@article {768, title = {Editorial: Critical assessment of massive data analysis (CAMDA) annual conference 2021.}, journal = {Front Genet}, volume = {14}, year = {2023}, month = {2023}, pages = {1154398}, issn = {1664-8021}, doi = {10.3389/fgene.2023.1154398}, author = {{\L}abaj, Pawe{\l} P and Dopazo, Joaquin and Xiao, Wenzhong and Kreil, David P} } @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 {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 {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} }