
The Intelligent Engine for Life Sciences. From the Creators of @nextflowio and @multiqc
Barcelona | New York | London
Joined May 2018
- Tweets1.6K
- Following13
- Followers2.4K
- Likes502
Seqera retweeted
Back in August, Anthropic showed Claude designing protein binders against 15 targets in up to 48 hours, work that has historically taken specialists weeks or months per target.🧵hubs.la/Q04FxhGt0
61 million more variants are now available to rare disease researchers.🧬 @GenomicsEngland set out to develop an aggregate data product that enables researchers to derive scientific insights from rare disease genomes at scale. 🧵
But at this scale, processing kept stalling as very different analyses shared one environment, with storage filling up unpredictably and container downloads timing out.
🤝 To solve this, they partnered with us to develop tailored solutions across infrastructure configuration, container management, and deployment tooling.
1
1
36
📈 The result: a near doubling of the throughput capacity, improved variant quality, and a significant increase in the breadth of genomic data available to researchers.
🔗 Learn more: hubs.la/Q04Ft78X0
1
26
Samples in, results out, and agents keep the line running in between.✨ Agents on Seqera Platform wake up on the events your stack already emits, like pipeline status changes, cron schedules or data landing in object storage.
Samples arrive, events feed the context and Seqera enforces the rules, so researchers, agents and pipelines work side by side without interruption.
Read the full post: hubs.la/Q04FnjgG0
20
Join us for our final @nextflowio Training Week of the year!🚀Work through beginner and advanced training courses, get live support from the team, and earn an official training certificate.
Nextflow Training Week by @SeqeraLabs kicks off today, and it’s not too late to join! 🔗 Online and free to attend: hubs.la/Q04FkyG30
🌱 Start out: Hello Nextflow, Nextflow Run & Nextflow for Science
🧭 Level up: Hello @nf_core, Side Quests & Training Collections
109
Seqera retweeted
Replying to @SeqeraLabs
@SeqeraLabs will be exhibiting at The Festival of Genomics & Biodata in London this January! Visit their stand to meet the team and discover how their workflow orchestration and data analysis solutions are helping researchers scale bioinformatics pipelines.
Register here: hubs.la/Q04F6dMb0
#FOG2027 #Bioinformatics #Genomics
How do you beat both OpenAI's Rosalind and Anthropic's Claude Science on biology problems?
We gave Nextflow Frontier and both of them the same 22 BioML-bench tasks, the same data and the freedom to keep experimenting as long as they liked. Here's what happened.🧵
Rosalind and Claude Science also had to find and run their own tools. Nextflow Frontier separates the science from the compute. Each idea becomes a @nextflowio pipeline that runs at scale on Seqera's platform, and every score feeds the next round.
1
60
Stopping at "it works" can be good engineering. In science, you don't know where the best answer is until you've looked.
Full results, task by task: hubs.la/Q04F5jmw0
53
❓The task: rank molecules by how likely they are to bind EGFR.✅The solution: Give Nextflow Frontier the problem, the score, and a blank canvas. After 80 hours, it tried 92 different ideas.🧵hubs.la/Q04DXxL50
So Nextflow Frontier built and trained a specific ML model to test that idea, then used those predictions to improve the result.
✅The result is ahead of every published result on this task, even beating specialized billion-parameter models.
1
11
Full write-up on how Nextflow Frontier got there, including the analysis behind the hypothesis and the benchmark it was scored against: hubs.la/Q04DXxL50
12





