Sign up here: luma.com/97vs6qk2
IGI BioML Journal Club - Protein Sequence Domain Annotation using Language Models · Luma
Arpan Sarkar will present his work from the Eddy Lab at Harvard on using protein language models for protein domain annotation! His team developed PSALM, which…
luma.com
November 2, 2026 at 6:31 PM
Sign up here: luma.com/97vs6qk2
📖 Read the Nextflow Frontier blog post: hubs.la/Q04CBwD30
Introducing Nextflow Frontier
A recursive closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench it has already scored better than 92% of leaderboard entries.
hubs.la
October 29, 2026 at 1:23 PM
📖 Read the Nextflow Frontier blog post: hubs.la/Q04CBwD30
📖 Read the Nextflow Frontier blog post: hubs.la/Q04CBwD30
Introducing Nextflow Frontier
A recursive closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench it has already scored better than 92% of leaderboard entries.
hubs.la
October 29, 2026 at 1:27 PM
📖 Read the Nextflow Frontier blog post: hubs.la/Q04CBwD30
We launched Nextflow Frontier: a recursive, closed-loop discovery system for the unsolved problems in life sciences. 📊On BioML-bench (24 agentic tasks), it scored in the 92nd percentile across all categories, outperforming previous published agentic systems by nearly 23%.
October 29, 2026 at 1:27 PM
We launched Nextflow Frontier: a recursive, closed-loop discovery system for the unsolved problems in life sciences. 📊On BioML-bench (24 agentic tasks), it scored in the 92nd percentile across all categories, outperforming previous published agentic systems by nearly 23%.
We launched Nextflow Frontier: a recursive, closed-loop discovery system for the unsolved problems in life sciences. 📊On BioML-bench (24 agentic tasks), it scored in the 92nd percentile across all categories, outperforming previous published agentic systems by nearly 23%.
October 29, 2026 at 1:23 PM
We launched Nextflow Frontier: a recursive, closed-loop discovery system for the unsolved problems in life sciences. 📊On BioML-bench (24 agentic tasks), it scored in the 92nd percentile across all categories, outperforming previous published agentic systems by nearly 23%.
🧪 Turns each hypothesis into a reproducible pipeline
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for @alloxbio.bsky.social that beat every published method they tested
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for @alloxbio.bsky.social that beat every published method they tested
October 28, 2026 at 4:57 PM
🧪 Turns each hypothesis into a reproducible pipeline
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for @alloxbio.bsky.social that beat every published method they tested
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for @alloxbio.bsky.social that beat every published method they tested
🧪 Turns each hypothesis into a reproducible @nextflow.io pipeline
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for ALLOX that beat every published method they tested
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for ALLOX that beat every published method they tested
October 28, 2026 at 4:47 PM
🧪 Turns each hypothesis into a reproducible @nextflow.io pipeline
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for ALLOX that beat every published method they tested
♻️ Tests thousands of them, then plans the next round
📊 Reaches the 92nd percentile on BioML-bench (24 tasks) vs the 75th for the best published AI system
🧬 Built a model for ALLOX that beat every published method they tested
Tool Duel: BoltzGen vs BindCraft2 — architecture, piece by piece.
Same input, same output. The middle differs: BindCraft2 optimises a backbone in an AlphaFold2 loop; BoltzGen generates one by diffusion in one pass.
Both collected at toolome.bio
#ProteinDesign #BioML
Same input, same output. The middle differs: BindCraft2 optimises a backbone in an AlphaFold2 loop; BoltzGen generates one by diffusion in one pass.
Both collected at toolome.bio
#ProteinDesign #BioML
October 24, 2026 at 6:01 PM
Tool Duel: BoltzGen vs BindCraft2 — architecture, piece by piece.
Same input, same output. The middle differs: BindCraft2 optimises a backbone in an AlphaFold2 loop; BoltzGen generates one by diffusion in one pass.
Both collected at toolome.bio
#ProteinDesign #BioML
Same input, same output. The middle differs: BindCraft2 optimises a backbone in an AlphaFold2 loop; BoltzGen generates one by diffusion in one pass.
Both collected at toolome.bio
#ProteinDesign #BioML
Today we are launching Nextflow Frontier
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
October 13, 2026 at 11:10 AM
Today we are launching Nextflow Frontier
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
Today we are launching Nextflow Frontier
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
October 13, 2026 at 11:08 AM
Today we are launching Nextflow Frontier
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
A closed-loop discovery system for the unsolved problems in life sciences. On BioML-bench, the previous best AI system scored better than 75% of leaderboard entries. Nextflow Frontier scored better than 92%.
nextflow.com/frontier?utm...
Trying to keep up with progress in BioML, but struggling to tell good science from AI slop? Us too!
Let’s struggle together 🧬
Welcome to Denoising the Noise, a monthly journal club at the Innovative Genomics Institute exploring the latest in biology + machine learning.
Let’s struggle together 🧬
Welcome to Denoising the Noise, a monthly journal club at the Innovative Genomics Institute exploring the latest in biology + machine learning.
September 10, 2026 at 3:24 PM
Trying to keep up with progress in BioML, but struggling to tell good science from AI slop? Us too!
Let’s struggle together 🧬
Welcome to Denoising the Noise, a monthly journal club at the Innovative Genomics Institute exploring the latest in biology + machine learning.
Let’s struggle together 🧬
Welcome to Denoising the Noise, a monthly journal club at the Innovative Genomics Institute exploring the latest in biology + machine learning.
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.
There are many more intricate hypothesis that I could think of, I think this is the right application of LLMs in bioml.
November 16, 2024 at 8:53 AM
There are many more intricate hypothesis that I could think of, I think this is the right application of LLMs in bioml.
Does the discovery feed account for your interests?
Following mainly #bioml people, yet my discovery is full of politics and cat pictures 😭 (I don't mind the latter)
Following mainly #bioml people, yet my discovery is full of politics and cat pictures 😭 (I don't mind the latter)
November 17, 2024 at 7:09 AM
Does the discovery feed account for your interests?
Following mainly #bioml people, yet my discovery is full of politics and cat pictures 😭 (I don't mind the latter)
Following mainly #bioml people, yet my discovery is full of politics and cat pictures 😭 (I don't mind the latter)
The first day of our bioML symposium at @iocbprague.bsky.social went very well. It is amazing to see how fast this field is moving forward. Thanks to everyone for the fantastic talks! 🤖🧬
August 21, 2025 at 8:22 PM
The first day of our bioML symposium at @iocbprague.bsky.social went very well. It is amazing to see how fast this field is moving forward. Thanks to everyone for the fantastic talks! 🤖🧬
Today is the registration deadline for our bioML symposium on Aug 21-22. Last chance to secure your spot! More info at tinyurl.com/bioMLPrague25
May 30, 2025 at 3:01 PM
Today is the registration deadline for our bioML symposium on Aug 21-22. Last chance to secure your spot! More info at tinyurl.com/bioMLPrague25
Back in July 2023 we organized a small bioML symposium at @iocbprague.bsky.social, and it turned out to be a very pleasant and successful event. This summer we are following up with a great line-up of speakers. Please register for free, deadline May 30. tinyurl.com/bioMLPrague25
April 11, 2025 at 11:34 AM
Back in July 2023 we organized a small bioML symposium at @iocbprague.bsky.social, and it turned out to be a very pleasant and successful event. This summer we are following up with a great line-up of speakers. Please register for free, deadline May 30. tinyurl.com/bioMLPrague25
BioML-bench: Evaluation of AI Agents for End-to-End Biomedical ML #SingleCell 🧪🧬🖥️
https://www.biorxiv.org/content/10.1101/2025.09.01.673319v1
https://www.biorxiv.org/content/10.1101/2025.09.01.673319v1
September 5, 2025 at 7:00 AM
BioML-bench: Evaluation of AI Agents for End-to-End Biomedical ML #SingleCell 🧪🧬🖥️
https://www.biorxiv.org/content/10.1101/2025.09.01.673319v1
https://www.biorxiv.org/content/10.1101/2025.09.01.673319v1
In the spirit of trying to be more active on here... the deadline for our BioML internship is tomorrow 11/22.
If you are currently a PhD student please consider applying --- all we need is a CV and research statement!
jobs.careers.microsoft.com/global/en/jo...
If you are currently a PhD student please consider applying --- all we need is a CV and research statement!
jobs.careers.microsoft.com/global/en/jo...
Search Jobs | Microsoft Careers
jobs.careers.microsoft.com
November 21, 2024 at 5:57 PM
In the spirit of trying to be more active on here... the deadline for our BioML internship is tomorrow 11/22.
If you are currently a PhD student please consider applying --- all we need is a CV and research statement!
jobs.careers.microsoft.com/global/en/jo...
If you are currently a PhD student please consider applying --- all we need is a CV and research statement!
jobs.careers.microsoft.com/global/en/jo...
At NeurIPS and interested in talking about BioML? Catch me at the Microsoft booth in the expo hall between 2:00-2:30p and 3:30-4:30p today!
December 11, 2024 at 5:34 PM
At NeurIPS and interested in talking about BioML? Catch me at the Microsoft booth in the expo hall between 2:00-2:30p and 3:30-4:30p today!
it leads to the obvious conclusion (from the OP) "hmm i guess AI isn't so bad after all." that's a reasonable conclusion for the practitioner's definition of AI, but it's a pretty unreasonable conclusion for LLMs and image generators. that's how BioML and LLMs are conflated under "AI"
June 6, 2026 at 2:41 PM
it leads to the obvious conclusion (from the OP) "hmm i guess AI isn't so bad after all." that's a reasonable conclusion for the practitioner's definition of AI, but it's a pretty unreasonable conclusion for LLMs and image generators. that's how BioML and LLMs are conflated under "AI"
my point is that "AI" is applied to BioML by biologists and big tech alike to associate the two. bio gets funding, big tech gets to stand next to less hated industries
the common understanding of "AI" does not look like any BioML model, so using the term is misleading
the common understanding of "AI" does not look like any BioML model, so using the term is misleading
June 6, 2026 at 2:15 PM
my point is that "AI" is applied to BioML by biologists and big tech alike to associate the two. bio gets funding, big tech gets to stand next to less hated industries
the common understanding of "AI" does not look like any BioML model, so using the term is misleading
the common understanding of "AI" does not look like any BioML model, so using the term is misleading
in BioML, we use ML or deep learning as more descriptive terms. AI is used when you want to signal that you’re doing something fancy. I wish we used it less because it is meaningless in this context, but unfortunately journals like it
June 6, 2026 at 1:31 PM
in BioML, we use ML or deep learning as more descriptive terms. AI is used when you want to signal that you’re doing something fancy. I wish we used it less because it is meaningless in this context, but unfortunately journals like it