Machine learning a model for RNA structure prediction
Nicola Calonaci, Alisha Jones, Francesca Cuturello, Michael Sattler, Giovanni Bussi
备注：
Supporting Information are reported in a Jupyter notebook, in both format .pdf (read-only) and .ipynb (interactive and editable). Full data required to run the .ipynb notebook can be found at the GitHub repository reported in the notebook
RNA function crucially depends on its structure. Thermodynamic models currently used for secondary structure prediction rely on computing the partition function of folding ensembles, and can thus estimate minimum free-energy structures and ensemble populations. These models sometimes fail in identifying native structures unless complemented by auxiliary experimental data. Here, we build a set of models that combine thermodynamic parameters, chemical probing data (DMS, SHAPE), and co-evolutionary data (Direct Coupling Analysis, DCA) through a network that outputs perturbations to the ensemble free energy. Perturbations are trained to increase the ensemble populations of a representative set of known native RNA structures. In the chemical probing nodes of the network, a convolutional window combines neighboring reactivities, enlightening their structural information content and the contribution of local conformational ensembles. Regularization is used to limit overfitting and improve transferability. The most transferable model is selected through a cross-validation strategy that estimates the performance of models on systems on which they are not trained. With the selected model we obtain increased ensemble populations for native structures and more accurate predictions in an independent validation set. The flexibility of the approach allows the model to be easily retrained and adapted to incorporate arbitrary experimental information.
RNA structure prediction is a challenging problem, especially with pseudoknots. Recently, there has been a shift from the classical minimum free energy-based methods (MFE) to partition function-based ones that assemble structures using base-pairing probabilities. Two examples of the latter group are the popular maximum expected accuracy (MEA) method and the ProbKnot method. ProbKnot is a fast heuristic that pairs nucleotides that are reciprocally most probable pairing partners, and unlike MEA, can also predict structures with pseudoknots. However, ProbKnot's full potential has been largely ove…
Many ncRNAs function through RNA-RNA interactions. Fast and reliable RNA structure prediction with consideration of RNA-RNA interaction is useful. Some existing tools are less accurate due to omitting the competing of intermolecular and intramolecular base pairs, or focus more on predicting the binding region rather than predicting the complete secondary structure of two interacting strands. Vienna RNAcofold, which reduces the problem into the classical single sequence folding by concatenating two strands, scales in cubic time against the combined sequence length, and is slow for long sequence…
Global coronavirus disease pandemic (COVID-19) caused by newly identified SARS- CoV-2 coronavirus continues to claim the lives of thousands of people worldwide. The unavailability of specific medications to treat COVID-19 has led to drug repositioning efforts using various approaches, including computational analyses. Such analyses mostly rely on molecular docking and require the 3D structure of the target protein to be available. In this study, we utilized a set of machine learning algorithms and trained them on a dataset of RNA-dependent RNA polymerase (RdRp) inhibitors to run inference anal…
Northeastern University（东北大学）；Dalian Maritime University（大连海事大学）；Dalian University of Technology（大连理工大学）；China Medical University（中国医科大学）；Liaoning University（辽宁大学）；Stevens Institute of Technology（斯蒂文斯理工学院）
Secondary structure plays an important role in determining the function of non-coding RNAs. Hence, identifying RNA secondary structures is of great value to research. Computational prediction is a mainstream approach for predicting RNA secondary structure. Unfortunately, even though new methods have been proposed over the past 40 years, the performance of computational prediction methods has stagnated in the last decade. Recently, with the increasing availability of RNA structure data, new methods based on machine-learning technologies, especially deep learning, have alleviated the issue. In t…
Structured RNA plays many functionally relevant roles in molecular life. Structural information, while required to understand the functional cycles in detail, is challenging to gather. Computational methods promise to complement experimental efforts by predicting three-dimensional RNA models. Here, we provide a concise view of the state of the art methodologies with a focus on the strengths and the weaknesses of the different approaches. Furthermore, we analyzed the recent developments regarding the use of coevolutionary information and how it can boost the prediction performances. We finally …
Accurate RNA 3D structure prediction using a language model-based deep learning approach
The Chinese University of Hong Kong（香港中文大学）；Zelixir Biotech（泽利昔生物科技公司）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Fudan University（复旦大学）；Shanghai AI Laboratory（上海人工智能实验室）；Wyss Institute for Biologically Inspired Engineering（威斯生物启发工程研究所）；Harvard University（哈佛大学）；Harvard Medical School（哈佛医学院）；Arizona State University（亚利桑那州立大学）；Massachusetts Institute of Technology（麻省理工学院）；Broad Institute of MIT and Harvard（麻省理工学院与哈佛大学博德研究所）；Synthetic Biology Center（合成生物学中心）；OneAIM Ltd.（OneAIM有限公司）
DNA and RNA are generally regarded as central molecules in molecular biology. Recent advancements in the field of DNA/RNA nanotechnology successfully used DNA/RNA as programmable molecules to construct molecular machines and nanostructures with predefined shapes and functions. The key mechanism for dynamic control of the conformations of these DNA/RNA nanodevices is a reaction called strand displacement, in which one strand in a formed duplex is replaced by a third invading strand. While DNA/RNA strand displacement has mainly been used to de-novo design molecular devices, we argue in this revi…
It is acknowledged that co-evolutionary nucleotide-nucleotide interactions are essential for RNA structures and functions. Currently, direct coupling analysis (DCA) infers nucleotide contacts in a sequence from its homologous sequence alignment across different species. DCA and similar approaches that use sequence information alone usually yield a low accuracy, especially when the available homologous sequences are limited. Here we present a new method that incorporates a Restricted Boltzmann Machine (RBM) to augment the information on sequence co-variations with structural patterns in contact…
Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction
City University of New York（纽约城市大学）；Hunter College（亨特学院）；Cornell University（康奈尔大学）；Weill Cornell Medicine（威尔康奈尔医学院）；Helen & Robert Appel Alzheimer’s Disease Research Institute（海伦与罗伯特·阿佩尔阿尔茨海默病研究所）；Feil Family Brain & Mind Research Institute（费尔家族脑与心智研究所）
In this paper, we use the biological domain knowledge incorporated into stochastic models for ab initio RNA secondary-structure prediction to improve the state of the art in joint compression of RNA sequence and structure data (Liu et al., BMC Bioinformatics, 2008). Moreover, we show that, conversely, compression ratio can serve as a cheap and robust proxy for comparing the prediction quality of different stochastic models, which may help guide the search for better RNA structure prediction models. Our results build on expert stochastic context-free grammar models of RNA secondary structures (…
We propose a new deterministic methodology to predict RNA sequence and protein folding. Is stem enough for structure prediction? The main idea is to consider all possible stem formation in the given sequence. With the stem loop energy and the strength of stem, we explore how to deterministically utilize stem information for RNA sequence and protein folding structure prediction. We use graph notation, where all possible stems are represented as vertices, and co-existence as edges. This full Stem-graph presents all possible folding structure, and we pick sub-graph(s) which give the best matching…
Computational prediction of RNA structures is an important problem in computational structural biology. Studies of RNA structure formation often assume that the process starts from a fully synthesized sequence. Experimental evidence, however, has shown that RNA folds concurrently with its elongation. We investigate RNA secondary structure formation, including pseudoknots, that takes into account the cotranscriptional effects. We propose a single-nucleotide resolution kinetic model of the folding process of RNA molecules, where the polymerase-driven elongation of an RNA strand by a new nucleoti…
The Chinese University of Hong Kong (CUHK)（香港中文大学）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；The CUHK Shenzhen Research Institute（香港中文大学深圳研究院）
Protein-RNA interactions are of vital importance to a variety of cellular activities. Both experimental and computational techniques have been developed to study the interactions. Due to the limitation of the previous database, especially the lack of protein structure data, most of the existing computational methods rely heavily on the sequence data, with only a small portion of the methods utilizing the structural information. Recently, AlphaFold has revolutionized the entire protein and biology field. Foreseeably, the protein-RNA interaction prediction will also be promoted significantly in …
The pandemic prevalence of COVID-19 has become a very serious global health issue. Scientists all over the world have been heavily invested in the discovery of a drug to combat SARS-CoV-2. It has been found that RNA-dependent RNA Polymerase (RdRp) plays a crucial role in SARS-CoV-2 replication, and thus could be a potential drug target. Here, comprehensive computational approaches including drug repurposing and molecular docking were employed to predict an effective drug candidate targeting RdRp of SARS-CoV-2. This study revealed that Rifabutin, Rifapentine, Fidaxomicin, 7-methyl-guanosine-5'-…
Institute of Systems and Physical Biology, Shenzhen Bay Laboratory（深圳湾实验室系统与物理生物学研究所）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Ribopeutic Inc（Ribopeutic公司）
RNA-RNA interaction (RRI) is ubiquitous and has complex roles in the cellular functions. In human health studies, miRNA-target and lncRNAs are among an elite class of RRIs that have been extensively studied. Bacterial ncRNA-target and RNA interference are other classes of RRIs that have received significant attention. In recent studies, mRNA-mRNA interaction instances have been observed, where both partners appear in the same pathway without any direct link between them, or any prior knowledge about their relationship. Those recently discovered cases suggest that RRI scope is much wider than t…
RNA pseudoknots are a kind of minimal RNA tertiary structural motifs, and their three-dimensional (3D) structures and stability play essential roles in a variety of biological functions. Therefore, to predict 3D structures and stability of RNA pseudoknots is essential for understanding their functions. In the work, we employed our previously developed coarse-grained model with implicit salt to make extensive predictions and comprehensive analyses on the 3D structures and stability for RNA pseudoknots in monovalent/divalent ion solutions. The comparisons with available experimental data show th…
We introduce the SPlit-and-conQueR (SPQR) model, a coarse-grained representation of RNA designed for structure prediction and refinement. In our approach, the representation of a nucleotide consists of a point particle for the phosphate group and an anisotropic particle for the nucleoside. The interactions are, in principle, knowledge-based potentials inspired by the ESCORE function, a base-centered scoring function. However, a special treatment is given to base-pairing interactions and certain geometrical conformations which are lost in a raw knowledge-base model. This results in a representa…
Molecular chaperones are ATP-consuming biological machines, which facilitate the folding of proteins and RNA molecules that are kinetically trapped in misfolded states for long times. Unassisted folding occurs by the kinetic partitioning mechanism according to which folding to the native state, with low probability as well as misfolding to one of the many metastable states, with high probability, occur rapidly on similar time scales. GroEL is an all-purpose stochastic machine that assists misfolded substrate proteins (SPs) to fold. The RNA chaperones (CYT-19) help the folding of ribozymes that…
