Filters








2,037 Hits in 5.0 sec

Decoy selection for protein structure prediction via extreme gradient boosting and ranking

Nasrin Akhter, Gopinath Chennupati, Hristo Djidjev, Amarda Shehu
2020 BMC Bioinformatics  
Results We propose a novel decoy selection method, ML-Select, a machine learning framework that exploits the energy landscape associated with the structure space probed through a template-free decoy generation  ...  This work suggests further research in finding more effective ways to adopt machine learning frameworks in achieving robust performance for decoy selection in template-free protein structure prediction  ...  Decoy selection via ML and ranking Shortcomings of ranking-based basin selection strategies necessitate a new basin selection strategy.  ... 
doi:10.1186/s12859-020-3523-9 pmid:33297949 fatcat:deqfs5ykibc3distorr4r2fzvu

Decoy Selection for Protein Structure Prediction Via Extreme Gradient Boosting and Ranking [article]

Nasrin Akhter and Gopinath Chennupati and Hristo Djidjev and Amarda Shehu
2020 arXiv   pre-print
We propose a novel decoy selection method, ML-Select, a machine learning framework that exploits the energy landscape associated with the structure space probed through a template-free decoy generation  ...  This work suggests further research in finding more effective ways to adopt machine learning frameworks in achieving robust performance for decoy selection in template-free protein structure prediction  ...  Decoy Selection via ML and Ranking Shortcomings of ranking-based basin selection strategies necessitate a new basin selection strategy.  ... 
arXiv:2010.01441v1 fatcat:6bv4jh33wrhwhm5iwgfcvcyid4

Unsupervised and Supervised Learning over the Energy Landscape for Protein Decoy Selection

Akhter, Chennupati, Kabir, Djidjev, Shehu
2019 Biomolecules  
More importantly, we furtheradvance the argument that the energy landscape holds valuable information to aid and advance thestate of protein decoy selection via novel machine learning methodologies that  ...  Here, we summarizesome of our successes so far in this direction via unsupervised learning.  ...  In the latter, methods can be evaluated via loss, a classic machine learning (ML)metric that we adopt and propose here.  ... 
doi:10.3390/biom9100607 pmid:31615116 pmcid:PMC6843838 fatcat:lxczkroqh5czdbotpylwlpnusm

SynthQA - Hierarchical Machine Learning-based Protein Quality Assessment [article]

Mikhail Korovnik, Kyle Hippe, Jie Hou, Dong Si, Kiyomi Kishaba, Renzhi Cao
2021 bioRxiv   pre-print
In the field of protein structure prediction, ranking the predicted protein decoys and selecting the one closest to the native structure is known as protein model quality assessment (QA), or accuracy estimation  ...  It also considers the relationship between features and generates more features to improve accuracy of machine learning techniques.  ...  By doing that, we will generate more features and could help to improve the performance of traditional machine learning model and deep learning technique.  ... 
doi:10.1101/2021.01.28.428710 fatcat:jwqoryg6gbbedmqymgofs37q6a

Rapid and Accurate Peptide Identification from Tandem Mass Spectra

Christopher Y. Park, Aaron A. Klammer, Lukas Käll, Michael J. MacCoss, William S. Noble
2008 Journal of Proteome Research  
between target and decoy matches.  ...  Both methods significantly improve the overall rate of peptide identification. Crux is implemented in C and is distributed with source code freely to noncommercial users.  ...  This material is available free of charge via the Internet at http://pubs.acs.org.  ... 
doi:10.1021/pr800127y pmid:18505281 pmcid:PMC2667385 fatcat:c5p6sanhp5eudc4qyzvxn5tnfq

Sorting protein decoys by machine-learning-to-rank

Xiaoyang Jing, Kai Wang, Ruqian Lu, Qiwen Dong
2016 Scientific Reports  
However, ranking the predicted models correctly and selecting the best predicted model from the candidate pool remain as challenging tasks.  ...  Many machine learning algorithms have been used to get an accurate estimation of the model quality from various features, such as support vector machine 9 , deep learning 10 , random forest 11 etc.  ...  The learning-to-rank methods combine information retrieval techniques with machine learning theory, and their goal is to obtain a ranking strategy from the training set using various algorithms and rank  ... 
doi:10.1038/srep31571 pmid:27530967 pmcid:PMC4987638 fatcat:abuurzdngfaszji55oaznekumu

Machine learning classification can reduce false positives in structure-based virtual screening [article]

Yusuf Adeshina, Eric J. Deeds, John Karanicolas
2020 bioRxiv   pre-print
and/or overtraining.  ...  Remarkably, we find that nearly all compounds selected by vScreenML show detectable activity at 50 uM, with 10 of 23 providing greater than 50% inhibition at this concentration.  ...  Acknowledgements We thank Joanna Slusky for a useful suggestion regarding presentation of the figures, and Juan Manuel Perez Bertoldi for his initial application of vScreenML to the PPI benchmark set.  ... 
doi:10.1101/2020.01.10.902411 fatcat:srhoxesav5g7lmyf7untfch6zm

IRaPPA: information retrieval based integration of biophysical models for protein assembly selection

Iain H Moal, Didier Barradas-Bautista, Brian Jiménez-García, Mieczyslaw Torchala, Arjan van der Velde, Thom Vreven, Zhiping Weng, Paul A Bates, Juan Fernández-Recio, Anna Tramontano
2017 Bioinformatics  
By considering this as an information retrieval problem, we have adapted methods developed for Internet search ranking and electoral voting into IRaPPA, a pipeline integrating biophysical properties.  ...  Results: Atomic modeling of protein-protein interactions requires the selection of near-native structures from a set of docked poses based on their calculable properties.  ...  Acknowledgements The authors thank Sarah Teichmann, Pedro Beltrao, Alexandre Bonvin, Roberto Mosca, Patrick Aloy, Nick Goldman and Rudi Agius for helpful comments. Conflict of Interest: none declared.  ... 
doi:10.1093/bioinformatics/btx068 pmid:28200016 pmcid:PMC5783285 fatcat:fncjdyk7tncn7c5w5k4l44ozii

MSCypher: an integrated database searching and machine learning workflow for multiplexed proteomics [article]

Eugene A Kapp, Giuseppe Infusini, Yunshan Zhong, Laura F. Dagley, Terence P. Speed, Andrew I. Webb
2018 bioRxiv   pre-print
This results in improved identification rates and quantification of low-abundant peptides and proteins.  ...  Here we describe MSCypher, a freely available software suite that enables an extensible workflow including a hybrid supervised machine learned strategy that dynamically adjusts to individual datasets.  ...  searching and machine learning using MSCypher.  ... 
doi:10.1101/397257 fatcat:j2cz5zco3jaurpjb7diggm4tzu

Graph-Based Community Detection for Decoy Selection in Template-Free Protein Structure Prediction

Kazi Kabir, Liban Hassan, Zahra Rajabi, Nasrin Akhter, Amarda Shehu
2019 Molecules  
We present a rigorous evaluation in the context of decoy selection in template-free protein structure prediction.  ...  Significant efforts in wet and dry laboratories are devoted to resolving molecular structures.  ...  The quality of the selected communities themselves can be further improved via a combination of unsupervised and supervised learning strategies.  ... 
doi:10.3390/molecules24050854 fatcat:xw4cpiqmknab5ddu7wkp7qmmsa

Improvements to the Percolator Algorithm for Peptide Identification from Shotgun Proteomics Data Sets

Marina Spivak, Jason Weston, Léon Bottou, Lukas Käll, William Stafford Noble
2009 Journal of Proteome Research  
A recent example is Percolator, which uses semi-supervised learning and a decoy database search strategy to learn to distinguish between correct and incorrect PSMs identified by a database search algorithm  ...  Several machine learning methods have been proposed to address the resulting classification task of distinguishing between correct and incorrect peptide-spectrum matches (PSMs).  ...  One drawback to these machine learning approaches is that they often do not generalize well across different machine platforms, chromatography conditions, etc.  ... 
doi:10.1021/pr801109k pmid:19385687 pmcid:PMC2710313 fatcat:cyj6akvg5jejbkemsqdm6zoj44

Machine learning classification can reduce false positives in structure-based virtual screening

Yusuf O. Adeshina, Eric J. Deeds, John Karanicolas
2020 Proceedings of the National Academy of Sciences of the United States of America  
and/or overtraining.  ...  Here, we report a strategy for building a training dataset (D-COID) that aims to generate highly compelling decoy complexes that are individually matched to available active complexes.  ...  This work was supported by grants from the National Institute of General Medical Sciences (R01GM099959, R01GM112736, and R01GM123336) and the National Science Foundation (CHE-1836950).  ... 
doi:10.1073/pnas.2000585117 pmid:32669436 fatcat:zdybg4t6ofbyfbdskwnevedp7q

An Unsupervised, Model-Free, Machine-Learning Combiner for Peptide Identifications from Tandem Mass Spectra

Nathan Edwards, Xue Wu, Chau-Wen Tseng
2009 Clinical Proteomics  
learning scoring and prediction, and combining or merging of search engine results.  ...  by Machine Learning (PepArML) unsupervised, model-free, combining framework can be easily extended to support an arbitrary number of additional searches, search engines, or specialized peptide-spectrum  ...  We thank Brian Balgley and Paul Rudnick for the use of an unpublished synthetic protein mixture MS/MS data set used in early PepArML development.  ... 
doi:10.1007/s12014-009-9024-5 fatcat:oyxradlxy5ht7a4seo4papj5ly

Key Topics in Molecular Docking for Drug Design

Pedro H. M. Torres, Ana C. R. Sodero, Paula Jofily, Floriano P. Silva-Jr
2019 International Journal of Molecular Sciences  
their advantages and caveats, (ii) the advances in consensus methods, (iii) recent algorithms and applications using fragment-based approaches, and (iv) the use of machine learning algorithms in molecular  ...  Molecular docking has been widely employed as a fast and inexpensive technique in the past decades, both in academic and industrial settings.  ...  It was later improved into the Directory of Useful Decoys-Enhanced (DUD-E) [92] , which selects decoys based on more physicochemical properties, adds more targets, and provides a tool for decoy generation  ... 
doi:10.3390/ijms20184574 pmid:31540192 pmcid:PMC6769580 fatcat:ye5rdnonofc3jjaizbncrdx2yu

Using neural networks and evolutionary information in decoy discrimination for protein tertiary structure prediction

Ching-Wai Tan, David T Jones
2008 BMC Bioinformatics  
Here, decoy discrimination is represented as a machine learning problem, where neural networks are used to learn the native-like features of protein structures using a set of positive and negative training  ...  We present a novel method of protein fold decoy discrimination using machine learning, more specifically using neural networks.  ...  Massimiliano Pontil and Dr. Denise Gorse for their invaluable comments in this work. For this work, CWT is funded by the Nanyang Technological University, Singapore.  ... 
doi:10.1186/1471-2105-9-94 pmid:18267018 pmcid:PMC2267779 fatcat:rwwr6tvqibcuxft5tmprkita7a
« Previous Showing results 1 — 15 out of 2,037 results