Learning to refine domain knowledge for biological network inference

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Peiwen, Wu, Menghua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914978326380544
author Li, Peiwen
Wu, Menghua
author_facet Li, Peiwen
Wu, Menghua
contents Perturbation experiments allow biologists to discover causal relationships between variables of interest, but the sparsity and high dimensionality of these data pose significant challenges for causal structure learning algorithms. Biological knowledge graphs can bootstrap the inference of causal structures in these situations, but since they compile vastly diverse information, they can bias predictions towards well-studied systems. Alternatively, amortized causal structure learning algorithms encode inductive biases through data simulation and train supervised models to recapitulate these synthetic graphs. However, realistically simulating biology is arguably even harder than understanding a specific system. In this work, we take inspiration from both strategies and propose an amortized algorithm for refining domain knowledge, based on data observations. On real and synthetic datasets, we show that our approach outperforms baselines in recovering ground truth causal graphs and identifying errors in the prior knowledge with limited interventional data.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14436
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to refine domain knowledge for biological network inference
Li, Peiwen
Wu, Menghua
Quantitative Methods
Artificial Intelligence
Machine Learning
Perturbation experiments allow biologists to discover causal relationships between variables of interest, but the sparsity and high dimensionality of these data pose significant challenges for causal structure learning algorithms. Biological knowledge graphs can bootstrap the inference of causal structures in these situations, but since they compile vastly diverse information, they can bias predictions towards well-studied systems. Alternatively, amortized causal structure learning algorithms encode inductive biases through data simulation and train supervised models to recapitulate these synthetic graphs. However, realistically simulating biology is arguably even harder than understanding a specific system. In this work, we take inspiration from both strategies and propose an amortized algorithm for refining domain knowledge, based on data observations. On real and synthetic datasets, we show that our approach outperforms baselines in recovering ground truth causal graphs and identifying errors in the prior knowledge with limited interventional data.
title Learning to refine domain knowledge for biological network inference
topic Quantitative Methods
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.14436