A5079270970- Single-cell and spatial transcriptomics
- Cell Image Analysis Techniques
- Genetics, Aging, and Longevity in Model Organisms
- Statistical Methods and Applications
- Cancer Immunotherapy and Biomarkers
- Neural dynamics and brain function
- Cancer Genomics and Diagnostics
- Neuroscience and Neural Engineering
- Data Analysis with R
- Advanced Statistical Methods and Models
- EEG and Brain-Computer Interfaces
- Domain Adaptation and Few-Shot Learning
- RNA Research and Splicing
University of California, Santa Cruz
2022-2025
Neuronal subtype generation in the mammalian central nervous system is governed by competing genetic programs. The medial ganglionic eminence (MGE) produces two major cortical interneuron (IN) populations, somatostatin (Sst) and parvalbumin (Pvalb), which develop on different timelines. extent to external signals influence these identities remains unclear. Pvalb-positive INs are crucial for circuit regulation but challenging model vitro. We grafted mouse MGE progenitors into diverse 2D 3D...
Cell atlases serve as vital references for automating cell labeling in new samples, yet existing classification algorithms struggle with accuracy. Here we introduce SIMS (scalable, interpretable machine learning single cell), a low-code data-efficient pipeline single-cell RNA classification. We benchmark against datasets from different tissues and species. demonstrate SIMS's efficacy classifying cells the brain, achieving high accuracy even small training sets (<3,500 cells) across samples....
Abstract Extracellular electrophysiological recordings present unique computational challenges for neuronal classification due to noise, technical variability, and batch effects across experimental systems. We introduce HIPPIE (High-dimensional Interpretation of Physiological Patterns In recordings), a deep learning framework that combines self-supervised pretraining on unlabeled datasets with supervised fine-tuning classify neurons from extracellular recordings. Using conditional...
The generation of neuronal subtypes in the mammalian central nervous system is driven by competing genetic programs. medial ganglionic eminence (MGE) gives rise to two major cortical interneuron (cIN) populations, marked Somatostatin (Sst) and Parvalbumin (Pvalb), which develop on different timelines. extent external signals influence these identities remains poorly understood. Pvalb-positive cINs are particularly important for regulating circuits through strong perisomatic inhibition, yet...
Laboratory scientists are well equipped with statistical tools for univariate data, yet many phenomena of scientific interest time-variant or otherwise multidimensional. Functional data analysis is one way approaching such data: by representing these more complex as single points in a mathematical space functions. The concept functional depth provides notion centrality which allows descriptive statistics and some comparative on data. Here, we present statdepth, Python package depth-based...
Abstract Large single-cell RNA datasets have contributed to unprecedented biological insight. Often, these take the form of cell atlases and serve as a reference for automating labeling newly sequenced samples. Yet, classification algorithms lacked capacity accurately annotate cells, particularly in complex datasets. Here we present SIMS (Scalable, Interpretable Ma-chine Learning Single-Cell), an end-to-end data-efficient machine learning pipeline discrete data that can be applied new with...
<h3>Background</h3> Despite the success of immunotherapy, clinical responses remain difficult to predict, likely due diverging tumor immune cell composition and function. Advances in single-cell analysis have revealed heterogeneous activity within across individuals with cancer. While CD8+ ?tumor-infiltrating lymphocytes (TILs) been extensively studied,<sup>1–4</sup> a pan-cancer consensus annotation CD4+ TIL immunotherapy is lacking. Robust identification T-cells from admixed transcriptomes...