Mathys Grapotte
@grapottem.bsky.social
currently building a test bench for dl models in genomics at https://github.com/nf-core/deepmodeloptim. PostDoc at @ CRG Barcelona
Reposted by Mathys Grapotte
🎉 That’s a wrap! The International CRG-BI Postdoc Symposium has come to an end after three incredible days of inspiring talks, engaging discussions, and valuable connections. I have to say I couldn’t be happier! #CRGBIpostdocs
A 🧵 below 👇🏼
A 🧵 below 👇🏼
March 2, 2025 at 11:41 PM
🎉 That’s a wrap! The International CRG-BI Postdoc Symposium has come to an end after three incredible days of inspiring talks, engaging discussions, and valuable connections. I have to say I couldn’t be happier! #CRGBIpostdocs
A 🧵 below 👇🏼
A 🧵 below 👇🏼
Reposted by Mathys Grapotte
Super impressive work by @angelp.bsky.social and colleagues at AWS / ARM on porting #Bioconda packages to #arm64 - there's potential for some big savings on compute as we scale this up!
Check out the @nf-co.re #arm64 channel for more and to get involved in the effort...
Check out the @nf-co.re #arm64 channel for more and to get involved in the effort...
This is a call out to bioinformatics developers that we are working to get all of NF-Core pipelines (and by extension most of Bioconda) to support Arm.
Spot price for c8g.16xlarge (Graviton4) and it is below 60¢/hr. Or < 1¢ per physical CPU if your application supports Arm ...
Spot price for c8g.16xlarge (Graviton4) and it is below 60¢/hr. Or < 1¢ per physical CPU if your application supports Arm ...
January 28, 2025 at 10:11 PM
Super impressive work by @angelp.bsky.social and colleagues at AWS / ARM on porting #Bioconda packages to #arm64 - there's potential for some big savings on compute as we scale this up!
Check out the @nf-co.re #arm64 channel for more and to get involved in the effort...
Check out the @nf-co.re #arm64 channel for more and to get involved in the effort...
Wow honored to get a shoutout on the podcast ! Talking at the nextflow summit was a great experience, and I encourage you to apply for a talk at the next iterations
A massive shout out to all of the speakers featured in the podcast:
Júlia Mir-Pedrol, @grapottem.bsky.social, Laurence Kuhlburger, Edwin Clark, @lukfor.bsky.social, Ziad Al-Bkhetan, @biowilko.bsky.social, @tokybo.bsky.social, @loiclnlg.bsky.social, Kevin Moore....
Júlia Mir-Pedrol, @grapottem.bsky.social, Laurence Kuhlburger, Edwin Clark, @lukfor.bsky.social, Ziad Al-Bkhetan, @biowilko.bsky.social, @tokybo.bsky.social, @loiclnlg.bsky.social, Kevin Moore....
November 29, 2024 at 7:36 PM
Wow honored to get a shoutout on the podcast ! Talking at the nextflow summit was a great experience, and I encourage you to apply for a talk at the next iterations
I saw the discussion on #BioMLeval pop up thanks to this post and @ianholmes.org. I think this is an interesting + extremely valuable discussion - super happy to see people interested in bioML eval.
www.anthropic.com/research/sta...
This is an excellent attempt (blog & paper) at bringing more statistical rigor to evaluation of ML models (this is specifically focused on LLM evals).
I feel like we need to have similar clear standards for many types of predictive models in biology. 1/
This is an excellent attempt (blog & paper) at bringing more statistical rigor to evaluation of ML models (this is specifically focused on LLM evals).
I feel like we need to have similar clear standards for many types of predictive models in biology. 1/
A statistical approach to model evaluations
A research paper from Anthropic on how to apply statistics to improve language model evaluations
www.anthropic.com
November 23, 2024 at 6:00 PM
I saw the discussion on #BioMLeval pop up thanks to this post and @ianholmes.org. I think this is an interesting + extremely valuable discussion - super happy to see people interested in bioML eval.
Imo, one of the most interesting figures (S6.b) is buried in the supp. data.
From how I understand it, "if evo is good at predicting the next token in that sequence, then if it makes a mistake, it is likely due to an unexpected and impactful variant"
From how I understand it, "if evo is good at predicting the next token in that sequence, then if it makes a mistake, it is likely due to an unexpected and impactful variant"
November 16, 2024 at 8:46 AM
Imo, one of the most interesting figures (S6.b) is buried in the supp. data.
From how I understand it, "if evo is good at predicting the next token in that sequence, then if it makes a mistake, it is likely due to an unexpected and impactful variant"
From how I understand it, "if evo is good at predicting the next token in that sequence, then if it makes a mistake, it is likely due to an unexpected and impactful variant"