Biology subjects

Cao, Z.-J.

Publications and source records attributed to Cao, Z.-J..

7 recordsLinked to original sources

bioRxiv2025

Causality-oriented regulatory inference and rational transcriptomic reprogramming design with CASCADE

Systematically elucidating the causal structure of gene expression regulation is the foundation for identifying key regulators of cellular function and designing rational interventions thereof. While advances in high-content perturbation screens enables experimental probing of causal regulatory effects, the massive genomic scale, measurement noise and confounding factors pose significant challenges for existing causal discovery and inference algorithms. Here, we present CASCADE, an end-to-end framework that integrates de novo causal discovery with prior regulatory knowledge for genome-wide causal discovery and inference. In addition to its superior performance on causal regulatory structure discovery and counterfactual inference for unseen perturbation effects, CASCADE enables, for the first time, causality-oriented rational intervention design for transcriptomic programming towards various targeted cells within a unified framework.

bioinformatics↗

bioRxiv2024

High-fidelity disentangled cellular embeddings for large-scale heterogeneous spatial omics via DECIPHER

The functional role of a cell, shaped by the sophisticated interplay between its molecular identity and spatial context, is often obscured in current spatial modeling. Aiming to model large-scale heterogeneous spatial data in silico properly, DECIPHER produces high-fidelity disentangled embeddings, not only achieving superior performance in systematic benchmarks, but also empowering various real-world applications. We further demonstrated that DECIPHER is scalable to atlas-scale datasets, enabling global analysis which is largely infeasible to current state-of-the-arts.

bioinformatics↗

bioRxiv2024

Learning phenotype associated signature in spatial transcriptomics with PASSAGE

Spatially resolved transcriptomics (SRT) is poised to advance our understanding of cellular organization within complex tissues under various physiological and pathological conditions at unprecedented resolution. Despite the development of numerous computational tools that facilitate the automatic identification of statistically significant intra-/inter-slice patterns (like spatial domains), these methods typically operate in an unsupervised manner, without leveraging sample characteristics like physiological/pathological states. Here we present PASSAGE (Phenotype Associated Spatial Signature Analysis with Graph-based Embedding), a rationally-designed deep learning framework for characterizing phenotype-associated signatures across multiple heterogeneous spatial slices effectively. In addition to its outstanding performance in systematic benchmarks, we have demonstrated PASSAGEs unique capability in identifying sophisticated signatures in multiple real-world datasets. The full package of PASSAGE is available at https://github.com/gao-lab/PASSAGE.

bioinformatics↗

bioRxiv2023

Spatial-linked alignment tool (SLAT) for aligning heterogenous slices properly

Spatially resolved omics technologies reveal the spatial organization of cells in various biological systems. Integrative and comparative analyses of spatial omics data depend on proper slice alignment, which should take both omics profiles and spatial context into account. Here we propose SLAT (Spatially-Linked Alignment Tool), a graph-based algorithm for efficient and effective alignment of spatial omics data. Adopting a graph adversarial matching strategy, SLAT is the first algorithm capable of aligning heterogenous spatial data across distinct technologies and modalities. Systematic benchmarks demonstrate SLATs superior precision, robustness, and speed vis a vis existing methods. Applications to multiple real-world datasets further show SLATs utility in enhancing cell-typing resolution, integrating multiple modalities for regulatory inference, and mapping fine-scale spatial-temporal changes during development. The full SLAT package is available at https://github.com/gao-lab/SLAT.

bioinformatics↗

bioRxiv2022

Multimodal single cell data integration challenge: results and lessons learned

Biology has become a data-intensive science. Recent technological advances in single-cell genomics have enabled the measurement of multiple facets of cellular state, producing datasets with millions of single-cell observations. While these data hold great promise for understanding molecular mechanisms in health and disease, analysis challenges arising from sparsity, technical and biological variability, and high dimensionality of the data hinder the derivation of such mechanistic insights. To promote the innovation of algorithms for analysis of multimodal single-cell data, we organized a competition at NeurIPS 2021 applying the Common Task Framework to multimodal single-cell data integration. For this competition we generated the first multimodal benchmarking dataset for single-cell biology and defined three tasks in this domain: prediction of missing modalities, aligning modalities, and learning a joint representation across modalities. We further specified evaluation metrics and developed a cloud-based algorithm evaluation pipeline. Using this setup, 280 competitors submitted over 2600 proposed solutions within a 3 month period, showcasing substantial innovation especially in the modality alignment task. Here, we present the results, describe trends of well performing approaches, and discuss challenges associated with running the competition.

bioinformatics↗

bioRxiv2021

Multi-omics integration and regulatory inference for unpaired single-cell data with a graph-linked unified embedding framework

With the ever-increasing amount of single-cell multi-omics data accumulated during the past years, effective and efficient computational integration is becoming a serious challenge. One major obstacle of unpaired multi-omics integration is the feature discrepancies among omics layers. Here, we propose a computational framework called GLUE (graph-linked unified embedding), which utilizes accessible prior knowledge about regulatory interactions to bridge the gaps between feature spaces. Systematic benchmarks demonstrated that GLUE is accurate, robust and scalable. We further employed GLUE for various challenging tasks, including triple-omics integration, model-based regulatory inference and multi-omics human cell atlas construction (over millions of cells) and found that GLUE achieved superior performance for each task. As a generalizable framework, GLUE features a modular design that can be flexibly extended and enhanced for new analysis tasks. The full package is available online at https://github.com/gao-lab/GLUE for the community.

bioinformatics↗

bioRxiv2019

Cell BLAST: Searching large-scale scRNA-seq database via unbiased cell embedding

An effective and efficient cell-querying method is critical for integrating existing scRNA-seq data and annotating new data. Herein, we present Cell BLAST, an accurate and robust cell-querying method. Powered by a well-curated reference database and a user-friendly Web server, Cell BLAST (http://cblast.gao-lab.org) provides a one-stop solution for real-world scRNA-seq cell querying and annotation.

bioinformatics↗