7,615 Hits in 11.1 sec

The impact of incomplete knowledge on the evaluation of protein function prediction: a structured-output learning perspective

Yuxiang Jiang, Wyatt T. Clark, Iddo Friedberg, Predrag Radivojac
2014 Computer applications in the biosciences : CABIOS  
Results: We study the effect of incomplete experimental annotations on the reliability of performance evaluation in protein function prediction.  ...  Using the structured-output learning framework, we provide theoretical analyses and carry out simulations to characterize the effect of growing experimental annotations on the correctness and stability  ...  Funding: This work was supported by the National Science Foundation grants DBI-0644017 and DBI-1146960 as well as the National Institutes of Health grant R01 LM009722-06A1.  ... 
doi:10.1093/bioinformatics/btu472 pmid:25161254 pmcid:PMC4147924 fatcat:32xv6we455cxjky4j7xwwwsahi

Predictive Systems Toxicology [chapter]

Narsis A. Kiani, Ming-Mei Shang, Hector Zenil, Jesper Tegner
2018 Msphere  
The next logical step is the current conception of evaluating drugs from a personalized medicine point-of-view.  ...  predictions depending on the toxicity endpoint [15] .  ...  The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.  ... 
doi:10.1007/978-1-4939-7899-1_25 pmid:29934910 fatcat:67btyybpxrc7dgu2d74fav7inq

Predicting functions of maize proteins using graph convolutional network

Guangjie Zhou, Jun Wang, Xiangliang Zhang, Maozu Guo, Guoxian Yu
2020 BMC Bioinformatics  
Some deep learning models have been proposed to predict the protein function, but the effectiveness of these approaches is unsatisfactory.  ...  To use the knowledge encoded in the GO hierarchy, we propose a deep Graph Convolutional Network (GCN) based model (DeepGOA) to predict GO annotations of proteins.  ...  Acknowledgements The authors would like to thank the anonymous reviewers for their critical reading and helpful comments and suggestions, which allowed us to improve the quality of this manuscript.  ... 
doi:10.1186/s12859-020-03745-6 pmid:33323113 fatcat:sueaa46xlrbq7f7u3earyre5km

Using bioinformatics to predict the functional impact of SNVs

M. S. Cline, R. Karchin
2010 Bioinformatics  
The functional assessment of single nucleotide polymorphism (SNP) prediction is a recent problem, yet some approaches have already  ...  Here, we describe the essential components of bionformatics tools that predict functional SNVs.  ...  ACKNOWLEDGEMENT We thank Laurence Meyer for insightful discussions and critical review of the manuscript.  ... 
doi:10.1093/bioinformatics/btq695 pmid:21159622 pmcid:PMC3105482 fatcat:ammdqhjj2re4dgpxyu6agn2bmm

DeepGOA: Predicting Gene Ontology Annotations of Proteins via Graph Convolutional Network

Guangjie Zhou, Jun Wang, Xiangliang Zhang, Guoxian Yu
2019 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)  
To use the knowledge encoded in the GO hierarchy, we propose a deep Graph Convolutional Network (GCN) based model (DeepGOA) to predict GO annotations of proteins.  ...  Some deep learning models have been proposed to utilize the GO hierarchy for protein function prediction, but they inadequately utilize GO hierarchy.  ...  When applying the deep learning model to protein function prediction, the challenge is its large and complex output space. Wehrmann et al.  ... 
doi:10.1109/bibm47256.2019.8983075 dblp:conf/bibm/ZhouWZY19 fatcat:yo5lt64m3vhjbgko2jfpq7hgdq

Hierarchical Ensemble Methods for Protein Function Prediction

Giorgio Valentini
2014 ISRN Bioinformatics  
In this paper, we provide a comprehensive review of hierarchical methods for protein function prediction based on ensembles of learning machines.  ...  Protein function prediction is a complex multiclass multilabel classification problem, characterized by multiple issues such as the incompleteness of the available annotations, the integration of multiple  ...  , funded by the italian Ministry of University.  ... 
doi:10.1155/2014/901419 pmid:25937954 pmcid:PMC4393075 fatcat:i6w56fpbqnekjozm2kdpik635e

A Literature Review of Gene Function Prediction by Modeling Gene Ontology

Yingwen Zhao, Jun Wang, Jian Chen, Xiangliang Zhang, Maozu Guo, Guoxian Yu
2020 Frontiers in Genetics  
Annotating the functional properties of gene products, i.e., RNAs and proteins, is a fundamental task in biology.  ...  First, we introduce the conventions of GO and the widely adopted evaluation metrics for gene function prediction.  ...  Several excellent surveys provide a comprehensive literature summation of the progress in gene function prediction (a.k.a. protein function prediction) and the studies of GO from different perspectives  ... 
doi:10.3389/fgene.2020.00400 pmid:32391061 pmcid:PMC7193026 fatcat:u3jc3ieejzebdfxlbfhrvdbvp4

Shapley Flow: A Graph-based Approach to Interpreting Model Predictions [article]

Jiaxuan Wang, Jenna Wiens, Scott Lundberg
2021 arXiv   pre-print
We demonstrate the benefit of using Shapley Flow to reason about the impact of a model's input on its output.  ...  In light of these limitations, we propose Shapley Flow, a novel approach to interpreting machine learning models.  ...  The evaluation of on a list of paths is the value of evaluated on the corresponding edge traversal ordering.  ... 
arXiv:2010.14592v3 fatcat:phrs7vdqhnacjpfpvnhrqdnfhy

Better prediction of functional effects for sequence variants

Maximilian Hecht, Yana Bromberg, Burkhard Rost
2015 BMC Genomics  
This article has been published as part of BMC Genomics Volume 16 Supplement 8, 2015: VarI-SIG 2014: Identification and annotation of genetic variants in the context of structure, function and disease.  ...  This work and its publication was supported by a grant from the Alexander von Humboldt foundation through the German Ministry for Research and Education (BMBF: Bundesministerium fuer Bildung und Forschung  ...  Input features Biophysical amino acid features and predicted aspects of protein function and structure help to predict the impact of variants.  ... 
doi:10.1186/1471-2164-16-s8-s1 pmid:26110438 pmcid:PMC4480835 fatcat:mirqs7wefffc3ojyhwhupeby6u

Bidirectional Dynamics for Protein Secondary Structure Prediction [chapter]

Pierre Baldi, Søren Brunak, Paolo Frasconi, Gianluca Pollastri, Giovanni Soda
2000 Lecture Notes in Computer Science  
The work of PB is in part supported by an NIH SBIR grant to Net-ID, Inc. The work of SB is supported by a grant from the Danish National Research Foundation.  ...  The work of PF and GS is partially supported by a "40%" grant from MURST, Italy.  ...  One step towards predicting how a protein folds is the prediction of its secondary structure.  ... 
doi:10.1007/3-540-44565-x_5 fatcat:vk2ijdihi5dvrbbryo6vjc4zxq

A model to predict the function of hypothetical proteins through a nine-point classification scoring schema

Johny Ijaq, Girik Malik, Anuj Kumar, Partha Sarathi Das, Narendra Meena, Neeraja Bethi, Vijayaraghava Seshadri Sundararajan, Prashanth Suravajhala
2019 BMC Bioinformatics  
Techniques to decipher sequence-structure-function relationship, especially in terms of functional modelling of the HPs have been developed by researchers, but using the features as classifiers for HPs  ...  Hypothetical proteins [HP] are those that are predicted to be expressed in an organism, but no evidence of their existence is known.  ...  JI acknowledges the support of CSIR for providing a research fellowship to pursue his Ph.D.  ... 
doi:10.1186/s12859-018-2554-y fatcat:oy4up2xx6bhrnpoe2z3g6qdvme

EPGAT: Gene Essentiality Prediction With Graph Attention Networks [article]

João Schapke, Anderson Tavares, Mariana Recamonde-Mendoza
2020 arXiv   pre-print
The identification of essential genes/proteins is a critical step towards a better understanding of human biology and pathology.  ...  Given these limitations, we proposed EPGAT, an approach for essentiality prediction based on Graph Attention Networks (GATs), which are attention-based Graph Neural Networks (GNNs) that operate on graph-structured  ...  The output vector is analyzed by a sequence of two fully connected layers using the rectified linear unit (ReLU) and softmax activation functions to predict the final label of a protein.  ... 
arXiv:2007.09671v1 fatcat:i2p6p2nguzfgfjiwofjgijdcam

From genome to phenome: Predicting multiple cancer phenotypes based on somatic genomic alterations via the genomic impact transformer [article]

Yifeng Tao and Chunhui Cai and William W. Cohen and Xinghua Lu
2019 arXiv   pre-print
GIT model learns a vector (gene embedding) as an abstract representation of functional impact for each SGA-affected gene.  ...  Here, we present a deep neural network model with encoder-decoder architecture, referred to as genomic impact transformer (GIT), to infer the functional impact of SGAs on cellular signaling systems through  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the above funding agencies.  ... 
arXiv:1902.00078v3 fatcat:64pefpmc6vg77grksdosxab6he

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Sean Whalen, Om Prakash Pandey, Gaurav Pandey
2016 Methods  
This is due in part to incomplete knowledge of the cellular phenomenon of interest, the appropriateness and data quality of the variables and measurements used for prediction, as well as a lack of consensus  ...  Prediction problems in biomedical sciences, including protein function prediction (PFP), are generally quite difficult.  ...  Acknowledgments We thank the Icahn Institute for Genomics and Multiscale Biology and the Minerva supercomputing team for their financial and technical support of this work.  ... 
doi:10.1016/j.ymeth.2015.08.016 pmid:26342255 pmcid:PMC4718788 fatcat:dwg3lg5rxfe3tntrzdibfucpqe

DeepIDA: predicting isoform-disease associations by data fusion and deep neural networks

Guoxian Yu, Yeqian Yang, Yangyang Yan, Maozu Guo, Xiangliang Zhang, Jun Wang
2021 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
at a large scale, mainly due to the lack of disease annotations of isoforms.  ...  The experimental results on public datasets show that DeepIDA can effectively predict IDAs with AUPRC of 0.9141 and macro F-measure of 0.9155, which are much higher than those of competitive methods.  ...  Ablation Study To investigate the impact of the focal loss function and network structure on the prediction results, we also introduced two variants of DeepIDA: DeepIDA-without focal loss and DeepIDA-without  ... 
doi:10.1109/tcbb.2021.3058801 pmid:33571094 fatcat:mb74sk3ukvalnjralsaidk2rnm
« Previous Showing results 1 — 15 out of 7,615 results