AI Article Synopsis

  • Proteins are crucial for life, and understanding their shapes can help reveal how they function, but only about 100,000 out of billions of protein sequences have their structures determined due to the lengthy and complex process involved.
  • To overcome the limitations of current methods that struggle with accuracy, especially when no similar structures exist, new computational approaches are needed for large-scale structural biology.
  • The advanced version of the AlphaFold model uses a redesigned neural network that combines machine learning with biological insights, showing competitive accuracy against experimental structures during the CASP14 assessment, thus presenting a breakthrough in protein structure prediction.

Article Abstract

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort, the structures of around 100,000 unique proteins have been determined, but this represents a small fraction of the billions of known protein sequences. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence-the structure prediction component of the 'protein folding problem'-has been an important open research problem for more than 50 years. Despite recent progress, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14), demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8371605PMC
http://dx.doi.org/10.1038/s41586-021-03819-2DOI Listing

Publication Analysis

Top Keywords

protein structure
16
structure prediction
12
structure
9
atomic accuracy
8
protein
7
highly accurate
4
accurate protein
4
prediction alphafold
4
alphafold proteins
4
proteins essential
4

Similar Publications

PDA/PMMA blend membrane utilized for the selective adsorption and separation of heavy metal ions.

Chemistry

December 2024

Central China Normal University, Key Laboratory of Pesticide & Chemical Biology CCNU , Ministry of Education;, 152#, luoyu road, 430079, Wuhan, CHINA.

The detrimental effects of heavy metal aqueous pollution are attracting people's attention increasingly. Membrane separation technology plays a pivotal role in the treatment of aqueous pollution due to its low energy consumption and excellent separation effect. Inspired by the strong adhesion of heavy metal ions by the dopamine in mussel protein, we have fabricated the 5%, 10%, 20% and 30% proportion of polydopamine (PDA)/Polymethyl methacrylate (PMMA) blend membranes with dopamine structure by solvent-induced phase conversion.

View Article and Find Full Text PDF

The threat posed by bacteria resistant to common antibiotics creates an urgent need for novel antimicrobials. Non-ribosomal peptide natural products that bind Lipid II, such as vancomycin, represent a promising source for such agents. The fungal defensin plectasin is one of a family of ribosomally produced miniproteins that exert antimicrobial activity via Lipid II binding.

View Article and Find Full Text PDF

The Schiff base metal complexes containing the transition metal ions Co(II), Ni(II) and Cu(II) were synthesized using their nitrate and acetate salts. An octahedral environment encircling metal complexes has been demonstrated by the findings of multiple spectroscopic approaches that were employed to demonstrate the structure of the metal complexes. The Coats-Redfern method of thermal analysis was employed to carry out the kinetic and thermodynamic calculations.

View Article and Find Full Text PDF

Peptide stapling has emerged as a versatile approach in drug discovery to reinforce secondary structure elements especially α-helices and improve properties of linear bioactive peptides. Inspired by the prevalence of arginine in protein-protein and protein-DNA interfaces, we investigated guanidinium-stapling as a means to constrain helical peptides. Guanidinium stapling was readily achieved on solid support, utilizing two orthogonally protected lysine or unatural α-amino acid residues with an amino function.

View Article and Find Full Text PDF

Polycyclic tetramate macrolactams (PoTeMs) represent a growing class of bioactive natural products that are derived from a common tetramate polyene precursor, lysobacterene A, produced by an unusual bacterial iterative polyketide synthase (PKS) / non-ribosomal peptide synthetase (NRPS). The structural and functional diversity of PoTeMs is biosynthetically elaborated from lysobacterene A by pathway-specific cyclizing and modifying enzymes. This results in diverse core structure decoration and cyclization patterns.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!

A PHP Error was encountered

Severity: Notice

Message: fwrite(): Write of 34 bytes failed with errno=28 No space left on device

Filename: drivers/Session_files_driver.php

Line Number: 272

Backtrace:

A PHP Error was encountered

Severity: Warning

Message: session_write_close(): Failed to write session data using user defined save handler. (session.save_path: /var/lib/php/sessions)

Filename: Unknown

Line Number: 0

Backtrace: