Chris Mungall
@cmungall.bsky.social
Berkeley Lab, Environmental Genomics and Systems Biology division. #GeneOntology #MonarchInitiative #AllianceGenome #NationalMicrobimeDataCollaborative #OBOFoundry.
See the thread (from the original arXiv preprint) over on Mastodon: genomic.social/@Cmungall/11...
Chris Mungall (@[email protected])
Attached: 1 image
How can we scale up manual classification of chemical structures in databases like ChEBI? Can we help curators place new structures into classes like "terpenoid", based on their che...
genomic.social
October 3, 2025 at 2:58 PM
See the thread (from the original arXiv preprint) over on Mastodon: genomic.social/@Cmungall/11...
Check out the pre-print here www.biorxiv.org/content/10.1.... Not sure if the other authors beyond @tkaraletsos.bsky.social are on bsky #CellBiology #AI #GeneSky #genomics #VirtualCell
rbio1-training scientific reasoning LLMs with biological world models as soft verifiers
Reasoning Models are typically trained against verification mechanisms in formally specified systems such as code or symbolic math. However, in open domains like biology, we do not generally have acce...
www.biorxiv.org
August 25, 2025 at 12:41 AM
Check out the pre-print here www.biorxiv.org/content/10.1.... Not sure if the other authors beyond @tkaraletsos.bsky.social are on bsky #CellBiology #AI #GeneSky #genomics #VirtualCell
One super pedantic minor ontological pet peeve is the use of the term "simulation", since that leads me to expect a agent-based or physics-style simulation of cell perturbations. But in fact this pattern could be used for those too! And I guess the terminological horse has long bolted here..
August 25, 2025 at 12:41 AM
One super pedantic minor ontological pet peeve is the use of the term "simulation", since that leads me to expect a agent-based or physics-style simulation of cell perturbations. But in fact this pattern could be used for those too! And I guess the terminological horse has long bolted here..
But of course rBio is very cool independent of my nerdy obsession with FMs using ontologies/KGs! This general distillation pattern is likely to be very useful for integrating knowledge with the weights in massive omics FMs..
two dalek robots are standing next to each other in a room with the words 76totterslane above them
Alt: Dalek meme: Daleks saying "EX-PLAIN" (alluding to use of technique to make foundation models, the "daleks", more explainable)
media.tenor.com
August 25, 2025 at 12:41 AM
But of course rBio is very cool independent of my nerdy obsession with FMs using ontologies/KGs! This general distillation pattern is likely to be very useful for integrating knowledge with the weights in massive omics FMs..
For another use of ontologies in genomic foundation models, see the recent AlphaGenome paper bsky.app/profile/cmun...
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...
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/
August 25, 2025 at 12:41 AM
For another use of ontologies in genomic foundation models, see the recent AlphaGenome paper bsky.app/profile/cmun...
Aside: I find that too many "defenses" of ontologies/KGs in the face of genAI fall back on a kind of GraphRAG use case, where the ontology/KG is used as some kind of bullwark against hallucination. Valid... but they can do so much more! Using as teacher in RL-loop on reasoner traces is v cool!
yoda from star wars is smoking a cigarette and says `` teach you i will ''
Alt: Yoda meme: "Teach you I will". Alluding to using the ontology as a "teacher" in the RL loop
media.tenor.com
August 25, 2025 at 12:41 AM
Aside: I find that too many "defenses" of ontologies/KGs in the face of genAI fall back on a kind of GraphRAG use case, where the ontology/KG is used as some kind of bullwark against hallucination. Valid... but they can do so much more! Using as teacher in RL-loop on reasoner traces is v cool!
In order to fine tune the reasoner model, the authors used three kinds of soft verifiers in the RL loop - experimental (e.g. CRISPRi knockdown), "simulation" (e.g Transcriptformer), and knowledge-based. For knowledge-based, they used GO @geneontology.bsky.social!
August 25, 2025 at 12:41 AM
In order to fine tune the reasoner model, the authors used three kinds of soft verifiers in the RL loop - experimental (e.g. CRISPRi knockdown), "simulation" (e.g Transcriptformer), and knowledge-based. For knowledge-based, they used GO @geneontology.bsky.social!
The applications of this are very interesting, allowing for interrogation in natural language, as well as background reasoning over the wealth of biology in the literature. So you can ask what happens to other genes if you knock down a gene in a cell type, and get a biological explanation
August 25, 2025 at 12:41 AM
The applications of this are very interesting, allowing for interrogation in natural language, as well as background reasoning over the wealth of biology in the literature. So you can ask what happens to other genes if you knock down a gene in a cell type, and get a biological explanation
I don’t have those details to hand, but this affects the 3 subcontract sites too…
August 15, 2025 at 9:47 PM
I don’t have those details to hand, but this affects the 3 subcontract sites too…
Mild frustration and eye rolling against the machine
August 14, 2025 at 4:23 AM
Mild frustration and eye rolling against the machine
Reposted by Chris Mungall
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.
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.
July 30, 2025 at 4:04 PM
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.
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.
Reposted by Chris Mungall
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.
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.
July 30, 2025 at 4:04 PM
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.
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.
Reposted by Chris Mungall
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.
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.
July 30, 2025 at 4:04 PM
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.
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.
Reposted by Chris Mungall
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
July 22, 2025 at 10:49 AM
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