Karolinska Institutet

8 related articles

Subscribe to updates

bioRxiv Nov 6, 2026
Neighbor transcripts leak into spatial cells: DisCell splits spillover from niche response and gives each finding a breakdown point
Single-cell spatial transcriptomics counts neighboring cells' transcripts inside a cell, and this spillover and a cell's real response to its niche both tie expression to surroundings, so counts alone cannot separate them. DisCell models intrinsic state, niche response and spillover jointly, refits over a range of spillover fractions, and assigns each finding a breakdown point. On ovarian and lung sections its intrinsic state keeps more cell-cycle information than any competing method holding as little neighborhood information, and a published esophageal EMT finding survives the modeled spillover range.
Single-cell spatial transcriptomics counts neighboring cells' transcripts inside a cell, and this spillover and a cell's real response to its niche both tie expression to surroundings, so counts alone cannot separate them. DisCell models intrinsic state, niche response and spillover jointly, refits over a range of spillover fractions, and assigns each finding a breakdown point. On ovarian and lung sections its intrinsic state keeps more cell-cycle information than any competing method holding as little neighborhood information, and a published esophageal EMT finding survives the modeled spillover range.
KTH Royal Institute of Technology Karolinska Institutet
Ricky Molén（First author, Corresponding author）
DisCell Spatial transcriptomics Transcript spillover Niche response
Nature Methods Oct 23, 2026
Cell segmentation in spatial transcriptomics gets a cross-platform test: SAM tops the raw score, SCS leads once coverage counts
Cell segmentation in spatial transcriptomics has lacked a cross-platform comparison with biologically meaningful metrics. A benchmark evaluates 11 image-based, transcriptomics-based and multimodal methods across 15 datasets from 5 technologies and about 2.3 million cells, scoring segmentation quality, transcript recovery, morphology, expression purity and spatial organization. On the average of 15 metrics, SAM scores highest (0.58), ahead of SAM2 (0.53), BIDCell (0.52) and SCS (0.48); after adjusting by the ratio of segmented to reference cells, SCS leads (0.34), with BIDCell and Baysor both at 0.33.
Cell segmentation in spatial transcriptomics has lacked a cross-platform comparison with biologically meaningful metrics. A benchmark evaluates 11 image-based, transcriptomics-based and multimodal methods across 15 datasets from 5 technologies and about 2.3 million cells, scoring segmentation quality, transcript recovery, morphology, expression purity and spatial organization. On the average of 15 metrics, SAM scores highest (0.58), ahead of SAM2 (0.53), BIDCell (0.52) and SCS (0.48); after adjusting by the ratio of segmented to reference cells, SCS leads (0.34), with BIDCell and Baysor both at 0.33.
Karolinska University Hospital King Abdullah University of Science and Technology Ilia State University Karolinska Institutet
Xabier Martinez‐de‐Morentin（First author, Corresponding author）Jesper N. Tegner（Corresponding author）David Gómez-Cabrero（Corresponding author）
Cell segmentation Spatial transcriptomics CellSPA Segment Anything Model
Nature Machine Intelligence Oct 19, 2026
Joint multi-sample network inference steadies omics reconstructions, but a prior cut to 20% leaves zero active reactions
Multi-sample regulatory network inference has long solved each sample separately and stitched shared structure from overlaps, which is unstable under noise. CORNETO instead solves several samples inside one mixed-integer constrained optimization with structured sparsity penalties. On haematopoietic and adult cortical single-cell data, joint inference generally improved robustness and reproducibility, while predictive gains depended on biological context and prior-network completeness.
Multi-sample regulatory network inference has long solved each sample separately and stitched shared structure from overlaps, which is unstable under noise. CORNETO instead solves several samples inside one mixed-integer constrained optimization with structured sparsity penalties. On haematopoietic and adult cortical single-cell data, joint inference generally improved robustness and reproducibility, while predictive gains depended on biological context and prior-network completeness.
Karolinska University Hospital King Abdullah University of Science and Technology Ilia State University Karolinska Institutet
Xabier Martinez‐de‐Morentin（First author, Corresponding author）David Gómez-Cabrero（Corresponding author）
CORNETO Multi-sample constrained network inference Bootstrap aggregation Selective re-expansion
arXiv Oct 6, 2026
S3N pairs finite-element LL–HP mapping with quad-spiral state-space scanning to cut 10-day forecast nRMSE to 0.5177
The work proposes S3N, a spherical spiral scanning network that uses the surface finite-element L2Proj method to bidirectionally map atmospheric fields between the latitude–longitude grid and the equal-area HEALPix grid, and an Attention-Guided Quad-Spiral State-Space Scanning block that propagates information across HEALPix base-face boundaries along four global pole-to-pole spiral paths guided by cross-latitude attention; on ERA5/WeatherBench 2, S3N attains lower nRMSE at 4-, 7-, and 10-day lead times (0.5177 at 10 days versus 0.6398 for OneForecast) with slower error growth, while being less competitive at 6-hour and 1-day lead times.
The work proposes S3N, a spherical spiral scanning network that uses the surface finite-element L2Proj method to bidirectionally map atmospheric fields between the latitude–longitude grid and the equal-area HEALPix grid, and an Attention-Guided Quad-Spiral State-Space Scanning block that propagates information across HEALPix base-face boundaries along four global pole-to-pole spiral paths guided by cross-latitude attention; on ERA5/WeatherBench 2, S3N attains lower nRMSE at 4-, 7-, and 10-day lead times (0.5177 at 10 days versus 0.6398 for OneForecast) with slower error growth, while being less competitive at 6-hour and 1-day lead times.
Princeton University Harbin Institute of Technology Nanyang Technological University Nanjing University of Information Science and Technology Karolinska Institutet
Fan Yan（First author）
State-Space Sequence Model Attention Mechanism Time Series Forecasting Machine Learning
发表出处待核验 Oct 1, 2026
A 45-member modified Delphi consensus: screen for eating disorders before GLP-1 receptor agonist prescribing, and generally avoid these agents in active anorexia and bulimia nervosa
Using a three-round modified Delphi method, a 45-member panel of clinicians and researchers in diabetes, obesity and/or eating disorders plus people with lived experience reached an average 91.7% consensus on recommendations for GLP-1 receptor agonist use in eating disorder contexts, covering pre-treatment screening, risk-stratified monitoring, standardized educational materials and concurrent evidence-based psychotherapy, stating that these agents should generally be avoided in active eating disorders, particularly anorexia nervosa, atypical anorexia nervosa and bulimia nervosa with marked dietary restraint and/or significant weight suppression, and setting out research priorities in epidemiology, regulation and binge eating disorder trials.
Using a three-round modified Delphi method, a 45-member panel of clinicians and researchers in diabetes, obesity and/or eating disorders plus people with lived experience reached an average 91.7% consensus on recommendations for GLP-1 receptor agonist use in eating disorder contexts, covering pre-treatment screening, risk-stratified monitoring, standardized educational materials and concurrent evidence-based psychotherapy, stating that these agents should generally be avoided in active eating disorders, particularly anorexia nervosa, atypical anorexia nervosa and bulimia nervosa with marked dietary restraint and/or significant weight suppression, and setting out research priorities in epidemiology, regulation and binge eating disorder trials.
NYU Langone Health University of Pennsylvania Johns Hopkins University University of North Carolina at Chapel Hill University of Virginia New York University University of Louisville University of Cincinnati
Aaron R. Keshen（First author）
GLP-1 receptor agonists (GLP-1RAs)Eating disorders (EDs)Modified Delphi Binge eating disorder (BED)
arXiv Sep 29, 2026
TT-VidT splits appearance and motion into two pathways: among 24 architecture-objective pairings, only TT3D with Diff Compression leads Jester, SSv2, ARID and Diving48 at once
The work proposes TT-VidT, which pairs a DINOv3-initialized ViT-B/16 per-frame spatial path with a compact Temporal Transfer Layer and trains it by Diff Compression to reconstruct target frames from a first-frame appearance anchor and frame-specific motion tokens; under a matched recipe at roughly 170M-190M encoder scale on 1.7M OpenVid and Moments-in-Time v2 clips for 8 epochs, a 24-cell architecture-objective sweep shows that only TT3D with Diff Compression enters the strongest motion-sensitive regime, and in the final comparison it leads Jester, Something-Something V2, ARID and Diving48 fine-tuning simultaneously while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA 2.
The work proposes TT-VidT, which pairs a DINOv3-initialized ViT-B/16 per-frame spatial path with a compact Temporal Transfer Layer and trains it by Diff Compression to reconstruct target frames from a first-frame appearance anchor and frame-specific motion tokens; under a matched recipe at roughly 170M-190M encoder scale on 1.7M OpenVid and Moments-in-Time v2 clips for 8 epochs, a 24-cell architecture-objective sweep shows that only TT3D with Diff Compression enters the strongest motion-sensitive regime, and in the final comparison it leads Jester, Something-Something V2, ARID and Diving48 fine-tuning simultaneously while using 48% fewer encoder FLOPs than DisMo and 55% fewer than VideoMAE or V-JEPA 2.
National Tsing Hua University Karolinska Institutet
Shih-Ying Yeh（First author）
TT-VidT Diff Compression Temporal Transfer Layer Self-Supervised Learning
Frontiers in Pharmacology Sep 25, 2026
Review proposes a microbiome-aware oral formulation framework: excipient risk classification, nanocarrier design rules, and a tiered testing roadmap
This review integrates evidence on microbial drug metabolism, excipient–microbiome interactions, nanocarrier–microbiome interfaces, microbiota-responsive release mechanisms, and experimental models to propose an authors' evidence-informed framework for oral formulation design, comprising an excipient–microbiome risk classification, nanocarrier design rules, microbiota-responsive delivery decision logic, and a tiered testing roadmap, illustrated by clinically relevant examples such as digoxin inactivation by Eggerthella lenta, bacterial levodopa metabolism, and microbial beta-glucuronidase-mediated irinotecan toxicity.
This review integrates evidence on microbial drug metabolism, excipient–microbiome interactions, nanocarrier–microbiome interfaces, microbiota-responsive release mechanisms, and experimental models to propose an authors' evidence-informed framework for oral formulation design, comprising an excipient–microbiome risk classification, nanocarrier design rules, microbiota-responsive delivery decision logic, and a tiered testing roadmap, illustrated by clinically relevant examples such as digoxin inactivation by Eggerthella lenta, bacterial levodopa metabolism, and microbial beta-glucuronidase-mediated irinotecan toxicity.
Karolinska University Hospital Egypt-Japan University of Science and Technology Cairo University Karolinska Institutet
mohamed sedeek（First author）Sadek Ahmed（Corresponding author）Osama Saher（Corresponding author）
Microbiome-Aware Oral Drug Delivery Excipient–Microbiome Interactions Microbial Drug Metabolism Controlled drug release
Nature News Sep 21, 2026
Human-supervised Agentic AI for Hypothesis Generation and Experimental Assistance in Drug Repurposing
The study developed RepurAgent, a hierarchical multi-agent AI system in which a supervisor agent and a planning agent coordinate four specialized sub-agents (research, prediction, data, and report) through a human-in-the-loop design with episodic memory and retrieval-augmented generation, and validated it across three scenarios spanning the drug repurposing lifecycle: in Acute Myeloid Leukemia a blinded expert evaluation indicated substantially more novel and mechanistically credible candidates than a vanilla LLM baseline; in a retrospective COVID-19 antiviral screen it prioritized compounds with AUC-ROC up to 0.
The study developed RepurAgent, a hierarchical multi-agent AI system in which a supervisor agent and a planning agent coordinate four specialized sub-agents (research, prediction, data, and report) through a human-in-the-loop design with episodic memory and retrieval-augmented generation, and validated it across three scenarios spanning the drug repurposing lifecycle: in Acute Myeloid Leukemia a blinded expert evaluation indicated substantially more novel and mechanistically credible candidates than a vanilla LLM baseline; in a retrospective COVID-19 antiviral screen it prioritized compounds with AUC-ROC up to 0.
Stanford University University of Göttingen Universitätsmedizin Göttingen University of Helsinki Uppsala University Karolinska Institutet
Dinh-Long Huynh（First author）Ola Spjuth（Corresponding author）
Virtual Biotech Agentic AI Drug Discovery

You’re all caught up