UniPert-G2CP is a two-stage deep learning framework that unifies multimodal molecular perturbagen representations to enable genetic-to-chemical perturbation phenotype transfer learning. Validated on large-scale genetic and chemical screening datasets, it supports simulation of multicellular and multidomain perturbation cause-effect spaces, and joint analysis of these spaces reveals cellular heterogeneity underlying drug responses. It offers a route toward unified modeling of genetic and chemical screens within the artificial intelligence virtual cell vision.
MetaSBT is a k-mer-based framework that uses Sequence Bloom Trees to incrementally cluster large collections of microbial reference genomes and metagenome-assembled genomes into taxonomy-aware groups, avoiding the fixed genetic-distance thresholds used by existing methods. The authors built and validated MetaSBT databases on publicly available viral genomes, used them to improve quantitative taxonomic profilers' detection of still-unknown viral species, and integrated the framework into the Galaxy platform.
Yi Chengqi's group at Peking University and collaborators published a study in Nature describing ContactSeek, an AI framework based on AlphaFold3 contact probabilities that systematically identifies amino acid residues determining editing specificity in base editors. The work combined AlphaFold3-predicted contact probabilities with off-target editing data from high-throughput sequencing, then engineered Cas proteins and deaminases accordingly, markedly improving editing specificity and establishing a new paradigm for precision design of gene-editing tools.
Why it matters: The coupling of AlphaFold3 contact probabilities with high-throughput off-target data can be transferred to specificity engineering of other base editors or Cas proteins.
A spatial CRISPR screening sequencing technology called SPAC-seq, developed jointly by Peking University, Tsinghua University and BGI, is featured on the cover of Cell. The work includes TARDIS, a statistical framework that links genetic perturbations to spatial phenotypes and the cellular microenvironment, enabling spatially resolved functional genomics research.
Why it matters: SPAC-seq couples CRISPR screening with spatial transcriptomics, and the TARDIS framework lets researchers dissect gene function across tissue locations in situ.
