Increased NKX6.1 expression and decreased ARX expression in alpha cells accompany reduced beta-cell volume in human subjects

Fujita, Yukari; Kozawa, Junji; Fukui, Kenji; Iwahashi, Hiromi; Eguchi, Hidetoshi; Shimomura, Iichiro

doi:10.1038/s41598-021-97235-1

Cited by 5 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We again see that many of the important genes predicted by our method using the consensus importance score ( Fig. 4c ) play a key role in pancreas development ( Table 2 ) ( Liu et al 2011 , Muraro et al 2016 , Byrnes et al 2018 , Millership et al 2018 , Sakata et al 2019 , Fujita et al 2021 , Bosi et al 2022 ). Moreover, we observe substantial enrichment of pathways and cellular components specific to pancreas-related functions within the gene sets associated with each cell type.…”

Section: Resultsmentioning

confidence: 65%

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Sadria,

Layton,

Bader

2023

Bioinformatics Advances

View full text Add to dashboard Cite

Motivation Predictive computational models must be accurate, robust, and interpretable to be considered reliable in important areas such as biology and medicine. A sufficiently robust model should not have its output affected significantly by a slight change in the input. Also, these models should be able to explain how a decision is made to support user trust in the results. Efforts have been made to improve the robustness and interpretability of predictive computational models independently; however, the interaction of robustness and interpretability is poorly understood. Results As an example task, we explore the computational prediction of cell type based on single-cell RNA-seq data and show that it can be made more robust by adversarially training a deep learning model. Surprisingly, we find this also leads to improved model interpretability, as measured by identifying genes important for classification using a range of standard interpretability methods. Our results suggest that adversarial training may be generally useful to improve deep learning robustness and interpretability and that it should be evaluated on a range of tasks. Availability and implementation Our Python implementation of all analysis in this publication can be found at: https://github.com/MehrshadSD/robustness-interpretability. The analysis was conducted using numPy 0.2.5, pandas 2.0.3, scanpy 1.9.3, tensorflow 2.10.0, matplotlib 3.7.1, seaborn 0.12.2, sklearn 1.1.1, shap 0.42.0, lime 0.2.0.1, matplotlib_venn 0.11.9.

show abstract

Section: Resultsmentioning

confidence: 65%

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Sadria,

Layton,

Bader

2023

Bioinformatics Advances

View full text Add to dashboard Cite

show abstract

“…4d,e). We again see that many of the important genes predicted by our method play a key role in pancreas development (Table 2) (30)(31)(32)(33)(34)(35)(36) and strong pathway and cellular component enrichment in the genes for each cell type related to pancreas functions (regulating cell secretion, hormone activity, hormone transport, and pancreas development). Table 1.…”

Section: Using Adversarial Training Can Discover Key Genes and Pathwa...mentioning

confidence: 73%

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Sadria

Bader

2023

Preprint

View full text Add to dashboard Cite

For predictive computational models to be considered reliable in crucial areas such as biology and medicine, it is essential for them to be accurate, robust, and interpretable. A sufficiently robust model should not have its output affected significantly by a slight change in the input. Also, these models should be able to explain how a decision is made. Efforts have been made to improve the robustness and interpretability of these models as independent challenges, however, the effect of robustness and interpretability on each other is poorly understood. Here, we show that predicting cell type based on single-cell RNA-seq data is more robust by adversarially training a deep learning model. Surprisingly, we find this also leads to improved model interpretability, as measured by identifying genes important for classification. We believe that adversarial training will be generally useful to improve deep learning robustness and interpretability, thereby facilitating biological discovery.

show abstract

“…The Ki-67 index was <2% (data not shown) and was thus classified as neuroendocrine tumor (NET) G1 (23). Immunohistochemical studies using an indirect immunofluorescence method (24) showed that most tu-mor cells were positive for both insulin and calcitonin immunoreactivity (Fig. 2) but negative for glucagon and somatostatin immunoreactivity (data not shown).…”

Section: Case Reportmentioning

confidence: 98%

Insulinoma with Hyperprocalcitoninemia and Hypercalcitoninemia Showing Coexpression of Insulin and Calcitonin in Its Tumor Cells

Kaketaka,

Mineo,

Kimura

et al. 2024

Intern. Med.

Self Cite

View full text Add to dashboard Cite

Neuroendocrine neoplasms can produce multiple hormones that are released into the bloodstream, causing symptoms that vary depending on the type and quantity of hormones involved. We herein report a 63-yearold asymptomatic patient with pancreatic insulinoma who showed marked elevations in circulating calcitonin and procalcitonin levels that returned to normal following surgery. Immunohistochemical analyses confirmed the co-staining of calcitonin and insulin immunoreactivity in the tumor cells, suggesting a calcitoninproducing insulinoma. This insulinoma released calcitonin and a considerable amount of its precursor peptide, procalcitonin, resulting in both hyperprocalcitoninemia and hypercalcitoninemia.

show abstract

Increased NKX6.1 expression and decreased ARX expression in alpha cells accompany reduced beta-cell volume in human subjects

Cited by 5 publications

References 31 publications

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Adversarial training improves model interpretability in single-cell RNA-seq analysis

Insulinoma with Hyperprocalcitoninemia and Hypercalcitoninemia Showing Coexpression of Insulin and Calcitonin in Its Tumor Cells

Contact Info

Product

Resources

About