#GEOquery is a @bioconductor.bsky.social package that allows us to acquire data from NCBI's Gene Expression Omnibus, which is why we should be thankful to @seandavi.bsky.social for keeping it up to date.
For more details, visit:
bioconductor.org/packages/3.2...

The second article in the short series on making spatial data more accessible through natural language querying is available. Here the value of human language querying is shown in 7 scenarios using GeoQuery.

Do check it out!

#datascience #LLM #maps #locationintelligence

medium.com/@alan.robert...

Firebase latest release notes. Nothing for our API that resonated with us. I’m glad to see that Firestore continually is being improved. m.youtube.com/watch?v=OmE6...

Besides learning #BASH, I explored #R packages such as #tidyverse, #ggplot2, #DESeq2, #GEOquery, #org.Hs.eg.db, #clusterProfiler, #EnhancedVolcano, #celldex, #pheatmap, and #pathview, which open doors to further exploration of #RNASeq data. #Bioinformatics #RProgramming #Linux

I’m writing a short series of three articles on the use of a Large Language Model (LLM) to open up access to spatial data. The first is now available - do check it out!

#datascience #maps #LLM #spatialdata

medium.com/@alan.robert...

We now also have a companion phantasusLite R package. Among other things, it allows an easy access to RNA-seq counts, compatible with GEOquery package bioconductor.org/packages/rel... 5/n

🚨 EUVD-2026-42215
📊 7.5/10
🏢 tainacan

📝 The Tainacan plugin for WordPress is vulnerable to time-based blind SQL Injection via the 'geoquery' parameter in all versions up to and including 1.0.3 ...

🔗 https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-42215

#cybersecurity #infosec #cve #euvd

But our main interest is in compositional generalization. We fine-tune our pretrained models on four different compositional generalization dataset (COGS, COGS-vf, GeoQuery, and English Passivization). Here too, depth helps but the marginal utility diminishes rapidly!

Ever looked at a map or spatial data and wanted to ask a question about the data but the technical barrier to doing so has seemed very high?

By enabling natural language querying of data, LLMs can break down this barrier. To explore this I’m developing GeoQuery. Try it at:
geoquery.alanwroberts.com

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

Xiao Cao, Yuze Li, Youmin Zhang, Jiayu Song, Cheng Yan, Wen Li, Lixin Duan

tl;dr: depth+pose->geometric correspondence field->proxy query features->window-based retrieval->diffusion

arxiv.org/abs/2605.12399

Besides basic #RProgramming ( #tidyverse · #ggplot2 · #DESeq2 · #GEOquery · #org.Hs.eg.db · #clusterProfiler · #DoubletFinder · #EnhancedVolcano · #celldex · #pheatmap · #SingleR · #pathview) for #RNASeq · advanced packges #Seurat · #SeuratExtend · #monocle3 open new insight into #SingleCellAnalysis

Xiao Cao, Yuze Li, Youmin Zhang, Jiayu Song, Cheng Yan, Wen Li, Lixin Duan: GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction https://arxiv.org/abs/2605.12399 https://arxiv.org/pdf/2605.12399 https://arxiv.org/html/2605.12399

Authors published a paper in Biorxiv, they used GEOquery in the study. Including #RRIDs will make this less ambiguous.

SciScore made a table with this resource, see “Automated Services” module (download as csv, xml or #jats) #reproducibility #OpenScience

Advancing sepsis diagnosis and immunotherapy machine learning-driven identification of stable molecular biomarkers and therapeutic targets
->Nature | More info from EcoSearch

Xiao Cao, Yuze Li, Youmin Zhang, Jiayu Song, Cheng Yan, Wen Li, Lixin Duan
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
https://arxiv.org/abs/2605.12399

language models can improve compositional generalization performance. Empirically, our results on four standard compositional generalization benchmarks(SCAN, COGS, GeoQuery, and COGS-QL) demonstrate the superiority of [8/9 of https://arxiv.org/abs/2502.20834v1]