	<rdf:RDF xmlns:admin="http://webns.net/mvcb/" xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:prism="http://purl.org/rss/1.0/modules/prism/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/">
	<channel rdf:about="https://biorxiv.org">
	<admin:errorReportsTo rdf:resource="mailto:biorxiv@cshlpress.edu"/>
	<title>bioRxiv Channel: DREAM</title>
	<link>https://biorxiv.org</link>
	<description>
	This feed contains articles for bioRxiv Channel "DREAM"
	</description>

		<items>
	<rdf:Seq>
		</rdf:Seq>
	</items>
	<prism:eIssn/>
	<prism:publicationName>bioRxiv</prism:publicationName>
	<prism:issn/>

	<image rdf:resource=""/>
	</channel>
	<image rdf:about="">
	<title>bioRxiv</title>
	<url/>
	<link>https://biorxiv.org</link>
	</image>
	<item rdf:about="https://biorxiv.org/cgi/content/short/082495v1?rss=1">
<title>
<![CDATA[
Reverse-engineering human olfactory perception from chemical features of odor molecules 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/082495v1?rss=1"
</link>
<description><![CDATA[
Despite 25 years of progress in understanding the molecular mechanisms of olfaction, it is still not possible to predict whether a given molecule will have a perceived odor, or what olfactory percept it will produce. To address this stimulus-percept problem for olfaction, we organized the crowd-sourced DREAM Olfaction Prediction Challenge. Working from a large olfactory psychophysical dataset, teams developed machine learning algorithms to predict sensory attributes of molecules based on their chemoinformatic features. The resulting models predicted odor intensity and pleasantness with high accuracy, and also successfully predicted eight semantic descriptors ("garlic", "fish", "sweet", "fruit", "burnt", "spices", "flower", "sour"). Regularized linear models performed nearly as well as random-forest-based approaches, with a predictive accuracy that closely approaches a key theoretical limit. The models presented here make it possible to predict the perceptual qualities of virtually any molecule with an impressive degree of accuracy to reverse-engineer the smell of a molecule.nnOne Sentence SummaryResults of a crowdsourcing competition show that it is possible to accurately predict and reverse-engineer the smell of a molecule.
]]></description>
<dc:creator>Keller, A.</dc:creator>
<dc:creator>Gerkin, R. C.</dc:creator>
<dc:creator>Guan, Y.</dc:creator>
<dc:creator>Dhurandhar, A.</dc:creator>
<dc:creator>Turu, G.</dc:creator>
<dc:creator>Szalai, B.</dc:creator>
<dc:creator>Mainland, J. D.</dc:creator>
<dc:creator>Ihara, Y.</dc:creator>
<dc:creator>Yu, C. W.</dc:creator>
<dc:creator>Wolfinger, R.</dc:creator>
<dc:creator>Vens, C.</dc:creator>
<dc:creator>Schietgat, L.</dc:creator>
<dc:creator>De Grave, K.</dc:creator>
<dc:creator>Norel, R.</dc:creator>
<dc:creator>DREAM Olfaction Prediction Challenge Consortium,</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:creator>Cecchi, G.</dc:creator>
<dc:creator>Vosshall, L. B.</dc:creator>
<dc:creator>Meyer, P.</dc:creator>
<dc:date>2016-10-21</dc:date>
<dc:identifier>doi:10.1101/082495</dc:identifier>
<dc:title><![CDATA[Reverse-engineering human olfactory perception from chemical features of odor molecules]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2016-10-21</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/265553v1?rss=1">
<title>
<![CDATA[
Open Community Challenge Reveals Molecular Network Modules with Key Roles in Diseases 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/265553v1?rss=1"
</link>
<description><![CDATA[
Identification of modules in molecular networks is at the core of many current analysis methods in biomedical research. However, how well different approaches identify disease-relevant modules in different types of gene and protein networks remains poorly understood. We launched the "Disease Module Identification DREAM Challenge", an open competition to comprehensively assess module identification methods across diverse protein-protein interaction, signaling, gene co-expression, homology, and cancer-gene networks. Predicted network modules were tested for association with complex traits and diseases using a unique collection of 180 genome-wide association studies (GWAS). Our critical assessment of 75 contributed module identification methods reveals novel top-performing algorithms, which recover complementary trait-associated modules. We find that most of these modules correspond to core disease-relevant pathways, which often comprise therapeutic targets and correctly prioritize candidate disease genes. This community challenge establishes benchmarks, tools and guidelines for molecular network analysis to study human disease biology (https://synapse.org/modulechallenge).
]]></description>
<dc:creator>Choobdar, S.</dc:creator>
<dc:creator>Ahsen, M. E.</dc:creator>
<dc:creator>Crawford, J.</dc:creator>
<dc:creator>Tomasoni, M.</dc:creator>
<dc:creator>Lamparter, D.</dc:creator>
<dc:creator>Lin, J.</dc:creator>
<dc:creator>Hescott, B.</dc:creator>
<dc:creator>Hu, X.</dc:creator>
<dc:creator>Mercer, J.</dc:creator>
<dc:creator>Natoli, T.</dc:creator>
<dc:creator>Narayan, R.</dc:creator>
<dc:creator>The DREAM Module Identification Challenge Consortium,</dc:creator>
<dc:creator>Subramanian, A.</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:creator>Kutalik, Z.</dc:creator>
<dc:creator>Lage, K.</dc:creator>
<dc:creator>Slonim, D. K.</dc:creator>
<dc:creator>Saez-Rodriguez, J.</dc:creator>
<dc:creator>Cowen, L. J.</dc:creator>
<dc:creator>Bergmann, S.</dc:creator>
<dc:creator>Marbach, D.</dc:creator>
<dc:date>2018-02-15</dc:date>
<dc:identifier>doi:10.1101/265553</dc:identifier>
<dc:title><![CDATA[Open Community Challenge Reveals Molecular Network Modules with Key Roles in Diseases]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2018-02-15</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/200451v1?rss=1">
<title>
<![CDATA[
Community assessment of cancer drug combination screens identifies strategies for synergy prediction 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/200451v1?rss=1"
</link>
<description><![CDATA[
The effectiveness of most cancer targeted therapies is short lived since tumors evolve and develop resistance. Combinations of drugs offer the potential to overcome resistance, however the number of possible combinations is vast necessitating data-driven approaches to find optimal treatments tailored to a patients tumor. AstraZeneca carried out 11,576 experiments on 910 drug combinations across 85 cancer cell lines, recapitulating in vivo response profiles. These data, the largest openly available screen, were hosted by DREAM alongside deep molecular characterization from the Sanger Institute for a Challenge to computationally predict synergistic drug pairs and associated biomarkers. 160 teams participated to provide the most comprehensive methodological development and subsequent benchmarking to date. Winning methods incorporated prior knowledge of putative drug target interactions. For >60% of drug combinations synergy was reproducibly predicted with an accuracy matching biological replicate experiments, however 20% of drug combinations were poorly predicted by all methods. Genomic rationale for synergy predictions were identified, including antagonism unique to combined PIK3CB/D inhibition with the ADAM17 inhibitor where synergy is seen with other PI3K pathway inhibitors. All data, methods and code are freely available as a resource to the community.
]]></description>
<dc:creator>Menden, M. P.</dc:creator>
<dc:creator>Wang, D.</dc:creator>
<dc:creator>Guan, Y.</dc:creator>
<dc:creator>Mason, M.</dc:creator>
<dc:creator>Szalai, B.</dc:creator>
<dc:creator>Bulusu, K. C.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Kang, J.</dc:creator>
<dc:creator>Jeon, M.</dc:creator>
<dc:creator>Wolfinger, R.</dc:creator>
<dc:creator>Nguyen, T.</dc:creator>
<dc:creator>Zaslavskiy, M.</dc:creator>
<dc:creator>AstraZeneca-Sanger Drug Combination DREAM Consorti,</dc:creator>
<dc:creator>Jang, I. S.</dc:creator>
<dc:creator>Ghazoui, Z.</dc:creator>
<dc:creator>Ahsen, M. E.</dc:creator>
<dc:creator>Vogel, R.</dc:creator>
<dc:creator>Chaibub Neto, E.</dc:creator>
<dc:creator>Norman, T.</dc:creator>
<dc:creator>Tang, E. K.</dc:creator>
<dc:creator>Garnett, M. J.</dc:creator>
<dc:creator>Di Veroli, G.</dc:creator>
<dc:creator>Fawell, S.</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:creator>Guinney, J.</dc:creator>
<dc:creator>Dry, J. R.</dc:creator>
<dc:creator>Saez-Rodriguez, J.</dc:creator>
<dc:date>2017-10-09</dc:date>
<dc:identifier>doi:10.1101/200451</dc:identifier>
<dc:title><![CDATA[Community assessment of cancer drug combination screens identifies strategies for synergy prediction]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2017-10-09</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/224733v1?rss=1">
<title>
<![CDATA[
Combining accurate tumour genome simulation with crowd sourcing to benchmark somatic structural variant detection 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/224733v1?rss=1"
</link>
<description><![CDATA[
BackgroundThe phenotypes of cancer cells are driven in part by somatic structural variants. Structural variants can initiate tumors, enhance their aggressiveness and provide unique therapeutic opportunities. Whole-genome sequencing of tumors can allow exhaustive identification of the specific structural variants present in an individual cancer, facilitating both clinical diagnostics and the discovery of novel mutagenic mechanisms. A plethora of somatic structural variant detection algorithms have been created to enable these discoveries, however there are no systematic benchmarks of them. Rigorous performance evaluation of somatic structural variant detection methods has been challenged by the lack of gold-standards, extensive resource requirements and difficulties arising from the need to share personal genomic information.nnResultsTo facilitate structural variant detection algorithm evaluations, we create a robust simulation framework for somatic structural variants by extending the BAMSurgeon algorithm. We then organize and enable a crowd-sourced benchmarking within the ICGC-TCGA DREAM Somatic Mutation Calling Challenge (SMC-DNA). We report here the results of structural variant benchmarking on three different tumors, comprising 204 submissions from 15 teams. In addition to ranking methods, we identify characteristic error-profiles of individual algorithms and general trends across them. Surprisingly, we find that ensembles of analysis pipelines do not always outperform the best individual method, indicating a need for new ways to aggregate somatic structural variant detection approaches.nnConclusionsThe synthetic tumors and somatic structural variant detection leaderboards remain available as a community benchmarking resource, and BAMSurgeon is available at https://github.com/adamewing/bamsurgeon.
]]></description>
<dc:creator>Lee, A. Y.-W.</dc:creator>
<dc:creator>Ewing, A. D.</dc:creator>
<dc:creator>Ellrott, K.</dc:creator>
<dc:creator>Hu, Y.</dc:creator>
<dc:creator>Houlahan, K. E.</dc:creator>
<dc:creator>Bare, J. C.</dc:creator>
<dc:creator>Espiritu, S. M. G.</dc:creator>
<dc:creator>Huang, V.</dc:creator>
<dc:creator>Dang, K.</dc:creator>
<dc:creator>Chong, Z.</dc:creator>
<dc:creator>Caloian, C.</dc:creator>
<dc:creator>Yamaguchi, T. N.</dc:creator>
<dc:creator>ICGC-TCGA DREAM Somatic Mutation Calling Challenge,</dc:creator>
<dc:creator>Kellen, M. R.</dc:creator>
<dc:creator>Chen, K.</dc:creator>
<dc:creator>Norman, T. C.</dc:creator>
<dc:creator>Friend, S. H.</dc:creator>
<dc:creator>Guinney, J.</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:creator>Haussler, D.</dc:creator>
<dc:creator>Margolin, A. A.</dc:creator>
<dc:creator>Stuart, J. M.</dc:creator>
<dc:creator>Boutros, P. C.</dc:creator>
<dc:date>2017-11-25</dc:date>
<dc:identifier>doi:10.1101/224733</dc:identifier>
<dc:title><![CDATA[Combining accurate tumour genome simulation with crowd sourcing to benchmark somatic structural variant detection]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2017-11-25</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/311696v1?rss=1">
<title>
<![CDATA[
A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/311696v1?rss=1"
</link>
<description><![CDATA[
Respiratory viruses are highly infectious; however, the variation of individuals physiologic responses to viral exposure is poorly understood. Most studies examining molecular predictors of response focus on late stage predictors, typically near the time of peak symptoms. To determine whether pre- or early post-exposure factors could predict response, we conducted a community-based analysis to identify predictors of resilience or susceptibility to several respiratory viruses (H1N1, H3N2, Rhinovirus, and RSV) using peripheral blood gene expression profiles collected from healthy subjects prior to viral exposure, as well as up to 24 hours following exposure. This analysis revealed that it is possible to construct models predictive of symptoms using profiles even prior to viral exposure. Analysis of predictive gene features revealed little overlap among models; however, in aggregate, these genes were enriched for common pathways. Heme Metabolism, the most significantly enriched pathway, was associated with higher risk of developing symptoms following viral exposure.
]]></description>
<dc:creator>Fourati, S.</dc:creator>
<dc:creator>Talla, A.</dc:creator>
<dc:creator>Mahmoudian, M.</dc:creator>
<dc:creator>Burkhart, J. G.</dc:creator>
<dc:creator>Klen, R.</dc:creator>
<dc:creator>Henao, R.</dc:creator>
<dc:creator>Aydin, Z.</dc:creator>
<dc:creator>Yeung, K. Y.</dc:creator>
<dc:creator>Ahsen, M. E.</dc:creator>
<dc:creator>Almugbel, R.</dc:creator>
<dc:creator>Jahandideh, S.</dc:creator>
<dc:creator>Liang, X.</dc:creator>
<dc:creator>Nordling, T. E. M.</dc:creator>
<dc:creator>Shiga, M.</dc:creator>
<dc:creator>Stanescu, A.</dc:creator>
<dc:creator>Vogel, R.</dc:creator>
<dc:creator>The Respiratory Viral DREAM Challenge Consortium,</dc:creator>
<dc:creator>Pandey, G.</dc:creator>
<dc:creator>Chiu, C.</dc:creator>
<dc:creator>McClain, M. T.</dc:creator>
<dc:creator>Woods, C. W.</dc:creator>
<dc:creator>Ginsburg, G. S.</dc:creator>
<dc:creator>Elo, L. L.</dc:creator>
<dc:creator>Tsalik, E. L.</dc:creator>
<dc:creator>Mangravite, L. M.</dc:creator>
<dc:creator>Sieberts, S. K.</dc:creator>
<dc:date>2018-04-30</dc:date>
<dc:identifier>doi:10.1101/311696</dc:identifier>
<dc:title><![CDATA[A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2018-04-30</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/087809v1?rss=1">
<title>
<![CDATA[
A community-based collaboration to build prediction models for short-term discontinuation of docetaxel in metastatic castration-resistant prostate cancer patients 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/087809v1?rss=1"
</link>
<description><![CDATA[
BackgroundDocetaxel has a demonstrated survival benefit for metastatic castration-resistant prostate cancer (mCRPC). However, 10-20% of patients discontinue docetaxel prematurely because of toxicity-induced adverse events, and managing risk factors for toxicity remains an ongoing challenge for health care providers and patients. Prospective identification of high-risk patients for early discontinuation has the potential to assist clinical decision-making and can improve the design of more efficient clinical trials. In partnership with Project Data Sphere (PDS), a non-profit initiative facilitating clinical trial data-sharing, we designed an open-data, crowdsourced DREAM (Dialogue for Reverse Engineering Assessments and Methods) Challenge for developing models to predict early discontinuation of docetaxelnnMethodsData from the comparator arms of four phase III clinical trials in first-line mCRPC were obtained from PDS, including 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 598 patients treated with docetaxel, prednisone/prednisolone, and placebo in the VENICE trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, and 528 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Early discontinuation was defined as treatment stoppage within three months due to adverse treatment effects. Over 150 clinical features including laboratory values, medical history, lesion measures, prior treatment, and demographic variables were curated and made freely available for model building for all four trials. The ASCENT2, VENICE, and MAINSAIL trial data sets formed the training set that also included patient discontinuation status. The ENTHUSE 33 trial, with patient discontinuation status hidden, was used as an independent validation set to evaluate model performance. Prediction performance was assessed using area under the precision-recall curve (AUPRC) and the Bayes factor was used to compare the performance between prediction models.nnResultsThe frequency of early discontinuation was similar between training (ASCENT2, VENICE, and MAINSAIL) and validation (ENTHUSE 33) sets, 12.3% versus 10.4% of docetaxel-treated patients, respectively. In total, 34 independent teams submitted predictions from 61 different models. AUPRC ranged from 0.088 to 0.178 across submissions with a random model performance of 0.104. Seven models with comparable AUPRC scores (Bayes factor [&le;]; 3) were observed to outperform all other models. A post-challenge analysis of risk predictions generated by these seven models revealed three distinct patient subgroups: patients consistently predicted to be at high-risk or low-risk for early discontinuation and those with discordant risk predictions. Early discontinuation events were two-times higher in the high-versus low-risk subgroup and baseline clinical features such as presence/absence of metastatic liver lesions, and prior treatment with analgesics and ACE inhibitors exhibited statistically significant differences between the high- and low-risk subgroups (adjusted P < 0.05). An ensemble-based model constructed from a post-Challenge community collaboration resulted in the best overall prediction performance (AUPRC = 0.230) and represented a marked improvement over any individual Challenge submission. AnnFindingsOur results demonstrate that routinely collected clinical features can be used to prospectively inform clinicians of mCRPC patients risk to discontinue docetaxel treatment early due to adverse events and to the best of our knowledge is the first to establish performance benchmarks in this area. This work also underscores the "wisdom of crowds" approach by demonstrating that improved prediction of patient outcomes is obtainable by combining methods across an extended community. These findings were made possible because data from separate trials were made publicly available and centrally compiled through PDS.
]]></description>
<dc:creator>Seyednasrollah, F.</dc:creator>
<dc:creator>Koestler, D. C.</dc:creator>
<dc:creator>Wang, T.</dc:creator>
<dc:creator>Piccolo, S. R.</dc:creator>
<dc:creator>Vega, R.</dc:creator>
<dc:creator>Greiner, R.</dc:creator>
<dc:creator>Fuchs, C.</dc:creator>
<dc:creator>Gofer, E.</dc:creator>
<dc:creator>Kumar, L.</dc:creator>
<dc:creator>Wolfinger, R. D.</dc:creator>
<dc:creator>Kanigel Winner, K.</dc:creator>
<dc:creator>Bare, C.</dc:creator>
<dc:creator>Neto, E. C.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Shen, L.</dc:creator>
<dc:creator>Abdallah, K.</dc:creator>
<dc:creator>Norman, T.</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:creator>PCC-DREAM Community,</dc:creator>
<dc:creator>Soule, H.</dc:creator>
<dc:creator>Sweeney, C. J.</dc:creator>
<dc:creator>Ryan, C. J.</dc:creator>
<dc:creator>Scher, H. I.</dc:creator>
<dc:creator>Sartor, O.</dc:creator>
<dc:creator>Elo, L. L.</dc:creator>
<dc:creator>Zhou, F. L.</dc:creator>
<dc:creator>Guinney, J.</dc:creator>
<dc:creator>Costello, J. C.</dc:creator>
<dc:date>2016-11-15</dc:date>
<dc:identifier>doi:10.1101/087809</dc:identifier>
<dc:title><![CDATA[A community-based collaboration to build prediction models for short-term discontinuation of docetaxel in metastatic castration-resistant prostate cancer patients]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2016-11-15</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/796029v1?rss=1">
<title>
<![CDATA[
Predicting cellular position in the Drosophila embryo from Single-Cell Transcriptomics data 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/796029v1?rss=1"
</link>
<description><![CDATA[
Single-cell RNA-seq technologies are rapidly evolving but while very informative, in standard scRNAseq experiments the spatial organization of the cells in the tissue of origin is lost. Conversely, spatial RNA-seq technologies designed to keep the localization of the cells have limited throughput and gene coverage. Mapping scRNAseq to genes with spatial information increases coverage while providing spatial location. However, methods to perform such mapping have not yet been benchmarked. To bridge the gap, we organized the DREAM Single-Cell Transcriptomics challenge focused on the spatial reconstruction of cells from the Drosophila embryo from scRNAseq data, leveraging as gold standard genes with in situ hybridization data from the Berkeley Drosophila Transcription Network Project reference atlas. The 34 participating teams used diverse algorithms for gene selection and location prediction, while being able to correctly localize rare subpopulations of cells. Selection of predictor genes was essential for this task and such genes showed a relatively high expression entropy, high spatial clustering and the presence of prominent developmental genes such as gap and pair-ruled genes and tissue defining markers.
]]></description>
<dc:creator>Tanevski, J.</dc:creator>
<dc:creator>Nguyen, T.</dc:creator>
<dc:creator>Truong, B.</dc:creator>
<dc:creator>Karaiskos, N.</dc:creator>
<dc:creator>Ahsen, M. E.</dc:creator>
<dc:creator>Zhang, X.</dc:creator>
<dc:creator>Shu, C.</dc:creator>
<dc:creator>Hu, Y.</dc:creator>
<dc:creator>Pham, H. V. V.</dc:creator>
<dc:creator>Li, X.</dc:creator>
<dc:creator>Le, T. D.</dc:creator>
<dc:creator>Tarca, A.</dc:creator>
<dc:creator>Bhatti, G.</dc:creator>
<dc:creator>Romero, R.</dc:creator>
<dc:creator>Karathanasis, N.</dc:creator>
<dc:creator>Loher, P.</dc:creator>
<dc:creator>Chen, Y.</dc:creator>
<dc:creator>Ouyang, Z.</dc:creator>
<dc:creator>Mao, D.</dc:creator>
<dc:creator>Zhang, Y.</dc:creator>
<dc:creator>Zand, M.</dc:creator>
<dc:creator>Ruan, J.</dc:creator>
<dc:creator>Hafemeister, C.</dc:creator>
<dc:creator>Qiu, P.</dc:creator>
<dc:creator>Tran, D.</dc:creator>
<dc:creator>Nguyen, T.</dc:creator>
<dc:creator>Gabor, A.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Glaab, E.</dc:creator>
<dc:creator>Krause, R.</dc:creator>
<dc:creator>Banda, P.</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:creator>Rajewsky, N.</dc:creator>
<dc:creator>Saez-Rodriguez, J.</dc:creator>
<dc:creator>Meyer, P.</dc:creator>
<dc:date>2019-10-10</dc:date>
<dc:identifier>doi:10.1101/796029</dc:identifier>
<dc:title><![CDATA[Predicting cellular position in the Drosophila embryo from Single-Cell Transcriptomics data]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2019-10-10</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/294231v1?rss=1">
<title>
<![CDATA[
Stratification of amyotrophic lateral sclerosis patients: a crowdsourcing approach 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/294231v1?rss=1"
</link>
<description><![CDATA[
Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease with substantial heterogeneity in clinical presentation with an urgent need for better stratification tools for clinical development and care. In this study we used a crowdsourcing approach to address the problem of ALS patient stratification. The DREAM Prize4Life ALS Stratification Challenge was a crowdsourcing initiative using data from >10,000 patients from completed ALS clinical trials and 1479 patients from community-based patient registers. Challenge participants used machine learning and clustering techniques to predict ALS progression and survival. By developing new approaches, the best performing teams were able to predict disease outcomes better than currently available methods. At the same time, the integration of clustering components across methods led to the emergence of distinct consensus clusters, separating patients into four consistent groups, each with its unique predictors for classification. This analysis reveals for the first time the potential of a crowdsourcing approach to uncover covert patient sub-populations, and to accelerate disease understanding and therapeutic development.
]]></description>
<dc:creator>Kueffner, R.</dc:creator>
<dc:creator>Zach, N.</dc:creator>
<dc:creator>Bronfeld, M.</dc:creator>
<dc:creator>Norel, R.</dc:creator>
<dc:creator>Atassi, N.</dc:creator>
<dc:creator>Balagurusamy, V.</dc:creator>
<dc:creator>di Camillo, B.</dc:creator>
<dc:creator>Chio, A.</dc:creator>
<dc:creator>Cudkowicz, M.</dc:creator>
<dc:creator>Dillenberger, D.</dc:creator>
<dc:creator>Garcia-Garcia, J.</dc:creator>
<dc:creator>Hardiman, O.</dc:creator>
<dc:creator>Hoff, B.</dc:creator>
<dc:creator>Knight, J.</dc:creator>
<dc:creator>Leitner, M. L.</dc:creator>
<dc:creator>Li, G.</dc:creator>
<dc:creator>Mangravite, L.</dc:creator>
<dc:creator>Norman, T.</dc:creator>
<dc:creator>Wang, L.</dc:creator>
<dc:creator>The ALS Stratification Consortium,</dc:creator>
<dc:creator>Xiao, J.</dc:creator>
<dc:creator>Fang, W.-C.</dc:creator>
<dc:creator>Peng, J.</dc:creator>
<dc:creator>Stolovitzky, G.</dc:creator>
<dc:date>2018-04-05</dc:date>
<dc:identifier>doi:10.1101/294231</dc:identifier>
<dc:title><![CDATA[Stratification of amyotrophic lateral sclerosis patients: a crowdsourcing approach]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2018-04-05</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/737122v1?rss=1">
<title>
<![CDATA[
Multiple Myeloma DREAM Challenge Reveals Epigenetic Regulator PHF19 As Marker of Aggressive Disease 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/737122v1?rss=1"
</link>
<description><![CDATA[
While the past decade has seen meaningful improvements in clinical outcomes for multiple myeloma patients, a subset of patients do not benefit from current therapeutics for unclear reasons. Many gene expression-based models of risk have been developed, but each model uses a different combination of genes and often involve assaying many genes making them difficult to implement. We organized the Multiple Myeloma DREAM Challenge, a crowdsourced effort to develop models of rapid progression in newly diagnosed myeloma patients and to benchmark these against previously published models. This effort lead to more robust predictors and found that incorporating specific demographic and clinical features improved gene expression-based models of high risk. Furthermore, post challenge analysis identified a novel expression-based risk marker and histone modifier, PHF19, which featured prominently in several independent models. Lastly, we show that a simple four feature predictor composed of age, International Staging System stage (ISS), and expression of PHF19 and MMSET performs similarly to more complex models with many more gene expression features included.nnKey pointsO_LIMost comprehensive and unbiased assessment of prognostic biomarkers in MM resulting in a robust and parsimonious model.nC_LIO_LIIdentification of PHF19 as the expression based biomarker most strongly associated with rapid progression in MM patients.nC_LI
]]></description>
<dc:creator>Mason, M. J.</dc:creator>
<dc:creator>Schinke, C.</dc:creator>
<dc:creator>Eng, C.</dc:creator>
<dc:creator>Towfic, F.</dc:creator>
<dc:creator>Gruber, F.</dc:creator>
<dc:creator>Dervan, A.</dc:creator>
<dc:creator>White, B. S.</dc:creator>
<dc:creator>Pratapa, A.</dc:creator>
<dc:creator>Guan, Y.</dc:creator>
<dc:creator>Chen, H.</dc:creator>
<dc:creator>Cui, Y.</dc:creator>
<dc:creator>Li, B.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Chaibub Neto, E.</dc:creator>
<dc:creator>Mavrommatis, K.</dc:creator>
<dc:creator>Ortiz, M.</dc:creator>
<dc:creator>Lyzogubov, V.</dc:creator>
<dc:creator>Bisht, K.</dc:creator>
<dc:creator>Dai, H. Y.</dc:creator>
<dc:creator>Schmitz, F.</dc:creator>
<dc:creator>Flynt, E.</dc:creator>
<dc:creator>Rozelle, D.</dc:creator>
<dc:creator>Danziger, S. A.</dc:creator>
<dc:creator>Ratushny, A.</dc:creator>
<dc:creator>Dalton, W. S.</dc:creator>
<dc:creator>Goldschmidt, H.</dc:creator>
<dc:creator>Avet-Loiseau, H.</dc:creator>
<dc:creator>Samur, M.</dc:creator>
<dc:creator>Hayete, B.</dc:creator>
<dc:creator>Sonneveld, P.</dc:creator>
<dc:creator>Shain, K. H.</dc:creator>
<dc:creator>Munshi, N.</dc:creator>
<dc:creator>Auclair, D.</dc:creator>
<dc:creator>Hose, D.</dc:creator>
<dc:creator>Morgan, G.</dc:creator>
<dc:creator>Trotter, M.</dc:creator>
<dc:creator>Bassett, D.</dc:creator>
<dc:creator>Goeke, J.</dc:creator>
<dc:creator>Walker, B. A.</dc:creator>
<dc:creator>Thakurta, A.</dc:creator>
<dc:creator>Guinney, J. A.</dc:creator>
<dc:date>2019-08-22</dc:date>
<dc:identifier>doi:10.1101/737122</dc:identifier>
<dc:title><![CDATA[Multiple Myeloma DREAM Challenge Reveals Epigenetic Regulator PHF19 As Marker of Aggressive Disease]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2019-08-22</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/856922v1?rss=1">
<title>
<![CDATA[
Ensemble Machine Learning Modeling for the Prediction of Artemisinin Resistance in Malaria 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/856922v1?rss=1"
</link>
<description><![CDATA[
Antiparasitic resistance in malaria is a growing concern affecting many areas of the eastern world. Since the emergence of artemisinin resistance in the late 2000s in Cambodia, research into the underlying mechanisms has been underway.

The 2019 Malaria Dream Challenge posited the task of developing computational models that address important problems in advancing the fight against malaria. The first goal was to accurately predict Artemisinin drug resistance levels of Plasmodium falciparum isolates, as quantified by the IC50. The second goal was to predict the parasite clearance rate of malaria parasite isolates based on in vitro transcriptional profiles.

In this work, we develop machine learning models using novel methods for transforming isolate data and handling the tens of thousands of variables that result from these data transformation exercises. This is demonstrated by using massively parallel processing of the data vectorization for use in scalable machine learning. In addition, we show the utility of ensemble machine learning modeling for highly effective predictions of both goals of this challenge. This is demonstrated by the use of multiple machine learning algorithms combined with various scaling and normalization preprocessing steps. Then, using a voting ensemble, multiple models are combined to generate a final model prediction.
]]></description>
<dc:creator>Ford, C. T.</dc:creator>
<dc:creator>Janies, D. A.</dc:creator>
<dc:date>2019-11-27</dc:date>
<dc:identifier>doi:10.1101/856922</dc:identifier>
<dc:title><![CDATA[Ensemble Machine Learning Modeling for the Prediction of Artemisinin Resistance in Malaria]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2019-11-27</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/204370v1?rss=1">
<title>
<![CDATA[
Germline Contamination and Leakage in Whole Genome Somatic Single Nucleotide Variant Detection 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/204370v1?rss=1"
</link>
<description><![CDATA[
BackgroundThe clinical sequencing of cancer genomes to personalize therapy is becoming routine across the world. However, concerns over patient re-identification from these data lead to questions about how tightly access should be controlled. It is not thought to be possible to re-identify patients from somatic variant data. However, somatic variant detection pipelines can mistakenly identify germline variants as somatic ones, a process called "germline leakage". The rate of germline leakage across different somatic variant detection pipelines is not well-understood, and it is uncertain whether or not somatic variant calls should be considered re-identifiable. To fill this gap, we quantified germline leakage across 259 sets of whole-genome somatic single nucleotide variant (SNVs) predictions made by 21 teams as part of the ICGC-TCGA DREAM Somatic Mutation Calling Challenge.nnResultsThe median somatic SNV prediction set contained 4,325 somatic SNVs and leaked one germline polymorphism. The level of germline leakage was inversely correlated with somatic SNV prediction accuracy and positively correlated with the amount of infiltrating normal cells. The specific germline variants leaked differed by tumour and algorithm. To aid in quantitation and correction of leakage, we created a tool, called GermlineFilter, for use in public-facing somatic SNV databases.nnConclusionsThe potential for patient re-identification from leaked germline variants in somatic SNV predictions has led to divergent open data access policies, based on different assessments of the risks. Indeed, a single, well-publicized re-identification event could reshape public perceptions of the values of genomic data sharing. We find that modern somatic SNV prediction pipelines have low germline-leakage rates, which can be further reduced, especially for cloud-sharing, using pre-filtering software.
]]></description>
<dc:creator>Sendorek, D. H.</dc:creator>
<dc:creator>Caloian, C.</dc:creator>
<dc:creator>Ellrott, K.</dc:creator>
<dc:creator>Bare, J. C.</dc:creator>
<dc:creator>Yamaguchi, T. N.</dc:creator>
<dc:creator>Ewing, A. D.</dc:creator>
<dc:creator>Houlahan, K. E.</dc:creator>
<dc:creator>Norman, T. C.</dc:creator>
<dc:creator>Margolin, A. A.</dc:creator>
<dc:creator>Stuart, J. M.</dc:creator>
<dc:creator>Boutros, P. C.</dc:creator>
<dc:date>2017-10-17</dc:date>
<dc:identifier>doi:10.1101/204370</dc:identifier>
<dc:title><![CDATA[Germline Contamination and Leakage in Whole Genome Somatic Single Nucleotide Variant Detection]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2017-10-17</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/254839v1?rss=1">
<title>
<![CDATA[
Valection: Design Optimization for Validation and Verification Studies 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/254839v1?rss=1"
</link>
<description><![CDATA[
BackgroundPlatform-specific error profiles necessitate confirmatory studies where predictions made on data generated using one technology are additionally verified by processing the same samples on an orthogonal technology. In disciplines that rely heavily on high-throughput data generation, such as genomics, reducing the impact of false positive and false negative rates in results is a top priority. However, verifying all predictions can be costly and redundant, and testing a subset of findings is often used to estimate the true error profile. To determine how to create subsets of predictions for validation that maximize inference of global error profiles, we developed Valection, a software program that implements multiple strategies for the selection of verification candidates.nnResultsTo evaluate these selection strategies, we obtained 261 sets of somatic mutation calls from a single-nucleotide variant caller benchmarking challenge where 21 teams competed on whole-genome sequencing datasets of three computationally-simulated tumours. By using synthetic data, we had complete ground truth of the tumours mutations and, therefore, we were able to accurately determine how estimates from the selected subset of verification candidates compared to the complete prediction set. We found that selection strategy performance depends on several verification study characteristics. In particular the verification budget of the experiment (i.e. how many candidates can be selected) is shown to influence estimates.nnConclusionsThe Valection framework is flexible, allowing for the implementation of additional selection algorithms in the future. Its applicability extends to any discipline that relies on experimental verification and will benefit from the optimization of verification candidate selection.
]]></description>
<dc:creator>Cooper, C. I.</dc:creator>
<dc:creator>Yao, D.</dc:creator>
<dc:creator>Sendorek, D. H.</dc:creator>
<dc:creator>Yamaguchi, T. N.</dc:creator>
<dc:creator>P'ng, C.</dc:creator>
<dc:creator>Houlahan, K. E.</dc:creator>
<dc:creator>Caloian, C.</dc:creator>
<dc:creator>Fraser, M.</dc:creator>
<dc:creator>SMC-DNA Challenge Participants,</dc:creator>
<dc:creator>Ellrott, K.</dc:creator>
<dc:creator>Margolin, A. A.</dc:creator>
<dc:creator>Bristow, R. G.</dc:creator>
<dc:creator>Stuart, J. M.</dc:creator>
<dc:creator>Boutros, P. C.</dc:creator>
<dc:date>2018-01-28</dc:date>
<dc:identifier>doi:10.1101/254839</dc:identifier>
<dc:title><![CDATA[Valection: Design Optimization for Validation and Verification Studies]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2018-01-28</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/243568v1?rss=1">
<title>
<![CDATA[
Identifying biomarkers of anti-cancer drug synergy using multi-task learning 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/243568v1?rss=1"
</link>
<description><![CDATA[
Combining anti-cancer drugs has the potential to increase treatment efficacy. Because patient responses to drug combinations are highly variable, predictive biomarkers of synergy are required to identify which patients are likely to benefit from a drug combination. To aid biomarker identification, the DREAM challenge consortium has recently released data from a screen containing 85 cell lines and 167 drug combinations. The main challenge of these data is the low sample size: per drug combination, a median of 14 cell lines have been screened. We found that widely used methods in single drug response prediction, such as Elastic Net regression per drug, are not predictive in this setting. Instead, we propose to use multi-task learning: training a single model simultaneously on all drug combinations, which we show results in increased predictive performance. In contrast to other multi-task learning approaches, our approach allows for the identification of biomarkers, by using a modified random forest variable importance score, which we illustrate using artificial data and the DREAM challenge data. Notably, we find that mutations in MYO15A are associated with synergy between ALK / IGFR dual inhibitors and PI3K pathway inhibitors in triple-negative breast cancer.nnAuthor summaryCombining drugs is a promising strategy for cancer treatment. However, it is often not known which patients will benefit from a particular drug combination. To identify patients that are likely to benefit, we need to identify biomarkers, such as mutations in the tumors DNA, that are associated with favorable response to the drug combination. In this work, we identified such biomarkers using the drug combination data released by the DREAM challenge consortium, which contain 85 tumor cell lines and 167 drug combinations. The main challenge of these data is the extremely low sample size: a median of 14 cell lines have been screened per drug combination. We found that traditional methods to identify biomarkers for monotherapy response, which analyze each drug separately, are not suitable in this low sample size setting. Instead, we used a technique called multi-task learning to jointly analyze all drug combinations in a single statistical model. In contrast to existing multi-task learning algorithms, which are black-box methods, our method allows for the identification of biomarkers. Notably, we find that, in a subset of breast cancer cell lines, MYO15A mutations associate with response to the combination of ALK / IGFR dual inhibitors and PI3K pathway inhibitors.
]]></description>
<dc:creator>Aben, N.</dc:creator>
<dc:creator>de Ruiter, J.</dc:creator>
<dc:creator>Bosdriesz, E.</dc:creator>
<dc:creator>Kim, Y.</dc:creator>
<dc:creator>Bounova, G.</dc:creator>
<dc:creator>Vis, D.</dc:creator>
<dc:creator>Wessels, L.</dc:creator>
<dc:creator>Michaut, M.</dc:creator>
<dc:date>2018-01-05</dc:date>
<dc:identifier>doi:10.1101/243568</dc:identifier>
<dc:title><![CDATA[Identifying biomarkers of anti-cancer drug synergy using multi-task learning]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2018-01-05</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2019.12.31.891812v1?rss=1">
<title>
<![CDATA[
Crowdsourced mapping of unexplored target space of kinase inhibitors 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2019.12.31.891812v1?rss=1"
</link>
<description><![CDATA[
Despite decades of intensive search for compounds that modulate the activity of particular targets, there are currently small-molecules available only for a small proportion of the human proteome. Effective approaches are therefore required to map the massive space of unexplored compound-target interactions for novel and potent activities. Here, we carried out a crowdsourced benchmarking of predictive models for kinase inhibitor potencies across multiple kinase families using unpublished bioactivity data. The top-performing predictions were based on kernel learning, gradient boosting and deep learning, and their ensemble resulted in predictive accuracy exceeding that of kinase activity assays. We then made new experiments based on the model predictions, which further improved the accuracy of experimental mapping efforts and identified unexpected potencies even for under-studied kinases. The open-source algorithms together with the novel bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking new prediction algorithms and for extending the druggable kinome.
]]></description>
<dc:creator>Cichonska, A.</dc:creator>
<dc:creator>Ravikumar, B.</dc:creator>
<dc:creator>Allaway, R. J.</dc:creator>
<dc:creator>Park, S.</dc:creator>
<dc:creator>Wan, F.</dc:creator>
<dc:creator>Isayev, O.</dc:creator>
<dc:creator>Li, S.</dc:creator>
<dc:creator>Mason, M. J.</dc:creator>
<dc:creator>Lamb, A.</dc:creator>
<dc:creator>Tanoli, Z.-u.-R.</dc:creator>
<dc:creator>Jeon, M.</dc:creator>
<dc:creator>Kim, S.</dc:creator>
<dc:creator>Popova, M.</dc:creator>
<dc:creator>Zeng, J.</dc:creator>
<dc:creator>Dang, K.</dc:creator>
<dc:creator>Koytiger, G.</dc:creator>
<dc:creator>Kang, J.</dc:creator>
<dc:creator>Wells, C. I.</dc:creator>
<dc:creator>Willson, T. M.</dc:creator>
<dc:creator>The IDG-DREAM Drug-Kinase Binding Prediction Challenge Consortium,</dc:creator>
<dc:creator>Oprea, T. I.</dc:creator>
<dc:creator>Schlessinger, A.</dc:creator>
<dc:creator>Drewry, D. H.</dc:creator>
<dc:creator>Stolovitzky, G. A.</dc:creator>
<dc:creator>Wennerberg, K.</dc:creator>
<dc:creator>Guinney, J.</dc:creator>
<dc:creator>Aittokallio, T.</dc:creator>
<dc:date>2020-01-07</dc:date>
<dc:identifier>doi:10.1101/2019.12.31.891812</dc:identifier>
<dc:title><![CDATA[Crowdsourced mapping of unexplored target space of kinase inhibitors]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2020-01-07</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2020.01.13.904722v1?rss=1">
<title>
<![CDATA[
Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2020.01.13.904722v1?rss=1"
</link>
<description><![CDATA[
Mobile health, the collection of data using wearables and sensors, is a rapidly growing field in health research with many applications. Deriving validated measures of disease and severity that can be used clinically or as outcome measures in clinical trials, referred to as digital biomarkers, has proven difficult. In part due to the complicated analytical approaches necessary to develop these metrics. Here we describe the use of crowdsourcing to specifically evaluate and benchmark features derived from accelerometer and gyroscope data in two different datasets to predict the presence of Parkinsons Disease (PD) and severity of three PD symptoms: tremor, dyskinesia and bradykinesia. Forty teams from around the world submitted features, and achieved drastically improved predictive performance for PD status (best AUROC=0.87), as well as tremor (best AUPR=0.75), dyskinesia (best AUPR=0.48) and bradykinesia (best AUPR=0.95) severity.
]]></description>
<dc:creator>Sieberts, S. K.</dc:creator>
<dc:creator>Schaff, J.</dc:creator>
<dc:creator>Duda, M.</dc:creator>
<dc:creator>Pataki, B. A.</dc:creator>
<dc:creator>Sun, M.</dc:creator>
<dc:creator>Snyder, P.</dc:creator>
<dc:creator>Daneault, J.-F.</dc:creator>
<dc:creator>Parisi, F.</dc:creator>
<dc:creator>Costante, G.</dc:creator>
<dc:creator>Rubin, U.</dc:creator>
<dc:creator>Banda, P.</dc:creator>
<dc:creator>Chae, Y.</dc:creator>
<dc:creator>Neto, E. C.</dc:creator>
<dc:creator>Dorsey, R.</dc:creator>
<dc:creator>Aydın, Z.</dc:creator>
<dc:creator>Chen, A.</dc:creator>
<dc:creator>Elo, L. L.</dc:creator>
<dc:creator>Espino, C.</dc:creator>
<dc:creator>Glaab, E.</dc:creator>
<dc:creator>Goan, E.</dc:creator>
<dc:creator>Golabchi, F. N.</dc:creator>
<dc:creator>Görmez, Y.</dc:creator>
<dc:creator>Jaakkola, M. K.</dc:creator>
<dc:creator>Jonnagaddala, J.</dc:creator>
<dc:creator>KLEn, R.</dc:creator>
<dc:creator>Li, D.</dc:creator>
<dc:creator>McDaniel, C.</dc:creator>
<dc:creator>Perrin, D.</dc:creator>
<dc:creator>Rad, N. M.</dc:creator>
<dc:creator>Rainaldi, E.</dc:creator>
<dc:creator>Sapienza, S.</dc:creator>
<dc:creator>Schwab, P.</dc:creator>
<dc:creator>Shokhirev, N.</dc:creator>
<dc:creator>Venäläinen, M. S.</dc:creator>
<dc:creator>Vergara-Diaz, G.</dc:creator>
<dc:creator>Zhang, Y.</dc:creator>
<dc:creator>Parkinson's Disease Digital Biomarker Challenge Consortium,</dc:creator>
<dc:creator>Wang, Y.</dc:creator>
<dc:creator>Guan, Y.</dc:creator>
<dc:creator>Brunner, D.</dc:creator>
<dc:creator>Bonato, P.</dc:creator>
<dc:creator>Mangravite, L. M.</dc:creator>
<dc:creator>Omberg</dc:creator>
<dc:date>2020-01-16</dc:date>
<dc:identifier>doi:10.1101/2020.01.13.904722</dc:identifier>
<dc:title><![CDATA[Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2020-01-16</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2020.06.05.130971v1?rss=1">
<title>
<![CDATA[
Crowdsourcing assessment of maternal blood multi-omics for predicting gestational age and preterm birth 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2020.06.05.130971v1?rss=1"
</link>
<description><![CDATA[
Identification of pregnancies at risk of preterm birth (PTB), the leading cause of newborn deaths, remains challenging given the syndromic nature of the disease. We report a longitudinal multi-omics study coupled with a DREAM challenge to develop predictive models of PTB. We found that whole blood gene expression predicts ultrasound-based gestational ages in normal and complicated pregnancies (r=0.83), as well as the delivery date in normal pregnancies (r=0.86), with an accuracy comparable to ultrasound. However, unlike the latter, transcriptomic data collected at <37 weeks of gestation predicted the delivery date of one third of spontaneous (sPTB) cases within 2 weeks of the actual date. Based on samples collected before 33 weeks in asymptomatic women we found expression changes preceding preterm prelabor rupture of the membranes that were consistent across time points and cohorts, involving, among others, leukocyte-mediated immunity. Plasma proteomic random forests predicted sPTB with higher accuracy and earlier in pregnancy than whole blood transcriptomic models (e.g. AUROC=0.76 vs. AUROC=0.6 at 27-33 weeks of gestation).
]]></description>
<dc:creator>Tarca, A.</dc:creator>
<dc:creator>Pataki, B. A.</dc:creator>
<dc:creator>Romero, R.</dc:creator>
<dc:creator>Sirota, M.</dc:creator>
<dc:creator>Guan, Y.</dc:creator>
<dc:creator>Kutum, R.</dc:creator>
<dc:creator>Gomez-Lopez, N.</dc:creator>
<dc:creator>Done, B.</dc:creator>
<dc:creator>Bhatti, G.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Andreoletti, G.</dc:creator>
<dc:creator>Chaiworapongsa, T.</dc:creator>
<dc:creator>Consortium, T. D. P. B. P. C.</dc:creator>
<dc:creator>Hassan, S. S.</dc:creator>
<dc:creator>Hsu, C.-D.</dc:creator>
<dc:creator>Aghaeepour, N.</dc:creator>
<dc:creator>Stolovitzky, G. A.</dc:creator>
<dc:creator>Csabai, I.</dc:creator>
<dc:creator>Costello, J. C.</dc:creator>
<dc:date>2020-06-06</dc:date>
<dc:identifier>doi:10.1101/2020.06.05.130971</dc:identifier>
<dc:title><![CDATA[Crowdsourcing assessment of maternal blood multi-omics for predicting gestational age and preterm birth]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2020-06-06</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2020.12.21.423514v1?rss=1">
<title>
<![CDATA[
A Community Challenge for Pancancer Drug Mechanism of Action Inference from Perturbational Profile Data 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2020.12.21.423514v1?rss=1"
</link>
<description><![CDATA[
The Columbia Cancer Target Discovery and Development (CTD2) Center has developed PANACEA (PANcancer Analysis of Chemical Entity Activity), a collection of dose-response curves and perturbational profiles for 400 clinical oncology drugs in cell lines selected to optimally represent 19 cancer subtypes. This resource, developed to study tumor-specific drug mechanism of action, was instrumental in hosting a DREAM Challenge to assess computational models for de novo drug polypharmacology prediction. Dose-response and perturbational profiles for 32 kinase inhibitors were provided to 21 participating teams, who did not know the identity or nature of the compounds, and they were asked to predict high-affinity binding among ~1,300 possible protein targets. Best performing methods leveraged both gene expression profile similarity analysis, and deep-learning methodologies trained on individual datasets. This study lays the foundation for future integrative analyses of pharmacogenomic data, reconciliation of polypharmacology effects in different tumor contexts, and insights into network-based assessment of context-specific drug mechanism of action.
]]></description>
<dc:creator>Douglass, E. F.</dc:creator>
<dc:creator>Allaway, R. J.</dc:creator>
<dc:creator>Szalai, B.</dc:creator>
<dc:creator>Wang, W.</dc:creator>
<dc:creator>Tian, T.</dc:creator>
<dc:creator>Fernandez, A.</dc:creator>
<dc:creator>Realubit, R.</dc:creator>
<dc:creator>Karan, C.</dc:creator>
<dc:creator>Zheng, S.</dc:creator>
<dc:creator>Pessia, A.</dc:creator>
<dc:creator>Tanoli, Z.</dc:creator>
<dc:creator>Jafari, M.</dc:creator>
<dc:creator>Wan, F.</dc:creator>
<dc:creator>Li, S.</dc:creator>
<dc:creator>Xiong, Y.</dc:creator>
<dc:creator>Duran-Frigola, M.</dc:creator>
<dc:creator>Bertoni, M.</dc:creator>
<dc:creator>Badia-i-Mompel, P.</dc:creator>
<dc:creator>Mateo, L.</dc:creator>
<dc:creator>Guitart-Pla, O.</dc:creator>
<dc:creator>Chung, V.</dc:creator>
<dc:creator>DREAM CTD-squared Pancancer Drug Activity Challenge Consortium,</dc:creator>
<dc:creator>Tang, J.</dc:creator>
<dc:creator>Zeng, J.</dc:creator>
<dc:creator>Aloy, P.</dc:creator>
<dc:creator>Saez-Rodriguez, J.</dc:creator>
<dc:creator>Guinney, J.</dc:creator>
<dc:creator>Gerhard, D. S.</dc:creator>
<dc:creator>Califano, A.</dc:creator>
<dc:date>2020-12-22</dc:date>
<dc:identifier>doi:10.1101/2020.12.21.423514</dc:identifier>
<dc:title><![CDATA[A Community Challenge for Pancancer Drug Mechanism of Action Inference from Perturbational Profile Data]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2020-12-22</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2021.02.15.430538v1?rss=1">
<title>
<![CDATA[
Crowdsourced Identification of Multi-Target Kinase Inhibitors for RET- and TAU- Based Disease: the Multi-Targeting Drug DREAM Challenge 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2021.02.15.430538v1?rss=1"
</link>
<description><![CDATA[
A continuing challenge in modern medicine is the identification of safer and more efficacious drugs. Precision therapeutics, which have one molecular target, have been long promised to be safer and more effective than traditional therapies. This approach has proven to be challenging for multiple reasons including lack of efficacy, rapidly acquired drug resistance, and narrow patient eligibility criteria. An alternative approach is the development of drugs that address the overall disease network by targeting multiple biological targets ( polypharmacology). Rational development of these molecules will require improved methods for predicting single chemical structures that target multiple drug targets. To address this need, we developed the Multi-Targeting Drug DREAM Challenge, in which we challenged participants to predict single chemical entities that target pro-targets but avoid anti-targets for two unrelated diseases: RET-based tumors and a common form of inherited Tauopathy. Here, we report the results of this DREAM Challenge and the development of two neural network-based machine learning approaches that were applied to the challenge of rational polypharmacology. Together, these platforms provide a potentially useful first step towards developing lead therapeutic compounds that address disease complexity through rational polypharmacology.

Author SummaryMany modern drugs are developed with the goal of modulating a single cellular pathway or target. However, many drugs are, in fact,  dirty; they target multiple cellular pathways or targets. This phenomenon is known as multi-targeting or polypharmacology. While some strive to develop  cleaner therapeutics that eliminate secondary targets, recent work has shown that multi-targeting therapeutics have key advantages for a variety of diseases. However, while multi-targeting drugs that affect a precisely-defined profile of targets may be more effective, it is difficult to computationally predict which molecules have desirable target profiles. Here, we report the results of a competitive crowdsourcing project (the Multi-Targeting Drug DREAM Challenge), where we challenged participants to predict chemicals that have desired target profiles for cancer and neurodegenerative disease.
]]></description>
<dc:creator>Xiong, Z.</dc:creator>
<dc:creator>Jeon, M.</dc:creator>
<dc:creator>Allaway, R. J.</dc:creator>
<dc:creator>Kang, J.</dc:creator>
<dc:creator>Park, D.</dc:creator>
<dc:creator>Lee, J.</dc:creator>
<dc:creator>Jeon, H.</dc:creator>
<dc:creator>Ko, M.</dc:creator>
<dc:creator>Jiang, H.</dc:creator>
<dc:creator>Zheng, M.</dc:creator>
<dc:creator>Tan, A. C.</dc:creator>
<dc:creator>Guo, X.</dc:creator>
<dc:creator>The Multi-Targeting Drug DREAM Challenge Community,</dc:creator>
<dc:creator>Dang, K. K.</dc:creator>
<dc:creator>Tropsha, A.</dc:creator>
<dc:creator>Hecht, C.</dc:creator>
<dc:creator>Das, T. K.</dc:creator>
<dc:creator>Carlson, H. A.</dc:creator>
<dc:creator>Abagyan, R.</dc:creator>
<dc:creator>Guinney, J.</dc:creator>
<dc:creator>Schlessinger, A.</dc:creator>
<dc:creator>Cagan, R.</dc:creator>
<dc:date>2021-02-17</dc:date>
<dc:identifier>doi:10.1101/2021.02.15.430538</dc:identifier>
<dc:title><![CDATA[Crowdsourced Identification of Multi-Target Kinase Inhibitors for RET- and TAU- Based Disease: the Multi-Targeting Drug DREAM Challenge]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2021-02-17</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2020.05.09.086397v1?rss=1">
<title>
<![CDATA[
The winning methods for predicting cellular position in the DREAM single cell transcriptomics challenge 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2020.05.09.086397v1?rss=1"
</link>
<description><![CDATA[
MotivationPredicting cell locations is important since with the understanding of cell locations, we may estimate the function of cells and their integration with the spatial environment. Thus, the DREAM Challenge on Single Cell Transcriptomics required participants to predict the locations of single cells in the Drosophila embryo using single cell transcriptomic data.

ResultsWe have developed over 50 pipelines by combining different ways of pre-processing the RNA-seq data, selecting the genes, predicting the cell locations, and validating predicted cell locations, resulting in the winning methods for two out of three sub-challenges in the competition. In this paper, we present an R package, SCTCwhatateam, which includes all the methods we developed and the Shiny web-application to facilitate the research on single cell spatial reconstruction. All the data and the example use cases are available in the Supplementary material.

AvailabilityThe scripts of the package are available at https://github.com/thanhbuu04/SCTCwhatateam and the Shiny application is available at https://github.com/pvvhoang/SCTCwhatateam-ShinyApp

ContactThuc.Le@unisa.edu.au

Supplementary informationSupplementary data are available at Briefings in Bioinformatics online.
]]></description>
<dc:creator>Pham, V. V. H.</dc:creator>
<dc:creator>Li, X.</dc:creator>
<dc:creator>Truong, B.</dc:creator>
<dc:creator>Nguyen, T.</dc:creator>
<dc:creator>Liu, L.</dc:creator>
<dc:creator>Li, J.</dc:creator>
<dc:creator>Le, T.</dc:creator>
<dc:date>2020-05-10</dc:date>
<dc:identifier>doi:10.1101/2020.05.09.086397</dc:identifier>
<dc:title><![CDATA[The winning methods for predicting cellular position in the DREAM single cell transcriptomics challenge]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2020-05-10</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2021.03.23.436603v1?rss=1">
<title>
<![CDATA[
Cell-to-cell and type-to-type heterogeneity of signaling networks: Insights from the crowd 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2021.03.23.436603v1?rss=1"
</link>
<description><![CDATA[
Recent technological developments allow us to measure the status of dozens of proteins in individual cells. This opens the way to understand the heterogeneity of complex multi-signaling networks across cells and cell-types, with important implications to understand and treat diseases such as cancer. These technologies are however limited to proteins for which antibodies are available and are fairly costly, making predictions of new markers and of existing markers under new conditions a valuable alternative. To assess our capacity to make such predictions and boost further methodological development, we organised the Single Cell Signaling in Breast Cancer DREAM challenge. We used a mass cytometry data set, covering 36 markers in over 4,000 conditions totalling 80 million single cells across 67 breast cancer cell lines. Through four increasingly difficult subchallenges, the participants predicted missing markers, new conditions, and the time course response of single cells to stimuli in the presence and absence of kinase inhibitors. The challenge results show that despite the stochastic nature of signal transduction in single cells, the signaling events are tightly controlled and machine learning methods can accurately predict new experimental data.

Graphical Abstract

O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=58 SRC="FIGDIR/small/436603v2_ufig1.gif" ALT="Figure 1">
View larger version (24K):
org.highwire.dtl.DTLVardef@a95337org.highwire.dtl.DTLVardef@966d5aorg.highwire.dtl.DTLVardef@1e55b18org.highwire.dtl.DTLVardef@bfb5d7_HPS_FORMAT_FIGEXP  M_FIG C_FIG Key pointsO_LIOver 80 million single-cell multiplexed measurements across 67 cell lines, 54 conditions and 10 time points to benchmark predictive models of single cell signaling
C_LIO_LI73 approaches from 27 teams for predicting response to kinase inhibitors on single cell level, and dynamic response from unperturbed basal omics data
C_LIO_LIPredictions of single marker models correlate with measurements with a correlation coefficient of 0.76
C_LIO_LITop models of whole signaling response models perform almost as well as a biological replicate
C_LIO_LICell-line specific variation in dynamics can be predicted from basal omics
C_LI
]]></description>
<dc:creator>Gabor, A.</dc:creator>
<dc:creator>Tognetti, M.</dc:creator>
<dc:creator>Driessen, A.</dc:creator>
<dc:creator>Tanevski, J.</dc:creator>
<dc:creator>Guo, B.</dc:creator>
<dc:creator>Cao, W.</dc:creator>
<dc:creator>Shen, H.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Chung, V.</dc:creator>
<dc:creator>Single Cell Signaling in Breast Cancer DREAM Consortium,</dc:creator>
<dc:creator>Bodenmiller, B.</dc:creator>
<dc:creator>Saez-Rodriguez, J.</dc:creator>
<dc:date>2021-03-23</dc:date>
<dc:identifier>doi:10.1101/2021.03.23.436603</dc:identifier>
<dc:title><![CDATA[Cell-to-cell and type-to-type heterogeneity of signaling networks: Insights from the crowd]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2021-03-23</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/2020.07.21.214205v1?rss=1">
<title>
<![CDATA[
DreamAI: algorithm for the imputation of proteomics data 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/2020.07.21.214205v1?rss=1"
</link>
<description><![CDATA[
Deep proteomics profiling using labeled LC-MS/MS experiments has been proven to be powerful to study complex diseases. However, due to the dynamic nature of the discovery mass spectrometry, the generated data contain a substantial fraction of missing values. This poses great challenges for data analyses, as many tools, especially those for high dimensional data, cannot deal with missing values directly. To address this problem, the NCI-CPTAC Proteogenomics DREAM Challenge was carried out to develop effective imputation algorithms for labeled LC-MS/MS proteomics data through crowd learning. The final resulting algorithm, DreamAI, is based on an ensemble of six different imputation methods. The imputation accuracy of DreamAI, as measured by Pearson correlation, is about 15%-50% greater than existing tools among less abundant proteins, which are more vulnerable to be missed in proteomics data sets. This new tool notably enhances data analysis capabilities in proteomics research.
]]></description>
<dc:creator>ma, w.</dc:creator>
<dc:creator>Kim, S.</dc:creator>
<dc:creator>Chowdhury, S.</dc:creator>
<dc:creator>li, z.</dc:creator>
<dc:creator>YANG, M.</dc:creator>
<dc:creator>Yoo, S.</dc:creator>
<dc:creator>Petralia, F.</dc:creator>
<dc:creator>Jacobsen, J.</dc:creator>
<dc:creator>Li, J. J.</dc:creator>
<dc:creator>Ge, X.</dc:creator>
<dc:creator>Li, K.</dc:creator>
<dc:creator>Yu, T.</dc:creator>
<dc:creator>Edwards, N. J.</dc:creator>
<dc:creator>Payne, S.</dc:creator>
<dc:creator>Boutros, P. C.</dc:creator>
<dc:creator>Rodriguez, H.</dc:creator>
<dc:creator>Stolovitzky, G. A.</dc:creator>
<dc:creator>Kang, J.</dc:creator>
<dc:creator>Fenyo, D.</dc:creator>
<dc:creator>Saez, J.</dc:creator>
<dc:creator>Wang, P.</dc:creator>
<dc:date>2020-07-22</dc:date>
<dc:identifier>doi:10.1101/2020.07.21.214205</dc:identifier>
<dc:title><![CDATA[DreamAI: algorithm for the imputation of proteomics data]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2020-07-22</prism:publicationDate>
<prism:section></prism:section>
</item>
<item rdf:about="https://biorxiv.org/cgi/content/short/310425v1?rss=1">
<title>
<![CDATA[
Creating Standards for Evaluating Tumour Subclonal Reconstruction 
]]>
</title>
<link>
https://biorxiv.org/cgi/content/short/310425v1?rss=1"
</link>
<description><![CDATA[
Tumours evolve through time and space. Computational techniques have been developed to infer their evolutionary dynamics from DNA sequencing data. A growing number of studies have used these approaches to link molecular cancer evolution to clinical progression and response to therapy. There has not yet been a systematic evaluation of methods for reconstructing tumour subclonality, in part due to the underlying mathematical and biological complexity and to difficulties in creating gold-standards. To fill this gap, we systematically elucidated the key algorithmic problems in subclonal reconstruction and developed mathematically valid quantitative metrics for evaluating them. We then created approaches to simulate realistic tumour genomes, harbouring all known mutation types and processes both clonally and subclonally. We then simulated 580 tumour genomes for reconstruction, varying tumour read-depth and benchmarking somatic variant detection and subclonal reconstruction strategies. The inference of tumour phylogenies is rapidly becoming standard practice in cancer genome analysis; this study creates a baseline for its evaluation.
]]></description>
<dc:creator>Boutros, P. C.</dc:creator>
<dc:creator>Salcedo, A.</dc:creator>
<dc:creator>Tarabichi, M.</dc:creator>
<dc:creator>Espiritu, S. M. G.</dc:creator>
<dc:creator>Deshwar, A. G.</dc:creator>
<dc:creator>David, M.</dc:creator>
<dc:creator>Wilson, N. M.</dc:creator>
<dc:creator>Dentro, S.</dc:creator>
<dc:creator>Wintersinger, J. A.</dc:creator>
<dc:creator>Liu, L. Y.</dc:creator>
<dc:creator>Ko, M.</dc:creator>
<dc:creator>Sivanandan, S.</dc:creator>
<dc:creator>Zhang, H.</dc:creator>
<dc:creator>Zhu, K.</dc:creator>
<dc:creator>Yang, T.-H.</dc:creator>
<dc:creator>Chilton, J. M.</dc:creator>
<dc:creator>Buchanan, A.</dc:creator>
<dc:creator>Lalansingh, C. M.</dc:creator>
<dc:creator>P'ng, C.</dc:creator>
<dc:creator>Anghel, C. V.</dc:creator>
<dc:creator>Umar, I.</dc:creator>
<dc:creator>Lo, B.</dc:creator>
<dc:creator>Simpson, J. T.</dc:creator>
<dc:creator>Stuart, J. M.</dc:creator>
<dc:creator>Anastassiou, D.</dc:creator>
<dc:creator>Guan, Y.</dc:creator>
<dc:creator>Ewing, A.</dc:creator>
<dc:creator>Ellrott, K.</dc:creator>
<dc:creator>Wedge, D. C.</dc:creator>
<dc:creator>Morris, Q. D.</dc:creator>
<dc:creator>Van Loo, P.</dc:creator>
<dc:creator>DREAM SMC-Het Participants,</dc:creator>
<dc:date>2018-04-28</dc:date>
<dc:identifier>doi:10.1101/310425</dc:identifier>
<dc:title><![CDATA[Creating Standards for Evaluating Tumour Subclonal Reconstruction]]></dc:title>
<dc:publisher>Cold Spring Harbor Laboratory Press</dc:publisher>
<prism:publicationDate>2018-04-28</prism:publicationDate>
<prism:section></prism:section>
</item>
</rdf:RDF>
