[ { "key": "7JQSU965", "version": 40, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/7JQSU965", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/7JQSU965", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/CUB9EDIE", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "7JQSU965", "version": 40, "parentItem": "CUB9EDIE", "itemType": "attachment", "linkMode": "imported_url", "title": "IEEE Xplore Abstract Record", "accessDate": "2017-08-03T08:53:27Z", "url": "http://ieeexplore.ieee.org/abstract/document/5767938/", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "5767938.html", "md5": "8f09ed1898418068edffd19e3338cdcb", "mtime": 1501750407000, "tags": [], "relations": {}, "dateAdded": "2017-08-03T08:53:27Z", "dateModified": "2017-08-03T08:53:27Z" } }, { "key": "CUB9EDIE", "version": 39, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/CUB9EDIE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/CUB9EDIE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Dou et al.", "parsedDate": "2011-04", "numChildren": 1 }, "data": { "key": "CUB9EDIE", "version": 39, "itemType": "conferencePaper", "title": "Scientific workflow design 2.0: Demonstrating streaming data collections in Kepler", "creators": [ { "creatorType": "author", "firstName": "L.", "lastName": "Dou" }, { "creatorType": "author", "firstName": "D.", "lastName": "Zinn" }, { "creatorType": "author", "firstName": "T.", "lastName": "McPhillips" }, { "creatorType": "author", "firstName": "S.", "lastName": "Köhler" }, { "creatorType": "author", "firstName": "S.", "lastName": "Riddle" }, { "creatorType": "author", "firstName": "S.", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "B.", "lastName": "Ludäscher" } ], "abstractNote": "Scientific workflow systems are used to integrate existing software components (actors) into larger analysis pipelines to perform in silico experiments. Current approaches for handling data in nested-collection structures, as required in many scientific domains, lead to many record-management actors (shims) that make the workflow structure overly complex, and as a consequence hard to construct, evolve and maintain. By constructing and executing workflows from bioinformatics and geosciences in the Kepler system, we will demonstrate how COMAD (Collection-Oriented Modeling and Design), an extension of conventional workflow design, addresses these shortcomings. In particular, COMAD provides a hierarchical data stream model (as in XML) and a novel declarative configuration language for actors that functions as a middleware layer between the workflow's data model (streaming nested collections) and the actor's data model (base data and lists thereof). Our approach allows actor developers to focus on the internal actor processing logic oblivious to the workflow structure. Actors can then be re-used in various workflows simply by adapting actor configurations. Due to streaming nested collections and declarative configurations, COMAD workflows can usually be realized as linear data processing pipelines, which often reflect the scientific data analysis intention better than conventional designs. This linear structure not only simplifies actor insertions and deletions (workflow evolution), but also decreases the overall complexity of the workflow, reducing future effort in maintenance.", "proceedingsTitle": "2011 IEEE 27th International Conference on Data Engineering", "conferenceName": "2011 IEEE 27th International Conference on Data Engineering", "publisher": "", "place": "", "date": "April 2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1296-1299", "series": "", "seriesNumber": "", "DOI": "10.1109/ICDE.2011.5767938", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Scientific workflow design 2.0", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Assembly", "type": 1 }, { "tag": "COMAD", "type": 1 }, { "tag": "Collection-Oriented Modeling and Design", "type": 1 }, { "tag": "Data models", "type": 1 }, { "tag": "Humidity", "type": 1 }, { "tag": "Middleware", "type": 1 }, { "tag": "Phylogeny", "type": 1 }, { "tag": "XML", "type": 1 }, { "tag": "bioinformatics", "type": 1 }, { "tag": "data analysis", "type": 1 }, { "tag": "data collection", "type": 1 }, { "tag": "hierarchical data stream model", "type": 1 }, { "tag": "internal actor processing", "type": 1 }, { "tag": "record management", "type": 1 }, { "tag": "records management", "type": 1 }, { "tag": "scientific workflow design", "type": 1 }, { "tag": "software component", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2017-08-03T08:53:16Z", "dateModified": "2017-08-03T08:53:16Z" } }, { "key": "EJVRDBMW", "version": 38, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/EJVRDBMW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/EJVRDBMW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Davidson et al.", "parsedDate": "2007-12-22", "numChildren": 0 }, "data": { "key": "EJVRDBMW", "version": 38, "itemType": "journalArticle", "title": "Provenance in Scientific Workflow Systems.", "creators": [ { "creatorType": "author", "firstName": "Susan B.", "lastName": "Davidson" }, { "creatorType": "author", "firstName": "Sarah Cohen", "lastName": "Boulakia" }, { "creatorType": "author", "firstName": "Anat", "lastName": "Eyal" }, { "creatorType": "author", "firstName": "Bertram", "lastName": "Ludäscher" }, { "creatorType": "author", "firstName": "Timothy M.", "lastName": "McPhillips" }, { "creatorType": "author", "firstName": "Shawn", "lastName": "Bowers" }, { "creatorType": "author", "firstName": "Manish Kumar", "lastName": "Anand" }, { "creatorType": "author", "firstName": "Juliana", "lastName": "Freire" } ], "abstractNote": "", "publicationTitle": "IEEE Data Eng. Bull.", "publisher": "", "place": "", "date": "2007-12-22", "volume": "30", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "44-50", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://dblp.uni-trier.de/db/journals/debu/debu30.html#DavidsonBELMBAF07", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "kepler keplerworkflow mypubs provenance workflow" } ], "collections": [], "relations": {}, "dateAdded": "2017-08-03T08:18:30Z", "dateModified": "2017-08-03T08:18:30Z" } }, { "key": "593WVSWR", "version": 37, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/593WVSWR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/593WVSWR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Davidson and Freire", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "593WVSWR", "version": 37, "itemType": "conferencePaper", "title": "Provenance and Scientific Workflows: Challenges and Opportunities", "creators": [ { "creatorType": "author", "firstName": "Susan B.", "lastName": "Davidson" }, { "creatorType": "author", "firstName": "Juliana", "lastName": "Freire" } ], "abstractNote": "Provenance in the context of workflows, both for the data they derive and for their specification, is an essential component to allow for result reproducibility, sharing, and knowledge re-use in the scientific community. Several workshops have been held on the topic, and it has been the focus of many research projects and prototype systems. This tutorial provides an overview of research issues in provenance for scientific workflows, with a focus on recent literature and technology in this area. It is aimed at a general database research audience and at people who work with scientific data and workflows. We will (1) provide a general overview of scientific workflows, (2) describe research on provenance for scientific workflows and show in detail how provenance is supported in existing systems; (3) discuss emerging applications that are enabled by provenance; and (4) outline open problems and new directions for database-related research.", "proceedingsTitle": "Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1345–1350", "series": "SIGMOD '08", "seriesNumber": "", "DOI": "10.1145/1376616.1376772", "ISBN": "978-1-60558-102-6", "citationKey": "", "url": "http://doi.acm.org/10.1145/1376616.1376772", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Provenance and Scientific Workflows", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "provenance", "type": 1 }, { "tag": "scientific workflows", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2017-08-03T08:17:04Z", "dateModified": "2017-08-03T08:17:04Z" } }, { "key": "DUGI79PG", "version": 41, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/DUGI79PG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/DUGI79PG", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Giardine et al.", "parsedDate": "2005-10", "numChildren": 3 }, "data": { "key": "DUGI79PG", "version": 41, "itemType": "journalArticle", "title": "Galaxy: A platform for interactive large-scale genome analysis", "creators": [ { "creatorType": "author", "firstName": "Belinda", "lastName": "Giardine" }, { "creatorType": "author", "firstName": "Cathy", "lastName": "Riemer" }, { "creatorType": "author", "firstName": "Ross C.", "lastName": "Hardison" }, { "creatorType": "author", "firstName": "Richard", "lastName": "Burhans" }, { "creatorType": "author", "firstName": "Laura", "lastName": "Elnitski" }, { "creatorType": "author", "firstName": "Prachi", "lastName": "Shah" }, { "creatorType": "author", "firstName": "Yi", "lastName": "Zhang" }, { "creatorType": "author", "firstName": "Daniel", "lastName": "Blankenberg" }, { "creatorType": "author", "firstName": "Istvan", "lastName": "Albert" }, { "creatorType": "author", "firstName": "James", "lastName": "Taylor" }, { "creatorType": "author", "firstName": "Webb", "lastName": "Miller" }, { "creatorType": "author", "firstName": "W. James", "lastName": "Kent" }, { "creatorType": "author", "firstName": "Anton", "lastName": "Nekrutenko" } ], "abstractNote": "Accessing and analyzing the exponentially expanding genomic sequence and functional data pose a challenge for biomedical researchers. Here we describe an interactive system, Galaxy, that combines the power of existing genome annotation databases with a simple Web portal to enable users to search remote resources, combine data from independent queries, and visualize the results. The heart of Galaxy is a flexible history system that stores the queries from each user; performs operations such as intersections, unions, and subtractions; and links to other computational tools. Galaxy can be accessed at http://g2.bx.psu.edu.", "publicationTitle": "Genome Research", "publisher": "", "place": "", "date": "Oct 2005", "volume": "15", "issue": "10", "section": "", "partNumber": "", "partTitle": "", "pages": "1451-1455", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Genome Res.", "DOI": "10.1101/gr.4086505", "citationKey": "", "url": "http://genome.cshlp.org/content/15/10/1451", "accessDate": "2015-07-04T19:18:35Z", "PMID": "16169926", "PMCID": "", "ISSN": "1088-9051, 1549-5469", "archive": "", "archiveLocation": "", "shortTitle": "Galaxy", "language": "en", "libraryCatalog": "genome.cshlp.org", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "F233BVGZ" ], "relations": {}, "dateAdded": "2015-10-13T12:56:13Z", "dateModified": "2016-03-29T11:33:08Z" } }, { "key": "CPED9ICK", "version": 29, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/CPED9ICK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/CPED9ICK", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/4H5MA82H", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "CPED9ICK", "version": 29, "parentItem": "4H5MA82H", "itemType": "attachment", "linkMode": "imported_url", "title": "Full Text PDF", "accessDate": "2015-12-14T20:19:40Z", "url": "http://journal.frontiersin.org/article/10.3389/fninf.2011.00013/pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Gorgolewski et al. - 2011 - Nipype a flexible, lightweight and extensible neu.pdf", "md5": "8a3f2fd44fe375a7d9aff62973e03b0c", "mtime": 1450124387000, "tags": [], "relations": {}, "dateAdded": "2015-12-14T20:19:40Z", "dateModified": "2015-12-14T20:19:47Z" } }, { "key": "4H5MA82H", "version": 28, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/4H5MA82H", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/4H5MA82H", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Gorgolewski et al.", "parsedDate": "2011", "numChildren": 1 }, "data": { "key": "4H5MA82H", "version": 28, "itemType": "journalArticle", "title": "Nipype: a flexible, lightweight and extensible neuroimaging data processing framework in Python", "creators": [ { "creatorType": "author", "firstName": "Krzysztof", "lastName": "Gorgolewski" }, { "creatorType": "author", "firstName": "Christopher D.", "lastName": "Burns" }, { "creatorType": "author", "firstName": "Cindee", "lastName": "Madison" }, { "creatorType": "author", "firstName": "Dav", "lastName": "Clark" }, { "creatorType": "author", "firstName": "Yaroslav O.", "lastName": "Halchenko" }, { "creatorType": "author", "firstName": "Michael L.", "lastName": "Waskom" }, { "creatorType": "author", "firstName": "Satrajit S.", "lastName": "Ghosh" } ], "abstractNote": "Current neuroimaging software offer users an incredible opportunity to analyze their data in different ways, with different underlying assumptions. Several sophisticated software packages (e.g., AFNI, BrainVoyager, FSL, FreeSurfer, Nipy, R, SPM) are used to process and analyze large and often diverse (highly multi-dimensional) data. However, this heterogeneous collection of specialized applications creates several issues that hinder replicable, efficient, and optimal use of neuroimaging analysis approaches: (1) No uniform access to neuroimaging analysis software and usage information; (2) No framework for comparative algorithm development and dissemination; (3) Personnel turnover in laboratories often limits methodological continuity and training new personnel takes time; (4) Neuroimaging software packages do not address computational efficiency; and (5) Methods sections in journal articles are inadequate for reproducing results. To address these issues, we present Nipype (Neuroimaging in Python: Pipelines and Interfaces; http://nipy.org/nipype), an open-source, community-developed, software package, and scriptable library. Nipype solves the issues by providing Interfaces to existing neuroimaging software with uniform usage semantics and by facilitating interaction between these packages using Workflows. Nipype provides an environment that encourages interactive exploration of algorithms, eases the design of Workflows within and between packages, allows rapid comparative development of algorithms and reduces the learning curve necessary to use different packages. Nipype supports both local and remote execution on multi-core machines and clusters, without additional scripting. Nipype is Berkeley Software Distribution licensed, allowing anyone unrestricted usage. An open, community-driven development philosophy allows the software to quickly adapt and address the varied needs of the evolving neuroimaging community, especially in the context of increasing demand for reproducible research.", "publicationTitle": "Frontiers in Neuroinformatics", "publisher": "", "place": "", "date": "2011", "volume": "5", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "13", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Front. Neuroinform.", "DOI": "10.3389/fninf.2011.00013", "citationKey": "", "url": "http://journal.frontiersin.org/article/10.3389/fninf.2011.00013/full", "accessDate": "2015-12-14T20:19:40Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Nipype", "language": "", "libraryCatalog": "Frontiers", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Python", "type": 1 }, { "tag": "data processing", "type": 1 }, { "tag": "neuroimaging", "type": 1 }, { "tag": "pipeline", "type": 1 }, { "tag": "reproducible research", "type": 1 }, { "tag": "workflow", "type": 1 } ], "collections": [ "XZIVK678" ], "relations": {}, "dateAdded": "2015-12-14T20:19:40Z", "dateModified": "2015-12-14T20:19:40Z" } }, { "key": "QS5ESPGU", "version": 27, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/QS5ESPGU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/QS5ESPGU", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/DRIBIG3Z", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "QS5ESPGU", "version": 27, "parentItem": "DRIBIG3Z", "itemType": "attachment", "linkMode": "linked_url", "title": "omicsOnline_NOW_153-0602-5-159.pdf", "accessDate": "2015-11-18T10:47:12Z", "url": "https://www.dropbox.com/s/6w6rcn18wakzm3b/omicsOnline_NOW_153-0602-5-159.pdf?dl=1", "note": "", "contentType": "application/pdf", "charset": "", "tags": [], "relations": {}, "dateAdded": "2015-11-18T10:47:12Z", "dateModified": "2015-11-18T10:47:12Z" } }, { "key": "E29W6IF2", "version": 26, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/E29W6IF2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/E29W6IF2", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/DRIBIG3Z", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "E29W6IF2", "version": 26, "parentItem": "DRIBIG3Z", "itemType": "attachment", "linkMode": "imported_url", "title": "\"Node-Oriented Workflow (NOW): A Command Template Workflow Management T\" by Eric B. Lipsky, Brian R. King et al.", "accessDate": "2015-11-18T10:45:26Z", "url": "http://digitalcommons.bucknell.edu/fac_journ/1022/", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "1022.html", "md5": "d19e333aa09235bfa99dfbf0eb29ebf3", "mtime": 1447843526000, "tags": [], "relations": {}, "dateAdded": "2015-11-18T10:45:26Z", "dateModified": "2015-11-18T10:45:26Z" } }, { "key": "DRIBIG3Z", "version": 24, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/DRIBIG3Z", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/DRIBIG3Z", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Lipsky et al.", "parsedDate": "2014-06-30", "numChildren": 2 }, "data": { "key": "DRIBIG3Z", "version": 24, "itemType": "journalArticle", "title": "Node-Oriented Workflow (NOW): A Command Template Workflow Management Tool for High Throughput Data Analysis Pipelines", "creators": [ { "creatorType": "author", "firstName": "Eric", "lastName": "Lipsky" }, { "creatorType": "author", "firstName": "Brian", "lastName": "King" }, { "creatorType": "author", "firstName": "Gerard", "lastName": "Tromp" } ], "abstractNote": "", "publicationTitle": "Journal of Data Mining in Genomics & Proteomics", "publisher": "", "place": "", "date": "2014-06-30", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://digitalcommons.bucknell.edu/fac_journ/1022", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Node-Oriented Workflow (NOW)", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "XZIVK678" ], "relations": {}, "dateAdded": "2015-11-18T10:45:21Z", "dateModified": "2015-11-18T10:45:21Z" } }, { "key": "9FC73FQU", "version": 22, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/9FC73FQU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/9FC73FQU", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/7SB9KAMQ", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "9FC73FQU", "version": 22, "parentItem": "7SB9KAMQ", "itemType": "attachment", "linkMode": "imported_file", "title": "0503025.pdf", "accessDate": "", "url": "", "note": "", "contentType": "application/pdf", "charset": "", "filename": "0503025.pdf", "md5": "e69bb2e51aba73fd4d2a88285676537e", "mtime": 1445028757000, "tags": [], "relations": {}, "dateAdded": "2015-10-16T20:52:37Z", "dateModified": "2015-10-16T20:52:40Z" } }, { "key": "U5SH24ZU", "version": 19, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/U5SH24ZU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/U5SH24ZU", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/5394NK65", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "U5SH24ZU", "version": 19, "parentItem": "5394NK65", "itemType": "attachment", "linkMode": "imported_file", "title": "sciflow2006.pdf", "accessDate": "", "url": "", "note": "", "contentType": "application/pdf", "charset": "", "filename": "sciflow2006.pdf", "md5": "c461fe5ebd24d499b907ba75a2fcad8a", "mtime": 1445028512000, "tags": [], "relations": {}, "dateAdded": "2015-10-16T20:48:32Z", "dateModified": "2015-10-16T20:48:38Z" } }, { "key": "SRIRBNU3", "version": 19, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/SRIRBNU3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/SRIRBNU3", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/5394NK65", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "SRIRBNU3", "version": 19, "parentItem": "5394NK65", "itemType": "attachment", "linkMode": "imported_url", "title": "IEEE Xplore Abstract Record", "accessDate": "2015-10-16T20:48:06Z", "url": "http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=1623866&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D1623866", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "login.html", "md5": "f6dd5ae95cd0beaf46adfe74b06a5d0e", "mtime": 1445028487000, "tags": [], "relations": {}, "dateAdded": "2015-10-16T20:48:06Z", "dateModified": "2015-10-16T20:48:06Z" } }, { "key": "5394NK65", "version": 17, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/5394NK65", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/5394NK65", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Callahan et al.", "parsedDate": "2006", "numChildren": 2 }, "data": { "key": "5394NK65", "version": 17, "itemType": "conferencePaper", "title": "Managing the Evolution of Dataflows with VisTrails", "creators": [ { "creatorType": "author", "firstName": "S.P.", "lastName": "Callahan" }, { "creatorType": "author", "firstName": "J.", "lastName": "Freire" }, { "creatorType": "author", "firstName": "J.", "lastName": "Freire" }, { "creatorType": "author", "firstName": "E.", "lastName": "Santos" }, { "creatorType": "author", "firstName": "C.E.", "lastName": "Scheidegger" }, { "creatorType": "author", "firstName": "C.T.", "lastName": "Silva" }, { "creatorType": "author", "firstName": "H.T.", "lastName": "Vo" } ], "abstractNote": "Scientists are now faced with an incredible volume of data to analyze. To successfully analyze and validate various hypotheses, it is necessary to pose several queries, correlate disparate data, and create insightful visualizations of both the simulated processes and observed phenomena. Data exploration through visualization requires scientists to go through several steps. In essence, they need to assemble complex workflows that consist of dataset selection, specification of series of operations that need to be applied to the data, and the creation of appropriate visual representations, before they can finally view and analyze the results. Often, insight comes from comparing the results of multiple visualizations that are created during the data exploration process.", "proceedingsTitle": "22nd International Conference on Data Engineering Workshops, 2006. Proceedings", "conferenceName": "22nd International Conference on Data Engineering Workshops, 2006. Proceedings", "publisher": "", "place": "", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "71-71", "series": "", "seriesNumber": "", "DOI": "10.1109/ICDEW.2006.75", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Analytical models", "type": 1 }, { "tag": "Assembly systems", "type": 1 }, { "tag": "Data visualization", "type": 1 }, { "tag": "History", "type": 1 }, { "tag": "Navigation", "type": 1 }, { "tag": "Pipelines", "type": 1 }, { "tag": "Software libraries", "type": 1 }, { "tag": "data analysis", "type": 1 } ], "collections": [ "NBTPSBFJ" ], "relations": {}, "dateAdded": "2015-10-16T20:48:00Z", "dateModified": "2015-10-16T20:48:00Z" } }, { "key": "BZPE358T", "version": 15, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/BZPE358T", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/BZPE358T", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/28WN2MDB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "BZPE358T", "version": 15, "parentItem": "28WN2MDB", "itemType": "attachment", "linkMode": "imported_file", "title": "1303.7195.pdf", "accessDate": "", "url": "", "note": "", "contentType": "application/pdf", "charset": "", "filename": "1303.7195.pdf", "md5": "a42807e00cd854ffaf9f078f8243e3ed", "mtime": 1444937393000, "tags": [], "relations": {}, "dateAdded": "2015-10-15T19:29:53Z", "dateModified": "2015-10-15T19:29:58Z" } }, { "key": "Z4QIFCKQ", "version": 13, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/Z4QIFCKQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/Z4QIFCKQ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/QB89K94A", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "Z4QIFCKQ", "version": 13, "parentItem": "QB89K94A", "itemType": "attachment", "linkMode": "imported_url", "title": "Full Text PDF", "accessDate": "2015-10-15T19:24:05Z", "url": "http://bib.oxfordjournals.org/content/9/1/57.full.pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Romano - 2008 - Automation of in-silico data analysis processes th.pdf", "md5": "10e8c7bfccb8890b896e0f5ff2664803", "mtime": 1444937054000, "tags": [], "relations": {}, "dateAdded": "2015-10-15T19:24:05Z", "dateModified": "2015-10-15T19:24:14Z" } }, { "key": "2AF8AZNB", "version": 13, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/2AF8AZNB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/2AF8AZNB", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/QB89K94A", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "2AF8AZNB", "version": 13, "parentItem": "QB89K94A", "itemType": "attachment", "linkMode": "imported_url", "title": "Snapshot", "accessDate": "2015-10-15T19:24:12Z", "url": "http://bib.oxfordjournals.org/content/9/1/57.full", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "57.html", "md5": "e508ddaabf0c5a9dab7bd73f335a8287", "mtime": 1444937053000, "tags": [], "relations": {}, "dateAdded": "2015-10-15T19:24:12Z", "dateModified": "2015-10-15T19:24:12Z" } }, { "key": "QB89K94A", "version": 41, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/QB89K94A", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/QB89K94A", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Romano", "parsedDate": "2008-01-01", "numChildren": 3 }, "data": { "key": "QB89K94A", "version": 41, "itemType": "journalArticle", "title": "Automation of in-silico data analysis processes through workflow management systems", "creators": [ { "creatorType": "author", "firstName": "Paolo", "lastName": "Romano" } ], "abstractNote": "Data integration is needed in order to cope with the huge amounts of biological information now available and to perform data mining effectively. Current data integration systems have strict limitations, mainly due to the number of resources, their size and frequency of updates, their heterogeneity and distribution on the Internet. Integration must therefore be achieved by accessing network services through flexible and extensible data integration and analysis network tools. EXtensible Markup Language (XML), Web Services and Workflow Management Systems (WMS) can support the creation and deployment of such systems. Many XML languages and Web Services for bioinformatics have already been designed and implemented and some WMS have been proposed. In this article, we review a methodology for data integration in biomedical research that is based on these technologies. We also briefly describe some of the available WMS and discuss the current limitations of this methodology and the ways in which they can be overcome.", "publicationTitle": "Briefings in Bioinformatics", "publisher": "", "place": "", "date": "01/01/2008", "volume": "9", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "57-68", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Brief Bioinform", "DOI": "10.1093/bib/bbm056", "citationKey": "", "url": "http://bib.oxfordjournals.org/content/9/1/57", "accessDate": "2015-10-15T19:24:05Z", "PMID": "18056132", "PMCID": "", "ISSN": "1467-5463, 1477-4054", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "bib.oxfordjournals.org", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "XML", "type": 1 }, { "tag": "automation of retrieval and analysis processes", "type": 1 }, { "tag": "biological data integration", "type": 1 }, { "tag": "ontologies", "type": 1 }, { "tag": "web services", "type": 1 }, { "tag": "workflow management systems", "type": 1 } ], "collections": [ "8T29XIKZ" ], "relations": {}, "dateAdded": "2015-10-15T19:24:05Z", "dateModified": "2015-10-15T19:24:05Z" } }, { "key": "F8IAKW2P", "version": 12, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/F8IAKW2P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/F8IAKW2P", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/QB89K94A", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "F8IAKW2P", "version": 12, "parentItem": "QB89K94A", "itemType": "attachment", "linkMode": "linked_url", "title": "PubMed entry", "accessDate": "2015-10-15T19:24:05Z", "url": "http://www.ncbi.nlm.nih.gov/pubmed/18056132", "note": "", "contentType": "text/html", "charset": "", "tags": [], "relations": {}, "dateAdded": "2015-10-15T19:24:05Z", "dateModified": "2015-10-15T19:24:05Z" } }, { "key": "28WN2MDB", "version": 11, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/28WN2MDB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/28WN2MDB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Bux and Leser", "parsedDate": "2013", "numChildren": 1 }, "data": { "key": "28WN2MDB", "version": 11, "itemType": "journalArticle", "title": "Parallelization in scientific workflow management systems", "creators": [ { "creatorType": "author", "firstName": "Marc", "lastName": "Bux" }, { "creatorType": "author", "firstName": "Ulf", "lastName": "Leser" } ], "abstractNote": "", "publicationTitle": "arXiv preprint arXiv:1303.7195", "publisher": "", "place": "", "date": "2013", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "8T29XIKZ" ], "relations": {}, "dateAdded": "2015-10-15T19:21:57Z", "dateModified": "2015-10-15T19:21:57Z" } }, { "key": "5X9RQ72K", "version": 10, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/5X9RQ72K", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/5X9RQ72K", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/9BT2NJB6", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "5X9RQ72K", "version": 10, "parentItem": "9BT2NJB6", "itemType": "attachment", "linkMode": "imported_url", "title": "Snapshot", "accessDate": "2015-10-15T09:57:26Z", "url": "http://www.biologydirect.com/content/10/1/43", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "43.html", "md5": "cb20068eefa101e69c9aeb5cafbd141c", "mtime": 1444903048000, "tags": [], "relations": {}, "dateAdded": "2015-10-15T09:57:26Z", "dateModified": "2015-10-15T09:57:26Z" } }, { "key": "X6FE742K", "version": 10, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/X6FE742K", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/X6FE742K", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/9BT2NJB6", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "X6FE742K", "version": 10, "parentItem": "9BT2NJB6", "itemType": "attachment", "linkMode": "imported_url", "title": "Full Text PDF", "accessDate": "2015-10-15T09:57:18Z", "url": "http://www.biologydirect.com/content/pdf/s13062-015-0071-8.pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Spjuth et al. - 2015 - Experiences with workflows for automating data-int.pdf", "md5": "4ec2ab498f7d4aaec70ecae66a3a45b3", "mtime": 1444903042000, "tags": [], "relations": {}, "dateAdded": "2015-10-15T09:57:18Z", "dateModified": "2015-10-15T09:57:22Z" } }, { "key": "9BT2NJB6", "version": 41, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/9BT2NJB6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/9BT2NJB6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Spjuth et al.", "parsedDate": "2015-08-19", "numChildren": 2 }, "data": { "key": "9BT2NJB6", "version": 41, "itemType": "journalArticle", "title": "Experiences with workflows for automating data-intensive bioinformatics", "creators": [ { "creatorType": "author", "firstName": "Ola", "lastName": "Spjuth" }, { "creatorType": "author", "firstName": "Erik", "lastName": "Bongcam-Rudloff" }, { "creatorType": "author", "firstName": "Guillermo C.", "lastName": "Hernández" }, { "creatorType": "author", "firstName": "Lukas", "lastName": "Forer" }, { "creatorType": "author", "firstName": "Mario", "lastName": "Giovacchini" }, { "creatorType": "author", "firstName": "Roman V.", "lastName": "Guimera" }, { "creatorType": "author", "firstName": "Aleksi", "lastName": "Kallio" }, { "creatorType": "author", "firstName": "Eija", "lastName": "Korpelainen" }, { "creatorType": "author", "firstName": "Maciej M.", "lastName": "Kańduła" }, { "creatorType": "author", "firstName": "Milko", "lastName": "Krachunov" }, { "creatorType": "author", "firstName": "David P.", "lastName": "Kreil" }, { "creatorType": "author", "firstName": "Ognyan", "lastName": "Kulev" }, { "creatorType": "author", "firstName": "Paweł P.", "lastName": "Łabaj" }, { "creatorType": "author", "firstName": "Samuel", "lastName": "Lampa" }, { "creatorType": "author", "firstName": "Luca", "lastName": "Pireddu" }, { "creatorType": "author", "firstName": "Sebastian", "lastName": "Schönherr" }, { "creatorType": "author", "firstName": "Alexey", "lastName": "Siretskiy" }, { "creatorType": "author", "firstName": "Dimitar", "lastName": "Vassilev" } ], "abstractNote": "High-throughput technologies, such as next-generation sequencing, have turned molecular biology into a data-intensive discipline, requiring bioinformaticians to use high-performance computing resources and carry out data management and analysis tasks on large scale. Workflow systems can be useful to simplify construction of analysis pipelines that automate tasks, support reproducibility and provide measures for fault-tolerance. However, workflow systems can incur significant development and administration overhead so bioinformatics pipelines are often still built without them. We present the experiences with workflows and workflow systems within the bioinformatics community participating in a series of hackathons and workshops of the EU COST action SeqAhead. The organizations are working on similar problems, but we have addressed them with different strategies and solutions. This fragmentation of efforts is inefficient and leads to redundant and incompatible solutions. Based on our experiences we define a set of recommendations for future systems to enable efficient yet simple bioinformatics workflow construction and execution.", "publicationTitle": "Biology Direct", "publisher": "", "place": "", "date": "2015-08-19", "volume": "10", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "43", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1186/s13062-015-0071-8", "citationKey": "", "url": "http://www.biologydirect.com/content/10/1/43/abstract", "accessDate": "2015-10-15T09:57:18Z", "PMID": "26282399", "PMCID": "", "ISSN": "1745-6150", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "www.biologydirect.com", "callNumber": "", "rights": "2015 Spjuth et al.", "extra": "", "tags": [ { "tag": "Automation", "type": 1 }, { "tag": "Big data", "type": 1 }, { "tag": "Data-intensive", "type": 1 }, { "tag": "High-performance computing", "type": 1 }, { "tag": "Reproducibility", "type": 1 }, { "tag": "workflow", "type": 1 } ], "collections": [ "8T29XIKZ" ], "relations": {}, "dateAdded": "2015-10-15T09:57:18Z", "dateModified": "2015-10-15T09:57:18Z" } }, { "key": "9PNK75F5", "version": 6, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/9PNK75F5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/9PNK75F5", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/325684/items/D6UHDZIT", "type": "application/json" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } } }, "data": { "key": "9PNK75F5", "version": 6, "parentItem": "D6UHDZIT", "itemType": "attachment", "linkMode": "linked_url", "title": "Falkon_SC07_v24.pdf", "accessDate": "2015-10-13T13:01:46Z", "url": "http://swift-lang.org/papers/pdfs/Falkon_SC07_v24.pdf", "note": "", "contentType": "application/pdf", "charset": "", "tags": [], "relations": {}, "dateAdded": "2015-10-13T13:01:46Z", "dateModified": "2015-10-13T13:01:46Z" } }, { "key": "D6UHDZIT", "version": 5, "library": { "type": "group", "id": 325684, "name": "ScientificWorkflowManagementSystems", "links": { "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/325684/items/D6UHDZIT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/scientificworkflowmanagementsystems/items/D6UHDZIT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 336891, "username": "pvanheus", "name": "Peter van Heusden", "links": { "alternate": { "href": "https://www.zotero.org/pvanheus", "type": "text/html" } } }, "creatorSummary": "Raicu et al.", "parsedDate": "2007", "numChildren": 1 }, "data": { "key": "D6UHDZIT", "version": 5, "itemType": "conferencePaper", "title": "Falkon: a Fast and Light-weight tasK executiON framework", "creators": [ { "creatorType": "author", "firstName": "Ioan", "lastName": "Raicu" }, { "creatorType": "author", "firstName": "Yong", "lastName": "Zhao" }, { "creatorType": "author", "firstName": "Catalin", "lastName": "Dumitrescu" }, { "creatorType": "author", "firstName": "Ian", "lastName": "Foster" }, { "creatorType": "author", "firstName": "Mike", "lastName": "Wilde" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 2007 ACM/IEEE conference on Supercomputing", "conferenceName": "", "publisher": "ACM", "place": "", "date": "2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "43", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "KHWA7Z9V" ], "relations": {}, "dateAdded": "2015-10-13T13:01:24Z", "dateModified": "2015-10-13T13:01:24Z" } } ]