The front page of AI-driven biology
Thursday, October 15, 2026Thu, Oct 15
Updated 7:01 PM PT
Researchers at MIT's Picower Institute found that the Alzheimer's risk variant APOE4 impairs myelination by suppressing Wnt signaling in oligodendrocytes, the brain cells responsible for insulating nerve fibers.
HitSV combines repeat-aware breakpoint detection with haplotype-resolved local DNA assembly to identify structural genomic variants across multiple sequencing platforms.
A combined statistical and neural-network method accurately infers anomalous diffusion parameters from noisy single-particle tracks.
A computational model called SVC treats subcellular RNA transcript locations as image patches, using surrounding molecules to predict where individual genes localize within single cells.
Neuroscientists developed LightSuite, an open-source image-processing framework that automates large-scale 3D anatomical alignment and single-cell detection across the central nervous system.
SpatialZoomer uses spectral graph theory to analyze spatial transcriptomics data simultaneously at individual cell resolution and across broad tissue domains.
CloneOT uses lineage tracing to learn custom cost functions for neural optimal transport, predicting how individual cancer clones change after therapeutic perturbation.
A new open-source simulator called ALBIS generates synthetic spatial transcriptomics datasets from simulated 3D tissues, providing an explicit molecular ground truth for benchmarking spatial analysis algorithms.
Researchers developed EcoNet, a deep-learning model using graph attention networks that predicts patient response to immunotherapy by modeling cell-cell signaling circuits inside the tumor microenvironment.
A computational framework named SPACER extracts gene-level recruitment rules directly from spatial transcriptomics data to explain how tissues attract specific cell types.
A computational tool called scMOCHA recovers mitochondrial DNA variants and heteroplasmy directly from standard single-cell RNA sequencing datasets.
Researchers built BioMod, a 50-million-parameter single-cell model trained on roughly 73 million human cells using 660 curated pathways and gene programs rather than thousands of individual genes as its basic input tokens.
Researchers have developed Scellmate, a computational framework designed to filter contamination and analyze large datasets of single-amplified genomes from single-cell microbial sequencing.
Benchmarking cell representations from four single-cell foundation models across 868 disease-prediction tasks and 65 cell-type datasets showed that standard log-normalized gene counts match or outperform the best model, TranscriptFormer-Sapiens, when full training data is available.
Benchmarking four major single-cell foundation models across cell-type and perturbation tasks revealed that intermediate layers frequently match or outperform the final layer representations standardly used in downstream biology.
Researchers have adapted a video-segmentation foundation model, named ETSAM, to accurately map cell membranes within noisy 3D cryo-electron tomograms.
Computational biologists introduced NetMap, a software pipeline that jointly infers single-cell gene regulatory networks and clusters cell populations without needing pre-assigned cell annotations.
EpiDiff uses machine learning on DNA methylation data to produce a continuous numerical score of cellular differentiation across single-cell, sorted, and bulk tissue samples.
A new evaluation framework named Cause-excluded Effect Evaluation exposes that previous single-cell target discovery benchmarks were inflated by data leakage and by leaking the target gene's own expression.
Scientists measured the functional impact of 186,676 protein variants across 17 enzymes in the RAS-MAPK signaling cascade, generating 503,099 total cellular readouts.
Researchers developed Droplet-MT, a microfluidic method that profiles the transcriptome and DNA methylation together across roughly 10,000 single cells per run.
Researchers combined two deep-learning approaches to overcome light-induced damage and slow acquisition in RESOLFT super-resolution microscopy.
Researchers developed DEPICT, a deep learning model trained on 231,880 cell line-drug pairs across 941 cancer cell lines and 289 compounds to rank which therapies work best inside a specific patient tumor profile.
A new cell-tracking framework uses human-in-the-loop feedback to propagate manual corrections across an entire live-microscopy dataset rather than editing one track at a time.
A computational pipeline called EpiFLAIR integrates long-read Oxford Nanopore sequencing of chromatin fibers, nascent RNA, and mature transcripts in yeast.
Researchers combined single-nucleus RNA sequencing across 413,697 nuclei with spatial transcriptomics in 56 lung sections to trace the progression of lung adenocarcinoma from early lesions to invasive cancer.
Genentech researchers developed CellMAPP and an analytical framework called CHART to track organelle changes across 524 genetic knockdowns in breast cancer cells.
Researchers built SpatialOmicsLab, an evaluation suite combining 113 analytical tools, 63 reference datasets, and 4,614 task specifications for spatial transcriptomics, alongside an AI agent named ST-Coscientist designed to assemble and run those workflows.
Two companion papers in Science and Cell report using synthetic DNA recording platforms, including DNA Typewriter, to reconstruct cell lineage trees from a fertilized egg through late organogenesis in mice.
Researchers developed VINTER, a generative vision-language model trained on 1.45 million histology-caption pairs that jointly processes tissue morphology, local gene counts, and spatial neighborhoods.