Multi-objective optimization based network control principles for identifying personalized drug targets with cancer

TL;DR

This paper introduces a multi-objective optimization framework, LSCV-MCEA, to identify personalized cancer drug targets by controlling gene interaction networks, improving accuracy and diversity over existing methods.

Contribution

It proposes a novel multi-objective optimization model and evolutionary algorithm for better identification of personalized drug targets in cancer, considering multiple candidate driver gene sets.

Findings

LSCV-MCEA outperforms other methods in predicting clinically relevant drug combinations.

The approach effectively detects disease signals for individual patients with BRCA cancer.

The method enhances understanding of tumor heterogeneity in cancer precision medicine.

Abstract

It is a big challenge to develop efficient models for identifying personalized drug targets (PDTs) from high-dimensional personalized genomic profile of individual patients. Recent structural network control principles have introduced a new approach to discover PDTs by selecting an optimal set of driver genes in personalized gene interaction network (PGIN). However, most of current methods only focus on controlling the system through a minimum driver-node set and ignore the existence of multiple candidate driver-node sets for therapeutic drug target identification in PGIN. Therefore, this paper proposed multi-objective optimization-based structural network control principles (MONCP) by considering minimum driver nodes and maximum prior-known drug-target information. To solve MONCP, a discrete multi-objective optimization problem is formulated with many constrained variables, and a novel evolutionary optimization model called LSCV-MCEA was developed by adapting a multi-tasking framework and a rankings-based fitness function method. With genomics data of patients with breast or lung cancer from The Cancer Genome Atlas database, the effectiveness of LSCV-MCEA was validated. The experimental results indicated that compared with other advanced methods, LSCV-MCEA can more effectively identify PDTs with the highest Area Under the Curve score for predicting clinically annotated combinatorial drugs. Meanwhile, LSCV-MCEA can more effectively solve MONCP than other evolutionary optimization methods in terms of algorithm convergence and diversity. Particularly, LSCV-MCEA can efficiently detect disease signals for individual patients with BRCA cancer. The study results show that multi-objective optimization can solve structural network control principles effectively and offer a new perspective for understanding tumor heterogeneity in cancer precision medicine.