Filters








2,221 Hits in 6.6 sec

Rich Parameterization Improves RNA Structure Prediction [chapter]

Shay Zakov, Yoav Goldberg, Michael Elhadad, Michal Ziv-Ukelson
2011 Lecture Notes in Computer Science  
RNAs functionalities depend on its structural features  Number of known RNA structures is still limited  Secondary structure or folding of RNA sequence: set of formed base-pairs (A,G,C,U) Preliminaries  ...  is beneficial to ML-based RNA structure prediction  Best model yields an error reduction of 50% over the previously best published results  Limitations with respect to the physics-based models  does  ...  Experiments  F 1 scores (in %) of on the development set, grouped by RNA family  ... 
doi:10.1007/978-3-642-20036-6_48 fatcat:z52w6bpctzdqtj6qiotex7vddu

Rich Parameterization Improves RNA Structure Prediction

Shay Zakov, Yoav Goldberg, Michael Elhadad, Michal Ziv-ukelson
2011 Journal of Computational Biology  
RNAs functionalities depend on its structural features  Number of known RNA structures is still limited  Secondary structure or folding of RNA sequence: set of formed base-pairs (A,G,C,U) Preliminaries  ...  is beneficial to ML-based RNA structure prediction  Best model yields an error reduction of 50% over the previously best published results  Limitations with respect to the physics-based models  does  ...  Experiments  F 1 scores (in %) of on the development set, grouped by RNA family  ... 
doi:10.1089/cmb.2011.0184 pmid:22035327 fatcat:57xmbqf43fexpcjfccqod5a36q

RNA secondary structure prediction using deep learning with thermodynamic integrations [article]

Kengo Sato, Manato Akiyama, Yasubumi Sakakibara
2020 bioRxiv   pre-print
RNA secondary structure prediction is one of the key technologies for unveiling the essential roles of functional non-coding RNAs.  ...  We propose a new algorithm for predicting RNA secondary structures using deep learning with thermodynamic integrations, which enable us robust predictions.  ...  The proposed MXfold2 algorithm should be useful for improving RNA structure modeling, especially for newly discovered RNAs.  ... 
doi:10.1101/2020.08.10.244442 fatcat:ewpmpzd4qfcspd2soy4aobxn7y

ConsAlign: simultaneous RNA structural aligner based on rich transfer learning and thermodynamic ensemble model of alignment scoring [article]

Masaki Tagashira
2022 bioRxiv   pre-print
AbstractMotivationTo capture structural homology in RNAs, predicting RNA structural alignments has been a fundamental framework around RNA science.  ...  Learning simultaneous RNA structural alignments in their rich scoring parameterization is an undeveloped subject because evaluating them is computationally expensive in nature.ResultsWe developed ConsTrain—a  ...  Akito Taneda regarding points to be improved. We performed most of the computations in this study on the NIG supercomputer at the ROIS National Institute of Genetics, Japan.  ... 
doi:10.1101/2022.04.27.489566 fatcat:2rpexlxrcbhjzlsobgsk7saba4

RNA secondary structure prediction using deep learning with thermodynamic integration

Kengo Sato, Manato Akiyama, Yasubumi Sakakibara
2021 Nature Communications  
The results suggest that integrating thermodynamic information could help improve the robustness of deep learning-based predictions of RNA secondary structure.  ...  AbstractAccurate predictions of RNA secondary structures can help uncover the roles of functional non-coding RNAs.  ...  However, rich parameterization can easily cause overfitting to the training data, thus preventing robust predictions for a wide range of RNA sequences 15 .  ... 
doi:10.1038/s41467-021-21194-4 pmid:33574226 fatcat:43fg2a322bfxbemsyxwtqcq2qu

Unified energetics analysis unravels SpCas9 cleavage activity for optimal gRNA design

Dong Zhang, Travis Hurst, Dongsheng Duan, Shi-Jie Chen
2019 Proceedings of the National Academy of Sciences of the United States of America  
This unified framework improves predictions for both on-target activities and off-target efficiencies of spCas9 and may be readily transferred to other systems with different guide RNAs or Cas9 ortholog  ...  While CRISPR/Cas9 is a powerful tool in genome engineering, the on-target activity and off-target effects of the system widely vary because of the differences in guide RNA (gRNA) sequences and genomic  ...  The uCRISPR Model Improves Off-Target Effect Predictions.  ... 
doi:10.1073/pnas.1820523116 pmid:30988204 pmcid:PMC6500161 fatcat:7tsrtogp6fhb5hm5pjeo7dvwum

Convolutional models of RNA energetics [article]

Michelle J. Wu
2018 bioRxiv   pre-print
Existing models utilize nearest neighbor rules, which were parameterized through careful optical melting measurements.  ...  Many of these efforts require the design of nucleic acid interactions, which relies on accurate models for DNA and RNA energetics.  ...  Here, we explore the use of CNNs for predicting the energies of unmeasured RNA structural motifs. Figure 1 : Nearest neighbor model for RNA energetics.  ... 
doi:10.1101/470740 fatcat:ni7psruujjg6fnzxlznzulk7ju

Analyzing the Flexibility of RNA Structures by Constraint Counting

Simone Fulle, Holger Gohlke
2008 Biophysical Journal  
The counting also explains why a protein-based parameterization results in overly rigid RNA structures.  ...  Here, a new topological network representation of RNA structures is presented that allows analyzing RNA flexibility/rigidity based on constraint counting.  ...  The RNA parameterization will be made available in the ambpdb program of the Amber 10 suite of packages (http://amber.scripps.edu) and the FIRST program (http://flexweb.asu.edu).  ... 
doi:10.1529/biophysj.107.113415 pmid:18281388 pmcid:PMC2480660 fatcat:hrkjh2fx7zd6vkq35y6looz7hi

Analysis and Prediction of RNA-Binding Residues Using Sequence, Evolutionary Conservation, and Predicted Secondary Structure and Solvent Accessibility

Tuo Zhang, Hua Zhang, Ke Chen, Jishou Ruan, Shiyi Shen, Lukasz Kurgan
2010 Current protein and peptide science  
This method was improved by Jeong and Miyano by adding weighted profiles [18] .  ...  In 2004, Jeong et al. built the first RNA-binding predictor using neural network with a single sequence and predicted secondary structure as the input [17] .  ...  Sequence-based features Weiss and Narayana have shown that Arginine-rich motifs are abundant in RNA binding sites [50] .  ... 
doi:10.2174/138920310794109193 pmid:20887256 fatcat:7tinne7hq5evrhjn3sk4dfj3ny

Multi-omic data integration enables discovery of hidden biological regularities

Ali Ebrahim, Elizabeth Brunk, Justin Tan, Edward J. O'Brien, Donghyuk Kim, Richard Szubin, Joshua A. Lerman, Anna Lechner, Anand Sastry, Aarash Bordbar, Adam M. Feist, Bernhard O. Palsson
2016 Nature Communications  
These regularities can be formally represented in a computable format allowing for coherent interpretation and prediction of fitness and selection that underlies cellular physiology.  ...  Integrating omics data with models enabled the discovery of two novel regularities: condition invariant in vivo turnover rates of enzymes and the correlation of protein structural motifs and translational  ...  Therefore, using the parameterized model, we are able to improve the prediction of gene regulation that accompanies changes in growth Codons downstream motif environment.  ... 
doi:10.1038/ncomms13091 pmid:27782110 pmcid:PMC5095171 fatcat:7dxw46xp5rdedhbtrczzaermhy

A range of complex probabilistic models for RNA secondary structure prediction that includes the nearest-neighbor model and more

E. Rivas, R. Lang, S. R. Eddy
2011 RNA: A publication of the RNA Society  
The most important barrier to improving statistical approaches for RNA secondary structure prediction is the lack of diversity of well-curated single-sequence RNA secondary structures in current RNA databases  ...  The standard approach for single-sequence RNA secondary structure prediction uses a nearest-neighbor thermodynamic model with several thousand experimentally determined energy parameters.  ...  Currently, most RNA folding packages use a MEA estimator to predict RNA structures (Lu et al. 2009 ).  ... 
doi:10.1261/rna.030049.111 pmid:22194308 pmcid:PMC3264907 fatcat:tpdxntyvavea5pm2bg5ifu53ri

Research on folding diversity in statistical learning methods for RNA secondary structure prediction

Yu Zhu, ZhaoYang Xie, YiZhou Li, Min Zhu, Yi-Ping Phoebe Chen
2018 International Journal of Biological Sciences  
How to improve the prediction accuracy of RNA secondary structure is currently a hot topic.  ...  This paper explores the relationship between folding diversity and prediction accuracy, and puts forward a new method to improve the prediction accuracy of RNA secondary structure.  ...  Introduction Predicting RNA secondary structure is one of the basic subjects of bioinformatics, and how to improve the prediction accuracy of RNA secondary structure is a hotspot in international research  ... 
doi:10.7150/ijbs.24595 pmid:29989089 pmcid:PMC6036747 fatcat:kzyc7yxkdjb7tgtvvg7h7h3opu

Why Can't We Predict RNA Structure At Atomic Resolution? [chapter]

Parin Sripakdeevong, Kyle Beauchamp, Rhiju Das
2012 Nucleic acids and molecular biology  
RNA as a Model System Predicting the three-dimensional structures of biopolymers from their primary sequence remains an unsolved but foundational problem in theoretical biophysics.  ...  This chapter outlines current algorithms for automated RNA structure prediction (including our own FARNA-FARFAR), highlights their successes, and dissects their limitations, using a tetraloop and the sarcin  ...  (The latter two terms appear to improve protein structure prediction as well.) The overall .  ... 
doi:10.1007/978-3-642-25740-7_4 fatcat:hcnwvqowmzbzpeo5rqotgmuiei

Equivariant Graph Neural Networks for 3D Macromolecular Structure [article]

Bowen Jing, Stephan Eismann, Pratham N. Soni, Ron O. Dror
2021 arXiv   pre-print
Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning.  ...  In addition, we demonstrate that transfer learning can further improve performance on certain downstream tasks. Code is available at https://github.com/drorlab/gvp-pytorch.  ...  ., pre-training on a data-rich task to improve performance on a data-poor task.  ... 
arXiv:2106.03843v2 fatcat:3uhjvnsrwjdyrghcb4c66c7vx4

CONTRAfold: RNA secondary structure prediction without physics-based models

C. B. Do, D. A. Woods, S. Batzoglou
2006 Bioinformatics  
Motivation: For several decades, free energy minimization methods have been the dominant strategy for single sequence RNA secondary structure prediction.  ...  secondary structure prediction.  ...  Modeling secondary structure with SCFGs In the RNA secondary structure prediction problem, we are given an input sequence x, and our goal is to predict the best structure y.  ... 
doi:10.1093/bioinformatics/btl246 pmid:16873527 fatcat:dgyvdrebejhqpo6ddprzwjpqsq
« Previous Showing results 1 — 15 out of 2,221 results