PeptiVerse is a unified platform that leverages large foundation models to predict diverse peptide developability properties from both amino acid sequences and SMILES representations, enabling accessible, scalable analysis for peptide drug design.
Abstract
Therapeutic peptides combine the advantages of small molecules and antibodies, offering target flexibility and low immunogenicity, yet their successful translation requires careful evaluation of multiple developability properties beyond binding alone. As chemically modified peptides become increasingly common in drug design, no unified platform currently supports systematic property assessment across both canonical sequences and SMILES-based representations. Leveraging the generalizability of large foundational models trained on protein and chemical data, we introduce PeptiVerse, a universal therapeutic peptide property prediction platform. PeptiVerse accepts either amino acid sequences or chemically modified peptide SMILES, delivers state-of-the-art performance across diverse property prediction tasks, and provides both a web interface and open-source implementation for rapid, accessible, and scalable peptide developability analysis. By unifying property prediction across representations, PeptiVerse directly supports early-stage peptide therapeutic development campaigns and property-aware generative design workflows. Therapeutic peptides are an increasingly important drug modality, combining the flexibility of small molecules with the specificity and low immunogenicity of antibodies, but their development requires simultaneous optimization of multiple physicochemical and pharmacological properties. Here, the authors present PeptiVerse, a unified platform that leverages large foundation models to predict diverse peptide developability properties from both amino acid sequences and SMILES representations, enabling accessible, scalable analysis for peptide drug design.
Abstract Therapeutic peptides show many biological activities and are now widely viewed as promising candidates for new drug development. Accurate functional annotation of therapeutic peptides is still difficult. This difficulty comes from their short sequence length, strong structural flexibility, and the presence of multiple biological functions within a single peptide.Here, we introduce Structure-Aware Multi-Label Therapeutic Peptide Predictor (SA-MTP), a structure-aware framework designed for multifunctional annotation of therapeutic peptides. SA-MTP combines pretrained protein language models with a graph attention network to capture sequence semantics and probabilistic structural features. Input-dependent structure-aware graphs are constructed to describe conformational variation, which is especially common in short peptides. Benchmarking experiments across 15 therapeutic function categories were conducted using datasets. The results show that SA-MTP achieves better performance than existing methods across several evaluation metrics, including accuracy, F1-score, and Matthews correlation coefficient.
Wenping Yu, Zhewen Li, Wei Xu et al.· Briefings in Bioinformatics· 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.
Accurate prediction of peptide structures and peptide-receptor complexes is essential for rational peptide drug development. However, the inherent conformational flexibility of short and disordered peptides presents a fundamental challenge. The AlphaFold model series, which has progressed from AlphaFold2 through AlphaFold-Multimer to AlphaFold3, has substantially advanced computational peptide structure prediction through innovations in geometric reasoning (invariant point attention) and interface-focused confidence metrics (ipTM score), achieving high accuracy for both monomeric peptide structures and multi-chain complexes. However, these models output static conformations, whereas many bioactive peptides adopt their functional conformations only upon binding-often corresponding to low-probability states that static predictions may overlook, leading to failures in virtual screening. This review synthesizes recent advances in the AlphaFold series for peptide studies and applications, discusses their current strengths in structure prediction and receptor-binding analysis, and examines the limitations in capturing conformational dynamics, transient interactions, and chemical modifications. Recent studies have suggested that integrated computational strategies that combine AlphaFold predictions with molecular dynamics simulations, free energy calculations, and ensemble sampling to enhance predictive accuracy and better represent the dynamic nature of peptide-drug interactions. These complementary approaches position AlphaFold as a central computational platform in structure-guided peptide drug design, enabling more efficient lead identification and optimization while bridging the gap between static computational predictions and the complex biophysical reality of peptide therapeutics.
Introduction Antibody-based therapeutics are a rapidly expanding class of treatments, with over 200 approved candidates and thousands in clinical trials. Computational pre-filtering using protein structure prediction models has the potential to reduce the cost of wet-lab screening, yet the relationship between model confidence measures and functional binding properties remains incompletely understood. Here, we evaluate whether confidence measures produced by contemporary open-source protein structure prediction models are suitable for in silico screening of nanobody–antigen interactions. Methods We benchmark Boltz-2, Chai-1, IntFold, and AlphaFold3 using two complementary tasks: (i) ranking true nanobody–antigen binding complexes above non-binding bait pairs across 17 antigens, and (ii) detecting out-of-distribution sequences generated by alanine substitution of all complementarity-determining region residues. We further assess confidence measure sensitivity through progressive alanine mutagenesis on 13 nanobody–antigen complexes spanning the range of CDR3 lengths in our dataset and evaluate generalizability using data from a camelid immunization campaign against CD33. Results Boltz-2-derived confidence measures achieved the highest median performance for identifying true binders. Local confidence measures, including pLDDT and interface- or CDR-focused metrics, were most effective at detecting out-of-distribution sequences and exhibited the greatest sensitivity to mutations. No single confidence measure performed best across both tasks, and all evaluated protein structure prediction models showed limited generalization to previously unseen antigens. Discussion Our results suggest that robust in silico nanobody candidate selection should combine complementary global and local confidence measures rather than relying on a single metric. These findings provide practical guidance for integrating open-source protein structure prediction models into AI-driven nanobody discovery pipelines while highlighting the need for improved generalization across antigens.
Yannick Vogt, Rebekka Roßberg, Jan Habermann et al.· Frontiers in Bioinformatics· 0 citations
Predicting drug-target affinity (DTA) is becoming increasingly vital in the field of drug discovery. Currently, many methods focus solely on the overall encoding of proteins, overlooking the abundant information contained within protein peptides. Therefore, this paper proposes a novel protein segment capture strategy for drug-target affinity prediction (SAPDTA), which is designed to extract local protein features through a local block capture approach. This strategy supports adaptive segmentation of amino acid chains, enabling more flexible extraction of protein structure information at different levels. A hybrid dual-network bilinear interaction module is proposed to address the challenge of protein feature extraction at various scales. Moreover, bilinear interaction blocks are employed to combine and process the chemical properties of drugs with the biological characteristics of their targets. SAPDTA’s performance is assessed using two publicly accessible DTA datasets (Davis and KIBA). According to the experimental results, SAPDTA demonstrates competitive performance compared to existing models across all evaluation metrics. Furthermore, visualization results on the ToxCast dataset highlight the model’s sensitivity to complex drug structures, revealing its capability to understand underlying structure-function relationships.
Zihao Fang, Guanqiu Qi, Stanley Tang et al.· Sensors and AI· 0 citations
Cyclic peptide drugs show great potential in antiviral, antibacterial, anticancer, and immunomodulatory therapies, yet accurate prediction of their membrane permeability remains challenging. Existing approaches based on SMILES, molecular graphs, or 3D structures have inherent limitations: SMILES lack spatial information, graphs inadequately capture stereochemistry, and 3D methods are sensitive to conformational variability. Moreover, current multimodal fusion strategies often fail to effectively integrate heterogeneous molecular information. To address these challenges, we propose MultiMol, a multimodal framework that integrates SMILES sequences, molecular images, molecular graphs, and 3D conformations through tailored pre-training tasks and a scalable fusion mechanism. Experiments show that MultiMol consistently outperforms existing methods in cyclic peptide permeability prediction. Visualization and interpretability analyses further demonstrate its strong feature extraction and generalization capabilities. MultiMol also prioritizes promising KRAS-targeting cyclic peptides, supporting its practical utility in virtual screening. The code is available at https://github.com/chaoxiuxiu/multi-mol.
Haowen Chen, Xiuxiu Chao, Weihao Ou et al.· IEEE journal of biomedical a...· 0 citations