Toward subtask-decomposition-based learning and benchmarking for predicting genetic perturbation outcomes and beyond.

Deciphering cellular responses to genetic perturbations is fundamental for a wide array of biomedical applications. However, there are three main challenges: predicting single-genetic-perturbation outcomes, predicting multiple-genetic-perturbation outcomes and predicting genetic outcomes across cell lines. Here we introduce Subtask Decomposition Modeling for Genetic Perturbation Prediction (STAMP), a flexible artificial intelligence strategy for genetic perturbation outcome prediction and downstream applications. STAMP formulates genetic perturbation prediction as a subtask decomposition problem by resolving three progressive subtasks in a problem decomposition manner, that is, identifying postperturbation differentially expressed genes, determining the expression change directions of differentially expressed genes and finally estimating the magnitudes of gene expression changes. STAMP exhibits a substantial improvement over the existing approaches on three subtasks and beyond, including the ability to identify key regulatory genes and pathways on small samples and to reveal precise genetic interactions of diverse types.

Unified cross-modality integration and analysis of T cell receptors and T cell transcriptomes by low-resource-aware representation learning.

Single-cell RNA sequencing (scRNA-seq) and T cell receptor sequencing (TCR-seq) are pivotal for investigating T cell heterogeneity. Integrating these modalities, which is expected to uncover profound insights in immunology that might otherwise go unnoticed with a single modality, faces computational challenges due to the low-resource characteristics of the multimodal data. Herein, we present UniTCR, a novel low-resource-aware multimodal representation learning framework designed for the unified cross-modality integration, enabling comprehensive T cell analysis. By designing a dual-modality contrastive learning module and a single-modality preservation module to effectively embed each modality into a common latent space, UniTCR demonstrates versatility in connecting TCR sequences with T cell transcriptomes across various tasks, including single-modality analysis, modality gap analysis, epitope-TCR binding prediction, and TCR profile cross-modality generation, in a low-resource-aware way. Extensive evaluations conducted on multiple scRNA-seq/TCR-seq paired datasets showed the superior performance of UniTCR, exhibiting the ability of exploring the complexity of immune system.

CiTSA: a comprehensive platform provides experimentally supported signatures of cancer immunotherapy and analysis tools based on bulk and scRNA-seq data.

Immunotherapy has greatly changed the status of cancer treatment, and many patients do not respond or develop acquired resistance. The related research is blocked by lacking of comprehensive resources for researchers to discovery and analysis signatures, then further exploring the mechanisms. Here, we first offered a benchmarking dataset of experimentally supported signatures of cancer immunotherapy by manually curated from published literature works and provided an overview. We then developed CiTSA ( http://bio-bigdata.hrbmu.edu.cn/CiTSA/ ) which stores 878 entries of experimentally supported associations between 412 signatures such as genes, cells, and immunotherapy across 30 cancer types. CiTSA also provides flexible online tools to identify and visualize molecular/cell feature and interaction, to perform function, correlation, and survival analysis, and to execute cell clustering, cluster activity, and cell-cell communication analysis based on single cell and bulk datasets of cancer immunotherapy. In summary, we provided an overview of experimentally supported cancer immunotherapy signatures and developed CiTSA which is a comprehensive and high-quality resource and is helpful for understanding the mechanism of cancer immunity and immunotherapy, developing novel therapeutic targets and promoting precision immunotherapy for cancer.