Salvato in:
Dettagli Bibliografici
Autori principali: Pasqui, Alessandro, Ocana, Jim Martin Catacora, Sinha, Anshuman, Perez, Matthieu, Delbary, Fabrice, Gosti, Giorgio, Miotto, Mattia, Caudo, Domenico, Ernoult, Maxence, Turlier, Hervé
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.06896
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911575906975744
author Pasqui, Alessandro
Ocana, Jim Martin Catacora
Sinha, Anshuman
Perez, Matthieu
Delbary, Fabrice
Gosti, Giorgio
Miotto, Mattia
Caudo, Domenico
Ernoult, Maxence
Turlier, Hervé
author_facet Pasqui, Alessandro
Ocana, Jim Martin Catacora
Sinha, Anshuman
Perez, Matthieu
Delbary, Fabrice
Gosti, Giorgio
Miotto, Mattia
Caudo, Domenico
Ernoult, Maxence
Turlier, Hervé
contents Epithelial tissues dynamically reshape through local mechanical interactions among cells, a process well captured by vertex models. Yet their many tunable parameters make inference and optimization challenging, motivating computational frameworks that flexibly model and learn tissue mechanics. We introduce VertAX, a differentiable JAX-based framework for vertex-modeling of confluent epithelia. VertAX provides automatic differentiation, GPU acceleration, and end-to-end bilevel optimization for forward simulation, parameter inference, and inverse mechanical design. Users can define arbitrary energy and cost functions in pure Python, enabling seamless integration with machine-learning pipelines. We demonstrate VertAX on three representative tasks: (i) forward modeling of tissue morphogenesis, (ii) mechanical parameter inference, and (iii) inverse design of tissue-scale behaviors. We benchmark three differentiation strategies-automatic differentiation, implicit differentiation, and equilibrium propagation-showing that the latter can approximate gradients using repeated forward, adjoint-free simulations alone, offering a simple route for extending inverse biophysical problems to non-differentiable simulators with limited additional engineering effort.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06896
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VertAX: a differentiable vertex model for learning epithelial tissue mechanics
Pasqui, Alessandro
Ocana, Jim Martin Catacora
Sinha, Anshuman
Perez, Matthieu
Delbary, Fabrice
Gosti, Giorgio
Miotto, Mattia
Caudo, Domenico
Ernoult, Maxence
Turlier, Hervé
Machine Learning
Software Engineering
Biological Physics
49, 92, 68
J.3; J.2; I.6.5; G.1.6
Epithelial tissues dynamically reshape through local mechanical interactions among cells, a process well captured by vertex models. Yet their many tunable parameters make inference and optimization challenging, motivating computational frameworks that flexibly model and learn tissue mechanics. We introduce VertAX, a differentiable JAX-based framework for vertex-modeling of confluent epithelia. VertAX provides automatic differentiation, GPU acceleration, and end-to-end bilevel optimization for forward simulation, parameter inference, and inverse mechanical design. Users can define arbitrary energy and cost functions in pure Python, enabling seamless integration with machine-learning pipelines. We demonstrate VertAX on three representative tasks: (i) forward modeling of tissue morphogenesis, (ii) mechanical parameter inference, and (iii) inverse design of tissue-scale behaviors. We benchmark three differentiation strategies-automatic differentiation, implicit differentiation, and equilibrium propagation-showing that the latter can approximate gradients using repeated forward, adjoint-free simulations alone, offering a simple route for extending inverse biophysical problems to non-differentiable simulators with limited additional engineering effort.
title VertAX: a differentiable vertex model for learning epithelial tissue mechanics
topic Machine Learning
Software Engineering
Biological Physics
49, 92, 68
J.3; J.2; I.6.5; G.1.6
url https://arxiv.org/abs/2604.06896