Search for: All records

Abstract MotivationRNA design is the search for a sequence or set of sequences that will fold to desired structure, also known as the inverse problem of RNA folding. However, the sequences designed by existing algorithms often suffer from low ensemble stability, which worsens for long sequence design. Additionally, for many methods only a small number of sequences satisfying the MFE criterion can be found by each run of design. These drawbacks limit their use cases. ResultsWe propose an innovative optimization paradigm, SAMFEO, which optimizes ensemble objectives (equilibrium probability or ensemble defect) by iterative search and yields a very large number of successfully designed RNA sequences as byproducts. We develop a search method which leverages structure level and ensemble level information at different stages of the optimization: initialization, sampling, mutation, and updating. Our work, while being less complicated than others, is the first algorithm that is able to design thousands of RNA sequences for the puzzles from the Eterna100 benchmark. In addition, our algorithm solves the most Eterna100 puzzles among all the general optimization based methods in our study. The only baseline solving more puzzles than our work is dependent on handcrafted heuristics designed for a specific folding model. Surprisingly, our approach shows superiority on designing long sequences for structures adapted from the database of 16S Ribosomal RNAs. Availability and implementationOur source code and data used in this article is available at https://github.com/shanry/SAMFEO. 

Abstract Many RNAs function through RNA–RNA interactions. Fast and reliable RNA structure prediction with consideration of RNA–RNA interaction is useful, however, existing tools are either too simplistic or too slow. To address this issue, we present LinearCoFold, which approximates the complete minimum free energy structure of two strands in linear time, and LinearCoPartition, which approximates the cofolding partition function and base pairing probabilities in linear time. LinearCoFold and LinearCoPartition are orders of magnitude faster than RNAcofold. For example, on a sequence pair with combined length of 26,190 nt, LinearCoFold is 86.8× faster than RNAcofold MFE mode, and LinearCoPartition is 642.3× faster than RNAcofold partition function mode. Surprisingly, LinearCoFold and LinearCoPartition’s predictions have higher PPV and sensitivity of intermolecular base pairs. Furthermore, we apply LinearCoFold to predict the RNA–RNA interaction between SARS-CoV-2 genomic RNA (gRNA) and human U4 small nuclear RNA (snRNA), which has been experimentally studied, and observe that LinearCoFold’s prediction correlates better with the wet lab results than RNAcofold’s. 

Abstract Many RNAs fold into multiple structures at equilibrium, and there is a need to sample these structures according to their probabilities in the ensemble. The conventional sampling algorithm suffers from two limitations: (i) the sampling phase is slow due to many repeated calculations; and (ii) the end-to-end runtime scales cubically with the sequence length. These issues make it difficult to be applied to long RNAs, such as the full genomes of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). To address these problems, we devise a new sampling algorithm, LazySampling, which eliminates redundant work via on-demand caching. Based on LazySampling, we further derive LinearSampling, an end-to-end linear time sampling algorithm. Benchmarking on nine diverse RNA families, the sampled structures from LinearSampling correlate better with the well-established secondary structures than Vienna RNAsubopt and RNAplfold. More importantly, LinearSampling is orders of magnitude faster than standard tools, being 428× faster (72 s versus 8.6 h) than RNAsubopt on the full genome of SARS-CoV-2 (29 903 nt). The resulting sample landscape correlates well with the experimentally guided secondary structure models, and is closer to the alternative conformations revealed by experimentally driven analysis. Finally, LinearSampling finds 23 regions of 15 nt with high accessibilities in the SARS-CoV-2 genome, which are potential targets for COVID-19 diagnostics and therapeutics. 

The constant emergence of COVID-19 variants reduces the effectiveness of existing vaccines and test kits. Therefore, it is critical to identify conserved structures in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) genomes as potential targets for variant-proof diagnostics and therapeutics. However, the algorithms to predict these conserved structures, which simultaneously fold and align multiple RNA homologs, scale at best cubically with sequence length and are thus infeasible for coronaviruses, which possess the longest genomes (∼30,000 nt) among RNA viruses. As a result, existing efforts on modeling SARS-CoV-2 structures resort to single-sequence folding as well as local folding methods with short window sizes, which inevitably neglect long-range interactions that are crucial in RNA functions. Here we present LinearTurboFold, an efficient algorithm for folding RNA homologs that scales linearly with sequence length, enabling unprecedented global structural analysis on SARS-CoV-2. Surprisingly, on a group of SARS-CoV-2 and SARS-related genomes, LinearTurboFold’s purely in silico prediction not only is close to experimentally guided models for local structures, but also goes far beyond them by capturing the end-to-end pairs between 5 ′ and 3 ′ untranslated regions (UTRs) (∼29,800 nt apart) that match perfectly with a purely experimental work. Furthermore, LinearTurboFold identifies undiscovered conserved structures and conserved accessible regions as potential targets for designing efficient and mutation-insensitive small-molecule drugs, antisense oligonucleotides, small interfering RNAs (siRNAs), CRISPR-Cas13 guide RNAs, and RT-PCR primers. LinearTurboFold is a general technique that can also be applied to other RNA viruses and full-length genome studies and will be a useful tool in fighting the current and future pandemics. 

Simultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay. However, due to the lack of large-scale, high-quality simultaneous translation datasets, most such systems are still trained on conventional full-sentence bitexts. This is far from ideal for the simultaneous scenario due to the abundance of unnecessary long-distance reorderings in those bitexts. We propose a novel method that rewrites the target side of existing full-sentence corpora into simultaneous-style translation. Experiments on Zh→En and Ja→En simultaneous translation show substantial improvements (up to +2.7 BLEU) with the addition of these generated pseudo-references. 

Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate these issues, recent efforts attempt to directly translate the source speech into target text simultaneously, but this is much harder due to the combination of two separate tasks. We instead propose a new paradigm with the advantages of both cascaded and endto-end approaches. The key idea is to use two separate, but synchronized, decoders on streaming ASR and direct speech-to-text translation (ST), respectively, and the intermediate results of ASR guide the decoding policy of (but is not fed as input to) ST. During training time, we use multitask learning to jointly learn these two tasks with a shared encoder. En-toDe and En-to-Es experiments on the MuSTC dataset demonstrate that our proposed technique achieves substantially better translation quality at similar levels of latency.