Jean-Paul Courneya

@gregisenberg Institutional Agent Installation engineer

@gregisenberg Any ideas about monetizing the various agentic components? Mcpaas

build startups for agents over the next 10 years, you'll have a market of billions of customers (agents) with millions of wallets that want to use your services go look at every saas tool you use. notion, slack, stripe etc now ask: "what's the version of this that's built purely for agents?" agent-native payments, agent-native communication, agent-native memory etc every single category gets rebuilt (for agents) we're entering the machine-to-machine economy and almost nobody is building for it yet.

@EITMonline Thanks for sharing. Smell my face

Talking to Shari Bailey... lailasgift.org/legislative-in…

Conserve The Sound: An online museum of vanishing and endangered sounds conservethesound.de

One more challenge: Even with cheaper library prep, sequencing costs are still massive, especially for 1M+ cell screens So we do a second fun thing! Since VIPerturb-seq is compatible w/fixation, we can phenotypically enrich for ‘Very Important Perturbations’ prior to sequencing

Chrome's WebMCP proposal is the way we will being AI into existing applications. Agents shouldn't have to screenshot or dump HTML to use your app. Just expose your tools via HTML form attributes or define the schemas in your JavaScript Quick 15 min explainer video → youtube.com/watch?v=sOPhVS…

@lzsthw Bioconductor project moved to zulip. Not that you asked. Maybe you hadn't checked it out.

Last night I evaluated a few open source projects for replacements for Discord for my courses. I've been trying to get off Discord for a month and their latest move is the final straw. Here's the timecodes for where I evaluate each thing so you can jump ahead, and some notes: 0:02:46 - SETUP 0:30:40 - EVAL OVER 0:32:45 - APACHE ANSWER 0:51:30 - CHECKING TEAMSPEAK 6 0:56:30 - ERGO IRC 0:59:00 - IRSSI WTF 1:01:30 - RESCUED by CATGIRL 1:11:00 - SELF-HOSTING ERGO 1:26:30 - GALENE VIDEO CONFERENCING 1:33:45 - PLAYING VIDEO TEST 1:40:56 - CONCLUSION Please remember that I'm looking for something that is _asynchronous_, let's people ask questions easily, and easily chat with me and other students. I don't really need voice chat, video, or really even images maybe. Adjust what I do to what you need.

@domenjemec @gptomics Hey just landed on your project and wanted to tip the hat your way for rapid development on this. Ive noticed Claude using skills and didn't realize you could give it skills. Does it run locally?

Because of this, @gptomics BioSkills is focused on use cases instead of tools, removing the burden. We're up to 412 skills now. Take a look

One thing I noticed while building agent skills: most bioinformatics skill libraries are very tool-focused (e.g., “Use STAR"). This puts a lot of burden on the user or the model since one of them has to convert their use case into the tool to trigger the skill.

🇬🇧Tomorrow, Geraldine Van der Auwera (Lead Developer Advocate at @SeqeraLabs), is giving a talk at #FOG2026 on modern genomics pipelines🎤 🎥 Get the talk recording: hubs.la/Q040tB750 📍 Stop by booth #67B to chat with the team

Arc bioinformatics scientists @noamteyssier and @a_dobin have just released cyto, an ultra-high throughput processor specifically optimized for @10xGenomics Flex single-cell data. We are excited to make this resource open source: biorxiv.org/content/10.648…

Sorry dinner is late, I had to charge my knife

New to Nextflow?💻 Kick start 2026 with beginners Nextflow training, from the creators of Nextflow! Free, online, and support from the global community🌍hubs.la/Q03-Jrwd0

Kickstart 2026 with all the latest features of Nextflow, including static types & workflow inputs/outputs!🚀 Watch the latest @SeqeraLabs webinar showcasing these capabilities using @nf_core /RNAseq! 👀 Watch on-demand: hubs.la/Q03ZR7q_0

AlphaFold DB v6 (synced with UniProt 2025_03) is live! Here are the details: Totals v4 → v6: 241,070,489 entries. Since v4: +65,711,653 added, 39,324,993 removed, 276,539 changed (in sequence), 175,082,297 unchanged (metadata refresh, relabelled v6). Details 👇

@OpenLitterMap @FineGael It boggles the mind how hard it is to grasp the concept but also what does it take to engage the citizens when you use social platforms freely and not get the right engagement.

@Rainmaker1973 In this case an actual smart ass

Having a smart friend x.com/epiccontentX/s…

@OpenLitterMap Yeah it is

Supercoding beyond institutional sclerosis is fun

We're thrilled to announce that one of our keynote speakers at #WABI2025 will be the inimitable Ben Langmead! wabiconf.github.io/2025/talks/tal…. Ben's keynote is titled "We are what we index; a primer for the Wheeler Graph era", and it's sure to be a whirlwind tour of full-text indexing!

In this blog, Lakmal outlines Oxford Nanopore's roadmap to proteomics. nanoporetech.com/blog/london-ca… #nanoporeconf

@tangming2005 Unix is beautiful! Ugly is in the eye of the beholder. Simplicity and effective. Remember all the args though... Need a cheat sheet or LLM!

I had a 26GB TSV file. R choked. So I turned to UNIX. And it worked. 1/ You only need 500 columns. But the file is 26GB. R freezes. Memory bleeds. You need the data—but you don’t need the pain. Here’s what I did.