De novo prediction of RNA 3D structures with deep generative models.
Ontology highlight
ABSTRACT:
SUBMITTER: Ramakers J
PROVIDER: S-EPMC10868834 | biostudies-literature | 2024
REPOSITORIES: biostudies-literature
Publications
De novo prediction of RNA 3D structures with deep generative models.
Ramakers Julius J Blum Christopher Frederik CF König Sabrina S Harmeling Stefan S Kollmann Markus M
PloS one 20240215 2
We present a Deep Learning approach to predict 3D folding structures of RNAs from their nucleic acid sequence. Our approach combines an autoregressive Deep Generative Model, Monte Carlo Tree Search, and a score model to find and rank the most likely folding structures for a given RNA sequence. We show that RNA de novo structure prediction by deep learning is possible at atom resolution, despite the low number of experimentally measured structures that can be used for training. We confirm the pre ...[more]
Similar Datasets
Project description:Current experiments on structural determination cannot keep up the pace with the steadily emerging RNA sequences and new functions. This underscores the request for an accurate model for RNA three-dimensional (3D) structural prediction. Although considerable progress has been made in mechanistic studies, accurate prediction for RNA tertiary folding from sequence remains an unsolved problem. The first and most important requirement for the prediction of RNA structure from physical principles is an accurate free energy model. A recently developed three-vector virtual bond-based RNA folding model ("Vfold") has allowed us to compute the chain entropy and predict folding free energies and structures for RNA secondary structures and simple pseudoknots. Here we develop a free energy-based method to predict larger more complex RNA tertiary folds. The approach is based on a multiscaling strategy: from the nucleotide sequence, we predict the two-dimensional (2D) structures (defined by the base pairs and tertiary contacts); based on the 2D structure, we construct a 3D scaffold; with the 3D scaffold as the initial state, we combine AMBER energy minimization and PDB-based fragment search to predict the all-atom structure. A key advantage of the approach is the statistical mechanical calculation for the conformational entropy of RNA structures, including those with cross-linked loops. Benchmark tests show that the model leads to significant improvements in RNA 3D structure prediction.
| S-EPMC3072456 | biostudies-literature
Project description:Deep generative models are attracting much attention in the field of de novo molecule design. Compared to traditional methods, deep generative models can be trained in a fully data-driven way with little requirement for expert knowledge. Although many models have been developed to generate 1D and 2D molecular structures, 3D molecule generation is less explored, and the direct design of drug-like molecules inside target binding sites remains challenging. In this work, we introduce DeepLigBuilder, a novel deep learning-based method for de novo drug design that generates 3D molecular structures in the binding sites of target proteins. We first developed Ligand Neural Network (L-Net), a novel graph generative model for the end-to-end design of chemically and conformationally valid 3D molecules with high drug-likeness. Then, we combined L-Net with Monte Carlo tree search to perform structure-based de novo drug design tasks. In the case study of inhibitor design for the main protease of SARS-CoV-2, DeepLigBuilder suggested a list of drug-like compounds with novel chemical structures, high predicted affinity, and similar binding features to those of known inhibitors. The current version of L-Net was trained on drug-like compounds from ChEMBL, which could be easily extended to other molecular datasets with desired properties based on users' demands and applied in functional molecule generation. Merging deep generative models with atomic-level interaction evaluation, DeepLigBuilder provides a state-of-the-art model for structure-based de novo drug design and lead optimization.
| S-EPMC8549794 | biostudies-literature
Project description:Modeling structures and functions of large ribonucleic acid (RNAs) especially with complicated topologies is highly challenging due to the inefficiency of large conformational sampling and the presence of complicated tertiary interactions. To address this problem, one highly promising approach is coarse-grained modeling. Here, following an iterative simulated reference state approach to decipher the correlations between different structural parameters, we developed a potent coarse-grained RNA model named as IsRNA1 for RNA studies. Molecular dynamics simulations in the IsRNA1 can predict the native structures of small RNAs from a sequence and fold medium-sized RNAs into near-native tertiary structures with the assistance of secondary structure constraints. A large-scale benchmark test on RNA 3D structure prediction shows that IsRNA1 exhibits improved performance for relatively large RNAs of complicated topologies, such as large stem-loop structures and structures containing long-range tertiary interactions. The advantages of IsRNA1 include the consideration of the correlations between the different structural variables, the appropriate characterization of canonical base-pairing and base-stacking interactions, and the better sampling for the backbone conformations. Moreover, a blind screening protocol was developed based on IsRNA1 to identify good structural models from a pool of candidates without prior knowledge of the native structures.
| S-EPMC8064582 | biostudies-literature
Project description:The rapid spread of COVID-19 is motivating development of antivirals targeting conserved SARS-CoV-2 molecular machinery. The SARS-CoV-2 genome includes conserved RNA elements that offer potential small-molecule drug targets, but most of their 3D structures have not been experimentally characterized. Here, we provide a compilation of chemical mapping data from our and other labs, secondary structure models, and 3D model ensembles based on Rosetta's FARFAR2 algorithm for SARS-CoV-2 RNA regions including the individual stems SL1-8 in the extended 5' UTR; the reverse complement of the 5' UTR SL1-4; the frameshift stimulating element (FSE); and the extended pseudoknot, hypervariable region, and s2m of the 3' UTR. For eleven of these elements (the stems in SL1-8, reverse complement of SL1-4, FSE, s2m and 3' UTR pseudoknot), modeling convergence supports the accuracy of predicted low energy states; subsequent cryo-EM characterization of the FSE confirms modeling accuracy. To aid efforts to discover small molecule RNA binders guided by computational models, we provide a second set of similarly prepared models for RNA riboswitches that bind small molecules. Both datasets ('FARFAR2-SARS-CoV-2', https://github.com/DasLab/FARFAR2-SARS-CoV-2; and 'FARFAR2-Apo-Riboswitch', at https://github.com/DasLab/FARFAR2-Apo-Riboswitch') include up to 400 models for each RNA element, which may facilitate drug discovery approaches targeting dynamic ensembles of RNA molecules.
| S-EPMC8034642 | biostudies-literature
Project description:Making no use of physical laws or co-evolutionary information, de novo deep learning (DL) models for RNA secondary structure prediction have achieved far superior performances than traditional algorithms. However, their statistical underpinning raises the crucial question of generalizability. We present a quantitative study of the performance and generalizability of a series of de novo DL models, with a minimal two-module architecture and no post-processing, under varied similarities between seen and unseen sequences. Our models demonstrate excellent expressive capacities and outperform existing methods on common benchmark datasets. However, model generalizability, i.e., the performance gap between the seen and unseen sets, degrades rapidly as the sequence similarity decreases. The same trends are observed from several recent DL and machine learning models. And an inverse correlation between performance and generalizability is revealed collectively across all learning-based models with wide-ranging architectures and sizes. We further quantitate how generalizability depends on sequence and structure identity scores via pairwise alignment, providing unique quantitative insights into the limitations of statistical learning. Generalizability thus poses a major hurdle for deploying de novo DL models in practice and various pathways for future advances are discussed.
| S-EPMC10138783 | biostudies-literature
Project description:RNA tertiary structure prediction has been based almost entirely on base-pairing constraints derived from phylogenetic covariation analysis. We describe here a complementary approach, inspired by the Rosetta low-resolution protein structure prediction method, that seeks the lowest energy tertiary structure for a given RNA sequence without using evolutionary information. In a benchmark test of 20 RNA sequences with known structure and lengths of approximately 30 nt, the new method reproduces better than 90% of Watson-Crick base pairs, comparable with the accuracy of secondary structure prediction methods. In more than half the cases, at least one of the top five models agrees with the native structure to better than 4 A rmsd over the backbone. Most importantly, the method recapitulates more than one-third of non-Watson-Crick base pairs seen in the native structures. Tandem stacks of "sheared" base pairs, base triplets, and pseudoknots are among the noncanonical features reproduced in the models. In the cases in which none of the top five models were native-like, higher energy conformations similar to the native structures are still sampled frequently but not assigned low energies. These results suggest that modest improvements in the energy function, together with the incorporation of information from phylogenetic covariance, may allow confident and accurate structure prediction for larger and more complex RNA chains.
| S-EPMC1955458 | biostudies-literature
Project description:Rational compound design remains a challenging problem for both computational methods and medicinal chemists. Computational generative methods have begun to show promising results for the design problem. However, they have not yet used the power of three-dimensional (3D) structural information. We have developed a novel graph-based deep generative model that combines state-of-the-art machine learning techniques with structural knowledge. Our method ("DeLinker") takes two fragments or partial structures and designs a molecule incorporating both. The generation process is protein-context-dependent, utilizing the relative distance and orientation between the partial structures. This 3D information is vital to successful compound design, and we demonstrate its impact on the generation process and the limitations of omitting such information. In a large-scale evaluation, DeLinker designed 60% more molecules with high 3D similarity to the original molecule than a database baseline. When considering the more relevant problem of longer linkers with at least five atoms, the outperformance increased to 200%. We demonstrate the effectiveness and applicability of this approach on a diverse range of design problems: fragment linking, scaffold hopping, and proteolysis targeting chimera (PROTAC) design. As far as we are aware, this is the first molecular generative model to incorporate 3D structural information directly in the design process. The code is available at https://github.com/oxpig/DeLinker.
| S-EPMC7189367 | biostudies-literature
Project description:As functional components in three-dimensional (3D) conformation of an RNA, the RNA structural motifs provide an easy way to associate the molecular architectures with their biological mechanisms. In the past years, many computational tools have been developed to search motif instances by using the existing knowledge of well-studied families. Recently, with the rapidly increasing number of resolved RNA 3D structures, there is an urgent need to discover novel motifs with the newly presented information. In this work, we classify all the loops in non-redundant RNA 3D structures to detect plausible RNA structural motif families by using a clustering pipeline. Compared with other clustering approaches, our method has two benefits: first, the underlying alignment algorithm is tolerant to the variations in 3D structures. Second, sophisticated downstream analysis has been performed to ensure the clusters are valid and easily applied to further research. The final clustering results contain many interesting new variants of known motif families, such as GNAA tetraloop, kink-turn, sarcin-ricin and T-loop. We have also discovered potential novel functional motifs conserved in ribosomal RNA, sgRNA, SRP RNA, riboswitch and ribozyme.
| S-EPMC5961109 | biostudies-literature
Project description:In recent years, the field of computational drug design has made significant strides in the development of artificial intelligence (AI) models for the generation of de novo chemical compounds with desired properties and biological activities, such as enhanced binding affinity to target proteins. These high-affinity compounds have the potential to be developed into more potent therapeutics for a broad spectrum of diseases. Due to the lack of data required for the training of deep generative models, however, some of these approaches have fine-tuned their molecular generators using data obtained from a separate predictor. While these studies show that generative models can produce structures with the desired target properties, it remains unclear whether the diversity of the generated structures and the span of their chemical space align with the distribution of the intended target molecules. In this study, we present a novel generative framework, LOGICS, a framework for Learning Optimal Generative distribution Iteratively for designing target-focused Chemical Structures. We address the exploration-exploitation dilemma, which weighs the choice between exploring new options and exploiting current knowledge. To tackle this issue, we incorporate experience memory and employ a layered tournament selection approach to refine the fine-tuning process. The proposed method was applied to the binding affinity optimization of two target proteins of different protein classes, κ-opioid receptors, and PIK3CA, and the quality and the distribution of the generative molecules were evaluated. The results showed that LOGICS outperforms competing state-of-the-art models and generates more diverse de novo chemical structures with optimized properties. The source code is available at the GitHub repository ( https://github.com/GIST-CSBL/LOGICS ).
| S-EPMC10483765 | biostudies-literature
Project description:Molecular generative models trained with small sets of molecules represented as SMILES strings can generate large regions of the chemical space. Unfortunately, due to the sequential nature of SMILES strings, these models are not able to generate molecules given a scaffold (i.e., partially-built molecules with explicit attachment points). Herein we report a new SMILES-based molecular generative architecture that generates molecules from scaffolds and can be trained from any arbitrary molecular set. This approach is possible thanks to a new molecular set pre-processing algorithm that exhaustively slices all possible combinations of acyclic bonds of every molecule, combinatorically obtaining a large number of scaffolds with their respective decorations. Moreover, it serves as a data augmentation technique and can be readily coupled with randomized SMILES to obtain even better results with small sets. Two examples showcasing the potential of the architecture in medicinal and synthetic chemistry are described: First, models were trained with a training set obtained from a small set of Dopamine Receptor D2 (DRD2) active modulators and were able to meaningfully decorate a wide range of scaffolds and obtain molecular series predicted active on DRD2. Second, a larger set of drug-like molecules from ChEMBL was selectively sliced using synthetic chemistry constraints (RECAP rules). In this case, the resulting scaffolds with decorations were filtered only to allow those that included fragment-like decorations. This filtering process allowed models trained with this dataset to selectively decorate diverse scaffolds with fragments that were generally predicted to be synthesizable and attachable to the scaffold using known synthetic approaches. In both cases, the models were already able to decorate molecules using specific knowledge without the need to add it with other techniques, such as reinforcement learning. We envision that this architecture will become a useful addition to the already existent architectures for de novo molecular generation.
| S-EPMC7260788 | biostudies-literature