A5081575273- Single-cell and spatial transcriptomics
- Gene Regulatory Network Analysis
- Robotic Path Planning Algorithms
- Distributed Control Multi-Agent Systems
- Immune Cell Function and Interaction
- Cell Image Analysis Techniques
- Epigenetics and DNA Methylation
- Control and Dynamics of Mobile Robots
- Bioinformatics and Genomic Networks
- Robotics and Automated Systems
- Industrial Vision Systems and Defect Detection
- Anomaly Detection Techniques and Applications
- Simulation and Modeling Applications
- Advanced Sensor and Control Systems
- Genomics and Chromatin Dynamics
- Advanced Fluorescence Microscopy Techniques
- Robotics and Sensor-Based Localization
- Image and Object Detection Techniques
Yale University
2022-2025
China Jiliang University
2021-2024
University of Rochester
2021
Computational Physics (United States)
2021
North Carolina State University
2021
Abstract Emerging spatial technologies, including transcriptomics and epigenomics, are becoming powerful tools for profiling of cellular states in the tissue context 1–5 . However, current methods capture only one layer omics information at a time, precluding possibility examining mechanistic relationship across central dogma molecular biology. Here, we present two technologies spatially resolved, genome-wide, joint epigenome transcriptome by cosequencing chromatin accessibility gene...
Abstract Recent advancements in single-cell technologies allow characterization of experimental perturbations at resolution. While methods have been developed to analyze such experiments, the application a strict causal framework has not yet explored for inference treatment effects level. Here we present causal-inference-based approach perturbation analysis, termed CINEMA-OT (causal independent effect module attribution + optimal transport). separates confounding sources variation from...
Advances in single-cell technology have enabled the measurement of cell-resolved molecular states across a variety cell lines and tissues under plethora genetic, chemical, environmental, or disease perturbations. Current methods focus on differential comparison are specific to particular task multi-condition setting with purely statistical perspectives. The quickly growing number, size, complexity such studies requires scalable analysis framework that takes existing biological context into...
Spatial omics technologies enable analysis of gene expression and interaction dynamics in relation to tissue structure function. However, existing computational methods may not properly distinguish cellular intrinsic variability intercellular interactions, thus fail reliably capture spatial regulations. Here, we present Interaction Modeling using Variational Inference (SIMVI), an annotation-free deep learning framework that disentangles cell spatial-induced latent variables data with...
Abstract Recent advancements in single-cell technologies allow characterization of experimental perturbations at resolution. While methods have been developed to analyze such experiments, the application a strict causal framework has not yet explored for inference treatment effects level. In this work, we present based approach perturbation analysis, termed CINEMA-OT (Causal INdependent Effect Module Attribution + Optimal Transport). separates confounding sources variation from obtain an...
Spatial omics technologies enable the analysis of gene expression and interaction dynamics in relation to tissue structure function. However, existing computational methods may not properly distinguish cellular intrinsic variability intercellular interactions, thus fail capture spatial regulations for further biological discoveries. Here, we present Interaction Modeling using Variational Inference (SIMVI), an annotation-free framework that disentangles cell spatial-induced latent variables...
Abstract An ackerman mobile robot system based on ROS and lidar was developed in this research. The i5 industrial control computer taken as the core controller, Ubuntu installed inside, of driving part STM32 microcontroller. Using external environment information obtained by IMU sensors, corresponding SLAM algorithm designed under Linux distributed framework operating system. Through establishing feature map environment, can locate position posture vehicle body real time, generate optimal...
The advent of deep reinforcement learning (DRL) has significantly expanded the application range for autonomous robots. However, safe navigation in crowded and complex environments remains a persistent challenge. This study proposes robot strategy that utilizes DRL, conceptualizing observation as convex static obstacle-free region, departure from traditional reliance on raw sensor inputs. novelty this work is threefold: (1) Formulating an action space includes both short-term long-term...
Automatic verification system is the future trend in metrological field. However, it still a problem waiting to be solved that can automatically recognize instrument interfaces with different models and record data. Based on YOLOv3 deep learning algorithm, this paper shoots makes interface data sets independently. In addition, network model training conducted under PaddlePaddle framework. On LabView platform, encapsulation has designed automatic recognition module used by system. Through...
How to identify true biological differences across samples while overcoming batch effects has been a persistent challenge in single-cell RNA-seq data analysis, hindering analyses datasets for transferable findings. In this work, we show that scaling up deep identifiable models leads surprisingly effective solution challenging task. We developed scShift, variational inference framework with theoretical support disentangling batch-dependent and independent variations. By training the model...