Single-cell analysis reveals transcriptional dynamics in healthy primary parathyroid tissue.

Studies on human parathyroids are generally limited to hyperfunctioning glands owing to the difficulty in obtaining normal human tissue. We therefore obtained non-human primate (NHP) parathyroids to provide a suitable alternative for sequencing that would bear a close semblance to human organs. Single-cell RNA expression analysis of parathyroids from four healthy adult reveals a continuous trajectory of epithelial cell states.

Single-cell multi-modal GAN reveals spatial patterns in single-cell data from triple-negative breast cancer.

Exciting advances in technologies to measure biological systems are currently at the forefront of research. The ability to gather data along an increasing number of omic dimensions has created a need for tools to analyze all of this information together, rather than siloing each technology into separate analysis pipelines. To advance this goal, we introduce a framework called the single-cell multi-modal generative adversarial network (scMMGAN) that integrates data from multiple modalities into a unified representation in the ambient data space for downstream analysis using a combination of adversarial learning and data geometry techniques.

LEARNING GENERAL TRANSFORMATIONS OF DATA FOR OUT-OF-SAMPLE EXTENSIONS.

While generative models such as GANs have been successful at mapping from noise to specific distributions of data, or more generally from one distribution of data to another, they cannot isolate the transformation that is occurring and apply it to a new distribution not seen in training. Thus, they memorize the domain of the transformation, and cannot generalize the transformation . To address this, we propose a new neural network called a (NTNet) that isolates the signal representing the transformation itself from the other signals representing internal distribution variation.

Generating hard-to-obtain information from easy-to-obtain information: Applications in drug discovery and clinical inference.

Often when biological entities are measured in multiple ways, there are distinct categories of information: some information is easy-to-obtain information (EI) and can be gathered on virtually every subject of interest, while other information is hard-to-obtain information (HI) and can only be gathered on some. We propose building a model to make probabilistic predictions of HI using EI. Our feature mapping GAN (FMGAN), based on the conditional GAN framework, uses an embedding network to process conditions as part of the conditional GAN training to create manifold structure when it is not readily present in the conditions.

Interpretable Neuron Structuring with Graph Spectral Regularization.

While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose for making hidden layers more interpretable without significantly impacting performance on the primary task. Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer.

Single cell immune profiling of dengue virus patients reveals intact immune responses to Zika virus with enrichment of innate immune signatures.

The genus Flavivirus contains many mosquito-borne human pathogens of global epidemiological importance such as dengue virus, West Nile virus, and Zika virus, which has recently emerged at epidemic levels. Infections with these viruses result in divergent clinical outcomes ranging from asymptomatic to fatal. Myriad factors influence infection severity including exposure, immune status and pathogen/host genetics.

Exploring single-cell data with deep multitasking neural networks.

It is currently challenging to analyze single-cell data consisting of many cells and samples, and to address variations arising from batch effects and different sample preparations. For this purpose, we present SAUCIE, a deep neural network that combines parallelization and scalability offered by neural networks, with the deep representation of data that can be learned by them to perform many single-cell data analysis tasks. Our regularizations (penalties) render features learned in hidden layers of the neural network interpretable.

Identification and Analysis of Islet Antigen-Specific CD8 T Cells with T Cell Libraries.

Type 1 diabetes (T1D) is most likely caused by killing of β cells by autoreactive CD8 T cells. Methods to isolate and identify these cells are limited by their low frequency in the peripheral blood. We analyzed CD8 T cells, reactive with diabetes Ags, with T cell libraries and further characterized their phenotype by CyTOF using class I MHC tetramers.