Informative RNA base embedding for RNA structural alignment and clustering by deep representation learning

Comprehensive translational profiling and STE AI uncover rapid control of protein biosynthesis during cell stress

Translational control is important in all life, but it remains a challenge to accurately quantify. When ribosomes translate messenger (m)RNA into proteins, they attach to the mRNA in series, forming poly(ribo)somes, and can co-localize. Here, we computationally model new types of co-localized ribosomal complexes on mRNA and identify them using enhanced translation complex profile sequencing (eTCP-seq) based on rapid in vivo crosslinking. We detect long disome footprints outside regions of non-random elongation stalls and show these are linked to translation initiation and protein biosynthesis rates. We subject footprints of disomes and other translation complexes to artificial intelligence (AI) analysis and construct a new, accurate and self-normalized measure of translation, termed stochastic translation efficiency (STE). We then apply STE to investigate rapid changes to mRNA translation in yeast undergoing glucose depletion. Importantly, we show that, well beyond tagging elongation stalls, footprints of co-localized ribosomes provide rich insight into translational mechanisms, polysome dynamics and topology. STE AI ranks cellular mRNAs by absolute translation rates under given conditions, can assist in identifying its control elements and will facilitate the development of next-generation synthetic biology designs and mRNA-based therapeutics.

ac4C-AFL: A high-precision identification of human mRNA N4-acetylcytidine sites based on adaptive feature representation learning

RNA N4-acetylcytidine (ac4C) is a highly conserved RNA modification that plays a crucial role in controlling mRNA stability, processing, and translation. Consequently, accurate identification of ac4C sites across the genome is critical for understanding gene expression regulation mechanisms. In this study, we have developed ac4C-AFL, a bioinformatics tool that precisely identifies ac4C sites from primary RNA sequences. In ac4C-AFL, we identified the optimal sequence length for model building and implemented an adaptive feature representation strategy that is capable of extracting the most representative features from RNA. To identify the most relevant features, we proposed a novel ensemble feature importance scoring strategy to rank features effectively. We then used this information to conduct the sequential forward search, which individually determine the optimal feature set from the 16 sequence-derived feature descriptors. Utilizing these optimal feature descriptors, we constructed 176 baseline models using 11 popular classifiers. The most efficient baseline models were identified using the two-step feature selection approach, whose predicted scores were integrated and trained with the appropriate classifier to develop the final prediction model. Our rigorous cross-validations and independent tests demonstrate that ac4C-AFL surpasses contemporary tools in predicting ac4C sites. Moreover, we have developed a publicly accessible web server at https://balalab-skku.org/ac4C-AFL/.

A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions

The 5' UTR, a regulatory region at the beginning of an mRNA molecule, plays a crucial role in regulating the translation process and impacts the protein expression level. Language models have showcased their effectiveness in decoding the functions of protein and genome sequences. Here, we introduced a language model for 5' UTR, which we refer to as the UTR-LM. The UTR-LM is pre-trained on endogenous 5' UTRs from multiple species and is further augmented with supervised information including secondary structure and minimum free energy. We fine-tuned the UTR-LM in a variety of downstream tasks. The model outperformed the best known benchmark by up to 5% for predicting the Mean Ribosome Loading, and by up to 8% for predicting the Translation Efficiency and the mRNA Expression Level. The model also applies to identifying unannotated Internal Ribosome Entry Sites within the untranslated region and improves the AUPR from 0.37 to 0.52 compared to the best baseline. Further, we designed a library of 211 novel 5' UTRs with high predicted values of translation efficiency and evaluated them via a wet-lab assay. Experiment results confirmed that our top designs achieved a 32.5% increase in protein production level relative to well-established 5' UTR optimized for therapeutics.

DeepRaccess: high-speed RNA accessibility prediction using deep learning

RNA accessibility is a useful RNA secondary structural feature for predicting RNA-RNA interactions and translation efficiency in prokaryotes. However, conventional accessibility calculation tools, such as Raccess, are computationally expensive and require considerable computational time to perform transcriptome-scale analysis. In this study, we developed DeepRaccess, which predicts RNA accessibility based on deep learning methods. DeepRaccess was trained to take artificial RNA sequences as input and to predict the accessibility of these sequences as calculated by Raccess. Simulation and empirical dataset analyses showed that the accessibility predicted by DeepRaccess was highly correlated with the accessibility calculated by Raccess. In addition, we confirmed that DeepRaccess could predict protein abundance in E.coli with moderate accuracy from the sequences around the start codon. We also demonstrated that DeepRaccess achieved tens to hundreds of times software speed-up in a GPU environment. The source codes and the trained models of DeepRaccess are freely available at https://github.com/hmdlab/DeepRaccess.

Sequence pre-training-based graph neural network for predicting lncRNA-miRNA associations

MicroRNAs (miRNAs) silence genes by binding to messenger RNAs, whereas long non-coding RNAs (lncRNAs) act as competitive endogenous RNAs (ceRNAs) that can relieve miRNA silencing effects and upregulate target gene expression. The ceRNA association between lncRNAs and miRNAs has been a research hotspot due to its medical importance, but it is challenging to verify experimentally. In this paper, we propose a novel deep learning scheme, i.e. sequence pre-training-based graph neural network (SPGNN), that combines pre-training and fine-tuning stages to predict lncRNA-miRNA associations from RNA sequences and the existing interactions represented as a graph. First, we utilize a sequence-to-vector technique to generate pre-trained embeddings based on the sequences of all RNAs during the pre-training stage. In the fine-tuning stage, we use Graph Neural Network to learn node representations from the heterogeneous graph constructed using lncRNA-miRNA association information. We evaluate our proposed scheme SPGNN on our newly collected animal lncRNA-miRNA association dataset and demonstrate that combining the $k$-mer technique and Doc2vec model for pre-training with the Simple Graph Convolution Network for fine-tuning is effective in predicting lncRNA-miRNA associations. Our approach outperforms state-of-the-art baselines across various evaluation metrics. We also conduct an ablation study and hyperparameter analysis to verify the effectiveness of each component and parameter of our scheme. The complete code and dataset are available on GitHub: https://github.com/zixwang/SPGNN.

Recent trends in RNA informatics: a review of machine learning and deep learning for RNA secondary structure prediction and RNA drug discovery

Computational analysis of RNA sequences constitutes a crucial step in the field of RNA biology. As in other domains of the life sciences, the incorporation of artificial intelligence and machine learning techniques into RNA sequence analysis has gained significant traction in recent years. Historically, thermodynamics-based methods were widely employed for the prediction of RNA secondary structures; however, machine learning-based approaches have demonstrated remarkable advancements in recent years, enabling more accurate predictions. Consequently, the precision of sequence analysis pertaining to RNA secondary structures, such as RNA-protein interactions, has also been enhanced, making a substantial contribution to the field of RNA biology. Additionally, artificial intelligence and machine learning are also introducing technical innovations in the analysis of RNA-small molecule interactions for RNA-targeted drug discovery and in the design of RNA aptamers, where RNA serves as its own ligand. This review will highlight recent trends in the prediction of RNA secondary structure, RNA aptamers and RNA drug discovery using machine learning, deep learning and related technologies, and will also discuss potential future avenues in the field of RNA informatics.

Deep self-supervised learning for biosynthetic gene cluster detection and product classification

Natural products are chemical compounds that form the basis of many therapeutics used in the pharmaceutical industry. In microbes, natural products are synthesized by groups of colocalized genes called biosynthetic gene clusters (BGCs). With advances in high-throughput sequencing, there has been an increase of complete microbial isolate genomes and metagenomes, from which a vast number of BGCs are undiscovered. Here, we introduce a self-supervised learning approach designed to identify and characterize BGCs from such data. To do this, we represent BGCs as chains of functional protein domains and train a masked language model on these domains. We assess the ability of our approach to detect BGCs and characterize BGC properties in bacterial genomes. We also demonstrate that our model can learn meaningful representations of BGCs and their constituent domains, detect BGCs in microbial genomes, and predict BGC product classes. These results highlight self-supervised neural networks as a promising framework for improving BGC prediction and classification.

MncR: Late Integration Machine Learning Model for Classification of ncRNA Classes Using Sequence and Structural Encoding

Non-coding RNA (ncRNA) classes take over important housekeeping and regulatory functions and are quite heterogeneous in terms of length, sequence conservation and secondary structure. High-throughput sequencing reveals that the expressed novel ncRNAs and their classification are important to understand cell regulation and identify potential diagnostic and therapeutic biomarkers. To improve the classification of ncRNAs, we investigated different approaches of utilizing primary sequences and secondary structures as well as the late integration of both using machine learning models, including different neural network architectures. As input, we used the newest version of RNAcentral, focusing on six ncRNA classes, including lncRNA, rRNA, tRNA, miRNA, snRNA and snoRNA. The late integration of graph-encoded structural features and primary sequences in our MncR classifier achieved an overall accuracy of >97%, which could not be increased by more fine-grained subclassification. In comparison to the actual best-performing tool ncRDense, we had a minimal increase of 0.5% in all four overlapping ncRNA classes on a similar test set of sequences. In summary, MncR is not only more accurate than current ncRNA prediction tools but also allows the prediction of long ncRNA classes (lncRNAs, certain rRNAs) up to 12.000 nts and is trained on a more diverse ncRNA dataset retrieved from RNAcentral.