Deep Learning-Based Advances in Protein Structure Prediction

Abstract

Obtaining an accurate description of protein structure is a fundamental step toward understanding the underpinning of biology. Although recent advances in experimental approaches have greatly enhanced our capabilities to experimentally determine protein structures, the gap between the number of protein sequences and known protein structures is ever increasing. Computational protein structure prediction is one of the ways to fill this gap. Recently, the protein structure prediction field has witnessed a lot of advances due to Deep Learning (DL)-based approaches as evidenced by the success of AlphaFold2 in the most recent Critical Assessment of protein Structure Prediction (CASP14). In this article, we highlight important milestones and progresses in the field of protein structure prediction due to DL-based methods as observed in CASP experiments. We describe advances in various steps of protein structure prediction pipeline viz. protein contact map prediction, protein distogram prediction, protein real-valued distance prediction, and Quality Assessment/refinement. We also highlight some end-to-end DL-based approaches for protein structure prediction approaches. Additionally, as there have been some recent DL-based advances in protein structure determination using Cryo-Electron (Cryo-EM) microscopy based, we also highlight some of the important progress in the field. Finally, we provide an outlook and possible future research directions for DL-based approaches in the protein structure prediction arena.

Natural Compound ZINC12899676 Reduces Porcine Epidemic Diarrhea Virus Replication by Inhibiting the Viral NTPase Activity

“…However, there is lack of online AlphaFold service to utilize, and it demands ultra-high hardware to deploy locally. Reassuringly, we selected the PEDV NTPase structure modeled by trRosetta, which showed performance similar to AlphaFold ( Pakhrin et al, 2021 ). In addition, other researchers revealed the enzyme catalytic center of several coronavirus replicative enzymes.…”

Interfacial Peptides as Affinity Modulating Agents of Protein-Protein Interactions

“…Recently, the AlphaFold2 approach has emerged as a powerful in silico instrument for the prediction of structure, topology, conformation and variants interpretation of most soluble and membrane proteins [ 144 , 145 ]. In the context of drug discovery, it will contribute to the optimization of binding models of pharmacological agents to their novel target proteins.…”

RNA Cleavage Properties of Nucleobase-Specific RNase MC1 and Cusativin Are Determined by the Dinucleotide-Binding Interactions in the Enzyme-Active Site

“…Nucleobase specificity of RNases is computed by the spectrophotometric kinetic analysis using dinucleotide or homopolymer substrates [17,18] and from the structural analysis of enzyme-nucleotide complexes [9,19,20]. Tertiary structures predicted based on the evolutionarily related structural templates of homologous proteins [21,22] are also being used for drug discovery, design, and understanding the site-specific interactions with small molecules or proteins [23,24]. Studies involving such tertiary structures and dinucleotide sequences could also help explain why bonds in certain dinucleotide sequences are not cleaved by MC1 and cusativin despite having the appropriate nucleotide in a sequence.…”