Aug 2026· Biomaterials Advances· Vol 189, pp.
215097
· 0 citations· 121 references
Medicine
TL;DR
This review systematically summarizes the core framework of machine learning-assisted peptide material design, covering three core components: data acquisition, feature engineering, and model selection and training.
Abstract
Peptide materials have shown their great promise in precision cancer therapy due to their accurate target recognition ability, diverse anti-tumor mechanisms, and biocompatibility. However, conventional peptide discovery largely relies on trial-and-error methods, which are inherently limited by lengthy development cycles, inefficient exploration of the vast sequence space, and inadequate characterization of structure-activity relationships. Recent advances in machine learning have fundamentally transformed peptide material design by shifting the discovery paradigm from empirical trial-and-error to data-driven rational design. This review systematically summarizes the core framework of machine learning-assisted peptide material design, covering three core components: data acquisition, feature engineering, and model selection and training. We focus on the cutting-edge research progress of machine learning in enhancing the tumor targeting of peptide materials and developing new anti-tumor peptide materials, and introduce the professional databases and algorithm tools that support the development of this field. Finally, we discuss the major challenges facing in machine learning-driven design of tumor-targeted peptide materials, and suggest the future development direction in this field, aiming to provide a systematic theoretical reference for the rational design and clinical translation of novel tumor-targeted peptide materials.
How advances in artificial intelligence and computational modeling may reshape the rational design of next-generation peptide therapeutics is explored and an integrated experimental–computational framework is proposed to facilitate the development of clinically actionable candidates is proposed.
Ha Thi Ngoc Nguyen, B. Le, Nhung Thi Hong Van et al.· Pharmaceuticals· 0 citations
This review systematically examines the key methodological innovations, including peptide representation learning, multi-modal fusion strategies, multi-label learning paradigms, and emerging predictive frameworks empowered by deep neural architectures and ProtLM-based embeddings, and summarizes the practical applications of these models in peptide database mining, functional mechanism interpretation, and mutation effect prediction.
With broad-spectrum, low resistance, and multifunctional properties, antimicrobial peptides (AMPs) are promising therapeutic agents against drug-resistant pathogens, yet their discovery and optimization still remain challenging due to the complexity of sequence-function associations. Artificial intelligence (AI), through the construction of comprehensive data-driven models that assisted with miscellaneous learning strategies, enables de novo peptide design by learning latent representations inherent in peptide sequences as well as their biological properties to ensure physically plausible and biologically relevant predictions. Consequently, this paradigm enhances the likelihood of designing peptide candidates with significantly improved therapeutic potential, reducing resource-intensive trial-and-error processes and revealing the transformative impact of computational innovation in advancing next-generation therapeutics. Here, we provide a snapshot of this field and survey two modes of AI-driven technologies for AMP design, one concentrated on identifying whether current data possess antimicrobial activity (identification-oriented) and the other on generating AMP candidates with potential therapeutic properties (generation-oriented). We also highlight the challenges and limitations that still hinder AMP development even accelerated by AI, as well as the foreseeable prospects, from finer-grained explorations to model-driven data enrichment and model enhancement.
Yongqiang Liu, Jie Hu, Ning Zhang et al.· Synthetic and Systems Biotec...· 0 citations
Solid tumors, the most prevalent form of malignancy, pose therapeutic challenges distinct from hematologic malignancies due to their complex biology, including high tumor heterogeneity, a dense extracellular matrix (ECM), an immunosuppressive tumor microenvironment (TME), and multifaceted drug resistance. Peptide drugs have emerged as a focal point in precision oncology, combining the deep tissue penetration of small molecules with the high target specificity, low immunogenicity, and sequence designability of antibodies. This review systematically summarizes advancements in peptide‐based therapeutics for solid tumors from 2020 to 2025. These agents are categorized by function into five classes: tumor‐homing peptides, surface receptor antagonist/inhibitory peptides, interfering peptides, peptide vaccines, and cell‐penetrating peptides as delivery tools. We also highlight the transformative role of artificial intelligence (AI) in peptide design and discovery. Finally, we discuss outcomes from clinical trials of peptide drugs in solid tumors, underscoring their potential as multifunctional agents in this setting.
Jinqiu Liang, Xiaochuan Tang, Haoqi Li et al.· Journal of Peptide Science· 0 citations
Peptide-based cancer vaccines represent a promising immunotherapeutic strategy aimed at inducing tumor-specific immune responses through the targeting of tumor-associated antigens and neoantigens. Recent advances in next-generation sequencing and immunogenomics have accelerated the identification of candidate neoantigens; however, the development of effective peptide vaccines remains limited by challenges related to antigen selection, HLA polymorphism, antigen processing, and variability in immunogenicity. Artificial intelligence (AI), including machine learning and deep learning approaches, has emerged as a transformative tool capable of addressing these limitations through large-scale integration and analysis of genomic, transcriptomic, proteomic, and immunological data. In this review, we summarize the current role of AI across the peptide cancer vaccine development pipeline, from neoantigen discovery and epitope prioritization to prediction of peptide–HLA binding, antigen presentation, and T-cell receptor recognition. We discuss the application of modern computational frameworks, including pan-allelic prediction models, transformer-based architectures, immunopeptidomics-informed learning, and multi-modal AI systems integrating tumor and immune microenvironment data. Furthermore, we examine the clinical translation of personalized neoantigen vaccines, including their combination with immune checkpoint inhibitors and their emerging role in aggressive malignancies such as glioblastoma. Despite substantial progress, significant challenges remain, including high false-positive prediction rates, limited diversity of training datasets, biological complexity of immunogenicity, and regulatory and manufacturing barriers associated with individualized therapies. Continued integration of AI-driven prediction tools with experimental validation and translational immunology will be essential for the development of clinically effective and scalable precision cancer vaccines.
P. Brlek, Jan Kolić, L. Bulić et al.· Frontiers in Genetics· 0 citations
A data-driven, multi-objective peptide design framework that inte-grates sequence-to-feature transformations using Fast Fourier Transform - based representations, and metric-learning based optimization strategies, to provide an interpretable and computationally efficient alternative for peptide design under limited-data constraints.
A. Trinh· Proceedings of the 3rd Found...· 0 citations