Spatial statistics is a comprehensive tool for quantifying cell neighbor relationships and biological processes via tissue image analysis

HD Summers, JW Wills, P Rees - Cell Reports Methods, 2022 - cell.com
Automated microscopy and computational image analysis has transformed cell biology,
providing quantitative, spatially resolved information on cells and their constituent molecules …

Robust neural posterior estimation and statistical model criticism

D Ward, P Cannon, M Beaumont… - Advances in …, 2022 - proceedings.neurips.cc
Computer simulations have proven a valuable tool for understanding complex phenomena
across the sciences. However, the utility of simulators for modelling and forecasting …

Detecting model misspecification in amortized Bayesian inference with neural networks

M Schmitt, PC Bürkner, U Köthe, ST Radev - DAGM German Conference …, 2023 - Springer
Recent advances in probabilistic deep learning enable efficient amortized Bayesian
inference in settings where the likelihood function is only implicitly defined by a simulation …

A generalizable data-driven multicellular model of pancreatic ductal adenocarcinoma

B Aguilar, DL Gibbs, DJ Reiss, M McConnell… - …, 2020 - academic.oup.com
Background Mechanistic models, when combined with pertinent data, can improve our
knowledge regarding important molecular and cellular mechanisms found in cancer. These …

Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigation

M Schmitt, PC Bürkner, U Köthe, ST Radev - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advances in probabilistic deep learning enable efficient amortized Bayesian
inference in settings where the likelihood function is only implicitly defined by a simulation …

What you see is not what is there: Mechanisms, models, and methods for point pattern deviations

P Guttorp, J Illian, J Kostensalo, M Kuronen… - arxiv preprint arxiv …, 2023 - arxiv.org
Many natural systems are observed as point patterns in time, space, or space and time.
Examples include plant and cellular systems, animal colonies, earthquakes, and wildfires. In …

Quantification of spatial tumor heterogeneity in immunohistochemistry staining images

I Chervoneva, AR Peck, M Yi, B Freydin, H Rui - Bioinformatics, 2021 - academic.oup.com
Motivation Quantitative immunofluorescence is often used for immunohistochemistry
quantification of proteins that serve as cancer biomarkers. Advanced image analysis …

Deep Multiple Instance Learning with Distance-Aware Self-Attention

G Wölflein, LC Magister, P Liò, DJ Harrison… - arxiv preprint arxiv …, 2023 - arxiv.org
Traditional supervised learning tasks require a label for every instance in the training set, but
in many real-world applications, labels are only available for collections (bags) of instances …

Discovery of novel antifungal resorcylate aminopyrazole Hsp90 inhibitors based on structural optimization by molecular simulations

Y Tuo, G Li, Z Liu, N Yu, Y Li, L Yang, H Liu… - New Journal of …, 2022 - pubs.rsc.org
Hsp90 is a highly conserved and essential stress protein located in all eukaryotes, involved
in the regulation of fungal survival, virulence and resistance, which is an important target for …

CytoSpatio: Learning cell type spatial relationships using multirange, multitype point process models

H Chen, RF Murphy - bioRxiv, 2024 - biorxiv.org
Recent advances in multiplexed fluorescence imaging have provided new opportunities for
deciphering the complex spatial relationships among various cell types across diverse …