New preprint: A large language model (LLM) powered framework for fully automated extraction and harmonization of subject metadata from research papers.
Applied to human gut microbiome studies:
- 26,435 papers processed
- 400,000+ samples integrated
- Metadata now searchable
Automated Harmonization and Large-Scale Integration of Heterogeneous Biomedical Sample Metadata Using Large Language Models https://t.co/6bY8SRVqzE #biorxiv_bioinfo
🧬 Our “Behind the Paper” is now online at Springer Nature Communities:
“Active chromatin is not simply open—it forms compact domains that cohesin keeps from mixing.”
📖 A short story behind our recent @NatureGenet paper.
https://t.co/02XXA6wNUe
https://t.co/HjjYOjycld
Is euchromatin really “open”? 🧬 Using super-resolution imaging🔬 our new study @NatureGenet reveals: Euchromatin forms condensed domains in live cells. Cohesin constrains them and prevents domain mixing for proper transcriptional insulation🚧 🔗https://t.co/HjjYOjycld (1/2)
Is euchromatin really “open”? 🧬Our new study @bioRxiv suggests otherwise. Using super-resolution imaging🔬 @shiori_iida@MasaAShimazoe reveals: Euchromatin forms condensed domains in live cells. Cohesin constrains them and prevents domain mixing. 🔗https://t.co/2iISQjxjgh (1/3)
Our new paper is out @ScienceAdvances👇
https://t.co/VF4XGubD3B
🧬Our Repli-Histo labeling marks nucleosomes in euchromatin and heterochromatin in live human cells. 🔍@katsu_s_minami et al.have developed a chromatin behavior atlas within the nucleus. 1/2
Automatically process PDFs, Excel & DB records into unified metadata for cross-study analysis.
Available at:
🔧 https://t.co/R9XmZ9E9zt
📊 https://t.co/51uQmn9S3T
🌐 https://t.co/6WfbTvl0SL
New preprint: A large language model (LLM) powered framework for fully automated extraction and harmonization of subject metadata from research papers.
Applied to human gut microbiome studies:
- 26,435 papers processed
- 400,000+ samples integrated
- Metadata now searchable
Automated Harmonization and Large-Scale Integration of Heterogeneous Biomedical Sample Metadata Using Large Language Models https://t.co/6bY8SRVqzE #biorxiv_bioinfo