Add BrightSurf on Google Email

Integration of single-cell multiomics data allows a more precise identification of rare cell types and states

Researchers developed an interpretable machine learning algorithm, scOMM, to classify cell types consistently across different single-cell methods. The integration strategies and scOMM establish a robust approach for cell atlas generation in complex tissues, leading to the discovery of previously undetected rare cell types.

SourceJosep Carreras Leukaemia Research Institute·JournalGenome Biology·TypeExperimental study·DateMar 31, 2026

Deep learning model predicts how individual cells influence disease outcomes

A computational method called scSurv links individual cells to patient outcomes using bulk RNA sequencing data, identifying cell populations associated with survival across several cancers. The model estimates the contributions of over 10,000 individual cells to disease risk and prognosis, providing a foundation for precision medicine.

SourceInstitute of Science Tokyo·JournalBioinformatics·TypeData/statistical analysis·DateMar 20, 2026

New computational biology tool automates and standardizes genome sequencing analysis

A new tool, metapipeline-DNA, automates and standardizes genome sequencing analysis, reducing the complexity of large and complicated data. The open-access resource, developed by Sanford Burnham Prebys and the University of California Los Angeles, aims to improve collaboration and reproducibility across research labs.

SourceSanford Burnham Prebys·JournalCell Reports Methods·TypeExperimental study·DateMar 17, 2026

New biomarker predicts chemotherapy response in triple-negative breast cancer

Researchers developed a new computational approach to predict chemotherapy response in triple-negative breast cancer, outperforming current methods. The TmS biomarker accurately sorts patients into those with favorable or poor prognosis, highlighting its potential as an effective starting point for patient stratification.

SourceUniversity of Texas M. D. Anderson Cancer Center·JournalCell Reports Medicine·DateFeb 17, 2026

Turning down the heat

A University of Houston professor has found that tree-like thin films release heat at least three times better than traditional methods, enabling more efficient cooling in AI data centers. The discovery demonstrates the power of physics-aware AI design for validating high-impact cooling solutions.

SourceUniversity of Houston·JournalInternational Journal of Heat and Mass Transfer·DateFeb 12, 2026

A systematic review organises available omics data on pituitary tumours

A recent systematic review has compiled and catalogued publicly available omics data on pituitary tumours, highlighting the need for standardisation and clinical annotation. The resulting catalogue facilitates the reuse of data for future research projects and precision medicine initiatives.

SourceGermans Trias i Pujol Research Institute·JournalMachine Learning and Knowledge Extraction·TypeSystematic review·DateFeb 2, 2026

Vaping zebrafish suggest E-cigarette exposure disrupts gut microbial networks and neurobehavior

A study published in Science of The Total Environment found that e-cigarette exposure alters gut microbiota composition and affects neurobehavior in zebrafish. The researchers observed disruptions in the gut microbiome, with reduced microbial network stability and altered community composition, suggesting potential health risks.

SourceKyushu University·JournalScience of The Total Environment·TypeExperimental study·DateJan 29, 2026

Using AI to uncover the secret lives of fungi

A new study using AI-powered BioBERT model accurately identifies fungal lifestyles, switching between helpful partner for plants to aggressive decomposers. The tool has nearly 90% accuracy and can scan thousands of papers in minutes, flagging species that may switch roles.

SourceNorthern Arizona University·JournalResearch Ideas and Outcomes·TypeComputational simulation/modeling·DateJan 28, 2026

An AI-guided framework reveals conserved features governing microRNA strand selection

Researchers have decoded the logic of microRNA strand selection using AI, revealing a conserved and programmable mechanism governing gene regulation. The study found that this decision follows conserved rules rather than chance, with mammalian microRNAs showing a strong bias towards a single dominant strand.

SourceArizona State University·JournalNucleic Acids Research·TypeExperimental study·DateJan 14, 2026

Vitamin C may help protect fertility from a harmful environmental chemical

Researchers found that male fish exposed to vitamin C and potassium perchlorate showed improved fertility and less damage to their testes compared to those exposed only to the chemical. The study suggests a potential safeguard for individuals regularly exposed to these chemicals, including military personnel.

SourceUniversity of Missouri-Columbia·JournalEnvironmental Science & Technology·TypeExperimental study·DateJan 6, 2026

New video dataset to advance AI for health care

Researchers have launched a new multimodal medical dataset, Observer, capturing anonymized, real-time interactions between patients and clinicians. The dataset links video, audio, transcripts, and electronic health records to study subtleties like body language and environmental factors affecting care.

SourceUniversity of Pennsylvania School of Engineering and Applied Science·JournalJournal of the American Medical Informatics Association·TypeExperimental study·DateDec 16, 2025

Who is more likely to get long COVID?

Researchers have identified 32 causal genes that increase the likelihood of developing long COVID, including 13 new genes not previously associated with the disease. The study's findings could lead to more precise diagnoses and treatment options for the condition, which affects an estimated 400 million people worldwide.

SourceUniversity of South Australia·JournalPLOS Computational Biology·TypeData/statistical analysis·DateDec 15, 2025

Refining the uncharted landscape of human transcription factors: a strategic framework for future prioritization

A study analyzed large-scale human ChIP-seq data to identify unmeasured transcription factor-tissue/cell type pairs, revealing significant gaps in current knowledge. These findings indicate that essential regulatory mechanisms may have been overlooked, emphasizing the need for strategic prioritization of measurement targets.

SourceUniversity of Tsukuba·JournalBriefings in Functional Genomics·DateDec 15, 2025

Rohan Chand Sahu from Indian Institute of Technology (IIT) explores AI-powered nanomedicine: Machine learning redefines precision cancer drug delivery

Machine learning (ML) streamlines nanomedicine development by predicting nanoparticle parameters and optimizing drug release profiles. ML models can personalize therapeutic regimens for individual patients, addressing longstanding challenges in cancer therapy.

SourceFAR Publishing Limited·JournalMed Research·TypeLiterature review·DateDec 2, 2025

Predicting how bones heal

An international team led by Lehigh University researcher Hannah Dailey is building predictive models to understand and eventually prevent bone healing complications. The team aims to incorporate biological differences into the model, using a library of imaging data from Switzerland's AO Research Institute Davos.

Computational deep dive surfaces unexplored world of cancer drug targets

A new computational tool called DeepTarget predicts direct and indirect targets of cancer drugs, revealing that small molecules can have different targets and effects depending on the disease and cell type. The study demonstrates the tool's superior performance in real-world scenarios, highlighting its potential to accelerate drug deve...

SourceSanford Burnham Prebys·Journalnpj Precision Oncology·TypeComputational simulation/modeling·DateNov 14, 2025

New software tool MARTi fast-tracks identification and response to microbial threats

MARTi enables rapid taxonomic classification and abundance analysis of microorganisms in various settings, including agriculture, environmental monitoring, and clinical environments. The tool provides immediate analysis results, allowing for quick identification and targeted treatments of pathogen infections.

SourceEarlham Institute·JournalGenome Research·TypeComputational simulation/modeling·DateOct 27, 2025

Szeged researchers accelerate personalized medicine with AI-powered 3D cell analysis

Researchers at HUN-REN Szegedi Biológiai Kutatóközpont have developed an AI-powered platform for automated 3D cell culture analysis, enabling high-precision screening of cellular models. The technology removes the limitation of throughput in personalized medicine, allowing for fast and accurate analysis of clinical samples.

SourceHUN-REN Szegedi Biológiai Kutatóközpont·JournalNature Communications·DateOct 21, 2025

Learning the language of lasso peptides to improve peptide engineering

A new large language model, LassoESM, has been developed to predict lasso peptide properties, enabling the acceleration of rational design for biomedical applications. The model was trained on thousands of lasso peptide sequences and demonstrated accurate prediction of various properties.