<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><submitter>Liu S</submitter><funding>NIDA NIH HHS</funding><funding>NHGRI NIH HHS</funding><funding>NCI NIH HHS</funding><funding>NIH HHS</funding><pubmed_abstract>The intricate spatial organization and molecular communication among cells are fundamental to multicellular systems. Spatial transcriptomics (ST) enables gene expression profiling while preserving spatial context, providing rich data for studying cellular interactions and tissue dynamics. However, most existing computational approaches focus on embedding-based tasks and provide limited generative capacity for simulating cell behavior &lt;i>in situ&lt;/i>. Moreover, accurately interpreting spatial interactions requires extensive biological knowledge, which current models do not incorporate. Here, we introduce TissueNarrator, a framework that reformulates spatial omics analysis as a language modeling problem. By representing tissue sections as spatial sentences - rank-based gene lists augmented wi</pubmed_abstract><journal>bioRxiv : the preprint server for biology</journal><pagination>2025.11.24.690325</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12697357</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>TissueNarrator: Generative Modeling of Spatial Transcriptomics with Large Language Models.</pubmed_title><pmcid>PMC12697357</pmcid><funding_grant_id>R21 DA061481</funding_grant_id><funding_grant_id>R03 OD039980</funding_grant_id><funding_grant_id>UM1 HG011593</funding_grant_id><funding_grant_id>R01 HG012303</funding_grant_id><funding_grant_id>UH3 CA268202</funding_grant_id><funding_grant_id>R01 HG007352</funding_grant_id><pubmed_authors>Liang S</pubmed_authors><pubmed_authors>Tang J</pubmed_authors><pubmed_authors>Ma J</pubmed_authors><pubmed_authors>Liu S</pubmed_authors></additional><is_claimable>false</is_claimable><name>TissueNarrator: Generative Modeling of Spatial Transcriptomics with Large Language Models.</name><description>The intricate spatial organization and molecular communication among cells are fundamental to multicellular systems. Spatial transcriptomics (ST) enables gene expression profiling while preserving spatial context, providing rich data for studying cellular interactions and tissue dynamics. However, most existing computational approaches focus on embedding-based tasks and provide limited generative capacity for simulating cell behavior &lt;i>in situ&lt;/i>. Moreover, accurately interpreting spatial interactions requires extensive biological knowledge, which current models do not incorporate. Here, we introduce TissueNarrator, a framework that reformulates spatial omics analysis as a language modeling problem. By representing tissue sections as spatial sentences - rank-based gene lists augmented wi</description><dates><release>2025-01-01T00:00:00Z</release><publication>2025 Nov</publication><modification>2026-06-14T03:15:17.928Z</modification><creation>2026-06-14T03:08:49.393Z</creation></dates><accession>S-EPMC12697357</accession><cross_references><pubmed>41394628</pubmed><doi>10.1101/2025.11.24.690325</doi></cross_references></HashMap>