What happened
Motivation: MicroRNA-target interaction prediction remains challenging because many existing tools provide prediction scores or ranked candidate lists without making the supporting evidence easy to interpret or relate to a specific biological context. Results: Here, we developed miRAssist, a context-aware evidence-integration framework for interpretable miRNA-target prioritization. miRAssist integrates six evidence families, including sequence complementarity, thermodynamic stability, sequence conservation, target-site accessibility, functional binding, and functional repression. A sequence-defined candidate universe was generated, resulting in 280,917 candidate interactions. Using miRTarBase-supported interactions as known-positive labels, six supervised scoring approaches were evaluated using a grouped train/test split by miRNA. Random forest showed the strongest performance and was selected. miRAssist also produced stronger known-positive enrichment than established miRNA-target prediction models in the evaluated benchmark. An LLM-assisted interface further supports natural-language database querying and evidence-grounded summarization of prioritized candidates. Update (2026-09-20): Language-Model-Based Detection of Genetic Editing in Bacteria . Recent advances in genome editing allow easy genetic manipulation of bacteria, providing them with new traits, some of which could be hazardous, e.g. enhanced virulence or extended resistance to antibiotics. The ability to detect artificially modified bacteria is crucial for identifying potential bio-threats. However, malicious genome editing could be challenging to trace due to the natural exchange of genes among bacteria through horizontal transfer. After curating extensive datasets including natural genomes and simulated edited genomes, we utilized a natural language processing approach to detect edited genomes. We developed a transformer-encoder-based machine-learning classifier that, instead of analyzing words in sentences, models gene families in genomes. After training the model on our datasets, it is able to accurately detect genes artificially added to bacterial genomes due to their unnatural context. Our approach provides a scalable method for identifying engineered sequences without relying on specific marker genes, with potential applications in biosecurity, agriculture, GMO regul Update (2026-09-23): Generative Access to Make-on-Demand Chemical Space Enables Ultra-Large Virtual Screening . Ultra-large-scale virtual screening (ULVS) increasingly relies on make-on-demand chemical spaces, but efficient access to these spaces remains challenging because their scale far exceeds what can be exhaustively enumerated and docked. Here, we present REAL-SWIT, a generative ULVS framework that learns Enamine REAL Space as a synthesizable molecular distribution and couples this generator with a target-specific scoring model to enable docking-guided exploration of REAL Space at the level of complete molecule. The generative model learned transferable features of the REAL Space distribution: approximately 96% of generated molecules were found in REAL Space, and a subset of generated molecules absent from the training release appeared in later expanded releases. In computational benchmarks, REAL-SWIT identified more molecules with favorable docking scores than representative fragment-based search strategies, including cooperative building-block combinations that fragment-level prioritization tended to miss. Experimental validation for ROCK1 yielded six biochemical inhi Update (2026-09-23): NoroScope: Exploring the Mutational Landscape of the Human Norovirus Capsid Protein with Context-Aware Machine Learning . Anticipating the effects of mutations in viral proteins is important for the development of therapeutics and control strategies but remains challenging as mutation phenotypes are shaped by complex overlapping sequence, structural and evolutionary constraints. Machine-learning approaches to mutation-effect prediction have shown considerable success for viruses with exceptionally rich training datasets, but their application to the majority of viruses with comparatively limited data remains underexplored. Here we introduce NoroScope, an interpretable machine-learning framework designed to prioritise plausible amino-acid substitutions in the human norovirus GII.4 capsid protein VP1 through integration of complementary biological evidence. Using VP1 protein sequences and experimentally resolved structures as a foundation, we generated datasets comprising zero-shot mutation scores from the Evolutionary Scale Modeling 2 protein large language model, in silico deep-mutational-scanning estimates of mutation-associated effects on protein stabil