The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 6:32 PM PT
BiomiX 3.0 adds four integration methods to its biological data analysis platform, including PRAMIGO, a new supervised model that uses graph neural networks to connect different molecular measurement layers.
Researchers generated an atlas of 459,856 single-nucleus gene expression and chromatin accessibility profiles across 21 adult human tissues from four donors, pinpointing over one million candidate regulatory elements.
ProteoScopeR is an open-source R package and Shiny web tool designed to run reproducible method comparisons across quantitative mass spectrometry datasets.
Researchers combined the dimension-reduction tool iNETgrate with harmonic persistent homology, a mathematical method that maps the shape of complex data, to rank disease-relevant genes across gene expression and DNA methylation layers.
Researchers built fastACCORD, a GPU-accelerated statistical framework that computes partial correlation networks across more than 300,000 multi-omic molecular features at once.
Researchers at the Helmholtz Center Munich built Crecerelle, a variational autoencoder that combines gene expression and alternative RNA splicing data to classify single cells.
Researchers have developed Brain Landscape In Situ Crosslinking Mass Spectrometry, or BLIS-XL-MS, to profile proteome-wide protein conformational shifts and complex remodeling directly in intact brain tissue.
Researchers designed DePass, a graph learning framework that combines paired single-cell and spatial multi-omics data using an iterative denoising process.
A combined imaging workflow links Xenium spatial transcriptomics with iterative indirect immunofluorescence imaging on the same section of preserved human brain tissue.
The funding supports clinical expansion for two lead oral small molecules, including mid-stage trials of ENV-294 in atopic dermatitis and asthma after early data showed an 85% symptom reduction by Day 42.
The German drugmaker added over $250 million in potential upfront, license, and milestone payments to tap Variant's machine-learning platform for cardiovascular drug targets.
Traffickome maps 754 transport proteins into 11 directed transitions across seven cellular compartments to infer where transmembrane cargo moves using standard proteomic profiles.
A spatial multi-omics study tracking over 112 million cells across three melanoma neoadjuvant immunotherapy regimens revealed that mature tertiary lymphoid structures with germinal centers, sustained by specialized fibroblast scaffolds, distinguish responders from non-responders.
Researchers applied a sparse machine learning workflow using Stabl and LASSO regression to analyze 45,000 cord blood features in a cohort of 217 infants at risk for bronchopulmonary dysplasia, a chronic lung condition affecting premature babies.
Researchers built OpenLipid, a workflow that uses large language models to identify target lipids from data-independent acquisition mass spectrometry.
Scientists developed MMAD-Risk, a multivariate survival model designed to predict long-term risk across 271 diseases simultaneously from blood plasma proteomic profiles.
The immgenT consortium developed immgenT-GP, a computational framework that deconvolves roughly 800,000 mouse T cells into 200 distinct, reproducible gene expression programs.
Combining a metastatic colonization score called MetScore with standard classical-basal tumor subtypes better predicts patient survival and chemotherapy response in pancreatic ductal adenocarcinoma than the single-subtype model alone.
A multiomics study published in Cell Reports Medicine by researchers at the Icahn School of Medicine at Mount Sinai mapped distinct tumor biology across developmental stages and sex in high-grade brain cancer.
A new generative method called high-dimensional adversarial random forests (h-ARF) synthesizes tabular molecular profiles to supplement small biological sample cohorts from hard-to-access tissues.
The Mayo Clinic and Thermo Fisher Scientific have launched Precure LLC, a joint venture built to assemble large-scale datasets combining genomic, proteomic, and longitudinal clinical records.
Profiling 384 plasma proteins across 62 untreated HIV elite controllers revealed that a distinct subset of 9 individuals has inflammatory profiles matching people without HIV.
A deep neural network evaluated 274,959 clinical lentiviral integration sites across 10 patients treated for severe combined immunodeficiency (SCID-X1) to examine where vectors insert into human DNA.
InstaNovo-FM is a self-supervised transformer model for bottom-up proteomics trained to interpret peptide mass fragmentation spectra across varying lab instruments and protocols.