@article {805, title = {Drug-target identification in COVID-19 disease mechanisms using computational systems biology approaches.}, journal = {Front Immunol}, volume = {14}, year = {2024}, month = {2023}, pages = {1282859}, abstract = {

INTRODUCTION: The COVID-19 Disease Map project is a large-scale community effort uniting 277 scientists from 130 Institutions around the globe. We use high-quality, mechanistic content describing SARS-CoV-2-host interactions and develop interoperable bioinformatic pipelines for novel target identification and drug repurposing.

METHODS: Extensive community work allowed an impressive step forward in building interfaces between Systems Biology tools and platforms. Our framework can link biomolecules from omics data analysis and computational modelling to dysregulated pathways in a cell-, tissue- or patient-specific manner. Drug repurposing using text mining and AI-assisted analysis identified potential drugs, chemicals and microRNAs that could target the identified key factors.

RESULTS: Results revealed drugs already tested for anti-COVID-19 efficacy, providing a mechanistic context for their mode of action, and drugs already in clinical trials for treating other diseases, never tested against COVID-19.

DISCUSSION: The key advance is that the proposed framework is versatile and expandable, offering a significant upgrade in the arsenal for virus-host interactions and other complex pathologies.

}, keywords = {Computer Simulation, COVID-19, drug repositioning, Humans, SARS-CoV-2, Systems biology}, issn = {1664-3224}, doi = {10.3389/fimmu.2023.1282859}, author = {Niarakis, Anna and Ostaszewski, Marek and Mazein, Alexander and Kuperstein, Inna and Kutmon, Martina and Gillespie, Marc E and Funahashi, Akira and Acencio, Marcio Luis and Hemedan, Ahmed and Aichem, Michael and Klein, Karsten and Czauderna, Tobias and Burtscher, Felicia and Yamada, Takahiro G and Hiki, Yusuke and Hiroi, Noriko F and Hu, Finterly and Pham, Nhung and Ehrhart, Friederike and Willighagen, Egon L and Valdeolivas, Alberto and Dugourd, Aur{\'e}lien and Messina, Francesco and Esteban-Medina, Marina and Pe{\~n}a-Chilet, Maria and Rian, Kinza and Soliman, Sylvain and Aghamiri, Sara Sadat and Puniya, Bhanwar Lal and Naldi, Aur{\'e}lien and Helikar, Tom{\'a}{\v s} and Singh, Vidisha and Fern{\'a}ndez, Marco Fari{\~n}as and Bermudez, Viviam and Tsirvouli, Eirini and Montagud, Arnau and No{\"e}l, Vincent and Ponce-de-Leon, Miguel and Maier, Dieter and Bauch, Angela and Gyori, Benjamin M and Bachman, John A and Luna, Augustin and Pi{\~n}ero, Janet and Furlong, Laura I and Balaur, Irina and Rougny, Adrien and Jarosz, Yohan and Overall, Rupert W and Phair, Robert and Perfetto, Livia and Matthews, Lisa and Rex, Devasahayam Arokia Balaya and Orlic-Milacic, Marija and Gomez, Luis Cristobal Monraz and De Meulder, Bertrand and Ravel, Jean Marie and Jassal, Bijay and Satagopam, Venkata and Wu, Guanming and Golebiewski, Martin and Gawron, Piotr and Calzone, Laurence and Beckmann, Jacques S and Evelo, Chris T and D{\textquoteright}Eustachio, Peter and Schreiber, Falk and Saez-Rodriguez, Julio and Dopazo, Joaquin and Kuiper, Martin and Valencia, Alfonso and Wolkenhauer, Olaf and Kitano, Hiroaki and Barillot, Emmanuel and Auffray, Charles and Balling, Rudi and Schneider, Reinhard} } @article {750, title = {CIBERER: Spanish National Network for Research on Rare Diseases: a highly productive collaborative initiative.}, journal = {Clin Genet}, year = {2022}, month = {2022 Jan 20}, abstract = {

CIBER (Center for Biomedical Network Research; Centro de Investigaci{\'o}n Biom{\'e}dica En Red) is a public national consortium created in 2006 under the umbrella of the Spanish National Institute of Health Carlos III (ISCIII). This innovative research structure comprises 11 different specific areas dedicated to the main public health priorities in the National Health System. CIBERER, the thematic area of CIBER focused on Rare Diseases currently consists of 75 research groups belonging to universities, research centers and hospitals of the entire country. CIBERER{\textquoteright}s mission is to be a center prioritizing and favoring collaboration and cooperation between biomedical and clinical research groups, with special emphasis on the aspects of genetic, molecular, biochemical and cellular research of rare diseases. This research is the basis for providing new tools for the diagnosis and therapy of low-prevalence diseases, in line with the International Rare Diseases Research Consortium (IRDiRC) objectives, thus favoring translational research between the scientific environment of the laboratory and the clinical setting of health centers. In this paper, we intend to review CIBERER{\textquoteright}s 15-year journey and summarize the main results obtained in terms of internationalization, scientific production, contributions towards the discovery of new therapies and novel genes associated to diseases, cooperation with patients{\textquoteright} associations and many other topics related to rare disease research. This article is protected by copyright. All rights reserved.

}, issn = {1399-0004}, doi = {10.1111/cge.14113}, author = {Luque, Juan and Mendes, Ingrid and G{\'o}mez, Beatriz and Morte, Beatriz and de Heredia, Miguel L{\'o}pez and Herreras, Enrique and Corrochano, Virginia and Bueren, Juan and Gallano, Pia and Artuch, Rafael and Fillat, Cristina and P{\'e}rez-Jurado, Luis A and Montoliu, Lluis and Carracedo, {\'A}ngel and Mill{\'a}n, Jos{\'e} M and Webb, Susan M and Palau, Francesc and Lapunzina, Pablo} } @article {736, title = {COVID19 Disease Map, a computational knowledge repository of virus-host interaction mechanisms.}, journal = {Mol Syst Biol}, volume = {17}, year = {2021}, month = {2021 10}, pages = {e10387}, abstract = {

We need to effectively combine the knowledge from surging literature with complex datasets to propose mechanistic models of SARS-CoV-2 infection, improving data interpretation and predicting key targets of intervention. Here, we describe a large-scale community effort to build an open access, interoperable and computable repository of COVID-19 molecular mechanisms. The COVID-19 Disease Map (C19DMap) is a graphical, interactive representation of disease-relevant molecular mechanisms linking many knowledge sources. Notably, it is a computational resource for graph-based analyses and disease modelling. To this end, we established a framework of tools, platforms and guidelines necessary for a multifaceted community of biocurators, domain experts, bioinformaticians and computational biologists. The diagrams of the C19DMap, curated from the literature, are integrated with relevant interaction and text mining databases. We demonstrate the application of network analysis and modelling approaches by concrete examples to highlight new testable hypotheses. This framework helps to find signatures of SARS-CoV-2 predisposition, treatment response or prioritisation of drug candidates. Such an approach may help deal with new waves of COVID-19 or similar pandemics in the long-term perspective.

}, keywords = {Antiviral Agents, Computational Biology, Computer Graphics, COVID-19, Cytokines, Data Mining, Databases, Factual, Gene Expression Regulation, Host Microbial Interactions, Humans, Immunity, Cellular, Immunity, Humoral, Immunity, Innate, Lymphocytes, Metabolic Networks and Pathways, Myeloid Cells, Protein Interaction Mapping, SARS-CoV-2, Signal Transduction, Software, Transcription Factors, Viral Proteins}, issn = {1744-4292}, doi = {10.15252/msb.202110387}, author = {Ostaszewski, Marek and Niarakis, Anna and Mazein, Alexander and Kuperstein, Inna and Phair, Robert and Orta-Resendiz, Aurelio and Singh, Vidisha and Aghamiri, Sara Sadat and Acencio, Marcio Luis and Glaab, Enrico and Ruepp, Andreas and Fobo, Gisela and Montrone, Corinna and Brauner, Barbara and Frishman, Goar and Monraz G{\'o}mez, Luis Crist{\'o}bal and Somers, Julia and Hoch, Matti and Kumar Gupta, Shailendra and Scheel, Julia and Borlinghaus, Hanna and Czauderna, Tobias and Schreiber, Falk and Montagud, Arnau and Ponce de Leon, Miguel and Funahashi, Akira and Hiki, Yusuke and Hiroi, Noriko and Yamada, Takahiro G and Dr{\"a}ger, Andreas and Renz, Alina and Naveez, Muhammad and Bocskei, Zsolt and Messina, Francesco and B{\"o}rnigen, Daniela and Fergusson, Liam and Conti, Marta and Rameil, Marius and Nakonecnij, Vanessa and Vanhoefer, Jakob and Schmiester, Leonard and Wang, Muying and Ackerman, Emily E and Shoemaker, Jason E and Zucker, Jeremy and Oxford, Kristie and Teuton, Jeremy and Kocakaya, Ebru and Summak, G{\"o}k{\c c}e Ya{\u g}mur and Hanspers, Kristina and Kutmon, Martina and Coort, Susan and Eijssen, Lars and Ehrhart, Friederike and Rex, Devasahayam Arokia Balaya and Slenter, Denise and Martens, Marvin and Pham, Nhung and Haw, Robin and Jassal, Bijay and Matthews, Lisa and Orlic-Milacic, Marija and Senff Ribeiro, Andrea and Rothfels, Karen and Shamovsky, Veronica and Stephan, Ralf and Sevilla, Cristoffer and Varusai, Thawfeek and Ravel, Jean-Marie and Fraser, Rupsha and Ortseifen, Vera and Marchesi, Silvia and Gawron, Piotr and Smula, Ewa and Heirendt, Laurent and Satagopam, Venkata and Wu, Guanming and Riutta, Anders and Golebiewski, Martin and Owen, Stuart and Goble, Carole and Hu, Xiaoming and Overall, Rupert W and Maier, Dieter and Bauch, Angela and Gyori, Benjamin M and Bachman, John A and Vega, Carlos and Grou{\`e}s, Valentin and Vazquez, Miguel and Porras, Pablo and Licata, Luana and Iannuccelli, Marta and Sacco, Francesca and Nesterova, Anastasia and Yuryev, Anton and de Waard, Anita and Turei, Denes and Luna, Augustin and Babur, Ozgun and Soliman, Sylvain and Valdeolivas, Alberto and Esteban-Medina, Marina and Pe{\~n}a-Chilet, Maria and Rian, Kinza and Helikar, Tom{\'a}{\v s} and Puniya, Bhanwar Lal and Modos, Dezso and Treveil, Agatha and Olbei, Marton and De Meulder, Bertrand and Ballereau, Stephane and Dugourd, Aur{\'e}lien and Naldi, Aur{\'e}lien and No{\"e}l, Vincent and Calzone, Laurence and Sander, Chris and Demir, Emek and Korcsmaros, Tamas and Freeman, Tom C and Aug{\'e}, Franck and Beckmann, Jacques S and Hasenauer, Jan and Wolkenhauer, Olaf and Wilighagen, Egon L and Pico, Alexander R and Evelo, Chris T and Gillespie, Marc E and Stein, Lincoln D and Hermjakob, Henning and D{\textquoteright}Eustachio, Peter and Saez-Rodriguez, Julio and Dopazo, Joaquin and Valencia, Alfonso and Kitano, Hiroaki and Barillot, Emmanuel and Auffray, Charles and Balling, Rudi and Schneider, Reinhard} } @article {728, title = {DOME: recommendations for supervised machine learning validation in biology.}, journal = {Nat Methods}, volume = {18}, year = {2021}, month = {2021 10}, pages = {1122-1127}, keywords = {Algorithms, Computational Biology, Guidelines as Topic, Humans, Models, Biological, Research Design, Supervised Machine Learning}, issn = {1548-7105}, doi = {10.1038/s41592-021-01205-4}, author = {Walsh, Ian and Fishman, Dmytro and Garcia-Gasulla, Dario and Titma, Tiina and Pollastri, Gianluca and Harrow, Jennifer and Psomopoulos, Fotis E and Tosatto, Silvio C E} } @article {714, title = {The NCI Genomic Data Commons}, journal = {Nature Genetics}, year = {2021}, month = {Oct-02-2022}, issn = {1061-4036}, doi = {10.1038/s41588-021-00791-5}, url = {http://www.nature.com/articles/s41588-021-00791-5}, author = {Heath, Allison P. and Ferretti, Vincent and Agrawal, Stuti and An, Maksim and Angelakos, James C. and Arya, Renuka and Bajari, Rosita and Baqar, Bilal and Barnowski, Justin H. B. and Burt, Jeffrey and Catton, Ann and Chan, Brandon F. and Chu, Fay and Cullion, Kim and Davidsen, Tanja and Do, Phuong-My and Dompierre, Christian and Ferguson, Martin L. and Fitzsimons, Michael S. and Ford, Michael and Fukuma, Miyuki and Gaheen, Sharon and Ganji, Gajanan L. and Garcia, Tzintzuni I. and George, Sameera S. and Gerhard, Daniela S. and Gerthoffert, Francois and Gomez, Fauzi and Han, Kang and Hernandez, Kyle M. and Issac, Biju and Jackson, Richard and Jensen, Mark A. and Joshi, Sid and Kadam, Ajinkya and Khurana, Aishmit and Kim, Kyle M. J. and Kraft, Victoria E. and Li, Shenglai and Lichtenberg, Tara M. and Lodato, Janice and Lolla, Laxmi and Martinov, Plamen and Mazzone, Jeffrey A. and Miller, Daniel P. and Miller, Ian and Miller, Joshua S. and Miyauchi, Koji and Murphy, Mark W. and Nullet, Thomas and Ogwara, Rowland O. and Ortu{\~n}o, Francisco M. and Pedrosa, Jes{\'u}s and Pham, Phuong L. and Popov, Maxim Y. and Porter, James J. and Powell, Raymond and Rademacher, Karl and Reid, Colin P. and Rich, Samantha and Rogel, Bessie and Sahni, Himanso and Savage, Jeremiah H. and Schmitt, Kyle A. and Simmons, Trevar J. and Sislow, Joseph and Spring, Jonathan and Stein, Lincoln and Sullivan, Sean and Tang, Yajing and Thiagarajan, Mathangi and Troyer, Heather D. and Wang, Chang and Wang, Zhining and West, Bedford L. and Wilmer, Alex and Wilson, Shane and Wu, Kaman and Wysocki, William P. and Xiang, Linda and Yamada, Joseph T. and Yang, Liming and Yu, Christine and Yung, Christina K. and Zenklusen, Jean Claude and Zhang, Junjun and Zhang, Zhenyu and Zhao, Yuanheng and Zubair, Ariz and Staudt, Louis M. and Grossman, Robert L.} } @article {742, title = {Reporting guidelines for human microbiome research: the STORMS checklist.}, journal = {Nat Med}, volume = {27}, year = {2021}, month = {2021 11}, pages = {1885-1892}, abstract = {

The particularly interdisciplinary nature of human microbiome research makes the organization and reporting of results spanning epidemiology, biology, bioinformatics, translational medicine and statistics a challenge. Commonly used reporting guidelines for observational or genetic epidemiology studies lack key features specific to microbiome studies. Therefore, a multidisciplinary group of microbiome epidemiology researchers adapted guidelines for observational and genetic studies to culture-independent human microbiome studies, and also developed new reporting elements for laboratory, bioinformatics and statistical analyses tailored to microbiome studies. The resulting tool, called {\textquoteright}Strengthening The Organization and Reporting of Microbiome Studies{\textquoteright} (STORMS), is composed of a 17-item checklist organized into six sections that correspond to the typical sections of a scientific publication, presented as an editable table for inclusion in supplementary materials. The STORMS checklist provides guidance for concise and complete reporting of microbiome studies that will facilitate manuscript preparation, peer review, and reader comprehension of publications and comparative analysis of published results.

}, keywords = {Computational Biology, Dysbiosis, Humans, Microbiota, Observational Studies as Topic, Research Design, Translational Science, Biomedical}, issn = {1546-170X}, doi = {10.1038/s41591-021-01552-x}, author = {Mirzayi, Chloe and Renson, Audrey and Zohra, Fatima and Elsafoury, Shaimaa and Geistlinger, Ludwig and Kasselman, Lora J and Eckenrode, Kelly and van de Wijgert, Janneke and Loughman, Amy and Marques, Francine Z and MacIntyre, David A and Arumugam, Manimozhiyan and Azhar, Rimsha and Beghini, Francesco and Bergstrom, Kirk and Bhatt, Ami and Bisanz, Jordan E and Braun, Jonathan and Bravo, Hector Corrada and Buck, Gregory A and Bushman, Frederic and Casero, David and Clarke, Gerard and Collado, Maria Carmen and Cotter, Paul D and Cryan, John F and Demmer, Ryan T and Devkota, Suzanne and Elinav, Eran and Escobar, Juan S and Fettweis, Jennifer and Finn, Robert D and Fodor, Anthony A and Forslund, Sofia and Franke, Andre and Furlanello, Cesare and Gilbert, Jack and Grice, Elizabeth and Haibe-Kains, Benjamin and Handley, Scott and Herd, Pamela and Holmes, Susan and Jacobs, Jonathan P and Karstens, Lisa and Knight, Rob and Knights, Dan and Koren, Omry and Kwon, Douglas S and Langille, Morgan and Lindsay, Brianna and McGovern, Dermot and McHardy, Alice C and McWeeney, Shannon and Mueller, Noel T and Nezi, Luigi and Olm, Matthew and Palm, Noah and Pasolli, Edoardo and Raes, Jeroen and Redinbo, Matthew R and R{\"u}hlemann, Malte and Balfour Sartor, R and Schloss, Patrick D and Schriml, Lynn and Segal, Eran and Shardell, Michelle and Sharpton, Thomas and Smirnova, Ekaterina and Sokol, Harry and Sonnenburg, Justin L and Srinivasan, Sujatha and Thingholm, Louise B and Turnbaugh, Peter J and Upadhyay, Vaibhav and Walls, Ramona L and Wilmes, Paul and Yamada, Takuji and Zeller, Georg and Zhang, Mingyu and Zhao, Ni and Zhao, Liping and Bao, Wenjun and Culhane, Aedin and Devanarayan, Viswanath and Dopazo, Joaquin and Fan, Xiaohui and Fischer, Matthias and Jones, Wendell and Kusko, Rebecca and Mason, Christopher E and Mercer, Tim R and Sansone, Susanna-Assunta and Scherer, Andreas and Shi, Leming and Thakkar, Shraddha and Tong, Weida and Wolfinger, Russ and Hunter, Christopher and Segata, Nicola and Huttenhower, Curtis and Dowd, Jennifer B and Jones, Heidi E and Waldron, Levi} } @article {696, title = {Community Assessment of the Predictability of Cancer Protein and Phosphoprotein Levels from Genomics and Transcriptomics.}, journal = {Cell Syst}, volume = {11}, year = {2020}, month = {2020 08 26}, pages = {186-195.e9}, abstract = {

Cancer is driven by genomic alterations, but the processes causing this disease are largely performed by proteins. However, proteins are harder and more expensive to measure than genes and transcripts. To catalyze developments of methods to infer protein levels from other omics measurements, we leveraged crowdsourcing via the NCI-CPTAC DREAM proteogenomic challenge. We asked for methods to predict protein and phosphorylation levels from genomic and transcriptomic data in cancer patients. The best performance was achieved by an ensemble of models, including as predictors transcript level of the corresponding genes, interaction between genes, conservation across tumor types, and phosphosite proximity for phosphorylation prediction. Proteins from metabolic pathways and complexes were the best and worst predicted, respectively. The performance of even the best-performing model was modest, suggesting that many proteins are strongly regulated through translational control and degradation. Our results set a reference for the limitations of computational inference in proteogenomics. A record of this paper{\textquoteright}s transparent peer review process is included in the Supplemental Information.

}, keywords = {Crowdsourcing, Female, Genomics, Humans, Machine Learning, Male, Neoplasms, Phosphoproteins, Proteins, Proteomics, Transcriptome}, issn = {2405-4720}, doi = {10.1016/j.cels.2020.06.013}, author = {Yang, Mi and Petralia, Francesca and Li, Zhi and Li, Hongyang and Ma, Weiping and Song, Xiaoyu and Kim, Sunkyu and Lee, Heewon and Yu, Han and Lee, Bora and Bae, Seohui and Heo, Eunji and Kaczmarczyk, Jan and St{\k e}pniak, Piotr and Warcho{\l}, Micha{\l} and Yu, Thomas and Calinawan, Anna P and Boutros, Paul C and Payne, Samuel H and Reva, Boris and Boja, Emily and Rodriguez, Henry and Stolovitzky, Gustavo and Guan, Yuanfang and Kang, Jaewoo and Wang, Pei and Feny{\"o}, David and Saez-Rodriguez, Julio} } @article {689, title = {COVID-19 Disease Map, building a computational repository of SARS-CoV-2 virus-host interaction mechanisms.}, journal = {Sci Data}, volume = {7}, year = {2020}, month = {2020 05 05}, pages = {136}, keywords = {Betacoronavirus, Computational Biology, Coronavirus Infections, COVID-19, Databases, Factual, Host Microbial Interactions, Host-Pathogen Interactions, Humans, International Cooperation, Models, Biological, Pandemics, Pneumonia, Viral, SARS-CoV-2}, issn = {2052-4463}, doi = {10.1038/s41597-020-0477-8}, author = {Ostaszewski, Marek and Mazein, Alexander and Gillespie, Marc E and Kuperstein, Inna and Niarakis, Anna and Hermjakob, Henning and Pico, Alexander R and Willighagen, Egon L and Evelo, Chris T and Hasenauer, Jan and Schreiber, Falk and Dr{\"a}ger, Andreas and Demir, Emek and Wolkenhauer, Olaf and Furlong, Laura I and Barillot, Emmanuel and Dopazo, Joaquin and Orta-Resendiz, Aurelio and Messina, Francesco and Valencia, Alfonso and Funahashi, Akira and Kitano, Hiroaki and Auffray, Charles and Balling, Rudi and Schneider, Reinhard} } @article {704, title = {Transparency and reproducibility in artificial intelligence.}, journal = {Nature}, volume = {586}, year = {2020}, month = {2020 10}, pages = {E14-E16}, keywords = {Algorithms, Artificial Intelligence, Reproducibility of Results}, issn = {1476-4687}, doi = {10.1038/s41586-020-2766-y}, author = {Haibe-Kains, Benjamin and Adam, George Alexandru and Hosny, Ahmed and Khodakarami, Farnoosh and Waldron, Levi and Wang, Bo and McIntosh, Chris and Goldenberg, Anna and Kundaje, Anshul and Greene, Casey S and Broderick, Tamara and Hoffman, Michael M and Leek, Jeffrey T and Korthauer, Keegan and Huber, Wolfgang and Brazma, Alvis and Pineau, Joelle and Tibshirani, Robert and Hastie, Trevor and Ioannidis, John P A and Quackenbush, John and Aerts, Hugo J W L} } @article {612, title = {Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen.}, journal = {Nat Commun}, volume = {10}, year = {2019}, month = {2019 06 17}, pages = {2674}, abstract = {

The effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca{\textquoteright}s large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60\% of combinations. However, 20\% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells.

}, keywords = {ADAM17 Protein, Antineoplastic Combined Chemotherapy Protocols, Benchmarking, Biomarkers, Tumor, Cell Line, Tumor, Computational Biology, Datasets as Topic, Drug Antagonism, Drug Resistance, Neoplasm, Drug Synergism, Genomics, Humans, Molecular Targeted Therapy, mutation, Neoplasms, pharmacogenetics, Phosphatidylinositol 3-Kinases, Phosphoinositide-3 Kinase Inhibitors, Treatment Outcome}, issn = {2041-1723}, doi = {10.1038/s41467-019-09799-2}, author = {Menden, Michael P and Wang, Dennis and Mason, Mike J and Szalai, Bence and Bulusu, Krishna C and Guan, Yuanfang and Yu, Thomas and Kang, Jaewoo and Jeon, Minji and Wolfinger, Russ and Nguyen, Tin and Zaslavskiy, Mikhail and Jang, In Sock and Ghazoui, Zara and Ahsen, Mehmet Eren and Vogel, Robert and Neto, Elias Chaibub and Norman, Thea and Tang, Eric K Y and Garnett, Mathew J and Veroli, Giovanni Y Di and Fawell, Stephen and Stolovitzky, Gustavo and Guinney, Justin and Dry, Jonathan R and Saez-Rodriguez, Julio} } @article {428, title = {A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection}, journal = {Nature Communications}, volume = {9}, year = {2018}, month = {Jan-12-2018}, doi = {10.1038/s41467-018-06735-8}, url = {http://www.nature.com/articles/s41467-018-06735-8http://www.nature.com/articles/s41467-018-06735-8.pdfhttp://www.nature.com/articles/s41467-018-06735-8.pdfhttp://www.nature.com/articles/s41467-018-06735-8}, author = {Fourati, Slim and Talla, Aarthi and Mahmoudian, Mehrad and Burkhart, Joshua G. and Kl{\'e}n, Riku and Henao, Ricardo and Yu, Thomas and Ayd{\i}n, Zafer and Yeung, Ka Yee and Ahsen, Mehmet Eren and Almugbel, Reem and Jahandideh, Samad and Liang, Xiao and Nordling, Torbj{\"o}rn E. M. and Shiga, Motoki and Stanescu, Ana and Vogel, Robert and Pandey, Gaurav and Chiu, Christopher and McClain, Micah T. and Woods, Christopher W. and Ginsburg, Geoffrey S. and Elo, Laura L. and Tsalik, Ephraim L. and Mangravite, Lara M. and Sieberts, Solveig K.} } @article {398, title = {Genomics of the origin and evolution of Citrus.}, journal = {Nature}, volume = {554}, year = {2018}, month = {2018 02 15}, pages = {311-316}, abstract = {

The genus Citrus, comprising some of the most widely cultivated fruit crops worldwide, includes an uncertain number of species. Here we describe ten natural citrus species, using genomic, phylogenetic and biogeographic analyses of 60 accessions representing diverse citrus germ plasms, and propose that citrus diversified during the late Miocene epoch through a rapid southeast Asian radiation that correlates with a marked weakening of the monsoons. A second radiation enabled by migration across the Wallace line gave rise to the Australian limes in the early Pliocene epoch. Further identification and analyses of hybrids and admixed genomes provides insights into the genealogy of major commercial cultivars of citrus. Among mandarins and sweet orange, we find an extensive network of relatedness that illuminates the domestication of these groups. Widespread pummelo admixture among these mandarins and its correlation with fruit size and acidity suggests a plausible role of pummelo introgression in the selection of palatable mandarins. This work provides a new evolutionary framework for the genus Citrus.

}, keywords = {Asia, Southeastern, Biodiversity, citrus, Crop Production, Evolution, Molecular, Genetic Speciation, Genome, Plant, Genomics, Haplotypes, Heterozygote, History, Ancient, Human Migration, Hybridization, Genetic, Phylogeny}, issn = {1476-4687}, doi = {10.1038/nature25447}, author = {Wu, Guohong Albert and Terol, Javier and Iba{\~n}ez, Victoria and L{\'o}pez-Garc{\'\i}a, Antonio and P{\'e}rez-Rom{\'a}n, Estela and Borred{\'a}, Carles and Domingo, Concha and Tadeo, Francisco R and Carbonell-Caballero, Jos{\'e} and Alonso, Roberto and Curk, Franck and Du, Dongliang and Ollitrault, Patrick and Roose, Mikeal L and Dopazo, Joaquin and Gmitter, Frederick G and Rokhsar, Daniel S and Talon, Manuel} } @article {383, title = {Integration of transcriptomic and metabolic data reveals hub transcription factors involved in drought stress response in sunflower (Helianthus annuus L.).}, journal = {Plant Mol Biol}, volume = {94}, year = {2017}, month = {2017 Jul}, pages = {549-564}, abstract = {

By integration of transcriptional and metabolic profiles we identified pathways and hubs transcription factors regulated during drought conditions in sunflower, useful for applications in molecular and/or biotechnological breeding. Drought is one of the most important environmental stresses that effects crop productivity in many agricultural regions. Sunflower is tolerant to drought conditions but the mechanisms involved in this tolerance remain unclear at the molecular level. The aim of this study was to characterize and integrate transcriptional and metabolic pathways related to drought stress in sunflower plants, by using a system biology approach. Our results showed a delay in plant senescence with an increase in the expression level of photosynthesis related genes as well as higher levels of sugars, osmoprotectant amino acids and ionic nutrients under drought conditions. In addition, we identified transcription factors that were upregulated during drought conditions and that may act as hubs in the transcriptional network. Many of these transcription factors belong to families implicated in the drought response in model species. The integration of transcriptomic and metabolomic data in this study, together with physiological measurements, has improved our understanding of the biological responses during droughts and contributes to elucidate the molecular mechanisms involved under this environmental condition. These findings will provide useful biotechnological tools to improve stress tolerance while maintaining crop yield under restricted water availability.

}, keywords = {Chlorophyll, Gene Expression Regulation, Plant, Helianthus, Plant Leaves, Plant Proteins, Protein Array Analysis, RNA, Plant, Stress, Physiological, Transcription Factors, Water}, issn = {1573-5028}, doi = {10.1007/s11103-017-0625-5}, author = {Moschen, Sebasti{\'a}n and Di Rienzo, Julio A and Higgins, Janet and Tohge, Takayuki and Watanabe, Mutsumi and Gonzalez, Sergio and Rivarola, M{\'a}ximo and Garcia-Garcia, Francisco and Dopazo, Joaquin and Hopp, H Esteban and Hoefgen, Rainer and Fernie, Alisdair R and Paniego, Norma and Fernandez, Paula and Heinz, Ruth A} } @article {1211, title = {Extension of human lncRNA transcripts by RACE coupled with long-read high-throughput sequencing (RACE-Seq).}, journal = {Nature communications}, volume = {7}, year = {2016}, month = {2016}, pages = {12339}, abstract = {Long non-coding RNAs (lncRNAs) constitute a large, yet mostly uncharacterized fraction of the mammalian transcriptome. Such characterization requires a comprehensive, high-quality annotation of their gene structure and boundaries, which is currently lacking. Here we describe RACE-Seq, an experimental workflow designed to address this based on RACE (rapid amplification of cDNA ends) and long-read RNA sequencing. We apply RACE-Seq to 398 human lncRNA genes in seven tissues, leading to the discovery of 2,556 on-target, novel transcripts. About 60\% of the targeted loci are extended in either 5{\textquoteright} or 3{\textquoteright}, often reaching genomic hallmarks of gene boundaries. Analysis of the novel transcripts suggests that lncRNAs are as long, have as many exons and undergo as much alternative splicing as protein-coding genes, contrary to current assumptions. Overall, we show that RACE-Seq is an effective tool to annotate an organism{\textquoteright}s deep transcriptome, and compares favourably to other targeted sequencing techniques.}, issn = {2041-1723}, doi = {10.1038/ncomms12339}, url = {http://www.nature.com/articles/ncomms12339}, author = {Lagarde, Julien and Uszczynska-Ratajczak, Barbara and Santoyo-L{\'o}pez, Javier and Gonzalez, Jose Manuel and Tapanari, Electra and Mudge, Jonathan M and Steward, Charles A and Wilming, Laurens and Tanzer, Andrea and Howald, C{\'e}dric and Chrast, Jacqueline and Vela-Boza, Alicia and Antonio Rueda and L{\'o}pez-Domingo, Francisco J and Dopazo, Joaquin and Reymond, Alexandre and Guig{\'o}, Roderic and Harrow, Jennifer} } @article {559, title = {Extension of human lncRNA transcripts by RACE coupled with long-read high-throughput sequencing (RACE-Seq)}, journal = {Nature Communications}, volume = {7}, year = {2016}, month = {Jan-11-2016}, doi = {10.1038/ncomms12339}, url = {http://www.nature.com/articles/ncomms12339http://www.nature.com/articles/ncomms12339.pdfhttp://www.nature.com/articles/ncomms12339.pdfhttp://www.nature.com/articles/ncomms12339}, author = {Lagarde, Julien and Uszczynska-Ratajczak, Barbara and Santoyo-L{\'o}pez, Javier and Gonzalez, Jose Manuel and Tapanari, Electra and Mudge, Jonathan M. and Steward, Charles A. and Wilming, Laurens and Tanzer, Andrea and Howald, C{\'e}dric and Chrast, Jacqueline and Vela-Boza, Alicia and Rueda, Antonio and Lopez-Domingo, Francisco J. and Dopazo, Joaquin and Reymond, Alexandre and Guig{\'o}, Roderic and Harrow, Jennifer} } @article {446, title = {Integrating transcriptomic and metabolomic analysis to understand natural leaf senescence in sunflower.}, journal = {Plant Biotechnol J}, volume = {14}, year = {2016}, month = {2016 Feb}, pages = {719-34}, abstract = {

Leaf senescence is a complex process, which has dramatic consequences on crop yield. In sunflower, gap between potential and actual yields reveals the economic impact of senescence. Indeed, sunflower plants are incapable of maintaining their green leaf area over sustained periods. This study characterizes the leaf senescence process in sunflower through a systems biology approach integrating transcriptomic and metabolomic analyses: plants being grown under both glasshouse and field conditions. Our results revealed a correspondence between profile changes detected at the molecular, biochemical and physiological level throughout the progression of leaf senescence measured at different plant developmental stages. Early metabolic changes were detected prior to anthesis and before the onset of the first senescence symptoms, with more pronounced changes observed when physiological and molecular variables were assessed under field conditions. During leaf development, photosynthetic activity and cell growth processes decreased, whereas sucrose, fatty acid, nucleotide and amino acid metabolisms increased. Pathways related to nutrient recycling processes were also up-regulated. Members of the NAC, AP2-EREBP, HB, bZIP and MYB transcription factor families showed high expression levels, and their expression level was highly correlated, suggesting their involvement in sunflower senescence. The results of this study thus contribute to the elucidation of the molecular mechanisms involved in the onset and progression of leaf senescence in sunflower leaves as well as to the identification of candidate genes involved in this process.

}, keywords = {Gas Chromatography-Mass Spectrometry, Gene Expression Profiling, Gene Expression Regulation, Plant, Gene ontology, Genes, Plant, Helianthus, Ions, metabolomics, Oligonucleotide Array Sequence Analysis, Plant Leaves, Principal Component Analysis, RNA, Messenger, Transcription Factors}, issn = {1467-7652}, doi = {10.1111/pbi.12422}, author = {Moschen, Sebasti{\'a}n and Bengoa Luoni, Sof{\'\i}a and Di Rienzo, Julio A and Caro, Mar{\'\i}a Del Pilar and Tohge, Takayuki and Watanabe, Mutsumi and Hollmann, Julien and Gonzalez, Sergio and Rivarola, M{\'a}ximo and Garcia-Garcia, Francisco and Dopazo, Joaquin and Hopp, Horacio Esteban and Hoefgen, Rainer and Fernie, Alisdair R and Paniego, Norma and Fernandez, Paula and Heinz, Ruth A} } @article {1132, title = {Combining tumor genome simulation with crowdsourcing to benchmark somatic single-nucleotide-variant detection.}, journal = {Nature methods}, year = {2015}, month = {2015 May 18}, abstract = {The detection of somatic mutations from cancer genome sequences is key to understanding the genetic basis of disease progression, patient survival and response to therapy. Benchmarking is needed for tool assessment and improvement but is complicated by a lack of gold standards, by extensive resource requirements and by difficulties in sharing personal genomic information. To resolve these issues, we launched the ICGC-TCGA DREAM Somatic Mutation Calling Challenge, a crowdsourced benchmark of somatic mutation detection algorithms. Here we report the BAMSurgeon tool for simulating cancer genomes and the results of 248 analyses of three in silico tumors created with it. Different algorithms exhibit characteristic error profiles, and, intriguingly, false positives show a trinucleotide profile very similar to one found in human tumors. Although the three simulated tumors differ in sequence contamination (deviation from normal cell sequence) and in subclonality, an ensemble of pipelines outperforms the best individual pipeline in all cases. BAMSurgeon is available at https://github.com/adamewing/bamsurgeon/.}, keywords = {cancer, NGS, variant calling}, issn = {1548-7105}, doi = {10.1038/nmeth.3407}, url = {http://www.nature.com/nmeth/journal/vaop/ncurrent/full/nmeth.3407.html}, author = {Ewing, Adam D and Houlahan, Kathleen E and Hu, Yin and Ellrott, Kyle and Caloian, Cristian and Yamaguchi, Takafumi N and Bare, J Christopher and P{\textquoteright}ng, Christine and Waggott, Daryl and Sabelnykova, Veronica Y and Kellen, Michael R and Norman, Thea C and Haussler, David and Friend, Stephen H and Stolovitzky, Gustavo and Margolin, Adam A and Stuart, Joshua M and Boutros, Paul C}, editor = {ICGC-TCGA DREAM Somatic Mutation Calling Challenge participants and Liu Xi and Ninad Dewal and Yu Fan and Wenyi Wang and David Wheeler and Andreas Wilm and Grace Hui Ting and Chenhao Li and Denis Bertrand and Niranjan Nagarajan and Qing-Rong Chen and Chih-Hao Hsu and Ying Hu and Chunhua Yan and Warren Kibbe and Daoud Meerzaman and Kristian Cibulskis and Mara Rosenberg and Louis Bergelson and Adam Kiezun and Amie Radenbaugh and Anne-Sophie Sertier and Anthony Ferrari and Laurie Tonton and Kunal Bhutani and Nancy F Hansen and Difei Wang and Lei Song and Zhongwu Lai and Liao, Yang and Shi, Wei and Carbonell-Caballero, Jos{\'e} and Joaqu{\'\i}n Dopazo and Cheryl C K Lau and Justin Guinney} } @article {1155, title = {Prediction of human population responses to toxic compounds by a collaborative competition.}, journal = {Nature biotechnology}, year = {2015}, month = {2015 Aug 10}, abstract = {The ability to computationally predict the effects of toxic compounds on humans could help address the deficiencies of current chemical safety testing. Here, we report the results from a community-based DREAM challenge to predict toxicities of environmental compounds with potential adverse health effects for human populations. We measured the cytotoxicity of 156 compounds in 884 lymphoblastoid cell lines for which genotype and transcriptional data are available as part of the Tox21 1000 Genomes Project. The challenge participants developed algorithms to predict interindividual variability of toxic response from genomic profiles and population-level cytotoxicity data from structural attributes of the compounds. 179 submitted predictions were evaluated against an experimental data set to which participants were blinded. Individual cytotoxicity predictions were better than random, with modest correlations (Pearson{\textquoteright}s r < 0.28), consistent with complex trait genomic prediction. In contrast, predictions of population-level response to different compounds were higher (r < 0.66). The results highlight the possibility of predicting health risks associated with unknown compounds, although risk estimation accuracy remains suboptimal.}, issn = {1546-1696}, doi = {10.1038/nbt.3299}, url = {http://www.nature.com/nbt/journal/vaop/ncurrent/full/nbt.3299.html}, author = {Eduati, Federica and Mangravite, Lara M and Wang, Tao and Tang, Hao and Bare, J Christopher and Huang, Ruili and Norman, Thea and Kellen, Mike and Menden, Michael P and Yang, Jichen and Zhan, Xiaowei and Zhong, Rui and Xiao, Guanghua and Xia, Menghang and Abdo, Nour and Kosyk, Oksana} } @article {1087, title = {Assessing technical performance in differential gene expression experiments with external spike-in RNA control ratio mixtures.}, journal = {Nature communications}, volume = {5}, year = {2014}, month = {2014}, pages = {5125}, abstract = {There is a critical need for standard approaches to assess, report and compare the technical performance of genome-scale differential gene expression experiments. Here we assess technical performance with a proposed standard {\textquoteright}dashboard{\textquoteright} of metrics derived from analysis of external spike-in RNA control ratio mixtures. These control ratio mixtures with defined abundance ratios enable assessment of diagnostic performance of differentially expressed transcript lists, limit of detection of ratio (LODR) estimates and expression ratio variability and measurement bias. The performance metrics suite is applicable to analysis of a typical experiment, and here we also apply these metrics to evaluate technical performance among laboratories. An interlaboratory study using identical samples shared among 12 laboratories with three different measurement processes demonstrates generally consistent diagnostic power across 11 laboratories. Ratio measurement variability and bias are also comparable among laboratories for the same measurement process. We observe different biases for measurement processes using different mRNA-enrichment protocols.}, keywords = {RNA-seq}, issn = {2041-1723}, doi = {10.1038/ncomms6125}, url = {http://www.nature.com/ncomms/2014/140925/ncomms6125/full/ncomms6125.html}, author = {Munro, Sarah A and Lund, Steven P and Pine, P Scott and Binder, Hans and Clevert, Djork-Arn{\'e} and Ana Conesa and Dopazo, Joaquin and Fasold, Mario and Hochreiter, Sepp and Hong, Huixiao and Jafari, Nadereh and Kreil, David P and Labaj, Pawe{\l} P and Li, Sheng and Liao, Yang and Lin, Simon M and Meehan, Joseph and Mason, Christopher E and Santoyo-L{\'o}pez, Javier and Setterquist, Robert A and Shi, Leming and Shi, Wei and Smyth, Gordon K and Stralis-Pavese, Nancy and Su, Zhenqiang and Tong, Weida and Wang, Charles and Wang, Jian and Xu, Joshua and Ye, Zhan and Yang, Yong and Yu, Ying and Salit, Marc} } @article {950, title = {Identification of yeast genes that confer resistance to chitosan oligosaccharide (COS) using chemogenomics.}, journal = {BMC genomics}, volume = {13}, year = {2012}, month = {2012}, pages = {267}, abstract = {BACKGROUND: Chitosan oligosaccharide (COS), a deacetylated derivative of chitin, is an abundant, and renewable natural polymer. COS has higher antimicrobial properties than chitosan and is presumed to act by disrupting/permeabilizing the cell membranes of bacteria, yeast and fungi. COS is relatively non-toxic to mammals. By identifying the molecular and genetic targets of COS, we hope to gain a better understanding of the antifungal mode of action of COS. RESULTS: Three different chemogenomic fitness assays, haploinsufficiency (HIP), homozygous deletion (HOP), and multicopy suppression (MSP) profiling were combined with a transcriptomic analysis to gain insight in to the mode of action and mechanisms of resistance to chitosan oligosaccharides. The fitness assays identified 39 yeast deletion strains sensitive to COS and 21 suppressors of COS sensitivity. The genes identified are involved in processes such as RNA biology (transcription, translation and regulatory mechanisms), membrane functions (e.g. signalling, transport and targeting), membrane structural components, cell division, and proteasome processes. The transcriptomes of control wild type and 5 suppressor strains overexpressing ARL1, BCK2, ERG24, MSG5, or RBA50, were analyzed in the presence and absence of COS. Some of the up-regulated transcripts in the suppressor overexpressing strains exposed to COS included genes involved in transcription, cell cycle, stress response and the Ras signal transduction pathway. Down-regulated transcripts included those encoding protein folding components and respiratory chain proteins. The COS-induced transcriptional response is distinct from previously described environmental stress responses (i.e. thermal, salt, osmotic and oxidative stress) and pre-treatment with these well characterized environmental stressors provided little or any resistance to COS. CONCLUSIONS: Overexpression of the ARL1 gene, a member of the Ras superfamily that regulates membrane trafficking, provides protection against COS-induced cell membrane permeability and damage. We found that the ARL1 COS-resistant over-expression strain was as sensitive to Amphotericin B, Fluconazole and Terbinafine as the wild type cells and that when COS and Fluconazole are used in combination they act in a synergistic fashion. The gene targets of COS identified in this study indicate that COS{\textquoteright}s mechanism of action is different from other commonly studied fungicides that target membranes, suggesting that COS may be an effective fungicide for drug-resistant fungal pathogens.}, issn = {1471-2164}, doi = {10.1186/1471-2164-13-267}, author = {Jaime, Mar{\'\i}a D L A and Lopez-Llorca, Luis Vicente and Ana Conesa and Lee, Anna Y and Proctor, Michael and Heisler, Lawrence E and Gebbia, Marinella and Giaever, Guri and Westwood, J Timothy and Nislow, Corey} } @article {549, title = {Exploring the link between germline and somatic genetic alterations in breast carcinogenesis.}, journal = {PLoS One}, volume = {5}, year = {2010}, month = {2010 Nov 22}, pages = {e14078}, abstract = {

Recent genome-wide association studies (GWASs) have identified candidate genes contributing to cancer risk through low-penetrance mutations. Many of these genes were unexpected and, intriguingly, included well-known players in carcinogenesis at the somatic level. To assess the hypothesis of a germline-somatic link in carcinogenesis, we evaluated the distribution of somatic gene labels within the ordered results of a breast cancer risk GWAS. This analysis suggested frequent influence on risk of genetic variation in loci encoding for "driver kinases" (i.e., kinases encoded by genes that showed higher somatic mutation rates than expected by chance and, therefore, whose deregulation may contribute to cancer development and/or progression). Assessment of these predictions using a population-based case-control study in Poland replicated the association for rs3732568 in EPHB1 (odds ratio (OR) = 0.79; 95\% confidence interval (CI): 0.63-0.98; P(trend) = 0.031). Analyses by early age at diagnosis and by estrogen receptor α (ERα) tumor status indicated potential associations for rs6852678 in CDKL2 (OR = 0.32, 95\% CI: 0.10-1.00; P(recessive) = 0.044) and rs10878640 in DYRK2 (OR = 2.39, 95\% CI: 1.32-4.30; P(dominant) = 0.003), and for rs12765929, rs9836340, rs4707795 in BMPR1A, EPHA3 and EPHA7, respectively (ERα tumor status P(interaction)<0.05). The identification of three novel candidates as EPH receptor genes might indicate a link between perturbed compartmentalization of early neoplastic lesions and breast cancer risk and progression. Together, these data may lay the foundations for replication in additional populations and could potentially increase our knowledge of the underlying molecular mechanisms of breast carcinogenesis.

}, keywords = {Adult, Bone Morphogenetic Protein Receptors, Type I, Breast, Breast Neoplasms, Calcium-Calmodulin-Dependent Protein Kinases, Case-Control Studies, Cyclin-Dependent Kinases, Disease Progression, Estrogen Receptor alpha, Female, Gene Frequency, Genetic Predisposition to Disease, Genome-Wide Association Study, Genotype, Germ-Line Mutation, Humans, Odds Ratio, Poland, Polymorphism, Single Nucleotide, Protein Serine-Threonine Kinases, Protein-Tyrosine Kinases, Receptor Protein-Tyrosine Kinases, Receptor, EphA3, Receptor, EphA7, Receptor, EphB1, Risk Factors}, issn = {1932-6203}, doi = {10.1371/journal.pone.0014078}, author = {Bonifaci, N{\'u}ria and G{\'o}rski, Bohdan and Masoj{\'c}, Bartlomiej and Woko{\l}orczyk, Dominika and Jakubowska, Anna and D{\k e}bniak, Tadeusz and Berenguer, Antoni and Serra Musach, Jordi and Brunet, Joan and Dopazo, Joaquin and Narod, Steven A and Lubi{\'n}ski, Jan and L{\'a}zaro, Conxi and Cybulski, Cezary and Pujana, Miguel Angel} } @article {20676074, title = {The MicroArray Quality Control (MAQC)-II study of common practices for the development and validation of microarray-based predictive models.}, journal = {Nature biotechnology}, volume = {28}, year = {2010}, month = {2010 Aug}, pages = {827-38}, abstract = {

Gene expression data from microarrays are being applied to predict preclinical and clinical endpoints, but the reliability of these predictions has not been established. In the MAQC-II project, 36 independent teams analyzed six microarray data sets to generate predictive models for classifying a sample with respect to one of 13 endpoints indicative of lung or liver toxicity in rodents, or of breast cancer, multiple myeloma or neuroblastoma in humans. In total, \>30,000 models were built using many combinations of analytical methods. The teams generated predictive models without knowing the biological meaning of some of the endpoints and, to mimic clinical reality, tested the models on data that had not been used for training. We found that model performance depended largely on the endpoint and team proficiency and that different approaches generated models of similar performance. The conclusions and recommendations from MAQC-II should be useful for regulatory agencies, study committees and independent investigators that evaluate methods for global gene expression analysis.

}, url = {http://www.nature.com/nbt/journal/v28/n8/full/nbt.1665.html}, author = {Shi, Leming and Campbell, Gregory and Jones, Wendell D and Campagne, Fabien and Wen, Zhining and Walker, Stephen J and Su, Zhenqiang and Chu, Tzu-Ming and Goodsaid, Federico M and Pusztai, Lajos and Shaughnessy, John D and Oberthuer, Andr{\'e} and Thomas, Russell S and Paules, Richard S and Fielden, Mark and Barlogie, Bart and Chen, Weijie and Du, Pan and Fischer, Matthias and Furlanello, Cesare and Gallas, Brandon D and Ge, Xijin and Megherbi, Dalila B and Symmans, W Fraser and Wang, May D and Zhang, John and Bitter, Hans and Brors, Benedikt and Bushel, Pierre R and Bylesjo, Max and Chen, Minjun and Cheng, Jie and Cheng, Jing and Chou, Jeff and Davison, Timothy S and Delorenzi, Mauro and Deng, Youping and Devanarayan, Viswanath and Dix, David J and Dopazo, Joaquin and Dorff, Kevin C and Elloumi, Fathi and Fan, Jianqing and Fan, Shicai and Fan, Xiaohui and Fang, Hong and Gonzaludo, Nina and Hess, Kenneth R and Hong, Huixiao and Huan, Jun and Irizarry, Rafael A and Judson, Richard and Juraeva, Dilafruz and Lababidi, Samir and Lambert, Christophe G and Li, Li and Li, Yanen and Li, Zhen and Lin, Simon M and Liu, Guozhen and Lobenhofer, Edward K and Luo, Jun and Luo, Wen and McCall, Matthew N and Nikolsky, Yuri and Pennello, Gene A and Perkins, Roger G and Philip, Reena and Popovici, Vlad and Price, Nathan D and Qian, Feng and Scherer, Andreas and Shi, Tieliu and Shi, Weiwei and Sung, Jaeyun and Thierry-Mieg, Danielle and Thierry-Mieg, Jean and Thodima, Venkata and Trygg, Johan and Vishnuvajjala, Lakshmi and Wang, Sue Jane and Wu, Jianping and Wu, Yichao and Xie, Qian and Yousef, Waleed A and Zhang, Liang and Zhang, Xuegong and Zhong, Sheng and Zhou, Yiming and Zhu, Sheng and Arasappan, Dhivya and Bao, Wenjun and Lucas, Anne Bergstrom and Berthold, Frank and Brennan, Richard J and Buness, Andreas and Catalano, Jennifer G and Chang, Chang and Chen, Rong and Cheng, Yiyu and Cui, Jian and Czika, Wendy and Demichelis, Francesca and Deng, Xutao and Dosymbekov, Damir and Eils, Roland and Feng, Yang and Fostel, Jennifer and Fulmer-Smentek, Stephanie and Fuscoe, James C and Gatto, Laurent and Ge, Weigong and Goldstein, Darlene R and Guo, Li and Halbert, Donald N and Han, Jing and Harris, Stephen C and Hatzis, Christos and Herman, Damir and Huang, Jianping and Jensen, Roderick V and Jiang, Rui and Johnson, Charles D and Jurman, Giuseppe and Kahlert, Yvonne and Khuder, Sadik A and Kohl, Matthias and Li, Jianying and Li, Li and Li, Menglong and Li, Quan-Zhen and Li, Shao and Li, Zhiguang and Liu, Jie and Liu, Ying and Liu, Zhichao and Meng, Lu and Madera, Manuel and Martinez-Murillo, Francisco and Medina, Ignacio and Meehan, Joseph and Miclaus, Kelci and Moffitt, Richard A and Montaner, David and Mukherjee, Piali and Mulligan, George J and Neville, Padraic and Nikolskaya, Tatiana and Ning, Baitang and Page, Grier P and Parker, Joel and Parry, R Mitchell and Peng, Xuejun and Peterson, Ron L and Phan, John H and Quanz, Brian and Ren, Yi and Riccadonna, Samantha and Roter, Alan H and Samuelson, Frank W and Schumacher, Martin M and Shambaugh, Joseph D and Shi, Qiang and Shippy, Richard and Si, Shengzhu and Smalter, Aaron and Sotiriou, Christos and Soukup, Mat and Staedtler, Frank and Steiner, Guido and Stokes, Todd H and Sun, Qinglan and Tan, Pei-Yi and Tang, Rong and Tezak, Zivana and Thorn, Brett and Tsyganova, Marina and Turpaz, Yaron and Vega, Silvia C and Visintainer, Roberto and von Frese, Juergen and Wang, Charles and Wang, Eric and Wang, Junwei and Wang, Wei and Westermann, Frank and Willey, James C and Woods, Matthew and Wu, Shujian and Xiao, Nianqing and Xu, Joshua and Xu, Lei and Yang, Lun and Zeng, Xiao and Zhang, Jialu and Zhang, Li and Zhang, Min and Zhao, Chen and Puri, Raj K and Scherf, Uwe and Tong, Weida and Wolfinger, Russell D} } @article {19587024, title = {Alignment of multiple protein structures based on sequence and structure features.}, journal = {Protein engineering, design \& selection : PEDS}, volume = {22}, year = {2009}, month = {2009 Sep}, pages = {569-74}, abstract = {

Comparing the structures of proteins is crucial to gaining insight into protein evolution and function. Here, we align the sequences of multiple protein structures by a dynamic programming optimization of a scoring function that is a sum of an affine gap penalty and terms dependent on various sequence and structure features (SALIGN). The features include amino acid residue type, residue position, residue accessible surface area, residue secondary structure state and the conformation of a short segment centered on the residue. The multiple alignment is built by following the {\textquoteright}guide{\textquoteright} tree constructed from the matrix of all pairwise protein alignment scores. Importantly, the method does not depend on the exact values of various parameters, such as feature weights and gap penalties, because the optimal alignment across a range of parameter values is found. Using multiple structure alignments in the HOMSTRAD database, SALIGN was benchmarked against MUSTANG for multiple alignments as well as against TM-align and CE for pairwise alignments. On the average, SALIGN produces a 15\% improvement in structural overlap over HOMSTRAD and 14\% over MUSTANG, and yields more equivalent structural positions than TM-align and CE in 90\% and 95\% of cases, respectively. The utility of accurate multiple structure alignment is illustrated by its application to comparative protein structure modeling.

}, author = {Madhusudhan, M. S. and Webb, Benjamin M and Marti-Renom, Marc A and Eswar, Narayanan and Sali, Andrej} } @article {18948282, title = {MODBASE, a database of annotated comparative protein structure models and associated resources}, journal = {Nucleic Acids Res}, volume = {37}, number = {Database issue}, year = {2009}, note = {Pieper, Ursula Eswar, Narayanan Webb, Ben M Eramian, David Kelly, Libusha Barkan, David T Carter, Hannah Mankoo, Parminder Karchin, Rachel Marti-Renom, Marc A Davis, Fred P Sali, Andrej GM08284/GM/NIGMS NIH HHS/United States P01 GM71790/GM/NIGMS NIH HHS/United States R01 GM54762/GM/NIGMS NIH HHS/United States U01 GM61390/GM/NIGMS NIH HHS/United States U54 GM074929/GM/NIGMS NIH HHS/United States U54 GM074945/GM/NIGMS NIH HHS/United States Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov{\textquoteright}t Research Support, U.S. Gov{\textquoteright}t, Non-P.H.S. England Nucleic acids research Nucleic Acids Res. 2009 Jan;37(Database issue):D347-54. Epub 2008 Oct 23.}, pages = {D347-54}, abstract = {MODBASE (http://salilab.org/modbase) is a database of annotated comparative protein structure models. The models are calculated by MODPIPE, an automated modeling pipeline that relies primarily on MODELLER for fold assignment, sequence-structure alignment, model building and model assessment (http:/salilab.org/modeller). MODBASE currently contains 5,152,695 reliable models for domains in 1,593,209 unique protein sequences; only models based on statistically significant alignments and/or models assessed to have the correct fold are included. MODBASE also allows users to calculate comparative models on demand, through an interface to the MODWEB modeling server (http://salilab.org/modweb). Other resources integrated with MODBASE include databases of multiple protein structure alignments (DBAli), structurally defined ligand binding sites (LIGBASE), predicted ligand binding sites (AnnoLyze), structurally defined binary domain interfaces (PIBASE) and annotated single nucleotide polymorphisms and somatic mutations found in human proteins (LS-SNP, LS-Mut). MODBASE models are also available through the Protein Model Portal (http://www.proteinmodelportal.org/).}, keywords = {*Databases, Molecular Mutation Polymorphism, Protein Genomics Humans Ligands *Models, Protein User-Computer Interface, Single Nucleotide Protein Folding Protein Interaction Domains and Motifs *Protein Structure, Tertiary Proteins/genetics *Structural Homology}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=18948282}, author = {Pieper, U. and Eswar, N. and Webb, B. M. and Eramian, D. and Kelly, L. and Barkan, D. T. and Carter, H. and Mankoo, P. and Karchin, R. and M. A. Marti-Renom and Davis, F. P. and Sali, A.} } @article { PubMed_19441879, title = {Modeling and managing experimental data using FuGE.}, journal = {OMICS}, volume = {13}, number = {3}, year = {2009}, pages = {239-51}, issn = {1557-8100}, author = {Andrew R Jones and Allyson L Lister and Leandro Hermida and Peter Wilkinson and Martin Eisenacher and Khalid Belhajjame and Frank Gibson and Phil Lord and Matthew Pocock and Heiko Rosenfelder and Santoyo-L{\'o}pez, Javier and Anil Wipat and Norman W Paton} } @article {722, title = {Statistical methods for analysis of high-throughput RNA interference screens}, journal = {Nature Methods}, volume = {6}, year = {2009}, note = {

10.1038/nmeth.1351

}, month = {2009/08//print}, pages = {569 - 575}, publisher = {Nature Publishing Group}, keywords = {gene silencing, regulation, siRNA}, isbn = {1548-7091}, url = {http://dx.doi.org/10.1038/nmeth.1351}, author = {Birmingham, Amanda and Selfors, Laura M and Forster, Thorsten and Wrobel, David and Kennedy, Caleb J and Shanks, Emma and Santoyo-L{\'o}pez, Javier and Dunican, Dara J and Long, Aideen and Kelleher, Dermot and Smith, Queta and Beijersbergen, Roderick L and Ghazal, Peter and Shamu, Caroline E} } @article {594, title = {High-throughput functional annotation and data mining with the Blast2GO suite.}, journal = {Nucleic Acids Res}, volume = {36}, year = {2008}, month = {2008 Jun}, pages = {3420-35}, abstract = {

Functional genomics technologies have been widely adopted in the biological research of both model and non-model species. An efficient functional annotation of DNA or protein sequences is a major requirement for the successful application of these approaches as functional information on gene products is often the key to the interpretation of experimental results. Therefore, there is an increasing need for bioinformatics resources which are able to cope with large amount of sequence data, produce valuable annotation results and are easily accessible to laboratories where functional genomics projects are being undertaken. We present the Blast2GO suite as an integrated and biologist-oriented solution for the high-throughput and automatic functional annotation of DNA or protein sequences based on the Gene Ontology vocabulary. The most outstanding Blast2GO features are: (i) the combination of various annotation strategies and tools controlling type and intensity of annotation, (ii) the numerous graphical features such as the interactive GO-graph visualization for gene-set function profiling or descriptive charts, (iii) the general sequence management features and (iv) high-throughput capabilities. We used the Blast2GO framework to carry out a detailed analysis of annotation behaviour through homology transfer and its impact in functional genomics research. Our aim is to offer biologists useful information to take into account when addressing the task of functionally characterizing their sequence data.

}, keywords = {Animals, Computational Biology, Computer Graphics, Databases, Genetic, Expressed Sequence Tags, Genes, Genomics, Sequence Analysis, DNA, Sequence Analysis, Protein, Software, Vocabulary, Controlled}, issn = {1362-4962}, doi = {10.1093/nar/gkn176}, author = {G{\"o}tz, Stefan and Garc{\'\i}a-G{\'o}mez, Juan Miguel and Terol, Javier and Williams, Tim D and Nagaraj, Shivashankar H and Nueda, Maria Jos{\'e} and Robles, Montserrat and Talon, Manuel and Dopazo, Joaquin and Conesa, Ana} } @article {595, title = {Interoperability with Moby 1.0--it{\textquoteright}s better than sharing your toothbrush!}, journal = {Brief Bioinform}, volume = {9}, year = {2008}, month = {2008 May}, pages = {220-31}, abstract = {

The BioMoby project was initiated in 2001 from within the model organism database community. It aimed to standardize methodologies to facilitate information exchange and access to analytical resources, using a consensus driven approach. Six years later, the BioMoby development community is pleased to announce the release of the 1.0 version of the interoperability framework, registry Application Programming Interface and supporting Perl and Java code-bases. Together, these provide interoperable access to over 1400 bioinformatics resources worldwide through the BioMoby platform, and this number continues to grow. Here we highlight and discuss the features of BioMoby that make it distinct from other Semantic Web Service and interoperability initiatives, and that have been instrumental to its deployment and use by a wide community of bioinformatics service providers. The standard, client software, and supporting code libraries are all freely available at http://www.biomoby.org/.

}, keywords = {Computational Biology, Database Management Systems, Databases, Factual, Information Storage and Retrieval, Internet, Programming Languages, Systems Integration}, issn = {1477-4054}, doi = {10.1093/bib/bbn003}, author = {Wilkinson, Mark D and Senger, Martin and Kawas, Edward and Bruskiewich, Richard and Gouzy, Jerome and Noirot, Celine and Bardou, Philippe and Ng, Ambrose and Haase, Dirk and Saiz, Enrique de Andres and Wang, Dennis and Gibbons, Frank and Gordon, Paul M K and Sensen, Christoph W and Carrasco, Jose Manuel Rodriguez and Fern{\'a}ndez, Jos{\'e} M and Shen, Lixin and Links, Matthew and Ng, Michael and Opushneva, Nina and Neerincx, Pieter B T and Leunissen, Jack A M and Ernst, Rebecca and Twigger, Simon and Usadel, Bjorn and Good, Benjamin and Wong, Yan and Stein, Lincoln and Crosby, William and Karlsson, Johan and Royo, Romina and P{\'a}rraga, Iv{\'a}n and Ram{\'\i}rez, Sergio and Gelpi, Josep Lluis and Trelles, Oswaldo and Pisano, David G and Jimenez, Natalia and Kerhornou, Arnaud and Rosset, Roman and Zamacola, Leire and T{\'a}rraga, Joaqu{\'\i}n and Huerta-Cepas, Jaime and Carazo, Jose Mar{\'\i}a and Dopazo, Joaquin and Guig{\'o}, Roderic and Navarro, Arcadi and Orozco, Modesto and Valencia, Alfonso and Claros, M Gonzalo and P{\'e}rez, Antonio J and Aldana, Jose and Rojano, M Mar and Fernandez-Santa Cruz, Raul and Navas, Ismael and Schiltz, Gary and Farmer, Andrew and Gessler, Damian and Schoof, Heiko and Groscurth, Andreas} } @article {18238804, title = {Interoperability with Moby 1.0{\textendash}it{\textquoteright}s better than sharing your toothbrush!}, journal = {Brief Bioinform}, volume = {9}, number = {3}, year = {2008}, note = {

BioMoby Consortium Wilkinson, Mark D Senger, Martin Kawas, Edward Bruskiewich, Richard Gouzy, Jerome Noirot, Celine Bardou, Philippe Ng, Ambrose Haase, Dirk Saiz, Enrique de Andres Wang, Dennis Gibbons, Frank Gordon, Paul M K Sensen, Christoph W Carrasco, Jose Manuel Rodriguez Fernandez, Jose M Shen, Lixin Links, Matthew Ng, Michael Opushneva, Nina Neerincx, Pieter B T Leunissen, Jack A M Ernst, Rebecca Twigger, Simon Usadel, Bjorn Good, Benjamin Wong, Yan Stein, Lincoln Crosby, William Karlsson, Johan Royo, Romina Parraga, Ivan Ramirez, Sergio Gelpi, Josep Lluis Trelles, Oswaldo Pisano, David G Jimenez, Natalia Kerhornou, Arnaud Rosset, Roman Zamacola, Leire Tarraga, Joaquin Huerta-Cepas, Jaime Carazo, Jose Maria Dopazo, Joaquin Guigo, Roderic Navarro, Arcadi Orozco, Modesto Valencia, Alfonso Claros, M Gonzalo Perez, Antonio J Aldana, Jose Rojano, M Mar Fernandez-Santa Cruz, Raul Navas, Ismael Schiltz, Gary Farmer, Andrew Gessler, Damian Schoof, Heiko Groscurth, Andreas Research Support, Non-U.S. Gov{\textquoteright}t Review England Briefings in bioinformatics Brief Bioinform. 2008 May;9(3):220-31. Epub 2008 Jan 31.

}, pages = {220-31}, abstract = {

The BioMoby project was initiated in 2001 from within the model organism database community. It aimed to standardize methodologies to facilitate information exchange and access to analytical resources, using a consensus driven approach. Six years later, the BioMoby development community is pleased to announce the release of the 1.0 version of the interoperability framework, registry Application Programming Interface and supporting Perl and Java code-bases. Together, these provide interoperable access to over 1400 bioinformatics resources worldwide through the BioMoby platform, and this number continues to grow. Here we highlight and discuss the features of BioMoby that make it distinct from other Semantic Web Service and interoperability initiatives, and that have been instrumental to its deployment and use by a wide community of bioinformatics service providers. The standard, client software, and supporting code libraries are all freely available at http://www.biomoby.org/.

}, keywords = {Computational Biology/*methods *Database Management Systems *Databases, Factual Information Storage and Retrieval/*methods *Internet *Programming Languages Systems Integration}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=18238804}, author = {Wilkinson, M. D. and Senger, M. and Kawas, E. and Bruskiewich, R. and Gouzy, J. and Noirot, C. and Bardou, P. and Ng, A. and Haase, D. and Saiz Ede, A. and Wang, D. and Gibbons, F. and Gordon, P. M. and Sensen, C. W. and Carrasco, J. M. and Fernandez, J. M. and Shen, L. and Links, M. and Ng, M. and Opushneva, N. and Neerincx, P. B. and Leunissen, J. A. and Ernst, R. and Twigger, S. and Usadel, B. and Good, B. and Wong, Y. and Stein, L. and Crosby, W. and Karlsson, J. and Royo, R. and Parraga, I. and Ramirez, S. and Gelpi, J. L. and Trelles, O. and Pisano, D. G. and Jimenez, N. and Kerhornou, A. and Rosset, R. and Zamacola, L. and Tarraga, J. and Huerta-Cepas, J. and Carazo, J. M. and Dopazo, J. and R. Guigo and Navarro, A. and Orozco, M. and Valencia, A. and Claros, M. G. and Perez, A. J. and Aldana, J. and Rojano, M. M. and Fernandez-Santa Cruz, R. and Navas, I. and Schiltz, G. and Farmer, A. and Gessler, D. and Schoof, H. and Groscurth, A.} } @article {17254327, title = {Analysis of 13000 unique Citrus clusters associated with fruit quality, production and salinity tolerance}, journal = {BMC Genomics}, volume = {8}, year = {2007}, note = {Terol, Javier Conesa, Ana Colmenero, Jose M Cercos, Manuel Tadeo, Francisco Agusti, Javier Alos, Enriqueta Andres, Fernando Soler, Guillermo Brumos, Javier Iglesias, Domingo J Gotz, Stefan Legaz, Francisco Argout, Xavier Courtois, Brigitte Ollitrault, Patrick Dossat, Carole Wincker, Patrick Morillon, Raphael Talon, Manuel Comparative Study Research Support, Non-U.S. Gov{\textquoteright}t England BMC genomics BMC Genomics. 2007 Jan 25;8:31.}, pages = {31}, abstract = {BACKGROUND: Improvement of Citrus, the most economically important fruit crop in the world, is extremely slow and inherently costly because of the long-term nature of tree breeding and an unusual combination of reproductive characteristics. Aside from disease resistance, major commercial traits in Citrus are improved fruit quality, higher yield and tolerance to environmental stresses, especially salinity. RESULTS: A normalized full length and 9 standard cDNA libraries were generated, representing particular treatments and tissues from selected varieties (Citrus clementina and C. sinensis) and rootstocks (C. reshni, and C. sinenis x Poncirus trifoliata) differing in fruit quality, resistance to abscission, and tolerance to salinity. The goal of this work was to provide a large expressed sequence tag (EST) collection enriched with transcripts related to these well appreciated agronomical traits. Towards this end, more than 54000 ESTs derived from these libraries were analyzed and annotated. Assembly of 52626 useful sequences generated 15664 putative transcription units distributed in 7120 contigs, and 8544 singletons. BLAST annotation produced significant hits for more than 80\% of the hypothetical transcription units and suggested that 647 of these might be Citrus specific unigenes. The unigene set, composed of 13000 putative different transcripts, including more than 5000 novel Citrus genes, was assigned with putative functions based on similarity, GO annotations and protein domains CONCLUSION: Comparative genomics with Arabidopsis revealed the presence of putative conserved orthologs and single copy genes in Citrus and also the occurrence of both gene duplication events and increased number of genes for specific pathways. In addition, phylogenetic analysis performed on the ammonium transporter family and glycosyl transferase family 20 suggested the existence of Citrus paralogs. Analysis of the Citrus gene space showed that the most important metabolic pathways known to affect fruit quality were represented in the unigene set. Overall, the similarity analyses indicated that the sequences of the genes belonging to these varieties and rootstocks were essentially identical, suggesting that the differential behaviour of these species cannot be attributed to major sequence divergences. This Citrus EST assembly contributes both crucial information to discover genes of agronomical interest and tools for genetic and genomic analyses, such as the development of new markers and microarrays.}, keywords = {Acclimatization/*genetics Amino Acid Motifs Citrus/*genetics Cluster Analysis Expressed Sequence Tags Fruit/genetics Gene Duplication *Gene Expression Regulation, Plant Gene Library Genes, Plant Genomics Molecular Sequence Data Multigene Family Phylogeny *Salts/adverse effects}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17254327}, author = {Terol, J. and A. Conesa and Colmenero, J. M. and Cercos, M. and Tadeo, F. and Agusti, J. and Alos, E. and Andres, F. and Soler, G. and Brumos, J. and Iglesias, D. J. and Gotz, S. and Legaz, F. and Argout, X. and Courtois, B. and Ollitrault, P. and Dossat, C. and Wincker, P. and Morillon, R. and Talon, M.} } @article {17519250, title = {Discovering gene expression patterns in time course microarray experiments by ANOVA-SCA}, journal = {Bioinformatics}, volume = {23}, number = {14}, year = {2007}, note = {Nueda, Maria Jose Conesa, Ana Westerhuis, Johan A Hoefsloot, Huub C J Smilde, Age K Talon, Manuel Ferrer, Alberto Research Support, Non-U.S. Gov{\textquoteright}t England Bioinformatics (Oxford, England) Bioinformatics. 2007 Jul 15;23(14):1792-800. Epub 2007 May 22.}, pages = {1792-800}, abstract = {MOTIVATION: Designed microarray experiments are used to investigate the effects that controlled experimental factors have on gene expression and learn about the transcriptional responses associated with external variables. In these datasets, signals of interest coexist with varying sources of unwanted noise in a framework of (co)relation among the measured variables and with the different levels of the studied factors. Discovering experimentally relevant transcriptional changes require methodologies that take all these elements into account. RESULTS: In this work, we develop the application of the Analysis of variance-simultaneous component analysis (ANOVA-SCA) Smilde et al. Bioinformatics, (2005) to the analysis of multiple series time course microarray data as an example of multifactorial gene expression profiling experiments. We denoted this implementation as ASCA-genes. We show how the combination of ANOVA-modeling and a dimension reduction technique is effective in extracting targeted signals from data by-passing structural noise. The methodology is valuable for identifying main and secondary responses associated with the experimental factors and spotting relevant experimental conditions. We additionally propose a novel approach for gene selection in the context of the relation of individual transcriptional patterns to global gene expression signals. We demonstrate the methodology on both real and synthetic datasets. AVAILABILITY: ASCA-genes has been implemented in the statistical language R and is available at http://www.ivia.es/centrodegenomica/bioinformatics.htm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.}, keywords = {Algorithms *Analysis of Variance Computational Biology/*methods Computer Simulation Data Interpretation, Genetic, Genetic Models, Statistical Gene Expression Profiling/*methods Models, Statistical Oligonucleotide Array Sequence Analysis/*methods Principal Component Analysis Time Factors Transcription}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17519250}, author = {Nueda, M. J. and A. Conesa and Westerhuis, J. A. and Hoefsloot, H. C. and Smilde, A. K. and Talon, M. and Ferrer, A.} } @article {17135190, title = {PeroxisomeDB: a database for the peroxisomal proteome, functional genomics and disease}, journal = {Nucleic Acids Res}, volume = {35}, number = {Database issue}, year = {2007}, note = {Schluter, Agatha Fourcade, Stephane Domenech-Estevez, Enric Gabaldon, Toni Huerta-Cepas, Jaime Berthommier, Guillaume Ripp, Raymond Wanders, Ronald J A Poch, Olivier Pujol, Aurora Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2007 Jan;35(Database issue):D815-22. Epub 2006 Nov 28.}, pages = {D815-22}, abstract = {Peroxisomes are essential organelles of eukaryotic origin, ubiquitously distributed in cells and organisms, playing key roles in lipid and antioxidant metabolism. Loss or malfunction of peroxisomes causes more than 20 fatal inherited conditions. We have created a peroxisomal database (http://www.peroxisomeDB.org) that includes the complete peroxisomal proteome of Homo sapiens and Saccharomyces cerevisiae, by gathering, updating and integrating the available genetic and functional information on peroxisomal genes. PeroxisomeDB is structured in interrelated sections {\textquoteright}Genes{\textquoteright}, {\textquoteright}Functions{\textquoteright}, {\textquoteright}Metabolic pathways{\textquoteright} and {\textquoteright}Diseases{\textquoteright}, that include hyperlinks to selected features of NCBI, ENSEMBL and UCSC databases. We have designed graphical depictions of the main peroxisomal metabolic routes and have included updated flow charts for diagnosis. Precomputed BLAST, PSI-BLAST, multiple sequence alignment (MUSCLE) and phylogenetic trees are provided to assist in direct multispecies comparison to study evolutionary conserved functions and pathways. Highlights of the PeroxisomeDB include new tools developed for facilitating (i) identification of novel peroxisomal proteins, by means of identifying proteins carrying peroxisome targeting signal (PTS) motifs, (ii) detection of peroxisomes in silico, particularly useful for screening the deluge of newly sequenced genomes. PeroxisomeDB should contribute to the systematic characterization of the peroxisomal proteome and facilitate system biology approaches on the organelle.}, keywords = {Animals *Databases, Protein Genomics Humans Internet Mice Peroxisomal Disorders/*genetics Peroxisomes/*metabolism Protein Sorting Signals Proteome/chemistry/*genetics/*physiology Rats Saccharomyces cerevisiae Proteins/genetics/physiology Software User-Computer Interface}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17135190}, author = {Schluter, A. and Fourcade, S. and Domenech-Estevez, E. and Gabald{\'o}n, T. and Huerta-Cepas, J. and Berthommier, G. and Ripp, R. and Wanders, R. J. and Poch, O. and Pujol, A.} } @article {17884042, title = {Protein translocation into peroxisomes by ring-shaped import receptors}, journal = {FEBS Lett}, volume = {581}, number = {25}, year = {2007}, note = {Stanley, Will A Fodor, Krisztian Marti-Renom, Marc A Schliebs, Wolfgang Wilmanns, Matthias Review Netherlands FEBS letters FEBS Lett. 2007 Oct 16;581(25):4795-802. Epub 2007 Sep 11.}, pages = {4795-802}, abstract = {Folded and functional proteins destined for translocation from the cytosol into the peroxisomal matrix are recognized by two different peroxisomal import receptors, Pex5p and Pex7p. Both cargo-loaded receptors dock on the same translocon components, followed by cargo release and receptor recycling, as part of the complete translocation process. Recent structural and functional evidence on the Pex5p receptor has provided insight on the molecular requirements of specific cargo recognition, while the remaining processes still remain largely elusive. Comparison of experimental structures of Pex5p and a structural model of Pex7p reveal that both receptors are built by ring-like arrangements with cargo binding sites, central to the respective structures. Although, molecular insight into the complete peroxisomal translocon still remains to be determined, emerging data allow to deduce common molecular principles that may hold for other translocation systems as well.}, keywords = {Amino Acid Sequence Binding Sites Humans Molecular Sequence Data Peroxisomes/*metabolism Protein Structure, Cytoplasmic and Nuclear/*chemistry, Tertiary Protein Transport Receptors}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17884042}, author = {Stanley, W. A. and Fodor, K. and M. A. Marti-Renom and Schliebs, W. and Wilmanns, M.} } @article {17951513, title = {Spatial differentiation in the vegetative mycelium of Aspergillus niger}, journal = {Eukaryot Cell}, volume = {6}, number = {12}, year = {2007}, note = {Levin, Ana M de Vries, Ronald P Conesa, Ana de Bekker, Charissa Talon, Manuel Menke, Hildegard H van Peij, Noel N M E Wosten, Han A B Research Support, Non-U.S. Gov{\textquoteright}t United States Eukaryotic cell Eukaryot Cell. 2007 Dec;6(12):2311-22. Epub 2007 Oct 19.}, pages = {2311-22}, abstract = {Fungal mycelia are exposed to heterogenic substrates. The substrate in the central part of the colony has been (partly) degraded, whereas it is still unexplored at the periphery of the mycelium. We here assessed whether substrate heterogeneity is a main determinant of spatial gene expression in colonies of Aspergillus niger. This question was addressed by analyzing whole-genome gene expression in five concentric zones of 7-day-old maltose- and xylose-grown colonies. Expression profiles at the periphery and the center were clearly different. More than 25\% of the active genes showed twofold differences in expression between the inner and outermost zones of the colony. Moreover, 9\% of the genes were expressed in only one of the five concentric zones, showing that a considerable part of the genome is active in a restricted part of the colony only. Statistical analysis of expression profiles of colonies that had either been or not been transferred to fresh xylose-containing medium showed that differential expression in a colony is due to the heterogeneity of the medium (e.g., genes involved in secretion, genes encoding proteases, and genes involved in xylose metabolism) as well as to medium-independent mechanisms (e.g., genes involved in nitrate metabolism and genes involved in cell wall synthesis and modification). Thus, we conclude that the mycelia of 7-day-old colonies of A. niger are highly differentiated. This conclusion is also indicated by the fact that distinct zones of the colony grow and secrete proteins, even after transfer to fresh medium.}, keywords = {Aspergillus niger/*metabolism Cell Wall/metabolism Fungal Proteins/metabolism *Gene Expression Regulation, Biological Mycelium/*metabolism Oligonucleotide Array Sequence Analysis RNA, Fungal Genes, Fungal Genome, Fungal Glucans/chemistry Maltose/chemistry Models, Fungal Time Factors Trans-Activators/metabolism Xylose/chemistry}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17951513}, author = {Levin, A. M. and de Vries, R. P. and A. Conesa and de Bekker, C. and Talon, M. and Menke, H. H. and van Peij, N. N. and Wosten, H. A.} } @article {18428767, title = {Comparative protein structure modeling using Modeller}, journal = {Curr Protoc Bioinformatics}, volume = {Chapter 5}, year = {2006}, note = {Eswar, Narayanan Webb, Ben Marti-Renom, Marc A Madhusudhan, M S Eramian, David Shen, Min-Yi Pieper, Ursula Sali, Andrej P01 A135707/PHS HHS/United States P01 GM71790/GM/NIGMS NIH HHS/United States R01 GM54762/GM/NIGMS NIH HHS/United States U54 GM62529/GM/NIGMS NIH HHS/United States Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov{\textquoteright}t United States Current protocols in bioinformatics / editoral board, Andreas D. Baxevanis ... [et al.] Curr Protoc Bioinformatics. 2006 Oct;Chapter 5:Unit 5.6.}, pages = {Unit 5 6}, abstract = {Functional characterization of a protein sequence is one of the most frequent problems in biology. This task is usually facilitated by accurate three-dimensional (3-D) structure of the studied protein. In the absence of an experimentally determined structure, comparative or homology modeling can sometimes provide a useful 3-D model for a protein that is related to at least one known protein structure. Comparative modeling predicts the 3-D structure of a given protein sequence (target) based primarily on its alignment to one or more proteins of known structure (templates). The prediction process consists of fold assignment, target-template alignment, model building, and model evaluation. This unit describes how to calculate comparative models using the program MODELLER and discusses all four steps of comparative modeling, frequently observed errors, and some applications. Modeling lactate dehydrogenase from Trichomonas vaginalis (TvLDH) is described as an example. The download and installation of the MODELLER software is also described.}, keywords = {Algorithms Amino Acid Sequence Computer Simulation Crystallography/*methods *Models, Chemical *Models, Molecular Molecular Sequence Data Protein Conformation Protein Folding Proteins/*chemistry/*ultrastructure Sequence Analysis, Protein/*methods *Software}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=18428767}, author = {Eswar, N. and Webb, B. and M. A. Marti-Renom and Madhusudhan, M. S. and Eramian, D. and Shen, M. Y. and Pieper, U. and Sali, A.} } @article {17120584, title = {Development of the GENIPOL European flounder (Platichthys flesus) microarray and determination of temporal transcriptional responses to cadmium at low dose}, journal = {Environ Sci Technol}, volume = {40}, number = {20}, year = {2006}, note = {Williams, Tim D Diab, Amer M George, Stephen G Godfrey, Rita E Sabine, Victoria Conesa, Ana Minchin, Steven D Watts, Phil C Chipman, James K Research Support, Non-U.S. Gov{\textquoteright}t United States Environmental science \& technology Environ Sci Technol. 2006 Oct 15;40(20):6479-88.}, pages = {6479-88}, abstract = {We have constructed a high density, 13 270-clone cDNA array for the sentinel fish species European flounder (Platichthys flesus), combining clones from suppressive subtractive hybridization and a liver cDNA library; DNA sequences of 5211 clones were determined. Fish were treated by single intraperitoneal injection with 50 micrograms cadmium chloride per kilogram body weight, a dose relevant to environmental exposures, and hepatic gene expression changes were determined at 1, 2, 4, 8, and 16 days postinjection in comparison to saline-treated controls. Gene expression responses were confirmed by real-time reverse transcription polymerase chain reaction (RT-PCR). Blast2GO gene ontology analysis highlighted a general induction of the unfolded protein response, response to oxidative stress, protein synthesis, transport, and degradation pathways, while apoptosis, cell cycle, cytoskeleton, and cytokine genes were also affected. Transcript levels of cytochrome P450 1A (CYP1A) were repressed and vitellogenin altered, real-time PCR showed induction of metallothionein. We thus describe the establishment of a useful resource for ecotoxicogenomics and the determination of the temporal molecular responses to cadmium, a prototypical heavy metal pollutant.}, keywords = {Animals Cadmium Chloride/administration \& dosage/*pharmacology Dose-Response Relationship, Developmental/drug effects Liver/drug effects/growth \& development/metabolism Oligonucleotide Array Sequence Analysis/*methods Reverse Transcriptase Polymerase Chain Reaction Transcription, Drug Environmental Monitoring/methods Flounder/*genetics/growth \& development Gene Expression Profiling Gene Expression Regulation, Genetic/*drug effects}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17120584}, author = {Williams, T. D. and Diab, A. M. and George, S. G. and Godfrey, R. E. and Sabine, V. and A. Conesa and Minchin, S. D. and Watts, P. C. and Chipman, J. K.} } @article {16381869, title = {MODBASE: a database of annotated comparative protein structure models and associated resources}, journal = {Nucleic Acids Res}, volume = {34}, number = {Database issue}, year = {2006}, note = {Pieper, Ursula Eswar, Narayanan Davis, Fred P Braberg, Hannes Madhusudhan, M S Rossi, Andrea Marti-Renom, Marc Karchin, Rachel Webb, Ben M Eramian, David Shen, Min-Yi Kelly, Libusha Melo, Francisco Sali, Andrej GM 08284/GM/NIGMS NIH HHS/United States P50 GM62529/GM/NIGMS NIH HHS/United States R01 GM 54762/GM/NIGMS NIH HHS/United States R33 CA84699/CA/NCI NIH HHS/United States U54 GM074945/GM/NIGMS NIH HHS/United States Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2006 Jan 1;34(Database issue):D291-5.}, pages = {D291-5}, abstract = {MODBASE (http://salilab.org/modbase) is a database of annotated comparative protein structure models for all available protein sequences that can be matched to at least one known protein structure. The models are calculated by MODPIPE, an automated modeling pipeline that relies on MODELLER for fold assignment, sequence-structure alignment, model building and model assessment (http:/salilab.org/modeller). MODBASE is updated regularly to reflect the growth in protein sequence and structure databases, and improvements in the software for calculating the models. MODBASE currently contains 3 094 524 reliable models for domains in 1 094 750 out of 1 817 889 unique protein sequences in the UniProt database (July 5, 2005); only models based on statistically significant alignments and models assessed to have the correct fold despite insignificant alignments are included. MODBASE also allows users to generate comparative models for proteins of interest with the automated modeling server MODWEB (http://salilab.org/modweb). Our other resources integrated with MODBASE include comprehensive databases of multiple protein structure alignments (DBAli, http://salilab.org/dbali), structurally defined ligand binding sites and structurally defined binary domain interfaces (PIBASE, http://salilab.org/pibase) as well as predictions of ligand binding sites, interactions between yeast proteins, and functional consequences of human nsSNPs (LS-SNP, http://salilab.org/LS-SNP).}, keywords = {Binding Sites *Databases, Molecular Polymorphism, Protein Humans Internet Ligands *Models, Protein Systems Integration User-Computer Interface, Single Nucleotide Protein Structure, Tertiary Proteins/*chemistry/genetics/metabolism Software *Structural Homology}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=16381869}, author = {Pieper, U. and Eswar, N. and Davis, F. P. and Braberg, H. and Madhusudhan, M. S. and Rossi, A. and M. A. Marti-Renom and Karchin, R. and Webb, B. M. and Eramian, D. and Shen, M. Y. and Kelly, L. and Melo, F. and Sali, A.} } @inbook {489, title = {Data and Predictive Model Integration: an Overview of Key Concepts, Problems and Solutions}, booktitle = {Data analysis and visualisation in genomics and proteomics}, year = {2005}, publisher = {Wiley, F. Azuaje and J. Dopazo}, organization = {Wiley, F. Azuaje and J. Dopazo}, author = {F. Azuaje and Dopazo, J. and Wang, H} } @inbook {490, title = {Gene expression Correlation and Gene Ontology-Based Similarity: An Assessment of Quantitative Relationship}, booktitle = {IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology}, year = {2004}, pages = {25-31}, author = {Wang, H and F. Azuaje and Bodenreider, O and Dopazo, J.} } @article {14681398, title = {MODBASE, a database of annotated comparative protein structure models, and associated resources}, journal = {Nucleic Acids Res}, volume = {32}, number = {Database issue}, year = {2004}, note = {Pieper, Ursula Eswar, Narayanan Braberg, Hannes Madhusudhan, M S Davis, Fred P Stuart, Ashley C Mirkovic, Nebojsa Rossi, Andrea Marti-Renom, Marc A Fiser, Andras Webb, Ben Greenblatt, Daniel Huang, Conrad C Ferrin, Thomas E Sali, Andrej P41 RR01081/RR/NCRR NIH HHS/United States P50 GM62529/GM/NIGMS NIH HHS/United States R01 GM 54762/GM/NIGMS NIH HHS/United States R33 CA84699/CA/NCI NIH HHS/United States Research Support, Non-U.S. Gov{\textquoteright}t Research Support, U.S. Gov{\textquoteright}t, P.H.S. England Nucleic acids research Nucleic Acids Res. 2004 Jan 1;32(Database issue):D217-22.}, pages = {D217-22}, abstract = {MODBASE (http://salilab.org/modbase) is a relational database of annotated comparative protein structure models for all available protein sequences matched to at least one known protein structure. The models are calculated by MODPIPE, an automated modeling pipeline that relies on the MODELLER package for fold assignment, sequence-structure alignment, model building and model assessment (http:/salilab.org/modeller). MODBASE uses the MySQL relational database management system for flexible querying and CHIMERA for viewing the sequences and structures (http://www.cgl.ucsf.edu/chimera/). MODBASE is updated regularly to reflect the growth in protein sequence and structure databases, as well as improvements in the software for calculating the models. For ease of access, MODBASE is organized into different data sets. The largest data set contains 1,26,629 models for domains in 659,495 out of 1,182,126 unique protein sequences in the complete Swiss-Prot/TrEMBL database (August 25, 2003); only models based on alignments with significant similarity scores and models assessed to have the correct fold despite insignificant alignments are included. Another model data set supports target selection and structure-based annotation by the New York Structural Genomics Research Consortium; e.g. the 53 new structures produced by the consortium allowed us to characterize structurally 24,113 sequences. MODBASE also contains binding site predictions for small ligands and a set of predicted interactions between pairs of modeled sequences from the same genome. Our other resources associated with MODBASE include a comprehensive database of multiple protein structure alignments (DBALI, http://salilab.org/dbali) as well as web servers for automated comparative modeling with MODPIPE (MODWEB, http://salilab. org/modweb), modeling of loops in protein structures (MODLOOP, http://salilab.org/modloop) and predicting functional consequences of single nucleotide polymorphisms (SNPWEB, http://salilab. org/snpweb).}, keywords = {Amino Acid Sequence Animals Binding Sites *Computational Biology *Databases, Molecular Molecular Sequence Data Polymorphism, Protein Genomics Humans Internet Ligands Models, Single Nucleotide Protein Binding Protein Conformation Proteins/*chemistry/genetics Sequence Alignment Software User-Computer Interface}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=14681398}, author = {Pieper, U. and Eswar, N. and Braberg, H. and Madhusudhan, M. S. and Davis, F. P. and Stuart, A. C. and Mirkovic, N. and Rossi, A. and M. A. Marti-Renom and Fiser, A. and Webb, B. and Greenblatt, D. and Huang, C. C. and Ferrin, T. E. and Sali, A.} } @article {15172985, title = {Structure-based assessment of missense mutations in human BRCA1: implications for breast and ovarian cancer predisposition}, journal = {Cancer Res}, volume = {64}, number = {11}, year = {2004}, note = {Mirkovic, Nebojsa Marti-Renom, Marc A Weber, Barbara L Sali, Andrej Monteiro, Alvaro N A CA92309/CA/NCI NIH HHS/United States GM54762/GM/NIGMS NIH HHS/United States GM61390/GM/NIGMS NIH HHS/United States Research Support, Non-U.S. Gov{\textquoteright}t Research Support, U.S. Gov{\textquoteright}t, Non-P.H.S. Research Support, U.S. Gov{\textquoteright}t, P.H.S. United States Cancer research Cancer Res. 2004 Jun 1;64(11):3790-7.}, pages = {3790-7}, abstract = {The BRCA1 gene from individuals at risk of breast and ovarian cancers can be screened for the presence of mutations. However, the cancer association of most alleles carrying missense mutations is unknown, thus creating significant problems for genetic counseling. To increase our ability to identify cancer-associated mutations in BRCA1, we set out to use the principles of protein three-dimensional structure as well as the correlation between the cancer-associated mutations and those that abolish transcriptional activation. Thirty-one of 37 missense mutations of known impact on the transcriptional activation function of BRCA1 are readily rationalized in structural terms. Loss-of-function mutations involve nonconservative changes in the core of the BRCA1 C-terminus (BRCT) fold or are localized in a groove that presumably forms a binding site involved in the transcriptional activation by BRCA1; mutations that do not abolish transcriptional activation are either conservative changes in the core or are on the surface outside of the putative binding site. Next, structure-based rules for predicting functional consequences of a given missense mutation were applied to 57 germ-line BRCA1 variants of unknown cancer association. Such a structure-based approach may be helpful in an integrated effort to identify mutations that predispose individuals to cancer.}, keywords = {BRCA1 Genetic Predisposition to Disease Humans *Mutation, BRCA1 Protein/*chemistry/genetics Breast Neoplasms/*genetics Female *Genes, Missense Ovarian Neoplasms/*genetics Pedigree Protein Conformation Structure-Activity Relationship Transcriptional Activation}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=15172985}, author = {Mirkovic, N. and M. A. Marti-Renom and Weber, B. L. and Sali, A. and Monteiro, A. N.} } @article {12471146, title = {Use of single point mutations in domain I of beta 2-glycoprotein I to determine fine antigenic specificity of antiphospholipid autoantibodies}, journal = {J Immunol}, volume = {169}, number = {12}, year = {2002}, note = {Iverson, G Michael Reddel, Stephen Victoria, Edward J Cockerill, Keith A Wang, Ying-Xia Marti-Renom, Marc A Sali, Andrej Marquis, David M Krilis, Steven A Linnik, Matthew D GM54762/GM/NIGMS NIH HHS/United States Research Support, Non-U.S. Gov{\textquoteright}t Research Support, U.S. Gov{\textquoteright}t, P.H.S. United States Journal of immunology (Baltimore, Md. : 1950) J Immunol. 2002 Dec 15;169(12):7097-103.}, pages = {7097-103}, abstract = {Autoantibodies against beta(2)-glycoprotein I (beta(2)GPI) appear to be a critical feature of the antiphospholipid syndrome (APS). As determined using domain deletion mutants, human autoantibodies bind to the first of five domains present in beta(2)GPI. In this study the fine detail of the domain I epitope has been examined using 10 selected mutants of whole beta(2)GPI containing single point mutations in the first domain. The binding to beta(2)GPI was significantly affected by a number of single point mutations in domain I, particularly by mutations in the region of aa 40-43. Molecular modeling predicted these mutations to affect the surface shape and electrostatic charge of a facet of domain I. Mutation K19E also had an effect, albeit one less severe and involving fewer patients. Similar results were obtained in two different laboratories using affinity-purified anti-beta(2)GPI in a competitive inhibition ELISA and with whole serum in a direct binding ELISA. This study confirms that anti-beta(2)GPI autoantibodies bind to domain I, and that the charged surface patch defined by residues 40-43 contributes to a dominant target epitope.}, keywords = {Amino Acid Substitution/genetics Antibodies, Antibody/genetics Binding, Antiphospholipid/blood/*metabolism Antibodies, Competitive/genetics/immunology Enzyme-Linked Immunosorbent Assay/methods Epitopes/analysis/*immunology/metabolism Glycine/genetics Glycoproteins/biosynthesis/*genetics/*immunology/isolation \& purification/metabolism Humans Models, Molecular Peptide Fragments/genetics/immunology/isolation \& purification/metabolism *Point Mutation Protein Structure, Monoclonal/blood/metabolism Antiphospholipid Syndrome/immunology Arginine/genetics *Binding Sites, Tertiary/genetics Recombinant Proteins/biosynthesis/immunology/isolation \& purification/metabolism Static Electricity beta 2-Glycoprotein I}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=12471146}, author = {Iverson, G. M. and Reddel, S. and Victoria, E. J. and Cockerill, K. A. and Wang, Y. X. and M. A. Marti-Renom and Sali, A. and Marquis, D. M. and Krilis, S. A. and Linnik, M. D.} } @article {11513866, title = {C-terminal propeptide of the Caldariomyces fumago chloroperoxidase: an intramolecular chaperone?}, journal = {FEBS Lett}, volume = {503}, number = {2-3}, year = {2001}, note = {Conesa, A Weelink, G van den Hondel, C A Punt, P J Netherlands FEBS letters FEBS Lett. 2001 Aug 17;503(2-3):117-20.}, pages = {117-20}, abstract = {The Caldariomyces fumago chloroperoxidase (CPO) is synthesised as a 372-aa precursor which undergoes two proteolytic processing events: removal of a 21-aa N-terminal signal peptide and of a 52-aa C-terminal propeptide. The Aspergillus niger expression system developed for CPO was used to get insight into the function of this C-terminal propeptide. A. niger transformants expressing a CPO protein from which the C-terminal propeptide was deleted failed in producing any extracellular CPO activity, although the CPO polypeptide was synthesised. Expression of the full-length gene in an A. niger strain lacking the KEX2-like protease PclA also resulted in the production of CPO cross-reactive material into the culture medium, but no CPO activity. Based on these results, a function of the C-terminal propeptide in CPO maturation is indicated.}, keywords = {Amino Acid Sequence Ascomycota/*enzymology/genetics Aspergillus niger/genetics Base Sequence Chloride Peroxidase/biosynthesis/*chemistry/genetics DNA Primers/genetics Enzyme Precursors/biosynthesis/chemistry/genetics Gene Expression Molecular Chaperones/b}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=11513866}, author = {A. Conesa and Weelink, G. and van den Hondel, C. A. and Punt, P. J.} }