Posted Content•
Protein-RNA interaction prediction with deep learning: Structure matters
TL;DR: A thorough review of the protein-RNA interaction prediction field can be found in this paper, which surveys both the binding site and binding preference prediction problems and covers the commonly used datasets, features, and models.
Abstract: 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 upcoming years. In this work, we give a thorough review of this field, surveying both the binding site and binding preference prediction problems and covering the commonly used datasets, features, and models. We also point out the potential challenges and opportunities in this field. This survey summarizes the development of the RBP-RNA interaction field in the past and foresees its future development in the post-AlphaFold era.
Citations
More filters
TL;DR: The adaptive and interference aspects of CRISPR–Cas function as well as open questions about the molecular mechanisms responsible for genome targeting are explored; structural insights reflect close evolutionary links between CRISpr–Cas systems and mobile genetic elements.
43 citations
TL;DR: This work proposes a novel RNA foundation model (RNA-FM) to take advantage of all the 23 million non-coding RNA sequences through self-supervised learning and discovers that the pre-trained RNA-FM could infer sequential and evolutionary information of non-Coding RNAs without using any labels.
Abstract: Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations. These are all among the core problems in the RNA field. With the rapid growth of sequencing technology, we have accumulated a massive amount of unannotated RNA sequences. On the other hand, expensive experimental observatory results in only limited numbers of annotated data and 3D structures. Hence, it is still challenging to design computational methods for predicting their structures and functions. The lack of annotated data and systematic study causes inferior performance. To resolve the issue, we propose a novel RNA foundation model (RNA-FM) to take advantage of all the 23 million non-coding RNA sequences through self-supervised learning. Within this approach, we discover that the pre-trained RNA-FM could infer sequential and evolutionary information of non-coding RNAs without using any labels. Furthermore, we demonstrate RNA-FM’s effectiveness by applying it to the downstream secondary/3D structure prediction, SARS-CoV-2 genome structure and evolution prediction, protein-RNA binding preference modeling, and gene expression regulation modeling. The comprehensive experiments show that the proposed method improves the RNA structural and functional modelling results significantly and consistently. Despite only being trained with unlabelled data, RNA-FM can serve as the foundational model for the field.
17 citations
TL;DR: Experimental results indicated that structure-based protein function prediction models could benefit from virtual training data consisting of AlphaFold-predicted structures, and suggested that predicted structures were almost equally effective in predicting protein functionality.
Abstract: The structure of a protein is of great importance in determining its functionality, and this characteristic can be leveraged to train data-driven prediction models. However, the limited number of available protein structures severely limits the performance of these models. AlphaFold2 and its open-source data set of predicted protein structures have provided a promising solution to this problem, and these predicted structures are expected to benefit the model performance by increasing the number of training samples. In this work, we constructed a new data set that acted as a benchmark and implemented a state-of-the-art structure-based approach for determining whether the performance of the function prediction model can be improved by putting additional AlphaFold-predicted structures into the training set and further compared the performance differences between two models separately trained with real structures only and AlphaFold-predicted structures only. Experimental results indicated that structure-based protein function prediction models could benefit from virtual training data consisting of AlphaFold-predicted structures. First, model performances were improved in all three categories of Gene Ontology terms (GO terms) after adding predicted structures as training samples. Second, the model trained only on AlphaFold-predicted virtual samples achieved comparable performances to the model based on experimentally solved real structures, suggesting that predicted structures were almost equally effective in predicting protein functionality.
6 citations
TL;DR: A comprehensive overview of representative deep learning methods for gene regulation can be found in this article , where the authors discuss and compare the design principles and datasets used by each method, creating a reference for researchers who wish to replicate or improve existing methods.
Abstract: Gene regulation is a central topic in cell biology. Advances in omics technologies and the accumulation of omics data have provided better opportunities for gene regulation studies than ever before. For this reason deep learning, as a data-driven predictive modeling approach, has been successfully applied to this field during the past decade. In this article, we aim to give a brief yet comprehensive overview of representative deep-learning methods for gene regulation. Specifically, we discuss and compare the design principles and datasets used by each method, creating a reference for researchers who wish to replicate or improve existing methods. We also discuss the common problems of existing approaches and prospectively introduce the emerging deep-learning paradigms that will potentially alleviate them. We hope that this article will provide a rich and up-to-date resource and shed light on future research directions in this area.
3 citations
TL;DR: Zhang et al. as mentioned in this paper proposed a deep contrastive learning framework for metagenome binning, which can efficiently eliminate the disturbance of noise and produce more stable and robust results.
Abstract: The reconstruction of microbial genomes from large metagenomic datasets is a critical procedure for finding uncultivated microbial populations and defining their microbial functional roles. To achieve that, we need to perform metagenomic binning, clustering the assembled contigs into draft genomes. Despite the existing computational tools, most of them neglect one important property of the metagenomic data, that is, the noise. To further improve the metagenomic binning step and reconstruct better metagenomes, we propose a deep Contrastive Learning framework for Metagenome Binning (CLMB), which can efficiently eliminate the disturbance of noise and produce more stable and robust results. Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data. Consequently, the trained model will be robust to noise and handle it implicitly during usage. CLMB outperforms the previous state-of-the-art binning methods significantly, recovering the most near-complete genomes on almost all the benchmarking datasets (up to 17% more reconstructed genomes compared to the second-best method). It also improves the performance of bin refinement, reconstructing 8-22 more high-quality genomes and 15-32 more middle-quality genomes than the second-best result. Impressively, in addition to being compatible with the binning refiner, single CLMB even recovers on average 15 more HQ genomes than the refiner of VAMB and Maxbin on the benchmarking datasets. On a real mother-infant microbiome dataset with 110 samples, CLMB is scalable and practical to recover 365 high-quality and middle-quality genomes (including 21 new ones), providing insights into the microbiome transmission. CLMB is open-source and available at https://github.com/zpf0117b/CLMB/.
3 citations
References
More filters
TL;DR: A new criterion for triggering the extension of word hits, combined with a new heuristic for generating gapped alignments, yields a gapped BLAST program that runs at approximately three times the speed of the original.
Abstract: The BLAST programs are widely used tools for searching protein and DNA databases for sequence similarities. For protein comparisons, a variety of definitional, algorithmic and statistical refinements described here permits the execution time of the BLAST programs to be decreased substantially while enhancing their sensitivity to weak similarities. A new criterion for triggering the extension of word hits, combined with a new heuristic for generating gapped alignments, yields a gapped BLAST program that runs at approximately three times the speed of the original. In addition, a method is introduced for automatically combining statistically significant alignments produced by BLAST into a position-specific score matrix, and searching the database using this matrix. The resulting Position-Specific Iterated BLAST (PSIBLAST) program runs at approximately the same speed per iteration as gapped BLAST, but in many cases is much more sensitive to weak but biologically relevant sequence similarities. PSI-BLAST is used to uncover several new and interesting members of the BRCT superfamily.
70,111 citations
Proceedings Article•
01 Jan 2014TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Abstract: How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions is two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.
20,769 citations
18 Jun 2018
TL;DR: This work proposes a novel architectural unit, which is term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and finds that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost.
Abstract: The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ${\sim }$ ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet .
14,807 citations
TL;DR: A set of simple and physically motivated criteria for secondary structure, programmed as a pattern‐recognition process of hydrogen‐bonded and geometrical features extracted from x‐ray coordinates is developed.
Abstract: For a successful analysis of the relation between amino acid sequence and protein structure, an unambiguous and physically meaningful definition of secondary structure is essential. We have developed a set of simple and physically motivated criteria for secondary structure, programmed as a pattern-recognition process of hydrogen-bonded and geometrical features extracted from x-ray coordinates. Cooperative secondary structure is recognized as repeats of the elementary hydrogen-bonding patterns “turn” and “bridge.” Repeating turns are “helices,” repeating bridges are “ladders,” connected ladders are “sheets.” Geometric structure is defined in terms of the concepts torsion and curvature of differential geometry. Local chain “chirality” is the torsional handedness of four consecutive Cα positions and is positive for right-handed helices and negative for ideal twisted β-sheets. Curved pieces are defined as “bends.” Solvent “exposure” is given as the number of water molecules in possible contact with a residue. The end result is a compilation of the primary structure, including SS bonds, secondary structure, and solvent exposure of 62 different globular proteins. The presentation is in linear form: strip graphs for an overall view and strip tables for the details of each of 10.925 residues. The dictionary is also available in computer-readable form for protein structure prediction work.
14,077 citations
TL;DR: WebLogo generates sequence logos, graphical representations of the patterns within a multiple sequence alignment that provide a richer and more precise description of sequence similarity than consensus sequences and can rapidly reveal significant features of the alignment otherwise difficult to perceive.
Abstract: WebLogo generates sequence logos, graphical representations of the patterns within a multiple sequence alignment. Sequence logos provide a richer and more precise description of sequence similarity than consensus sequences and can rapidly reveal significant features of the alignment otherwise difficult to perceive. Each logo consists of stacks of letters, one stack for each position in the sequence. The overall height of each stack indicates the sequence conservation at that position (measured in bits), whereas the height of symbols within the stack reflects the relative frequency of the corresponding amino or nucleic acid at that position. WebLogo has been enhanced recently with additional features and options, to provide a convenient and highly configurable sequence logo generator. A command line interface and the complete, open WebLogo source code are available for local installation and customization.
10,721 citations