbot.bsky.social · 2w ago

We're offering grants of up to $50,000 in Claude usage credits to researchers accelerating cures for rare diseases. This is our first focused call within AI for Science, our program supporting scientists using Claude to speed up discovery. https://www.anthropic.com/news/rare-disease-research-grants

The microbial unknome, a repertoire for microbial chatting? www.nature.com/articles/s41... #jcampubs

The microbial unknome, a repertoire for microbial chatting? - Heredity

Heredity - The microbial unknome, a repertoire for microbial chatting?

nature.com

This is a very elegant bridge between classic prokaryotic pathway hole filling algorithms and logical ontology formalisms -- and is also very practical! Some comments on top of @leechuck.bsky.social's thread:🧵

Robert Hoehndorf@leechuck.bsky.social · last mo.

New in Briefings in Bioinformatics: we use the Gene Ontology @geneontology.bsky.social as a logical framework to ask whether genome-scale function annotations are biologically plausible, not only accurate protein by protein. #GeneOntology #Bioinformatics 1/6

What is it with "dossiers"? My Claude Code has become obsessed with using the word dossier to describe any kind of report or summary document. Curious if this is something that just leaked into my context and propagated, or if it got imprinted upstream at the RLHF stage. Anyone else see this?

JG Ballard’s Prang

Emily PhD 🎓@ejwillingham.bsky.social · 3mo ago

Slightly diminish a book: Pride and Preconception

This! AlphaFold is PDB + UniProt + Deep learning. No data sharing, no curation, no data standards, no AlphaFold.

Excited to share this review🔔, we spent sometime thinking about phage–microbiome–immune–oncology axis for phage therapy in cancer! #phage #phagesky Phage therapy in oncology: opportunities for cancer prevention and treatment: Trends in Molecular Medicine www.cell.com/trends/molec...

Phage therapy in oncology: opportunities for cancer prevention and treatment

Bacteriophages (phages) are emerging as programmable biological therapeutics in oncology, extending beyond their traditional antimicrobial applications. This review proposes a phage–microbiome–immune–...

cell.com

Tomorrow is pi day, a good time to check out the pi coding agent pi.dev. Yes I know there are many coding agents, but pi is self-extensible in a way that should appeal to the emacs enthusiasts among you.

pi.dev

A terminal-based coding agent

pi.dev

Every Valentine’s Day I ponder the ontological, ontogenic, and phylogenetic basis of the metazoan primary pulsatile organ. Enjoy this old thread (originally posted on twitter many years ago, the import didn’t preserve the dates)

Chris Mungall@cmungall.bsky.social · 6y ago

Happy #ValentinesDay! The 🤎 has been associated with love since ancient Greece. While humans only have one kind of 🤎, there is a large diversity of pumping organs in animals. Our #ComparativeAnatomy ontology Uberon (@uberanat) has 12 different kinds of 🤎! Here are a few: 1/

Over the last few months I've been helping organize various tutorials and workshops on agentic AI, aimed mostly at biocurators, ontology developers, and PIs of knowledge bases / data resources. Some of this might be generally useful to folks who don't identify as a 'technical' or an 'AI' person.🧵

Last year we made a CLI wrapper for different deep research APIs. As a baseline implementation we do a simple Claude Code in a loop. It works rather well! Well, I discovered there is a name for this pattern: Ralph. We made a Ralph Wiggum deep researcher. monarch-initiative.github.io/deep-researc...

📣 New preprint from us at phagefoundry.org 📣 A solid machine learning framework & to predict strain-level phage-host interactions across diverse bacterial genera from genome sequences alone. Avery Noonan from the Arkin Lab led this massive effort www.biorxiv.org/content/10.1...

We developed and evaluated a method to learn python chemical structure classifiers using LLMs. These can give classifications+explanations at runtime. With @jannahastings.bsky.social @justaddcoffee.bsky.social Noel O'Boyle, Daniel Korn, Adnan Malik jcheminf.biomedcentral.com/articles/10....

Chemical classification program synthesis using generative artificial intelligence - Journal of Cheminformatics

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

jcheminf.biomedcentral.com

Hiding in plain sight - how close are we to mapping ALL 🧬enhancers🧬 in the genome? Our new paper by Mannion et al. takes a systematic look at "hidden enhancers" and why they remain so hard to find. With @mosterwalder.bsky.social, @jlopezrios.bsky.social & many more www.nature.com/articles/s41...

Very exciting to see the research from @cziscience.bsky.social on the rBio distilling a black box foundation model (in this case a "virtual cell" perturbation model) into a smaller reasoner LLM. And it uses ontologies as part of RL! chanzuckerberg.com/blog/rbio-re...

rBio: Reasoning Model Trained on Virtual Cell Simulations

Scientists can ask complex biological questions in plain language and get predictions about gene interactions.

chanzuckerberg.com

The Alliance webinar for August is this Thursday (Aug 21, noon EDT), on Ontologies and the Alliance, presented by Chris Mungall. You can preregister for the zoom link here forms.gle/GzMnmwK23SzP...; please preregister by midnight EDT Wednesday Aug 20.

Alliance Of Genome Resources Event Registration

Webinar recordings are posted at https://www.youtube.com/@AllianceOfGenomeResources A schedule of future events is on the Alliance Events Calendar https://www.alliancegenome.org/event-calendar

forms.gle

Alliance of Genome Resources@alliancegenome.bsky.social · 12mo ago

The next Alliance webinar will be Thursday Aug 21, at noon EDT. The topic will be Ontologies and the Alliance, presented by Chris Mungall. You can register for the Zoom link here forms.gle/GzMnmwK23SzP... or via the link on the Alliance Event Calendar www.alliancegenome.org/event-calendar

This is terrible news, not just for fly research, Drosophila is a key model organism that helps us understand shared biological pathways and the systems that underpin many human diseases 💔💔💔

The Transmitter @thetransmitter.bsky.social · 12mo ago

FlyBase, a Drosophila database, will lose a third of its team in early October because the Harvard grant that covered the employees’ salaries was canceled. Scientists warn that losing FlyBase could devastate fly research. By @claudia-lopez.bsky.social www.thetransmitter.org/community/ha...

FlyBase needs your help! We ask that European labs continue to contribute to Cambridge, UK FlyBase, whereas US and other non-European labs can contribute to US FlyBase. For more information and how to donate: wiki.flybase.org/wiki/FlyBase...

@cmungall.bsky.social‬ tackles complex #knowledgeManagement challenges in the life sciences with well-honed collaborative methods and AI-augmented computational tooling, streamlining #ontology creation and #knowledgeGraph building. knowledgegraphinsights.com/chris-mungall/

Chris Mungall: collaborative knowledge graphs in the life sciences

Chris Mungall is an expert on building knowledge graphs for the life sciences with a wide variety of scientific collaborators.

knowledgegraphinsights.com

Exceptional Contributions to Biocuration - Lifetime Achievement Award winner: Ruth Lovering Ruth has contributed extensively to the curation of key resources such as HGNC, Gene Ontology (GO), and IMEx, and has been instrumental in developing curation standards. Ruth is a past chair of the ISB EC.

Exceptional Contributions to Biocuration - Advanced Career Award winner: Kimberly Van Auken Kimberly's career reflects expertise, sustained innovation, & dedicated service to community. She's contributed to many projects, including WormBase, the Gene Ontology, & the Alliance of Genome Resources.

Exceptional Contributions to Biocuration - Early Career Award winner: Tiago Lubiano. Tiago's a passionate and motivated scientist interested in linked open data, ontologies, the semantic web, and their application in modeling cells and cell types. He is active in many curation projects & with ISB.

@severaltimes.bsky.social talking about the BioPortal MCP at #BOSC2025 / #BOKR2025 #ISMBECCB2025

Nice Chris is raising the topic of AI-assisted coding. There are huge advantages of Agentic AI applications here, but there are also risks (watch this space for more on this topic) #ISMBECCB2025 #BOSC2025

Just as Chris launched into the topic of knowledge censorship, the AI transcription and the slides stopped working. Coincidence?? 🤔 #BOSC2025

A full room during @cmungall.bsky.social's #BOSC2025 / #BOKR2025 keynote talk at #ISMBECCB2025

Looking forward to seeing many of you this week at ISMB, and talking to you about our work on agentic AI and knowledge bases! Doubly honored to be selected for this joint session, the open-bio community has been a huge influence on how I approach ontologies and knowledge base development.

Bioinformatics Open Source Conference (BOSC)@bosc.bsky.social · last yr.

On Day 2, kicking off the joint BOSC/BOKR session, Chris Mungall (@cmungall.bsky.social) will discuss "Open Knowledge Bases in the Age of Generative AI". @bokr.bsky.social More info: www.open-bio.org/events/bosc-... (2/2)

Wow, AlphaGenome is a huge deal, 1mb context windows, and prediction of a variety of features, with cell and tissue specificity! Read @anshulkundaje.bsky.social's excellent thread for the details. I want to additionally highlight one additional thing for my structured data nerd friends...

Anshul Kundaje@anshulkundaje.bsky.social · last yr.

This a really exciting leap forward for genomic sequence to activity gene regulation models. It is a genuine improvement over pretty much all SOTA models spanning a wide range of regulatory, transcriptional and post-transcriptional processes. 1/