CRISPR screens coupled with single-cell RNA sequencing are transforming high-throughput functional genomics. However, applications in vivo remain limited and are confounded by difficulties in identify...

npj Precision Oncology - The hegemonic EWSR1::ETS oncoprotein overrules core regulatory circuitry principles in Ewing sarcoma

RNA modifications dynamically regulate cancer hallmarks. Deng et al. summarize how epitranscriptomic marks (e.g., m6A, m5C, Ψ, and A-to-I editing) orchestrate tumor proliferation, stemness, metabolism, immune evasion, and therapy resistance. Emerging detection, single-cell mapping, and therapeutic targeting strategies position RNA epitranscriptomics as a new frontier in cancer biology and treatment.

This analysis performs comprehensive comparisons of 27 single-cell perturbation response prediction methods using 29 datasets under different test scenarios and against multiple evaluation metrics.

The clinical development of novel cancer therapeutics is rapidly evolving with the integration of molecular biomarkers to advance precision medicine. Circulating tumor DNA (ctDNA) represents a versatile tool to detect targetable alterations, predict therapeutic response, monitor tumor evolution, and inform pharmacokinetic and pharmacodynamic effects. This could accelerate early phase drug development and deepen understanding of biological drivers of response and resistance. Herein, we highlight current applications and future opportunities for ctDNA as a multi-utility biomarker in early phase clinical trials.

This Perspective overviews recent and emerging developments in building and using multimodal foundation models based on transformers for analyzing various types of genomics data.

This Perspective reviews computational methods for cross-species knowledge transfer and introduces ‘agnology’, a data-driven concept of functional equivalence independent of evolutionary origin.

Nature Biotechnology - Exploring the use of AI authors and reviewers at Agents4Science

Novae, a self-supervised graph attention network, is a foundation model excelling at a diverse spectrum of spatial transcriptomics modeling and analysis tasks.

Virtual cells based on artificial intelligence models are on the horizon

Artificial intelligence agents may have a transformative effect on how biological research is performed.

This Review summarizes current and emerging liquid biopsy methods, together with their clinical validity and utility, and highlights opportunities to support their implementation throughout the cancer care continuum.

Approaches combining genetic association and Perturb-seq data that link genetic variants to functional programs to traits are described.

GigaTIME leverages multimodal AI to generate virtual multiplex immunofluorescence (mIF) profiles from standard H&E slides, enabling comprehensive tumor immune microenvironment modeling across a large (>14,000) and diverse patient population. This virtual approach unlocks new opportunities for large-scale clinical discoveries that were previously hindered by the scarcity of mIF data.

Today, medical research builds up an understanding of the whole from molecular parts, but artificial intelligence can revive an approach building down from patient-level data to theory and understa...

A lightweight AI method called Scouter that predicts genome-wide transcriptional responses to single- and two-gene perturbations using large language model embeddings is presented and achieves substan...