Biology subjects

Venegas, J.

Publications and source records attributed to Venegas, J..

3 recordsLinked to original sources

bioRxiv2023

SpatialCTD: a large-scale TME spatial transcriptomic dataset to evaluate cell type deconvolution for immuno-oncology

Recent technological advancements have enabled spatially resolved transcriptomic profiling but at multi-cellular resolution. The task of cell type deconvolution has been introduced to disentangle discrete cell types from such multi-cellular spots. However, existing datasets for cell type deconvolution are limited in scale, predominantly encompassing data on mice, and are not designed for human immuno-oncology. In order to overcome these limitations and promote comprehensive investigation of cell type deconvolution for human immuno-oncology, we introduce a large-scale spatial transcriptomic dataset named SO_SCPLOWPATIALC_SCPLOWCTD, encompassing 1.8 million cells from the human tumor microenvironment across the lung, kidney, and liver. Distinct from existing approaches that primarily depend on single-cell RNA sequencing data as a reference without incorporating spatial information, we introduce Graph Neural Network-based method (i.e., GNNDO_SCPLOWECONVOLVERC_SCPLOW) that effectively utilize the spatial information from reference samples, and extensive experiments show that GNNDO_SCPLOWECONVOLVERC_SCPLOW often outperforms existing state-of-the-art methods by a substantial margin, without requiring single-cell RNA-seq data. To enable comprehensive evaluations on spatial transcriptomics data from flexible protocols, we provide an online tool capable of converting spatial transcriptomic data from other platforms (e.g., 10x Visium, MERFISH and sci-Space) into pseudo spots, featuring adjustable spot size. The SO_SCPLOWPATIALC_SCPLOWCTD dataset and GNNDO_SCPLOWECONVOLVERC_SCPLOW implementation are available at https://github.com/OmicsML/SpatialCTD, and the online converter tool can be accessed at https://omicsml.github.io/SpatialCTD/.

bioinformatics↗

bioRxiv2022

DANCE: A Deep Learning Library and Benchmark for Single-Cell Analysis

In the realm of single-cell analysis, computational approaches have brought an increasing number of fantastic prospects for innovation and invention. Meanwhile, it also presents enormous hurdles to reproducing the results of these models due to their diversity and complexity. In addition, the lack of gold-standard benchmark datasets, metrics, and implementations prevents systematic evaluations and fair comparisons of available methods. Thus, we introduce the DANCE platform, the first standard, generic, and extensible benchmark platform for accessing and evaluating computational methods across the spectrum of benchmark datasets for numerous single-cell analysis tasks. Currently, DANCE supports 3 modules and 8 popular tasks with 32 state-of-art methods on 21 benchmark datasets. People can easily reproduce the results of supported algorithms across major benchmark datasets via minimal efforts (e.g., only one command line). In addition, DANCE provides an ecosystem of deep learning architectures and tools for researchers to develop their own models conveniently. The goal of DANCE is to accelerate the development of deep learning models with complete validation and facilitate the overall advancement of single-cell analysis research. DANCE is an open-source python package that welcomes all kinds of contributions. All resources are integrated and available at https://omicsml.ai/.

bioinformatics↗

bioRxiv2020

Composite modeling of leaf shape across shoots discriminates Vitis species better than individual leaves

Premise of studyLeaf morphology is dynamic, continuously deforming during leaf expansion and among leaves within a shoot. We measured leaf morphology from over 200 vines over four years, and modeled changes in leaf shape along the shoot to determine if a composite "shape of shapes" can better capture variation and predict species identity compared to individual leaves. MethodsUsing homologous universal landmarks found in grapevine leaves, we modeled various morphological features as a polynomial function of leaf node. The resulting functions are used to reconstruct modeled leaf shapes across shoots, generating composite leaves that comprehensively capture the spectrum of possible leaf morphologies. ResultsWe found that composite leaves are better predictors of species identity than individual leaves from the same plant. We were able to use composite leaves to predict species identity of previously unassigned vines, which were verified with genotyping. DiscussionObservations of individual leaf shape fail to capture the true diversity between species. Composite leaf shape--an assemblage of modeled leaf snapshots across the shoot--is a better representation of the dynamic and essential shapes of leaves, as well as serving as a better predictor of species identity than individual leaves.

plant biology↗