The Master Database of All Possible RNA Sequences and Its Integration with RNAcmap for RNA Homology Search

Chen, Ke; Litfin, Thomas; Singh, Jaswinder; Zhan, Jian; Zhou, Yaoqi

doi:10.1101/2023.02.01.526559

Cited by 5 publications

(6 citation statements)

References 41 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deeper MSAs for RNAs can be constructed using the new RNA database published by Chen at al. [77]. To improve the input ss we recommend to use a consensus ss predicted by multiple methods, especially the latest ML-based methods [78].…”

Section: Discussionmentioning

confidence: 99%

Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction

Bahai,

Kwoh,

et al. 2024

Preprint

View full text Add to dashboard Cite

The 3D structure of RNA critically influences its functionality, and understanding this structure is vital for deciphering RNA biology. Experimental methods for determining RNA structures are labour-intensive, expensive, and time-consuming. Computational approaches have emerged as valuable tools, leveraging physics-based-principles and machine learning to predict RNA structures rapidly. Despite advancements, the accuracy of computational methods remains modest, especially when compared to protein structure prediction. Deep learning methods, while successful in protein structure prediction, have shown some promise for RNA structure prediction as well but face unique challenges. This study systematically benchmarks state-of-the-art deep learning methods for RNA structure prediction across diverse datasets. Our aim is to identify factors influencing performance variation, such as RNA family diversity, sequence length, RNA type, multiple sequence alignment (MSA) quality, and deep learning model architecture. We show that generally ML-based methods perform much better than non-ML methods on most RNA targets, although the performance difference is not substantial when working with unseen novel or synthetic RNAs. The quality of the MSA and secondary structure prediction both play an important role and most methods are not able to predict non-Watson-Crick pairs in the RNAs. Overall, DeepFoldRNA has the best prediction followed by DRFold as the second best method. Finally, we also suggest possible mitigations to improve the quality of the prediction for future method development.

show abstract

Section: Discussionmentioning

confidence: 99%

Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction

Bahai,

Kwoh,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…We downloaded 4069 RNA families (version 14.7) from https://rfam.xfam.org on 09/04/2022. The fully automatic RNAcmap3 for homolog search and sequence alignment ( 33 ) was employed for these 4069 RNA families by using their covariance models (CMs) for each family. Although the language model is unsupervised learning, we excluded the Rfam families which contain RNA sequences with experimentally determined structures in order to minimize potential overfitting for structural inference.…”

Section: Methodsmentioning

confidence: 99%

“…This problem was solved with the development of RNAcmap ( 30 ), which integrates BLAST-N, Infernal and a secondary structure predictor such as RNAfold ( 31 ) for a fully automatic homology search. RNAcmap was further improved with additional iteration ( 32 ) and a large expansion of the sequence database ( 33 ).…”

Section: Introductionmentioning

confidence: 99%

Multiple sequence alignment-based RNA language model and its application to structural inference

Zhang,

Lang,

Jiang

et al. 2023

Nucleic Acids Research

Self Cite

View full text Add to dashboard Cite

Compared with proteins, DNA and RNA are more difficult languages to interpret because four-letter coded DNA/RNA sequences have less information content than 20-letter coded protein sequences. While BERT (Bidirectional Encoder Representations from Transformers)-like language models have been developed for RNA, they are ineffective at capturing the evolutionary information from homologous sequences because unlike proteins, RNA sequences are less conserved. Here, we have developed an unsupervised multiple sequence alignment-based RNA language model (RNA-MSM) by utilizing homologous sequences from an automatic pipeline, RNAcmap, as it can provide significantly more homologous sequences than manually annotated Rfam. We demonstrate that the resulting unsupervised, two-dimensional attention maps and one-dimensional embeddings from RNA-MSM contain structural information. In fact, they can be directly mapped with high accuracy to 2D base pairing probabilities and 1D solvent accessibilities, respectively. Further fine-tuning led to significantly improved performance on these two downstream tasks compared with existing state-of-the-art techniques including SPOT-RNA2 and RNAsnap2. By comparison, RNA-FM, a BERT-based RNA language model, performs worse than one-hot encoding with its embedding in base pair and solvent-accessible surface area prediction. We anticipate that the pre-trained RNA-MSM model can be fine-tuned on many other tasks related to RNA structure and function.

show abstract

“…We downloaded 4069 RNA families (version 14.7) from https://rfam.xfam.org on 09/04/2022. The fully automatic RNAcmap3 for homolog search and sequence alignment 34 was employed for these 4069 RNA families by using their covariance models (CM) for each family. Although the language model is unsupervised learning, we excluded the Rfam families which contains RNA sequences with experimentally determined structures to minimize potential over-fitting for structural inference.…”

Section: Msa Generationmentioning

confidence: 99%

“…This problem was solved with the development of RNAcmap 31 , which integrates BLAST-N, Infernal, and a secondary structure predictor such as RNAfold 32 for a fully automatic homology search. RNAcmap was further improved with additional iteration 33 and a large expansion of sequence database 34 . This work reports an RNA MSA-transformer language model (RNA-MSM) based on homologous sequences generated from RNAcmap3.…”

Section: Introductionmentioning

confidence: 99%

Multiple sequence-alignment-based RNA language model and its application to structural inference

Zhang

Lang

Jiang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Compared to proteins, DNA and RNA are more difficult languages to interpret because 4-letter-coded DNA/RNA sequences have less information content than 20-letter-coded protein sequences. While BERT (Bidirectional Encoder Representations from Transformers)-like language models have been developed for RNA, they are ineffective at capturing the evolutionary information from homologous sequences because unlike proteins, RNA sequences are less conserved. Here, we have developed an unsupervised Multiple sequence-alignment-based RNA language model (RNA-MSM) by utilizing homologous sequences from an automatic pipeline, RNAcmap. The resulting unsupervised, two-dimensional attention maps and one-dimensional embeddings from RNA-MSM can be directly mapped with high accuracy to 2D base pairing probabilities and 1D solvent accessibilities, respectively. Further fine-tuning led to significantly improved performance on these two downstream tasks over existing state-of-the-art techniques. We anticipate that the pre-trained RNA-MSM model can be fine-tuned on many other tasks related to RNA structure and function.

show abstract

The Master Database of All Possible RNA Sequences and Its Integration with RNAcmap for RNA Homology Search

Cited by 5 publications

References 41 publications

Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction

Systematic benchmarking of deep-learning methods for tertiary RNA structure prediction

Multiple sequence alignment-based RNA language model and its application to structural inference

Multiple sequence-alignment-based RNA language model and its application to structural inference

Contact Info

Product

Resources

About