Recent Progress of Protein Tertiary Structure Prediction Protein tertiary structure prediction has seen significant advancements, particularly with the integration of artificial intelligence (AI) algorithms. AlphaFold2, an end-to-end deep learning method, has achieved remarkable performance, often competing with experimental structures in the 14th Critical Assessment of Protein Structure Prediction (CASP14). This review discusses various methodologies, assessments, and databases in protein structure prediction, including traditional methods like template-based modeling (TBM) and template-free modeling (FM), as well as recent deep learning-based approaches such as contact/distance-guided methods, end-to-end folding methods, and protein language model (PLM)-based methods. It also covers multi-domain protein structure prediction, CASP experiments, and the recently released AlphaFold Protein Structure Database (AlphaFold DB). The review discusses the advantages, disadvantages, and application scopes of these methods, aiming to provide researchers with insights into the limitations, contexts, and effective selections of protein structure prediction methods. The review begins with an overview of protein structure prediction, including TBM and FM methods. TBM methods predict protein structures by refining existing templates from the PDB, while FM methods construct structures without relying on templates. Recent advancements in deep learning have led to the development of contact/distance-guided methods, end-to-end folding methods, and PLM-based methods. These methods have significantly contributed to various biomedical investigations, including structure-based protein function annotation, mutation analysis, ligand screening, and drug discovery. The review also discusses the progress in multi-domain protein structure prediction, highlighting the challenges and recent developments in this area. The CASP experiments and related assessments are described, along with the introduction of AlphaFold DB. The review emphasizes the importance of accurate and efficient protein structure prediction methods, particularly for multi-domain proteins, and highlights the need for further improvements in this area. The review concludes with a discussion of the latest CASP results, demonstrating the progress made in protein structure prediction.Recent Progress of Protein Tertiary Structure Prediction Protein tertiary structure prediction has seen significant advancements, particularly with the integration of artificial intelligence (AI) algorithms. AlphaFold2, an end-to-end deep learning method, has achieved remarkable performance, often competing with experimental structures in the 14th Critical Assessment of Protein Structure Prediction (CASP14). This review discusses various methodologies, assessments, and databases in protein structure prediction, including traditional methods like template-based modeling (TBM) and template-free modeling (FM), as well as recent deep learning-based approaches such as contact/distance-guided methods, end-to-end folding methods, and protein language model (PLM)-based methods. It also covers multi-domain protein structure prediction, CASP experiments, and the recently released AlphaFold Protein Structure Database (AlphaFold DB). The review discusses the advantages, disadvantages, and application scopes of these methods, aiming to provide researchers with insights into the limitations, contexts, and effective selections of protein structure prediction methods. The review begins with an overview of protein structure prediction, including TBM and FM methods. TBM methods predict protein structures by refining existing templates from the PDB, while FM methods construct structures without relying on templates. Recent advancements in deep learning have led to the development of contact/distance-guided methods, end-to-end folding methods, and PLM-based methods. These methods have significantly contributed to various biomedical investigations, including structure-based protein function annotation, mutation analysis, ligand screening, and drug discovery. The review also discusses the progress in multi-domain protein structure prediction, highlighting the challenges and recent developments in this area. The CASP experiments and related assessments are described, along with the introduction of AlphaFold DB. The review emphasizes the importance of accurate and efficient protein structure prediction methods, particularly for multi-domain proteins, and highlights the need for further improvements in this area. The review concludes with a discussion of the latest CASP results, demonstrating the progress made in protein structure prediction.