From Early Diagnosis to Therapy Response: Machine Learning Driven Biomarker Discovery

Dear Colleagues,

Introduction

Early and accurate identification of clinically meaningful biomarkers is central to advancing precision oncology, yet it remains challenging throughout the continuum from disease onset to therapeutic decision-making. Tumor initiation, progression and therapy response are governed by intricate biological processes involving genetic and epigenetic alterations, dynamic tumor–microenvironment interactions and profound spatial–temporal heterogeneity at the cellular and tissue levels. Traditional biomarker discovery approaches, which are often reductionist and constrained by data dimensionality, have struggled to capture these multifaceted layers of complexity.

Recent advances in machine learning and artificial intelligence have fundamentally reshaped the methodological landscape. High-throughput sequencing technologies, multi-parametric imaging and liquid biopsy platforms now generate massive datasets that require computational frameworks capable of extracting clinically actionable signatures. Machine learning-driven analytics, including deep learning-based radiogenomics, cross-modal feature fusion and interpretable model architectures, have begun to reveal previously inaccessible molecular–phenotypic relationships. Meanwhile, organoid systems, spatial omics and high-content imaging provide robust platforms for functional validation and mechanistic interpretation. Collectively, these emerging approaches offer unprecedented opportunities to bridge early detection with therapeutic response prediction, accelerating biomarker development from discovery to clinical implementation.

Aim and Scope

This Special Issue aims to bring together cutting-edge research at the intersection of biomarker discovery, machine learning and translational oncology. Focusing on methodologies that integrate imaging, liquid biopsy, multi-omics and clinical data, the series seeks to highlight innovative strategies for identifying and validating biomarkers relevant to early disease detection, prognostic stratification, therapy resistance and treatment response monitoring. Particular emphasis will be placed on artificial intelligence-driven analytical frameworks and experimental platforms that enable mechanistic insights and support the rapid translation of biomarker candidates into clinical applications.

The overarching goal is to advance a comprehensive and multidisciplinary understanding of biomarker science, encourage methodological innovation and provide a foundation for next - generation diagnostic and therapeutic paradigms.

Themes include, but are not limited to:

• AI-driven biomarker discovery for early cancer detection, including liquid biopsy, cfDNA/cfRNA, microRNA signatures and multimodal data integration.
• Machine learning models for predicting therapeutic response, resistance development and clinical outcomes across solid tumors.
• Radiomics and radiogenomics approaches that couple imaging phenotypes with molecular signatures using deep learning and transformer-based architectures.
• Multi-omics integration frameworks, combining transcriptomics, proteomics, epigenomics, metabolomics and spatial omics for precision biomarker identification.
• Functional validation strategies, including organoids, cancer stem cell models, in vitro synthetic ecosystems and high-throughput perturbation assays.

Dr. Wenjie Shi
Dr. Rudy Leon De Wilde
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• biomarker discovery
• early diagnosis
• liquid biopsy
• precision medicine