
Martín Beracochea
@_martinbc
Work at @emblebi
ID: 55616850
https://www.mberacochea.cc/ 10-07-2009 17:30:07
1,1K Tweet
268 Takipçi
1,1K Takip Edilen







We are releasing OMG📷, an Open MetaGenomic dataset on Hugging Face. Similar to FineWeb for NLP, OMG is a massive dataset for open-science in genomics. We train a genomic language model gLM2 on OMG, demonstrating new capabilities like unsupervised protein-protein interaction.




🚨 UNDERCOVER: A few weeks ago I visited a salmon farm on the Faroe Islands– what I saw shocked me– it's an environmental and social disaster, it cannot go on. Yet Bakkafrost in the UK are certified RSPCA Assured– RSPCA (England & Wales), do the right thing and drop the scheme 🎣🍣




Join Evangelos Karatzas on the 13th of November for a webinar: how our MGnify Proteins resource helps with exploration of the metagenomics sequence space. He'll demo newly released ways to query the dataset, and MGnifams - a new set of protein families derived from it.





Blog post about the "Introduction to Nextflow" workshop in Montevideo last week. This workshop was organized by the lovely people of the ISCB Regional Student Group Uruguay rsg-uruguay.iscbsc.org. mberacochea.cc/posts/workshop… daniel rosales ISCB RSG Uruguay Joaquín Pereira