相关实验视频

Updated: Jul 4, 2025

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

蛋白质语言模型满足了减少的氨基酸字母表

Ioan Ieremie¹, Rob M Ewing², Mahesan Niranjan¹

¹Vision, Learning & Control Group, University of Southampton, Southampton SO17 1BJ, United Kingdom.

Bioinformatics (Oxford, England)

|February 4, 2024

概括

在减少的氨基酸字母表上训练的蛋白质语言模型 (PLM) 显示,完整的字母表捕获更多细节. 然而,在某些情况下,减少的字母可以提高蛋白质结构预测的准确性.

科学领域:

计算生物学计算生物学
生物信息学是一种生物信息学.
蛋白质科学蛋白质科学

背景情况:

蛋白质语言模型 (PLM) 利用自然语言处理技术进行无监督表示学习.
在各种下游蛋白质相关任务中,PLM显著提高了性能.
之前的研究探讨了基于物理化学性质的减少氨基酸字母,但它们在PLM和折叠模型中的使用仍然未得到充分探索.

研究的目的:

为了评估在减少的氨基酸字母表上训练的PLM的有效性.
了解字母缩减导致的信息丢失如何影响学习的蛋白质表示和下游任务执行.
用ESMFold评估缩小字母对蛋白质结构预测的影响.

主要方法:

在减少氨基酸字母的数据集上训练蛋白质语言模型.
比较在全字母和缩小字母训练的PLM的代表能力.
使用ESMFold来预测蛋白质的结构,将其翻译成缩小的字母.
分析缩小字母对结构预测准确性的影响 (LDDT-Cα).

主要成果:

在全氨基酸字母表和广泛的序列数据上接受培训的PLM与缩小字母表方法相比,可以捕获更细致的细节.
使用减少字母的ESMFold进行蛋白质结构预测,在50个CASP14目标中的10个中显示出更好的结果.
在特定蛋白质的LDDT-Cα差异中,结构预测准确度的提高达到了19%.

结论:

虽然PLM中的完整字母保留了更详细的进化信息,但减少的字母提供了在特定情况下提高蛋白质结构预测准确性的潜在途径.
这些发现突出了信息丰富性和下游应用的潜在改进之间的权衡,例如在使用减少的氨基酸字母表时进行结构预测.

更多相关视频

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

Residue-specific Incorporation of Noncanonical Amino Acids into Model Proteins Using an Escherichia coli Cell-free Transcription-translation System

Residue-specific Incorporation of Noncanonical Amino Acids into Model Proteins Using an Escherichia coli Cell-free Transcription-translation System

Published on: August 1, 2016

相关概念视频

From DNA to Protein

From DNA to Protein

The flow of genetic information in cells from DNA to mRNA to protein is described by the central dogma, which states that genes specify the sequence of mRNAs, which in turn specify the sequence of amino acids making up all proteins. The decoding of one molecule to another is performed by specific proteins and RNAs. Because the information stored in DNA is so central to cellular function, it makes intuitive sense that the cell would make mRNA copies of this information for protein synthesis...

Amino acids

Amino acids

Amino acids are the monomers that comprise proteins. Each amino acid has the same fundamental structure, which consists of a central carbon atom, or the alpha (α) carbon, bonded to an amino group (NH2), a carboxyl group (COOH), and to a hydrogen atom. Every amino acid also has another atom or group of atoms bonded to the central atom known as the R group. There are 20 common amino acids present in proteins, each with a different R group. Variation in the amino acid sequence is responsible...

tRNA Activation

tRNA Activation

Aminoacyl-tRNA synthetases are present in both eukaryotes and bacteria. Though eukaryotes have 20 different aminoacyl-tRNA synthetases to couple to 20 amino acids, many bacteria do not have genes for all of these aminoacyl-tRNA synthetases. Despite this, they still use all 20 amino acids to synthesize their proteins. For instance, some bacteria do not have the gene encoding the enzyme that couples glutamine with its partner tRNA. In these organisms, one enzyme adds glutamic acid to all of the...

What are Proteins?

What are Proteins?

Proteins are polymers of amino acids linked together by peptide bonds. Proteins and polypeptides are interchangeably used to refer to long chains of amino acids. However, polypeptides have a molecular weight of fewer than 10,000 daltons, while proteins have greater molecular weight. Polypeptides with less than 20 amino acids are called oligopeptides or simply peptides. Interactions among the constituent amino acid side chains of proteins help them fold into a stable 3-dimensional...

The Central Dogma

The Central Dogma

Protein Organization

Protein Organization