@article{kanehisa_kegg_2012, title = {{KEGG} for integration and interpretation of large-scale molecular data sets}, volume = {40}, issn = {0305-1048}, url = {https://doi.org/10.1093/nar/gkr988}, doi = {10.1093/nar/gkr988}, abstract = {Kyoto Encyclopedia of Genes and Genomes (KEGG, http://www.genome.jp/kegg/ or http://www.kegg.jp/) is a database resource that integrates genomic, chemical and systemic functional information. In particular, gene catalogs from completely sequenced genomes are linked to higher-level systemic functions of the cell, the organism and the ecosystem. Major efforts have been undertaken to manually create a knowledge base for such systemic functions by capturing and organizing experimental knowledge in computable forms; namely, in the forms of KEGG pathway maps, BRITE functional hierarchies and KEGG modules. Continuous efforts have also been made to develop and improve the cross-species annotation procedure for linking genomes to the molecular networks through the KEGG Orthology system. Here we report KEGG Mapper, a collection of tools for KEGG PATHWAY, BRITE and MODULE mapping, enabling integration and interpretation of large-scale data sets. We also report a variant of the KEGG mapping procedure to extend the knowledge base, where different types of data and knowledge, such as disease genes and drug targets, are integrated as part of the KEGG molecular networks. Finally, we describe recent enhancements to the KEGG content, especially the incorporation of disease and drug information used in practice and in society, to support translational bioinformatics.}, number = {D1}, urldate = {2022-05-30}, journal = {Nucleic Acids Research}, author = {Kanehisa, Minoru and Goto, Susumu and Sato, Yoko and Furumichi, Miho and Tanabe, Mao}, month = jan, year = {2012}, pages = {D109--D114}, } @article{marcotte_detecting_1999, title = {Detecting {Protein} {Function} and {Protein}-{Protein} {Interactions} from {Genome} {Sequences}}, volume = {285}, issn = {0036-8075, 1095-9203}, url = {https://science.sciencemag.org/content/285/5428/751}, doi = {10.1126/science.285.5428.751}, abstract = {A computational method is proposed for inferring protein interactions from genome sequences on the basis of the observation that some pairs of interacting proteins have homologs in another organism fused into a single protein chain. Searching sequences from many genomes revealed 6809 such putative protein-protein interactions inEscherichia coli and 45,502 in yeast. Many members of these pairs were confirmed as functionally related; computational filtering further enriches for interactions. Some proteins have links to several other proteins; these coupled links appear to represent functional interactions such as complexes or pathways. Experimentally confirmed interacting pairs are documented in a Database of Interacting Proteins.}, language = {en}, number = {5428}, urldate = {2020-03-11}, journal = {Science}, author = {Marcotte, Edward M. and Pellegrini, Matteo and Ng, Ho-Leung and Rice, Danny W. and Yeates, Todd O. and Eisenberg, David}, month = jul, year = {1999}, pmid = {10427000}, note = {Publisher: American Association for the Advancement of Science Section: Report}, pages = {751--753}, } @article{ben-hur_kernel_2005, title = {Kernel methods for predicting protein-protein interactions}, volume = {21}, issn = {1367-4803, 1460-2059}, url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/bti1016}, doi = {10.1093/bioinformatics/bti1016}, abstract = {Motivation: Despite advances in high-throughput methods for discovering protein–protein interactions, the interaction networks of even well-studied model organisms are sketchy at best, highlighting the continued need for computational methods to help direct experimentalists in the search for novel interactions.}, language = {en}, number = {Suppl 1}, urldate = {2021-09-28}, journal = {Bioinformatics}, author = {Ben-Hur, A. and Noble, W. S.}, month = jun, year = {2005}, pages = {i38--i46}, } @article{pitre_pipe_2006, title = {{PIPE}: a protein-protein interaction prediction engine based on the re-occurring short polypeptide sequences between known interacting protein pairs}, volume = {7}, issn = {1471-2105}, shorttitle = {{PIPE}}, url = {https://doi.org/10.1186/1471-2105-7-365}, doi = {10.1186/1471-2105-7-365}, abstract = {Identification of protein interaction networks has received considerable attention in the post-genomic era. The currently available biochemical approaches used to detect protein-protein interactions are all time and labour intensive. Consequently there is a growing need for the development of computational tools that are capable of effectively identifying such interactions.}, language = {en}, number = {1}, urldate = {2020-06-23}, journal = {BMC Bioinformatics}, author = {Pitre, Sylvain and Dehne, Frank and Chan, Albert and Cheetham, Jim and Duong, Alex and Emili, Andrew and Gebbia, Marinella and Greenblatt, Jack and Jessulat, Mathew and Krogan, Nevan and Luo, Xuemei and Golshani, Ashkan}, month = jul, year = {2006}, pages = {365}, } @article{chen_multifaceted_2019, title = {Multifaceted protein–protein interaction prediction based on {Siamese} residual {RCNN}}, volume = {35}, issn = {1367-4803, 1460-2059}, url = {https://academic.oup.com/bioinformatics/article/35/14/i305/5529260}, doi = {10.1093/bioinformatics/btz328}, abstract = {Motivation: Sequence-based protein–protein interaction (PPI) prediction represents a fundamental computational biology problem. To address this problem, extensive research efforts have been made to extract predefined features from the sequences. Based on these features, statistical algorithms are learned to classify the PPIs. However, such explicit features are usually costly to extract, and typically have limited coverage on the PPI information.}, language = {en}, number = {14}, urldate = {2021-08-09}, journal = {Bioinformatics}, author = {Chen, Muhao and Ju, Chelsea J -T and Zhou, Guangyu and Chen, Xuelu and Zhang, Tianran and Chang, Kai-Wei and Zaniolo, Carlo and Wang, Wei}, month = jul, year = {2019}, pages = {i305--i314}, } @article{park_flaws_2012, title = {Flaws in evaluation schemes for pair-input computational predictions}, volume = {9}, copyright = {2012 Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.}, issn = {1548-7105}, url = {https://www.nature.com/articles/nmeth.2259}, doi = {10.1038/nmeth.2259}, language = {en}, number = {12}, urldate = {2021-07-08}, journal = {Nature Methods}, author = {Park, Yungki and Marcotte, Edward M.}, month = dec, year = {2012}, note = {Bandiera\_abtest: a Cg\_type: Nature Research Journals Number: 12 Primary\_atype: Correspondence Publisher: Nature Publishing Group Subject\_term: Bioinformatics;Proteome informatics;Systems biology Subject\_term\_id: bioinformatics;proteome-informatics;systems-biology}, pages = {1134--1136}, } @article{merity_regularizing_2017, title = {Regularizing and {Optimizing} {LSTM} {Language} {Models}}, url = {http://arxiv.org/abs/1708.02182}, abstract = {Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this paper, we consider the specific problem of word-level language modeling and investigate strategies for regularizing and optimizing LSTM-based models. We propose the weight-dropped LSTM which uses DropConnect on hidden-to-hidden weights as a form of recurrent regularization. Further, we introduce NT-ASGD, a variant of the averaged stochastic gradient method, wherein the averaging trigger is determined using a non-monotonic condition as opposed to being tuned by the user. Using these and other regularization strategies, we achieve state-of-the-art word level perplexities on two data sets: 57.3 on Penn Treebank and 65.8 on WikiText-2. In exploring the effectiveness of a neural cache in conjunction with our proposed model, we achieve an even lower state-of-the-art perplexity of 52.8 on Penn Treebank and 52.0 on WikiText-2.}, urldate = {2021-08-11}, journal = {arXiv:1708.02182 [cs]}, author = {Merity, Stephen and Keskar, Nitish Shirish and Socher, Richard}, month = aug, year = {2017}, note = {arXiv: 1708.02182}, keywords = {Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing}, } @misc{izmailov_stochastic_2019, title = {Stochastic {Weight} {Averaging} in {PyTorch}}, url = {https://pytorch.org/blog/stochastic-weight-averaging-in-pytorch/}, language = {en}, urldate = {2022-06-03}, journal = {PyTorch}, author = {Izmailov, Pavel and Wilson, Andrew Gordon}, month = apr, year = {2019}, }