APCyc: AI Framework for Designing Cyclic Peptides with Optimized Drug Properties
Researchers have developed APCyc, an artificial intelligence framework that automates the design of cyclic peptides—promising therapeutic compounds—by explicitly modeling cyclization patterns and optimizing multiple drug-relevant properties simultaneously. Cyclic peptides offer improved stability and binding affinity compared to linear peptides, but their de novo design has been challenging because existing generative models were trained primarily on linear peptide data. This advance could accelerate drug discovery by enabling more effective and controllable design of cyclic peptide therapeutics.
APCyc is a target-aware generative framework that addresses a key limitation in computational drug design: most machine learning models for peptide generation were trained on linear peptides and struggle to capture the specific constraints of cyclization. The framework uses an expanded residue vocabulary and explicitly encodes cyclization-site and linkage-type information, allowing it to learn cyclization-aware representations. By combining these representations with Bayesian posterior guidance, APCyc can steer the generation process toward cyclic peptides that simultaneously satisfy multiple physicochemical property objectives. Experimental results show that the model learns target-dependent cyclization preferences and enables effective multi-property optimization. The authors have made their source code publicly available, supporting reproducibility and broader adoption in the research community.
What's missing
The paper does not provide details on experimental validation against known cyclic peptide therapeutics, comparison with other state-of-the-art cyclic peptide design methods, or results from wet-lab synthesis and binding assays to confirm computational predictions.
What different sources said
- arXiv cs.AICenter
APCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclization
Related
Topology-Aware Thermodynamics Improves DNA Probe Specificity Design
Researchers developed a new framework for designing DNA probes that accounts for the spatial organization of matched sequences, not just overall thermodynamic stability. Traditional methods rely on scalar measures like melting temperature and free energy, which miss how mismatches are distributed along the probe. The approach could improve diagnostic accuracy in applications like HPV detection and gene expression profiling.
Study Identifies Optimal Thermal Dose for Combining Focused Ultrasound with Immunotherapy in Tumors
Researchers used multimodal PET imaging to identify an optimal thermal dose range for focused ultrasound ablation that destroys tumor tissue while preserving conditions for immunotherapy delivery. The study found that excessive heating collapses blood vessels needed for antibody access, while insufficient heating fails to adequately reduce tumor burden. The findings could guide clinical design of combination treatments pairing thermal ablation with immunotherapies.
Plant MSH1 Protein Functions as Mismatch-Directed Nuclease for Organelle Genome Maintenance
Researchers have identified the precise mechanism by which the AtMSH1 protein in Arabidopsis plants recognizes and cleaves DNA mismatches and lesions, preventing mutations in organellar genomes. The protein combines a DNA mismatch recognition module with a nuclease domain that makes staggered cuts at specific positions relative to DNA damage. This discovery explains how plants maintain unusually low mutation rates in their mitochondrial and chloroplast DNA compared to other eukaryotes.