Dataset Information

Cross-species conservation of complementary amino acid-ribonucleobase interactions and their potential for ribosome-free encoding.

ABSTRACT: The role of amino acid-RNA nucleobase interactions in the evolution of RNA translation and protein-mRNA autoregulation remains an open area of research. We describe the inference of pairwise amino acid-RNA nucleobase interaction preferences using structural data from known RNA-protein complexes. We observed significant matching between an amino acid's nucleobase affinity and corresponding codon content in both the standard genetic code and mitochondrial variants. Furthermore, we showed that knowledge of nucleobase preferences allows statistically significant prediction of protein primary sequence from mRNA using purely physiochemical information. Interestingly, ribosomal primary sequences were more accurately predicted than non-ribosomal sequences, suggesting a potential role for direct amino acid-nucleobase interactions in the genesis of amino acid-based ribosomal components. Finally, we observed matching between amino acid-nucleobase affinities and corresponding mRNA sequences in 35 evolutionarily diverse proteomes. We believe these results have important implications for the study of the evolutionary origins of the genetic code and protein-mRNA cross-regulation.

SUBMITTER: Cannon JG

PROVIDER: S-EPMC4674897 | biostudies-literature | 2015 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Cross-species conservation of complementary amino acid-ribonucleobase interactions and their potential for ribosome-free encoding.

Cannon John G D JG Sherman Rachel M RM Wang Victoria M Y VM Newman Grace A GA

Scientific reports 20151210

The role of amino acid-RNA nucleobase interactions in the evolution of RNA translation and protein-mRNA autoregulation remains an open area of research. We describe the inference of pairwise amino acid-RNA nucleobase interaction preferences using structural data from known RNA-protein complexes. We observed significant matching between an amino acid's nucleobase affinity and corresponding codon content in both the standard genetic code and mitochondrial variants. Furthermore, we showed that know ...[more]

PMID: 26656258

Similar Datasets

Project description:BackgroundThe number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction - a process called 'end-to-end learning' - has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN.ResultsBy using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension.ConclusionOur study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Dataset Information

Cross-species conservation of complementary amino acid-ribonucleobase interactions and their potential for ribosome-free encoding.

Publications

Cross-species conservation of complementary amino acid-ribonucleobase interactions and their potential for ribosome-free encoding.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure