Robert Hoehndorf

@KAUST_News @CBRC_KAUST

🧬 Proud to share our new paper! A complete genome assembly from Saudi Arabia (KSA001), freely available to all. Special shoutout to @coolmaksat for leading the bioinformatics. Also hard work to get this IRB-approved nature.com/articles/s4159…

2nd day of #NeSy2024 is about to start, with a session on neurosymbolic languages. Will be great to see how this work can contribute to reproducibility of NeSy research and experiments.

@CPesquita How do you determine whether a prediction is (scientifically) interesting? Is it just novelty, or is there a role for causality? #NeSy2024

Ontologies model a consensus, not reality. (@CPesquita at #NeSy2024)

Billions of statements in biological knowledge graphs! Millions of nodes, billions of triples. Neurosymbolic methods are not yet ready to handle this data. (From @CPesquita's keynote at #NeSy2024)

"Size matters" --- knowledge graphs and ontologies in life sciences are possibly larger than in any other field; they are a formidable challenge for any AI method, symbolic or neural #nesy2024

At the #nesy2024 keynote today, @CPesquita highlights how medical and biological research was one main driver in the developments in logic and AI throughout history - in the words of Galen, "That the best doctor is also a philosopher" #nesy2024

What can life sciences do for neuro-symbolic AI? Excited for the #bioinformatics-related keynote by @CPesquita at #NeSy2024 - starting soon!

Happy to be at #NeSy2024 in Barcelona, just opened by @ejimenez_ruiz. First session on #XAI just starting.

We recently wrote a survey on #ontology #embedding. Great contributions from @leechuck Olga and Fernando from @CBRC_KAUST , @lawhy_AI and Ian Horrocks. #knowledgegraphs #survey #KnowledgeRepresentation. With methods, applications and system (mOWL). arxiv.org/abs/2406.10964

@azzathamer Read the article to find out how the neurosymbolic model learns to interpret different types of evidence (from model organism phenotypes over #GeneOntology functions to anatomical site of gene expression) and finally link the variant to #RareDisease phenotypes.

Latest work by my former student @azzathamer on using #neurosymbolicAI and biomedical ontologies to help diagnose #RareDisease is now online: academic.oup.com/bioinformatics…

Really happy to host @ChenJiaoyan1 at @KAUST_News - learned a lot about #neurosymbolic AI on the #SemanticWeb, #ontology embeddings, and using #LLM for knowledge engineering.

@scientistswrite Title. In particular if it needs a name or acronym. Takes hour in each meeting to decide on it.

Which section of a paper do you think is the most difficult to write?

We have brought together about 25 people for an @H3ABioNet African reference graph/pangenome and T2T hackathon in Cape Town. This week we will work with the HPRC team on long read data to build an African reference.

New work by my former student (now Prof) @azzathamer on phenotype-based prioritization of genetic variants for #RareDisease The work demonstrates how neurosymbolic AI can be used in domains like #RareDisease with little training data biorxiv.org/content/10.110…

@CBRC_KAUST @SarahAl33162257 Right afterwards, @azzathamer will defend her PhD thesis on variant prioritization with phenotype ontologies and machine learning cemse.kaust.edu.sa/events/event/p… Again, let me know if you like to attend.

Today is an exciting day @CBRC_Kaust: first, my student @SarahAl33162257 will defend her PhD thesis on ontology design patterns and phenotype ontologies. cemse.kaust.edu.sa/events/event/o… Msg me if you like to join by Zoom and hear about integrating and evaluating ontologies!

Finally arrived in Japan for #biohackjp (first time after the long COVID break). Still waiting for my flight to Tokamatsu, seems I will arrive 2 hours late for the symposium; hope I am still let in!