# Edge-level multi-constraint graph pattern matching with lung cancer knowledge graph

## TL;DR

This paper introduces new graph pattern matching algorithms that improve efficiency and effectiveness in analyzing lung cancer data.

## Contribution

The paper proposes novel edge-level and hologram pattern matching algorithms using the Monte Carlo method for lung cancer knowledge graphs.

## Key findings

- The TEM algorithm was experimentally verified for effectiveness and efficiency in graph pattern matching.
- The proposed methods outperform existing algorithms in handling uncertainty in lung cancer knowledge graphs.

## Abstract

Traditional Graph Pattern Matching (GPM) research mainly focuses on improving the accuracy and efficiency of complex network analysis and fast subgraph retrieval. Despite their ability to return subgraphs quickly and accurately, these methods are limited to their applications without medical data research.

In order to overcome this limitation, based on the existing research on GPM with the lung cancer knowledge graph, this paper introduces the Monte Carlo method and proposes an edge-level multi-constraint graph pattern matching algorithm TEM with lung cancer knowledge graph. Furthermore, we apply Monte Carlo method to both nodes and edges, and propose a multi-constraint hologram pattern matching algorithm THM with lung cancer knowledge graph.

The experiments have verified the effectiveness and efficiency of TEM algorithm.

This method effectively addresses the complexity of uncertainty in lung cancer knowledge graph, and is significantly better than the existing algorithms on efficiency.