Author Correction: Mask-prior-guided denoising diffusion improves inverse protein folding

2026-02-24 · Source: Nature Machine Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Life Sciences & Biology · Depth: Advanced, quick

Summary

An author correction was issued for the article "Mask-prior-guided denoising diffusion improves inverse protein folding," originally published on 16 June 2025, in Nature Machine Intelligence. The correction, published on 24 February 2026, addresses an error in the "Sequence recovery performance" section. Specifically, the original text incorrectly stated that the MapDiff model achieved over 50% recovery rate in predicting "hydrophobic amino acids." This has been corrected to accurately reflect that MapDiff achieved this performance for "hydrophilic amino acids." The updated HTML and PDF versions of the article now incorporate this change, ensuring factual accuracy regarding the model's performance in protein folding predictions.

Key takeaway

For AI researchers evaluating protein folding models, you should note that the MapDiff model's reported performance of over 50% recovery rate applies to hydrophilic amino acids, not hydrophobic ones. This correction, published on February 24, 2026, is crucial for accurately assessing MapDiff's capabilities and ensuring your research relies on precise data regarding its sequence recovery performance.

Key insights

A published correction clarifies MapDiff's amino acid prediction accuracy in inverse protein folding.

Topics

• Inverse Protein Folding
• Denoising Diffusion Models
• MapDiff Model
• Protein Sequence Recovery
• Amino Acid Prediction

Best for: AI Researcher, AI Scientist, Research Scientist

Related on AIssential

• 🔬 The Coolest Diffusion Research Isn't in LLMs — Evan Feinberg & Sergey Edunov, Genesis Molecular AI — Diffusion models, enhanced with physical priors and synthetic data, are achieving critical resolution in 3D protein-ligand prediction, transforming drug discovery.
• Learning Topological Representations for Molecular Dynamics — Masked Flood complex enhances persistent homology for molecular dynamics by incorporating protein-specific structural bias.
• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage — Fun-DDPS combines diffusion models and neural operators for robust, efficient, and physics-consistent CCS modeling.
• Two-dimensional geometric template diffusion for boosting single-sequence protein structure prediction — TDFold uses 2D geometric template diffusion for efficient, accurate single-sequence protein structure prediction.
• ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration — ResilPhase accelerates diffusion models by reformulating inference as stable, derivative-free macro-trajectory extrapolation in ODE space, improving fidelity.
• Conditional diffusion with locality-aware modal alignment for generating diverse protein conformational ensembles — Mac-Diff uses a novel diffusion model with locality-aware attention and PLM embeddings to generate diverse protein conformational ensembles efficiently.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Nature Machine Intelligence.