Stephen Turner
@stephenturner.us
Associate Professor of Data Science & asst. Dean of Research at UVA School of Data Science, #Rstats enthusiast, dad, runner, guitar noise-maker. Views my own.
Web: https://stephenturner.us/
Newsletter: https://blog.stephenturner.us
Web: https://stephenturner.us/
Newsletter: https://blog.stephenturner.us
Pinned
Stephen Turner
@stephenturner.us
· Aug 29
All models are wrong; some are useful.
All LLM outputs are hallucinations. Some are useful.
All LLM outputs are hallucinations. Some are useful.
The Era of Agentic Organization: Learning to Organize with Language Models arxiv.org/abs/2510.26658
November 25, 2025 at 7:02 PM
The Era of Agentic Organization: Learning to Organize with Language Models arxiv.org/abs/2510.26658
Report Launch: Safeguarding AIxBio Capabilities to Prevent Global Catastrophe www.nti.org/events/repor...
Report Launch: Safeguarding AIxBio Capabilities to Prevent Global Catastrophe
"Safeguarding Against Global Catastrophe: Risks, Opportunities, and Governance Options at the Intersection of Artificial Intelligence and Biology," highlights actions the international community can…
www.nti.org
November 25, 2025 at 5:01 PM
Report Launch: Safeguarding AIxBio Capabilities to Prevent Global Catastrophe www.nti.org/events/repor...
Data-driven strategies for drug repurposing: insights, recommendations, and case studies academic.oup.com/bib/article/... 🧬🖥️🧪
November 25, 2025 at 3:00 PM
Data-driven strategies for drug repurposing: insights, recommendations, and case studies academic.oup.com/bib/article/... 🧬🖥️🧪
Nice talk from my colleague Antonios Mamalakis at @uvadatascience.bsky.social on the AI for Good webinar series: " Do AI models know what they know? How explainable AI can help us trust what machines learn" www.youtube.com/live/oO8WSvY...
Do AI models know what they know? How explainable AI can help us trust what machines learn
YouTube video by AI for Good
www.youtube.com
November 25, 2025 at 2:25 PM
Nice talk from my colleague Antonios Mamalakis at @uvadatascience.bsky.social on the AI for Good webinar series: " Do AI models know what they know? How explainable AI can help us trust what machines learn" www.youtube.com/live/oO8WSvY...
Shutdown fallout: >370 study sections, >24,000 apps were bumped. To keep Jan+May 2026 councils on track, most panels will now only discuss ~30-35% of applications, add a new “competitive but not discussed” tier, and use shorter bullet-style summaries. grants.nih.gov/grants/guide...
November 25, 2025 at 11:52 AM
Shutdown fallout: >370 study sections, >24,000 apps were bumped. To keep Jan+May 2026 councils on track, most panels will now only discuss ~30-35% of applications, add a new “competitive but not discussed” tier, and use shorter bullet-style summaries. grants.nih.gov/grants/guide...
Reposted by Stephen Turner
Tech I'm thankful for blog.stephenturner.us/p/tech-im-th... #rstats 🧬🖥️🧪
Tech I'm thankful for (2024)
Data science and bioinformatics tech I'm thankful for in 2024: tidyverse, RStudio, Positron, Bluesky, blogs, Quarto, bioRxiv, LLMs for code, Ollama, Seqera Containers, StackOverflow, ...
blog.stephenturner.us
November 25, 2024 at 2:29 PM
Tech I'm thankful for blog.stephenturner.us/p/tech-im-th... #rstats 🧬🖥️🧪
Integrative deep learning of spatial multi-omics with SWITCH www.nature.com/articles/s43... 🧬🖥️🧪
Integrative deep learning of spatial multi-omics with SWITCH - Nature Computational Science
In this study the authors present SWITCH, a deep learning model that integrates unpaired spatial multi-omics data and enables unsupervised cross-modal prediction, aiding spatial domain identification…
www.nature.com
November 25, 2025 at 9:55 AM
Integrative deep learning of spatial multi-omics with SWITCH www.nature.com/articles/s43... 🧬🖥️🧪
Generating long deletions across the genome with pooled paired prime editing screens www.biorxiv.org/content/10.1... 🧬🖥️🧪 github.com/julianewelle...
November 25, 2025 at 9:54 AM
Generating long deletions across the genome with pooled paired prime editing screens www.biorxiv.org/content/10.1... 🧬🖥️🧪 github.com/julianewelle...
Language models cannot reliably distinguish belief from knowledge and fact www.nature.com/articles/s42...
November 25, 2025 at 9:54 AM
Language models cannot reliably distinguish belief from knowledge and fact www.nature.com/articles/s42...
Claude Opus 4.5 System Card (PDF) assets.anthropic.com/m/64823ba748... bioinformatics, virology uplift, CBRN safety analysis
November 25, 2025 at 9:46 AM
Claude Opus 4.5 System Card (PDF) assets.anthropic.com/m/64823ba748... bioinformatics, virology uplift, CBRN safety analysis
New EO dropped yesterday on "The Genesis Mission" - an AI "Manhattan Project" for Science and Biotech blog.stephenturner.us/p/genesis-mi...
The Genesis Mission
An AI Manhattan Project for Science and Biotech
blog.stephenturner.us
November 25, 2025 at 9:38 AM
New EO dropped yesterday on "The Genesis Mission" - an AI "Manhattan Project" for Science and Biotech blog.stephenturner.us/p/genesis-mi...
Proteome-wide model for human disease genetics www.nature.com/articles/s41... (read free: rdcu.be/eRvLm) 🧬🖥️🧪 github.com/debbiemarksl...
November 24, 2025 at 8:40 PM
Proteome-wide model for human disease genetics www.nature.com/articles/s41... (read free: rdcu.be/eRvLm) 🧬🖥️🧪 github.com/debbiemarksl...
To be or not to be a protein coding mutation, that’s the question! academic.oup.com/nargab/artic... 🧬🖥️🧪
November 24, 2025 at 7:00 PM
To be or not to be a protein coding mutation, that’s the question! academic.oup.com/nargab/artic... 🧬🖥️🧪
Human Genome Diversity Project data use and implications for the governance of legacy genomic data www.nature.com/articles/s41... (free: rdcu.be/eRxWJ) github.com/UW-GAC/HGDP_...
November 24, 2025 at 5:00 PM
Human Genome Diversity Project data use and implications for the governance of legacy genomic data www.nature.com/articles/s41... (free: rdcu.be/eRxWJ) github.com/UW-GAC/HGDP_...
An Economy of AI Agents arxiv.org/abs/2509.01063
November 24, 2025 at 3:00 PM
An Economy of AI Agents arxiv.org/abs/2509.01063
The Pratt Ginkgo at the UVA rotunda is peak ginkgo today
November 23, 2025 at 8:28 PM
The Pratt Ginkgo at the UVA rotunda is peak ginkgo today
Getting my kids (9 and 11) a meta quest for Xmas. Besides beat saber what are a couple must have games (for them and me!)?
November 23, 2025 at 3:19 PM
Getting my kids (9 and 11) a meta quest for Xmas. Besides beat saber what are a couple must have games (for them and me!)?
I honestly didn't believe this at first. So I fired up gpt-oss in Ollama and tried it. First, a denial when asking about how to engineer avian influenza to better infect human cells. 1/2 🧵...
November 22, 2025 at 4:20 PM
I honestly didn't believe this at first. So I fired up gpt-oss in Ollama and tried it. First, a denial when asking about how to engineer avian influenza to better infect human cells. 1/2 🧵...
Review: Evaluation of metagenome binning: advances and challenges academic.oup.com/bib/article/... 🧬🖥️🧪
November 21, 2025 at 7:00 PM
Review: Evaluation of metagenome binning: advances and challenges academic.oup.com/bib/article/... 🧬🖥️🧪
Orchestrating Spatial Transcriptomics Analysis with Bioconductor
(including interoperability with Python)
Paper: www.biorxiv.org/content/10.1...
Book: bioconductor.org/books/OSTA/
#Rstats
(including interoperability with Python)
Paper: www.biorxiv.org/content/10.1...
Book: bioconductor.org/books/OSTA/
#Rstats
November 21, 2025 at 5:39 PM
Orchestrating Spatial Transcriptomics Analysis with Bioconductor
(including interoperability with Python)
Paper: www.biorxiv.org/content/10.1...
Book: bioconductor.org/books/OSTA/
#Rstats
(including interoperability with Python)
Paper: www.biorxiv.org/content/10.1...
Book: bioconductor.org/books/OSTA/
#Rstats
Nascent transcription quantification with scFLUENT-seq www.nature.com/articles/s41... (read free: rdcu.be/ePaym)
November 21, 2025 at 5:35 PM
Nascent transcription quantification with scFLUENT-seq www.nature.com/articles/s41... (read free: rdcu.be/ePaym)
Surgeons' awareness, expectations, and involvement with artificial intelligence: a survey pre and post the GPT era pubmed.ncbi.nlm.nih.gov/41197550/
Surgeons' awareness, expectations, and involvement with artificial intelligence: a survey pre and post the GPT era - PubMed
Surgeons' perceptions of AI are evolving, driven by the rise of generative AI and the advancements in surgical data science. While enthusiasm for integration is strong, knowledge gaps and…
pubmed.ncbi.nlm.nih.gov
November 21, 2025 at 5:35 PM
Surgeons' awareness, expectations, and involvement with artificial intelligence: a survey pre and post the GPT era pubmed.ncbi.nlm.nih.gov/41197550/
ybyra: Y-chromosome haplogroup calling using a tree-based scoring method www.biorxiv.org/content/10.1... 🧬🖥️🧪 github.com/tpinotti/ybyra
November 21, 2025 at 3:00 PM
ybyra: Y-chromosome haplogroup calling using a tree-based scoring method www.biorxiv.org/content/10.1... 🧬🖥️🧪 github.com/tpinotti/ybyra
New ARPA-H program: Autonomous Interventions and Robotics (AIR) arpa-h.gov/explore-fund...
November 21, 2025 at 1:55 PM
New ARPA-H program: Autonomous Interventions and Robotics (AIR) arpa-h.gov/explore-fund...
New paper from OpenAI: Early science acceleration experiments with GPT-5 arxiv.org/abs/2511.16072
November 21, 2025 at 1:47 PM
New paper from OpenAI: Early science acceleration experiments with GPT-5 arxiv.org/abs/2511.16072