Network as biomarker

Role of Artificial Intelligence in Drug Discovery and Target Identification in Cancer

Drug discovery and development (DDD) is a highly complex process that necessitates precise monitoring and extensive data analysis at each stage. Furthermore, the DDD process is both timeconsuming and costly. To tackle these concerns, artificial intelligence (AI) technology can be used, which facilitates rapid and precise analysis of extensive datasets within a limited timeframe. The pathophysiology of cancer disease is complicated and requires extensive research for novel drug discovery and development. The first stage in the process of drug discovery and development involves identifying targets. Cell structure and molecular functioning are complex due to the vast number of molecules that function constantly, performing various roles. Furthermore, scientists are continually discovering novel cellular mechanisms and molecules, expanding the range of potential targets. Accurately identifying the correct target is a crucial step in the preparation of a treatment strategy. Various forms of AI, such as machine learning, neural-based learning, deep learning, and network-based learning, are currently being utilised in applications, online services, and databases. These technologies facilitate the identification and validation of targets, ultimately contributing to the success of projects. This review focuses on the different types and subcategories of AI databases utilised in the field of drug discovery and target identification for cancer.

Complex network-based approaches to biomarker discovery

Many studies on biomarker discovery have been done by analyzing mutations in DNA sequences and differences in gene expression patterns. As a new branch of the latter approach, the concept of network biomarkers has been proposed, in which expression data of small subnetworks are used as markers. Furthermore, network biomarkers have been extended to dynamical network biomarkers, in which time series expression data of subnetworks are used as markers. On the other hand, the methodologies in complex networks have also been applied to biomarker discovery. For example, various centrality measures and the concept of observability have been applied. In this article, we review these new approaches for biomarker discovery with focusing on the computational/methodological aspects.

Integrative analysis of cancer imaging readouts by networks

Cancer is a multifactorial and heterogeneous disease. The corresponding complexity appears at multiple levels: from the molecular and the cellular constitution to the macroscopic phenotype, and at the diagnostic and therapeutic management stages. The overall complexity can be approximated to a certain extent, e.g. characterized by a set of quantitative phenotypic observables recorded in time‐space resolved dimensions by using multimodal imaging approaches. The transition from measures to data can be made effective through various computational inference methods, including networks, which are inherently capable of mapping variables and data to node‐ and/or edge‐valued topological properties, dynamic modularity configurations, and functional motifs. We illustrate how networks can integrate imaging data to explain cancer complexity, and assess potential pre‐clinical and clinical impact.

Computational Multiplexing Imaging merges imaging and networks.

Networks show signatures of tumor heterogeneity and phenotypic profiles observed in‐vivo.

A profile ensemble establishes a tumor fingerprint, and this constitutes a novel type of marker.

Personalized treatment is embedded in a systems medicine approach.

PhenoNet: identification of key networks associated with disease phenotype

MOTIVATION

At the core of transcriptome analyses of cancer is a challenge to detect molecular differences affiliated with disease phenotypes. This approach has led to remarkable progress in identifying molecular signatures and in stratifying patients into clinical groups. Yet, despite this progress, many of the identified signatures are not robust enough to be clinically used and not consistent enough to provide a follow-up on molecular mechanisms.

RESULTS

To address these issues, we introduce PhenoNet, a novel algorithm for the identification of pathways and networks associated with different phenotypes. PhenoNet uses two types of input data: gene expression data (RMA, RPKM, FPKM, etc.) and phenotypic information, and integrates these data with curated pathways and protein-protein interaction information. Comprehensive iterations across all possible pathways and subnetworks result in the identification of key pathways or subnetworks that distinguish between the two phenotypes.

AVAILABILITY AND IMPLEMENTATION

Matlab code is available upon request.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.