Bioinformatician, microbial genomics, high-throughput sequencing data analysis. Also on https://xitter.cf/t.co/dSdObksWQH
Lyon, France
Joined November 2008
- Tweets7K
- Following364
- Followers474
- Likes8.6K
Erwin Sentausa retweeted
🚨 Our first peer-reviewed paper on the challenges and opportunities of automating science with AI is now available at the Proceedings of the National Academy of Sciences. Read the full paper here: pnas.org/doi/epdf/10.1073/pn…
2026 is the year of AI Scientists, among many other things. At Carnegie Mellon University, we‘re conducting some exciting research on the performance and safety of AI scientists.
Our first paper “The more you automate, the less you see: hidden pitfalls of AI scientist systems” is revised and available for reading. Our work has been coverred by undark too; links to the paper and coverage here:
arxiv.org/pdf/2509.08713?
undark.org/2026/01/26/ai-sci…
Erwin Sentausa retweeted
Science – debatably the #1 journal in the world – published a paper on a "virtual biotech" AI system this week
but the authors never even test if it works well!
all the evidence for its performance is 3 anecdotes
the paper has no benchmark scores, no baselines, no replicates
Erwin Sentausa retweeted
Super excited that #VirtualBiotech is published in @ScienceMagazine today!
Tens of thousands of AI scientist agents work together across drug discovery + development, from target discovery to clinical trial design. Our blueprint for agentic R&D 🧵
Erwin Sentausa retweeted
Long-read #sequencing is transforming our understanding of the human #genome by revealing complex genetic variations often missed by traditional methods. This #Primer explores the computational techniques enabling these insights.
nature.com/articles/s43586-0…
Erwin Sentausa retweeted
A new core-genome MLST approach for Chlamydia trachomatis genomic surveillance and research nature.com/articles/s41467-0…
Erwin Sentausa retweeted
Automatic generation of model sequences for complex regions in assembly graphs with TTT dlvr.it/TV0Nv5
Erwin Sentausa retweeted
An AI biologist augmented discovery of disease mechanisms and targets for drug treatment.
Working autonomously, trained with >24 million publications and >600TB of biomedical data
@natBME
nature.com/articles/s41551-0…
Erwin Sentausa retweeted
Trimeric autotransporter adhesins driving chain-like adhesion diversify surface colonization strategies in Shiga toxin-producing Escherichia coli nature.com/articles/s41467-0…
Erwin Sentausa retweeted
🧬 Introducing 𝐄𝐌𝐁𝐋 𝐀𝐈 𝐋𝐈𝐁𝐑𝐀𝐑𝐈𝐀𝐍.
A knowledge layer for life-science AI agents.
Natural-language question in. Evidence snippet out.
No vector database. No separate literature index. Always up to date.
Open source ↓
Erwin Sentausa retweeted
1/ Out today in Cell Genomics: "Agentic genomics: From pipeline automation to autonomous validation." With @HeinnerGuio and @SFatumo .
For 20 years the bottleneck in genomics was writing the code. That is going away.
Erwin Sentausa retweeted
Nature research paper: A global view of human centromere variation and evolution
go.nature.com/4bnIAb7
Erwin Sentausa retweeted
Can AI take proteomics to a virtual cell? Our new perspective maps the path — from better peptide/protein ID to spatial & perturbation proteomics to AI Virtual Cells — and calls for an AI-friendly data ecosystem to get there. @guomics and Zhang lab.
nature.com/articles/s41592-0…
Erwin Sentausa retweeted
A prehistoric East-Asian Yersinia pestis genome and a ~5.3 ka trans-Eurasian expansion of plague nature.com/articles/s41467-0…
Erwin Sentausa retweeted
Someone asks me every other week if AI is going to replace bioinformaticians.
A new npj Digital Medicine paper finally said what I have been telling them for two years.
Erwin Sentausa retweeted
Our new genome annotation method relies almost entirely on transcriptome and alignment evidence, and as a result outperforms pretty much all other de novo pipelines. Paper just out, led by @AlekseyZimin5: rdcu.be/frSOg
Erwin Sentausa retweeted
Excited to introduce Paperclip Chat!🖇️
Now you can use #Paperclip directly in your browser for deep literature synthesis for free
⚡️ Each claim is grounded with inline citations
⚡️ Upload your own PDFs. They're automatically integrated into Paperclip's virtual filesystem
Erwin Sentausa retweeted
Nextflow log files are great for debugging, but digging through 1000s of debug lines to find an error can be difficult.🧵 That's why we've introduced native log viewers in the Nextflow CLI and VS Code extension.
youtube.com/watch?v=h9VEV5O8…
Erwin Sentausa retweeted
A syntenic pangenome of Gardnerella reveals novel plasmids and phage, taxonomic boundaries, and species-level stratification of metabolic and virulence potential nature.com/articles/s41467-0…
@rrwick benchmarked Dorado's [email protected] vs [email protected] for microbial WGS.
TLDR: @nanopore claimed no sup model is needed anymore. The data disagrees: [email protected] still wins at both read and assembly level.
rrwick.github.io/2026/06/11/…
And the 2nd part on assembly polishing rrwick.github.io/2026/06/19/…
Erwin Sentausa retweeted
can AI write engaging news that people can trust?
introducing ✨Data2Story: a data journalist agent.
give it raw data, it generate a verifiable, multimodal article.
🔍verifiable: every claim is evidence-grounded, traces back to data, code, or a cited source.
🔮multimodal: the article is a generative UI — images, videos, audio, interactive charts.
not just readable, but trustworthy and playable. 🧵1/N