Biology subjects

Hollmann, T. J.

Publications and source records attributed to Hollmann, T. J..

5 recordsLinked to original sources

bioRxiv2024

Automated classification of cellular expression in multiplexed imaging data with Nimbus

Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, the specific combination of markers that are present in each cell must be enumerated to enable accurate phenotyping, a process that often relies on unsupervised clustering. We constructed the Pan-Multiplex (Pan-M) dataset containing 197 million distinct annotations of marker expression across 15 different cell types. We used Pan-M to create Nimbus, a deep learning model to predict marker positivity from multiplexed image data. Nimbus is a pre-trained model that uses the underlying images to classify marker expression across distinct cell types, from different tissues, acquired using different microscope platforms, without requiring any retraining. We demonstrate that Nimbus predictions capture the underlying staining patterns of the full diversity of markers present in Pan-M. We then show how Nimbus predictions can be integrated with downstream clustering algorithms to robustly identify cell subtypes in image data. We have open-sourced Nimbus and Pan-M to enable community use at https://github.com/angelolab/Nimbus-Inference.

bioinformatics↗

bioRxiv2021

Electrical activity between skin cells regulates melanoma initiation

Oncogenes can only initiate tumors in certain cellular contexts, which is referred to as oncogenic competence. In melanoma, whether cells in the microenvironment can endow such competence remains unclear. Using a combination of zebrafish transgenesis coupled with human tissues, we demonstrate that GABAergic signaling between keratinocytes and melanocytes promotes melanoma initiation by BRAFV600E. GABA is synthesized in melanoma cells, which then acts on GABA-A receptors on keratinocytes. Electron microscopy demonstrates synapse-like structures between keratinocytes and melanoma cells, and multi-electrode array analysis shows that GABA acts to inhibit electrical activity in melanoma/keratinocyte co-cultures. Genetic and pharmacologic perturbation of GABA synthesis abrogates melanoma initiation in vivo. These data suggest that electrical activity across the skin microenvironment determines the ability of oncogenes to initiate melanoma.

cancer biology↗

bioRxiv2021

DeepLIIF: Deep Learning-Inferred Multiplex ImmunoFluorescence for IHC Quantification

Reporting biomarkers assessed by routine immunohistochemical (IHC) staining of tissue is broadly used in diagnostic pathology laboratories for patient care. To date, clinical reporting is predominantly qualitative or semi-quantitative. By creating a multitask deep learning framework referred to as DeepLIIF, we present a single-step solution to stain deconvolution/separation, cell segmentation, and quantitative single-cell IHC scoring. Leveraging a unique de novo dataset of co-registered IHC and multiplex immunofluorescence (mpIF) staining of the same slides, we segment and translate low-cost and prevalent IHC slides to more expensive-yet-informative mpIF images, while simultaneously providing the essential ground truth for the superimposed brightfield IHC channels. Moreover, a new nuclear-envelop stain, LAP2beta, with high (>95%) cell coverage is introduced to improve cell delineation/segmentation and protein expression quantification on IHC slides. By simultaneously translating input IHC images to clean/separated mpIF channels and performing cell segmentation/classification, we show that our model trained on clean IHC Ki67 data can generalize to more noisy and artifact-ridden images as well as other nuclear and non-nuclear markers such as CD3, CD8, BCL2, BCL6, MYC, MUM1, CD10, and TP53. We thoroughly evaluate our method on publicly available benchmark datasets as well as against pathologists semi-quantitative scoring. The code, the pre-trained models, along with easy-to-run containerized docker files as well as Google CoLab project are available at https://github.com/nadeemlab/deepliif.

bioinformatics↗

bioRxiv2021

ImPartial: Partial Annotations for Cell Instance Segmentation

Segmenting noisy multiplex spatial tissue images constitutes a challenging task, since the characteristics of both the noise and the biology being imaged differs significantly across tissues and modalities; this is compounded by the high monetary and time costs associated with manual annotations. It is therefore imperative to build algorithms that can accurately segment the noisy images based on a small number of annotations. Recently techniques to derive such an algorithm from a few scribbled annotations have been proposed, mostly relying on the refinement and estimation of pseudo-labels. Other techniques leverage the success of self-supervised denoising as a parallel task to potentially improve the segmentation objective when few annotations are available. In this paper, we propose a method that augments the segmentation objective via self-supervised multi-channel quantized imputation, meaning that each class of the segmentation objective can be characterized by a mixture of distributions. This approach leverages the observation that perfect pixel-wise reconstruction or denoising of the image is not needed for accurate segmentation, and introduces a self-supervised classification objective that better aligns with the overall segmentation goal. We demonstrate the superior performance of our approach for a variety of cancer datasets acquired with different highly-multiplexed imaging modalities in real clinical settings. Code for our method along with a benchmarking dataset is available at https://github.com/natalialmg/ImPartial.

bioengineering↗

bioRxiv2018

Cancer modeling by Transgene Electroporation in Adult Zebrafish (TEAZ)

Transgenic animals are invaluable for modeling cancer genomics, but often require complex crosses of multiple germline alleles to obtain the desired combinations. Zebrafish models have advantages in that transgenes can be rapidly tested by mosaic expression, but these typically lack spatial and temporal control of tumor onset, which limits their utility for the study of tumor progression and metastasis. To overcome these limitations, we have developed a method called Transgene Electroporation in Adult Zebrafish (TEAZ). TEAZ can deliver DNA constructs with promoter elements of interest to drive fluorophores, oncogenes, or CRISPR-Cas9-based mutagenic cassettes in specific cell types. Using TEAZ, we created a highly aggressive melanoma model by expression of BRAFV600E in spatially constrained melanocytes in the context of p53 deficiency and Cas9-mediated inactivation of Rb1. Unlike prior models that take ~4 months to develop, we found that TEAZ leads to tumor onset in ~7 weeks and these develop in fully immunocompetent animals. As the resulting tumors initiated at highly defined locations, we could track their progression via fluorescence and documented deep invasion into tissues and metastatic deposits. TEAZ can be deployed to other tissues and cell types such as the heart with the use of suitable transgenic promoters. The versatility of TEAZ makes it widely accessible for rapid modeling of somatic gene alterations and cancer progression at a scale not achievable in other in vivo systems.

cancer biology↗