Prokaryotic genomes encode a vast repertoire of noncoding elements such as ribozymes, riboswitches, and CRISPR RNAs. Here, we show that a genomic language model fine-tuned on prokaryotic intergenic sequences learns representations of noncoding elements from DNA sequence.
We developed Bolero, a sequence-to-function model whose parameters condition on atlas-scale cell-state embeddings and additional biological variables to predict cell-state-specific chromatin accessibility and transcript abundance from DNA.
RNA-binding proteins control post-transcriptional gene expression by regulating RNA processing, localization, stability, and translation. Here we introduce a high-throughput CLIP-seq platform that combines endogenous protein tagging for uniform affinity capture with ligation-free library preparation to generate high-resolution RNA-protein binding profiles.
The genetic code is decoded by a highly redundant transfer RNA (tRNA) repertoire. Here, we establish an atlas of tRNA dependencies through large-scale CRISPRi perturbation mapping across matched in vivo tumor growth and in vitro cell culture for 16 cancer cell lines spanning seven tissue types.
Predicting cellular response to perturbations is key to understanding biological mechanisms and selecting therapeutic targets. Here, we introduce PIE, a model that addresses these limitations by reformulating the learning task around population level perturbation effects and incorporating auxiliary inputs that better characterize the biological system.
Neuroinflammation drives neurodegeneration and cognitive decline in aging, but the signals that spread this inflammation across the CNS remain unclear. Here, we show in mice that advanced age and experimental autoimmune encephalomyelitis both result in elevated cytosolic mtDNA in microglia.
Microbial genomes encode essential ncRNAs and nucleic-acid-interacting proteins. However, discovery of these systems remains based on similarity to known sequences. Here, we introduce Minerva, a framework for coevolutionary mining that uses genome language models to predict pairwise interactions directly from sequence.
Tahoe-100M, generated by Tahoe, is a giga-scale single-cell perturbation atlas comprising 100 million transcriptomes from 50 diverse cancer cell lines treated with 1,100 drug-dose conditions. This parallel profiling of thousands of perturbations at single-cell resolution with minimal batch effects is enabled by the Mosaic platform.
Here, we introduce scBaseCount, a database that leverages an AI agent to automate discovery and metadata extraction and standardize data processing. It is the largest public repository of single-cell gene expression data, comprising over 502 million cells across 27 organisms and 75 tissues.
The mechanism underlying the role of ENPP1 in metabolic disease remains unsolved. Using a 2′3′-cyclic GMP-AMP (cGAMP)-hydrolysis-deficient mouse (Enpp1H362A), we show that selective loss of this activity exacerbates high-fat diet (HFD)-induced weight gain and insulin resistance.