#BiotechNatureComms
LightNews LightNews
qchengx1e3.bsky.social
A biophysically principled sequence model IceQream characterises complex Transcription Factor-DNA interactions from chromosome accessibility analysis.
@Akhiad.bsky.social
#BiotechNatureComms
www.nature.com/articles/s41...
IceQream: Quantitative chromosome accessibility analysis using physical TF models - Nature Communications
Cis regulatory elements endow genomes with sequence-encoded logic to drive cellular differentiation. Here, the authors introduce a biophysically principled sequence model that characterises complex TF...
www.nature.com
October 14, 2025 at 5:52 PM
qchengx1e3.bsky.social
A multi-scale, multi-context, and interpretable mapping strategy to map cells across space, time, and disease. @pcnmartin.bsky.social @wonkj.bsky.social

#spatialMapping #spatialOmics #BiotechNatureComms

www.nature.com/articles/s41...
Multi-scale and multi-context interpretable mapping of cell states across heterogeneous spatial samples - Nature Communications
The alignment of heterogeneous spatial samples has become a growing challenge. Here, authors present a multi-scale, multi-context, and interpretable mapping strategy to map cells across space, time, a...
www.nature.com
August 22, 2025 at 2:18 PM
qchengx1e3.bsky.social
Using microfluidics and endogenous reporters, single cells are tracked to reveal how temporal dosing rewires chromatin in a model with near single-cell accuracy. @stevenwsmeal.bsky.social @robineclee.bsky.social #BiotechNatureComms

www.nature.com/articles/s41...
Time-varying stimuli that prolong IKK activation promote nuclear remodeling and mechanistic switching of NF-κB dynamics - Nature Communications
Cells rely on limited numbers of transmembrane receptors to process signals from dynamic microenvironments. Using microfluidics and endogenous reporters, the authors track single cells to reveal how t...
www.nature.com
August 14, 2025 at 8:51 PM
qchengx1e3.bsky.social
A computational framework for single cell and spatial alternative splicing analysis with Nanopore long read sequencing

@nancyrzhang.bsky.social
#BiotechNatureComms

www.nature.com/articles/s41...
Single cell and spatial alternative splicing analysis with Nanopore long read sequencing - Nature Communications
Single-cell isoform quantification using Nanopore long reads remains limited by sequencing errors. Here, authors present Longcell, a computational framework that corrects these errors and uncovers spl...
www.nature.com
July 22, 2025 at 1:28 PM
qchengx1e3.bsky.social
A computational tool #SCALPEL for #isoform quantification at the single-cell level using 3’ scRNA-seq data @franzake.bsky.social @mireyaplass.bsky.social #BiotechNatureComms

doi.org/10.1038/s414...
Quantification of transcript isoforms at the single-cell level using SCALPEL - Nature Communications
Single-cell RNA-seq facilitates the study of transcriptome diversity in individual cells. Here, authors introduce a tool for isoform quantification at the single-cell level using 3’ scRNA-seq data, co...
doi.org
July 13, 2025 at 5:41 PM
qchengx1e3.bsky.social
A fully automated AI ImageJ plugin that detects and classifies #exocytosis events from synaptic transmission to single-vesicle fusion. @alishaib.bsky.social #BiotechNatureComms

doi.org/10.1038/s414...
Highly adaptable deep-learning platform for automated detection and analysis of vesicle exocytosis - Nature Communications
Activity recognition in live-cell imaging is laborious. Here, authors present, IVEA, a fully automated AI ImageJ plugin, that efficiently detects and classifies exocytosis events, from synaptic transm...
doi.org
July 13, 2025 at 5:39 PM
qchengx1e3.bsky.social
ToxACoL is an endpoint-aware and task-focused compound representation learning paradigm for #Acute_Toxicity_Assessment #BiotechNatureComms

doi.org/10.1038/s414...
ToxACoL: an endpoint-aware and task-focused compound representation learning paradigm for acute toxicity assessment - Nature Communications
Multi-species acute systemic toxicity assessment is fundamental for chemical classification, labelling and risk management. Here, the authors propose a machine learning paradigm, Adjoint Correlation L...
doi.org
July 7, 2025 at 3:16 PM
qchengx1e3.bsky.social
Binarized gene expression data can be concatenated with chromatin accessibility data for effective and integrated cell clustering @zhengdy.bsky.social @einsteinmededu.bsky.social #BiotechNatureComms

doi.org/10.1038/s414...
Facilitate integrated analysis of single cell multiomic data by binarizing gene expression values - Nature Communications
Individual data types in a single cell multi-omic assay are often processed and clustered independently before combined for further analysis. Here, authors showed that binarized gene expression d...
doi.org
July 7, 2025 at 3:15 PM
qchengx1e3.bsky.social
A virtual single-cell NFκB signalling networks that recapitulate heterogenous experimental stimulus-response dynamics @xiaoluguo.bsky.social #BiotechNatureComms

doi.org/10.1038/s414...
Modeling heterogeneous signaling dynamics of macrophages reveals principles of information transmission in stimulus responses - Nature Communications
To develop virtual cells, mathematical models must account for the heterogeneity of single cells. Here, authors develop virtual single cell NFκB signalling networks that recapitulate heterogenous expe...
doi.org
July 7, 2025 at 3:13 PM
qchengx1e3.bsky.social
DOLPHIN: a deep learning method that enables exon- and junction-level analysis to improve cell representation and detect alternative #splicing. Ding Lab junding.lab.mcgill.ca #BiotechNatureComms

doi.org/10.1038/s414...
Ding Lab
website description
junding.lab.mcgill.ca
July 7, 2025 at 3:09 PM
qchengx1e3.bsky.social
A deep learning and immune-fluorescence-guided cell labelling method for accurate cell pattern identification. #BiotechNatureComms

doi.org/10.1038/s414...
Automated cell annotation and classification on histopathology for spatial biomarker discovery - Nature Communications
Histopathology is essential for diagnosing cancer, but cell annotation remains unreliable and inefficient. Here, authors develop a method using deep learning and immune-fluorescence-guided cell labell...
doi.org
July 7, 2025 at 3:08 PM
qchengx1e3.bsky.social
Cell Marker Accordion is a user-friendly platform providing robust automatic cell annotation of #single_cell and spatial populations @rdds-lab.bsky.social #BiotechNatureComms

doi.org/10.1038/s414...
Cell Marker Accordion: interpretable single-cell and spatial omics annotation in health and disease - Nature Communications
Accurate cell type annotation is a major challenge in single-cell and spatial omics. Here, authors present a user-friendly platform providing robust automatic annotation and enhanced biological interp...
doi.org
July 7, 2025 at 3:08 PM
qchengx1e3.bsky.social
A Bayesian optimisation-based iterative experimental design framework that integrates data generation, modelling, and optimisation to accelerate cell culture media development #BiotechNatureComms

doi.org/10.1038/s414...
Accelerating cell culture media development using Bayesian optimization-based iterative experimental design - Nature Communications
Optimising operational conditions for biological systems is a complex task. Here, authors present a Bayesian optimisation-based iterative experimental design framework that integrates data generation,...
doi.org
July 7, 2025 at 3:05 PM
qchengx1e3.bsky.social
A multiplexed super-resolution imaging protocol studies how nuclear proteins are distributed relative to each other from the micro to the nanoscale. #BiotechNatureComms

doi.org/10.1038/s414...
Mapping the nuclear landscape with multiplexed super-resolution fluorescence microscopy - Nature Communications
The cell nucleus coordinates diverse functions. Here, the authors utilise multiplexed super-resolution imaging to study how nuclear proteins are distributed relative to each other from the micro to th...
doi.org
July 7, 2025 at 3:05 PM
qchengx1e3.bsky.social
CellFM: A 800-million-parameter foundation model pre-trained on transcriptomics of 100 million human cells. #BiotechNatureComms @natcomms.nature.com

www.nature.com/articles/s41...
CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells - Nature Communications
Single-cell sequencing reveals cellular heterogeneity but is challenged by technical noise and batch effects. Here, authors present CellFM, an 800-million-parameter foundation model trained on 100 mil...
www.nature.com
May 28, 2025 at 2:33 PM
qchengx1e3.bsky.social
Kasumi identifies local patterns in tissue patches in spatial omics data @tanevski.bsky.social, @saezlab.bsky.social #BiotechNatureComms

www.nature.com/articles/s41...
Learning tissue representation by identification of persistent local patterns in spatial omics data - Nature Communications
Spatial omics reveal tissue structures and can aid patient stratification. The authors present a method to identify patterns in tissue patches, enabling analysis of disease progression and treatment r...
www.nature.com
May 8, 2025 at 1:30 PM
qchengx1e3.bsky.social
A data-efficient, generative AI-based toolkit for designing a diverse set of RNA molecules. #BiotechNatureComms

www.nature.com/articles/s41...

alexgreenlab.org
Green Laboratory
Visit the post for more.
alexgreenlab.org
May 8, 2025 at 1:30 PM
qchengx1e3.bsky.social
@pranam.bsky.social  present FusOn-pLM, which uses dynamic masking to outperform baselines in fusion-specific tasks and predict drug-resistant mutations
#BiotechNatureComms

www.nature.com/articles/s41...
FusOn-pLM: a fusion oncoprotein-specific language model via adjusted rate masking - Nature Communications
Fusion oncoproteins drive paediatric cancers but are challenging to target due to their intrinsic disorder and lack of druggable pockets. Here, authors present FusOn-pLM, trained on FusOn-DB, which us...
www.nature.com
February 11, 2025 at 7:37 AM
qchengx1e3.bsky.social
Authors introduce a practical training framework to improve protein language model representations by integrating biological features and prior information through contrastive learning. #BiotechNatureComms
www.nature.com/articles/s41...
Contrastive-learning of language embedding and biological features for cross modality encoding and effector prediction - Nature Communications
Identifying and characterizing secreted virulence proteins are fundamental for deciphering microbial pathogenicity. Here, the authors introduce a practical training framework to improve protein langua...
www.nature.com
February 4, 2025 at 10:39 AM
qchengx1e3.bsky.social
.@jiyang_yu @StJudeResearch introduce new methods for cell type deconvolution and scRNA-seq data normalisation. #BiotechNatureComms
www.nature.com/articles/s41...
Transcriptome size matters for single-cell RNA-seq normalization and bulk deconvolution - Nature Communications
Existing cell type deconvolution methods, crucial for studying tumour environments, overlook some critical issues. Here, authors analyse how these issues impact on deconvolution and develop methods to...
www.nature.com
February 4, 2025 at 10:38 AM
qchengx1e3.bsky.social
SIMO maps diverse single-cell modalities, including RNA, chromatin accessibility, and DNA methylation, onto spatial tissues. #BiotechNatureComms
www.nature.com/articles/s41...
Spatial integration of multi-omics single-cell data with SIMO - Nature Communications
Existing tools face limitations in integrating spatial data with single-cell multi-omics datasets. Here, authors introduce a computational tool that maps diverse single-cell modalities, including RNA,...
www.nature.com
February 4, 2025 at 10:37 AM
qchengx1e3.bsky.social
MetaQ is a metacell algorithm that supports both uni- and multi-omics data for large-scale single-cell data analyses. 
#BiotechNatureComms
www.nature.com/articles/s41...
MetaQ: fast, scalable and accurate metacell inference via single-cell quantization - Nature Communications
Large-scale single-cell sequencing data brings computational barriers for downstream analysis. Here, the authors propose MetaQ, a metacell algorithm that reduces cell number while preserving biologica...
www.nature.com
February 4, 2025 at 10:37 AM
qchengx1e3.bsky.social
Celina detects cell type-specific spatially variable genes in spatial transcriptomics, offering insights into the transcriptomic mechanism underlying cellular heterogeneity. #BiotechNatureComms
www.nature.com/articles/s41...
Statistical identification of cell type-specific spatially variable genes in spatial transcriptomics - Nature Communications
The authors develop Celina to detect cell type-specific spatially variable genes (ct-SVGs) in spatial transcriptomics. These ct-SVGs exhibit distinct spatial expression patterns within specific cell t...
www.nature.com
February 4, 2025 at 10:36 AM
qchengx1e3.bsky.social
The geigerlab provide the open-source 3D-cell-image analysis platform #CellDetail for quantitative spatial distribution analyses. #BiotechNatureComms

www.nature.com/articles/s41...
Quantitative determination of the spatial distribution of components in single cells with CellDetail - Nature Communications
Tools to determine the spatial distribution of components and their networks inside cells are not well developed. Here, authors provide the open-source 3D-cell-image analysis platform Cell Detection a...
www.nature.com
December 6, 2024 at 8:10 AM
qchengx1e3.bsky.social
PREVENT learns both the sequence and thermodynamic landscape of a protein and generates new functional variants. #BiotechNatureComms

www.nature.com/articles/s41...
Protein engineering using variational free energy approximation - Nature Communications
Generative deep learning models can generate novel proteins, but these are often not functional due to thermodynamic instability. Here, authors present a method to learn both the sequence and thermody...
www.nature.com
December 6, 2024 at 8:09 AM