[ { "key": "TW59BJ7W", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/TW59BJ7W", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/TW59BJ7W", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Chovancová et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "TW59BJ7W", "version": 1, "itemType": "journalArticle", "title": "Phylogenetic analysis of haloalkane dehalogenases", "creators": [ { "creatorType": "author", "firstName": "Eva", "lastName": "Chovancová" }, { "creatorType": "author", "firstName": "Jan", "lastName": "Kosinski" }, { "creatorType": "author", "firstName": "Janusz M.", "lastName": "Bujnicki" }, { "creatorType": "author", "firstName": "Jiří", "lastName": "Damborský" } ], "abstractNote": "", "publicationTitle": "Proteins: Structure, Function, and Bioinformatics", "publisher": "", "place": "", "date": "02/2007", "volume": "67", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "305-316", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Proteins", "DOI": "10.1002/prot.21313", "citationKey": "", "url": "file:///C:/tonik/rozbal/Phylogenetic%20analysis%20of%20haloalkane%20dehalogenases%20-%20Chovancov%C3%A1%20-%202007%20-%20Proteins%20%20Structure,%20Function,%20and%20Bioinformatics%20-%20Wiley%20Online%20Library.htm", "accessDate": "2011-08-30T10:56:06Z", "PMID": "", "PMCID": "", "ISSN": "08873585", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2011-08-30T10:56:06Z", "dateModified": "2011-08-30T10:56:06Z" } }, { "key": "UTIT3F3S", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/UTIT3F3S", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/UTIT3F3S", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Chovancová et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "UTIT3F3S", "version": 1, "itemType": "journalArticle", "title": "Phylogenetic analysis of haloalkane dehalogenases", "creators": [ { "creatorType": "author", "firstName": "Eva", "lastName": "Chovancová" }, { "creatorType": "author", "firstName": "Jan", "lastName": "Kosinski" }, { "creatorType": "author", "firstName": "Janusz M.", "lastName": "Bujnicki" }, { "creatorType": "author", "firstName": "Jiří", "lastName": "Damborský" } ], "abstractNote": "", "publicationTitle": "Proteins: Structure, Function, and Bioinformatics", "publisher": "", "place": "", "date": "02/2007", "volume": "67", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "305-316", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Proteins", "DOI": "10.1002/prot.21313", "citationKey": "", "url": "file:///C:/tonik/rozbal/Phylogenetic%20analysis%20of%20haloalkane%20dehalogenases%20-%20Chovancov%C3%A1%20-%202007%20-%20Proteins%20%20Structure,%20Function,%20and%20Bioinformatics%20-%20Wiley%20Online%20Library.htm", "accessDate": "2011-08-30T10:55:58Z", "PMID": "", "PMCID": "", "ISSN": "08873585", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2011-08-30T10:55:58Z", "dateModified": "2011-08-30T10:55:58Z" } }, { "key": "CW24AS7K", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/CW24AS7K", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/CW24AS7K", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/13757/items/CH4ZD9CC", "type": "application/json" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } } }, "data": { "key": "CW24AS7K", "version": 1, "parentItem": "CH4ZD9CC", "itemType": "attachment", "linkMode": "linked_url", "title": "HotSpot Wizard: a web server for identification of hot spots in protein engineering", "accessDate": "2011-08-26T10:11:09Z", "url": "http://nar.oxfordjournals.org/content/37/suppl_2/W376.abstract", "note": "", "contentType": "text/html", "charset": "", "tags": [], "relations": {}, "dateAdded": "2011-08-26T10:11:09Z", "dateModified": "2011-08-26T10:11:09Z" } }, { "key": "CH4ZD9CC", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/CH4ZD9CC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/CH4ZD9CC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Pavelka et al.", "parsedDate": "2009", "numChildren": 1 }, "data": { "key": "CH4ZD9CC", "version": 1, "itemType": "journalArticle", "title": "HotSpot Wizard: a web server for identification of hot spots in protein engineering", "creators": [ { "creatorType": "author", "firstName": "A.", "lastName": "Pavelka" }, { "creatorType": "author", "firstName": "E.", "lastName": "Chovancova" }, { "creatorType": "author", "firstName": "J.", "lastName": "Damborsky" } ], "abstractNote": "", "publicationTitle": "Nucleic Acids Research", "publisher": "", "place": "", "date": "05/2009", "volume": "37", "issue": "Web Server", "section": "", "partNumber": "", "partTitle": "", "pages": "W376-W383", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Nucleic Acids Research", "DOI": "10.1093/nar/gkp410", "citationKey": "", "url": "http://nar.oxfordjournals.org/content/37/suppl_2/W376.abstract", "accessDate": "2011-08-26T10:11:09Z", "PMID": "", "PMCID": "", "ISSN": "0305-1048", "archive": "", "archiveLocation": "", "shortTitle": "HotSpot Wizard", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "CT9IKJRE" ], "relations": {}, "dateAdded": "2011-08-26T10:11:09Z", "dateModified": "2011-08-26T10:11:09Z" } }, { "key": "N9TAENGV", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/N9TAENGV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/N9TAENGV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Ng and Henikoff", "parsedDate": "2001-05", "numChildren": 0 }, "data": { "key": "N9TAENGV", "version": 1, "itemType": "journalArticle", "title": "Predicting deleterious amino acid substitutions", "creators": [ { "creatorType": "author", "firstName": "P C", "lastName": "Ng" }, { "creatorType": "author", "firstName": "S", "lastName": "Henikoff" } ], "abstractNote": "Many missense substitutions are identified in single nucleotide polymorphism (SNP) data and large-scale random mutagenesis projects. Each amino acid substitution potentially affects protein function. We have constructed a tool that uses sequence homology to predict whether a substitution affects protein function. SIFT, which sorts intolerant from tolerant substitutions, classifies substitutions as tolerated or deleterious. A higher proportion of substitutions predicted to be deleterious by SIFT gives an affected phenotype than substitutions predicted to be deleterious by substitution scoring matrices in three test cases. Using SIFT before mutagenesis studies could reduce the number of functional assays required and yield a higher proportion of affected phenotypes. may be used to identify plausible disease candidates among the SNPs that cause missense substitutions.", "publicationTitle": "Genome Research", "publisher": "", "place": "", "date": "May 2001", "volume": "11", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "863-874", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Genome Res", "DOI": "10.1101/gr.176601", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/11337480", "accessDate": "2011-04-28T11:41:19Z", "PMID": "", "PMCID": "", "ISSN": "1088-9051", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 11337480", "tags": [ { "tag": "Amino Acid Sequence", "type": 1 }, { "tag": "Amino Acid Substitution", "type": 1 }, { "tag": "Bacterial Proteins", "type": 1 }, { "tag": "Bacteriophage T4", "type": 1 }, { "tag": "Computational Biology", "type": 1 }, { "tag": "Conserved Sequence", "type": 1 }, { "tag": "Escherichia coli Proteins", "type": 1 }, { "tag": "Genetic Diseases, Inborn", "type": 1 }, { "tag": "HIV Protease", "type": 1 }, { "tag": "HIV-1", "type": 1 }, { "tag": "Humans", "type": 1 }, { "tag": "Lac Repressors", "type": 1 }, { "tag": "Lactose", "type": 1 }, { "tag": "Molecular Sequence Data", "type": 1 }, { "tag": "Muramidase", "type": 1 }, { "tag": "Mutation, Missense", "type": 1 }, { "tag": "Phenotype", "type": 1 }, { "tag": "Probability", "type": 1 }, { "tag": "Repressor Proteins", "type": 1 }, { "tag": "Sequence Alignment", "type": 1 }, { "tag": "Software", "type": 1 } ], "collections": [ "CT9IKJRE" ], "relations": {}, "dateAdded": "2011-04-28T11:41:19Z", "dateModified": "2011-04-28T11:41:19Z" } }, { "key": "RAVE7CIK", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/RAVE7CIK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/RAVE7CIK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Boas and Harbury", "parsedDate": "2007-04", "numChildren": 0 }, "data": { "key": "RAVE7CIK", "version": 1, "itemType": "journalArticle", "title": "Potential energy functions for protein design", "creators": [ { "creatorType": "author", "firstName": "F Edward", "lastName": "Boas" }, { "creatorType": "author", "firstName": "Pehr B", "lastName": "Harbury" } ], "abstractNote": "Different potential energy functions have predominated in protein dynamics simulations, protein design calculations, and protein structure prediction. Clearly, the same physics applies in all three cases. The differences in potential energy functions reflect differences in how the calculations are performed. With improvements in computer power and algorithms, the same potential energy function should be applicable to all three problems. In this review, we examine energy functions currently used for protein design, and look to the molecular mechanics field for advances that could be used in the next generation of design algorithms. In particular, we focus on improved models of the hydrophobic effect, polarization and hydrogen bonding.", "publicationTitle": "Current Opinion in Structural Biology", "publisher": "", "place": "", "date": "Apr 2007", "volume": "17", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "199-204", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Curr. Opin. Struct. Biol", "DOI": "10.1016/j.sbi.2007.03.006", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/17387014", "accessDate": "2011-02-08T10:29:12Z", "PMID": "", "PMCID": "", "ISSN": "0959-440X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 17387014", "tags": [ { "tag": "Algorithms", "type": 1 }, { "tag": "Drug Design", "type": 1 }, { "tag": "Hydrogen Bonding", "type": 1 }, { "tag": "Hydrophobic and Hydrophilic Interactions", "type": 1 }, { "tag": "Protein Conformation", "type": 1 }, { "tag": "Proteins", "type": 1 }, { "tag": "Quantum Theory", "type": 1 }, { "tag": "Solvents", "type": 1 }, { "tag": "Thermodynamics", "type": 1 }, { "tag": "Water", "type": 1 } ], "collections": [ "W8QQPHAW" ], "relations": {}, "dateAdded": "2011-02-08T10:29:12Z", "dateModified": "2011-02-08T10:29:12Z" } }, { "key": "Z5JTDKQU", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/Z5JTDKQU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/Z5JTDKQU", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Wainreb et al.", "parsedDate": "2010-07", "numChildren": 0 }, "data": { "key": "Z5JTDKQU", "version": 1, "itemType": "journalArticle", "title": "MuD: an interactive web server for the prediction of non-neutral substitutions using protein structural data", "creators": [ { "creatorType": "author", "firstName": "Gilad", "lastName": "Wainreb" }, { "creatorType": "author", "firstName": "Haim", "lastName": "Ashkenazy" }, { "creatorType": "author", "firstName": "Yana", "lastName": "Bromberg" }, { "creatorType": "author", "firstName": "Alina", "lastName": "Starovolsky-Shitrit" }, { "creatorType": "author", "firstName": "Turkan", "lastName": "Haliloglu" }, { "creatorType": "author", "firstName": "Eytan", "lastName": "Ruppin" }, { "creatorType": "author", "firstName": "Karen B", "lastName": "Avraham" }, { "creatorType": "author", "firstName": "Burkhard", "lastName": "Rost" }, { "creatorType": "author", "firstName": "Nir", "lastName": "Ben-Tal" } ], "abstractNote": "The discrimination between functionally neutral amino acid substitutions and non-neutral mutations, affecting protein function, is very important for our understanding of diseases. The rapidly growing amounts of experimental data enable the development of computational tools to facilitate the annotation of these substitutions. Here, we describe a Random Forests-based classifier, named Mutation Detector (MuD) that utilizes structural and sequence-derived features to assess the impact of a given substitution on the protein function. In its automatic mode, MuD is comparable to alternative tools in performance. However, the uniqueness of MuD is that user-reported protein-specific structural and functional information can be added at run-time, thereby enhancing the prediction accuracy further. The MuD server, available at http://mud.tau.ac.il, assigns a reliability score to every prediction, thus offering a useful tool for the prioritization of substitutions in proteins with an available 3D structure.", "publicationTitle": "Nucleic Acids Research", "publisher": "", "place": "", "date": "Jul 2010", "volume": "38", "issue": "Web Server issue", "section": "", "partNumber": "", "partTitle": "", "pages": "W523-528", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Nucleic Acids Res", "DOI": "10.1093/nar/gkq528", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/20542913", "accessDate": "2011-01-08T11:01:35Z", "PMID": "", "PMCID": "", "ISSN": "1362-4962", "archive": "", "archiveLocation": "", "shortTitle": "MuD", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 20542913", "tags": [ { "tag": "Algorithms", "type": 1 }, { "tag": "Amino Acid Substitution", "type": 1 }, { "tag": "Artificial Intelligence", "type": 1 }, { "tag": "Internet", "type": 1 }, { "tag": "Protein Conformation", "type": 1 }, { "tag": "Reproducibility of Results", "type": 1 }, { "tag": "Sequence Homology, Amino Acid", "type": 1 }, { "tag": "Software", "type": 1 } ], "collections": [ "W8QQPHAW" ], "relations": {}, "dateAdded": "2011-01-08T11:01:35Z", "dateModified": "2011-01-08T11:01:35Z" } }, { "key": "35J6RHFM", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/35J6RHFM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/35J6RHFM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Adzhubei et al.", "parsedDate": "2010-04", "numChildren": 0 }, "data": { "key": "35J6RHFM", "version": 1, "itemType": "journalArticle", "title": "A method and server for predicting damaging missense mutations", "creators": [ { "creatorType": "author", "firstName": "Ivan A", "lastName": "Adzhubei" }, { "creatorType": "author", "firstName": "Steffen", "lastName": "Schmidt" }, { "creatorType": "author", "firstName": "Leonid", "lastName": "Peshkin" }, { "creatorType": "author", "firstName": "Vasily E", "lastName": "Ramensky" }, { "creatorType": "author", "firstName": "Anna", "lastName": "Gerasimova" }, { "creatorType": "author", "firstName": "Peer", "lastName": "Bork" }, { "creatorType": "author", "firstName": "Alexey S", "lastName": "Kondrashov" }, { "creatorType": "author", "firstName": "Shamil R", "lastName": "Sunyaev" } ], "abstractNote": "", "publicationTitle": "Nature Methods", "publisher": "", "place": "", "date": "Apr 2010", "volume": "7", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "248-249", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Nat. Methods", "DOI": "10.1038/nmeth0410-248", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/20354512", "accessDate": "2011-01-08T10:59:08Z", "PMID": "", "PMCID": "", "ISSN": "1548-7105", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 20354512", "tags": [ { "tag": "Data Interpretation, Statistical", "type": 1 }, { "tag": "Genetic Variation", "type": 1 }, { "tag": "Humans", "type": 1 }, { "tag": "Models, Genetic", "type": 1 }, { "tag": "Mutation, Missense", "type": 1 }, { "tag": "Software", "type": 1 } ], "collections": [ "EQBWXCMP" ], "relations": {}, "dateAdded": "2011-01-08T10:59:08Z", "dateModified": "2011-01-08T10:59:08Z" } }, { "key": "8MT3ZWHR", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/8MT3ZWHR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/8MT3ZWHR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Yuan et al.", "parsedDate": "2006-07-01", "numChildren": 0 }, "data": { "key": "8MT3ZWHR", "version": 1, "itemType": "journalArticle", "title": "FASTSNP: an always up-to-date and extendable service for SNP function analysis and prioritization", "creators": [ { "creatorType": "author", "firstName": "Hsiang-Yu", "lastName": "Yuan" }, { "creatorType": "author", "firstName": "Jen-Jie", "lastName": "Chiou" }, { "creatorType": "author", "firstName": "Wen-Hsien", "lastName": "Tseng" }, { "creatorType": "author", "firstName": "Chia-Hung", "lastName": "Liu" }, { "creatorType": "author", "firstName": "Chuan-Kun", "lastName": "Liu" }, { "creatorType": "author", "firstName": "Yi-Jung", "lastName": "Lin" }, { "creatorType": "author", "firstName": "Hui-Hung", "lastName": "Wang" }, { "creatorType": "author", "firstName": "Adam", "lastName": "Yao" }, { "creatorType": "author", "firstName": "Yuan-Tsong", "lastName": "Chen" }, { "creatorType": "author", "firstName": "Chun-Nan", "lastName": "Hsu" } ], "abstractNote": "Single nucleotide polymorphism (SNP) prioritization based on the phenotypic risk is essential for association studies. Assessment of the risk requires access to a variety of heterogeneous biological databases and analytical tools. FASTSNP (function analysis and selection tool for single nucleotide polymorphisms) is a web server that allows users to efficiently identify and prioritize high-risk SNPs according to their phenotypic risks and putative functional effects. A unique feature of FASTSNP is that the functional effect information used for SNP prioritization is always up-to-date, because FASTSNP extracts the information from 11 external web servers at query time using a team of web wrapper agents. Moreover, FASTSNP is extendable by simply deploying more Web wrapper agents. To validate the results of our prioritization, we analyzed 1569 SNPs from the SNP500Cancer database. The results show that SNPs with a high predicted risk exhibit low allele frequencies for the minor alleles, consistent with a well-known finding that a strong selective pressure exists for functional polymorphisms. We have been using FASTSNP for 2 years and FASTSNP enables us to discover a novel promoter polymorphism. FASTSNP is available at http://fastsnp.ibms.sinica.edu.tw.", "publicationTitle": "Nucleic Acids Research", "publisher": "", "place": "", "date": "Jul 1, 2006", "volume": "34", "issue": "Web Server issue", "section": "", "partNumber": "", "partTitle": "", "pages": "W635-641", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Nucleic Acids Res", "DOI": "10.1093/nar/gkl236", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/16845089", "accessDate": "2011-01-08T10:56:56Z", "PMID": "", "PMCID": "", "ISSN": "1362-4962", "archive": "", "archiveLocation": "", "shortTitle": "FASTSNP", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 16845089", "tags": [ { "tag": "Gene Frequency", "type": 1 }, { "tag": "Genetic Predisposition to Disease", "type": 1 }, { "tag": "Internet", "type": 1 }, { "tag": "Phenotype", "type": 1 }, { "tag": "Polymorphism, Single Nucleotide", "type": 1 }, { "tag": "Proteins", "type": 1 }, { "tag": "Risk", "type": 1 }, { "tag": "Software", "type": 1 }, { "tag": "User-Computer Interface", "type": 1 } ], "collections": [ "CT9IKJRE" ], "relations": {}, "dateAdded": "2011-01-08T10:56:56Z", "dateModified": "2011-01-08T10:56:56Z" } }, { "key": "WSADP697", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/WSADP697", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/WSADP697", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Lee and Shatkay", "parsedDate": "2008-01", "numChildren": 0 }, "data": { "key": "WSADP697", "version": 1, "itemType": "journalArticle", "title": "F-SNP: computationally predicted functional SNPs for disease association studies", "creators": [ { "creatorType": "author", "firstName": "Phil Hyoun", "lastName": "Lee" }, { "creatorType": "author", "firstName": "Hagit", "lastName": "Shatkay" } ], "abstractNote": "The Functional Single Nucleotide Polymorphism (F-SNP) database integrates information obtained from 16 bioinformatics tools and databases about the functional effects of SNPs. These effects are predicted and indicated at the splicing, transcriptional, translational and post-translational level. As such, the database helps identify and focus on SNPs with potential deleterious effect to human health. In particular, users can retrieve SNPs that disrupt genomic regions known to be functional, including splice sites and transcriptional regulatory regions. Users can also identify non-synonymous SNPs that may have deleterious effects on protein structure or function, interfere with protein translation or impede post-translational modification. A web interface enables easy navigation for obtaining information through multiple starting points and exploration routes (e.g. starting from SNP identifier, genomic region, gene or target disease). The F-SNP database is available at http://compbio.cs.queensu.ca/F-SNP/.", "publicationTitle": "Nucleic Acids Research", "publisher": "", "place": "", "date": "Jan 2008", "volume": "36", "issue": "Database issue", "section": "", "partNumber": "", "partTitle": "", "pages": "D820-824", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Nucleic Acids Res", "DOI": "10.1093/nar/gkm904", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/17986460", "accessDate": "2011-01-08T10:56:12Z", "PMID": "", "PMCID": "", "ISSN": "1362-4962", "archive": "", "archiveLocation": "", "shortTitle": "F-SNP", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 17986460", "tags": [ { "tag": "Computational Biology", "type": 1 }, { "tag": "Databases, Nucleic Acid", "type": 1 }, { "tag": "Genetic Diseases, Inborn", "type": 1 }, { "tag": "Genetic Predisposition to Disease", "type": 1 }, { "tag": "Genomics", "type": 1 }, { "tag": "Humans", "type": 1 }, { "tag": "Internet", "type": 1 }, { "tag": "Polymorphism, Single Nucleotide", "type": 1 }, { "tag": "Proteins", "type": 1 }, { "tag": "Software", "type": 1 }, { "tag": "User-Computer Interface", "type": 1 } ], "collections": [ "CT9IKJRE" ], "relations": {}, "dateAdded": "2011-01-08T10:56:12Z", "dateModified": "2011-01-08T10:56:12Z" } }, { "key": "6CZZKDRB", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/6CZZKDRB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/6CZZKDRB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Thusberg and Vihinen", "parsedDate": "2009-05", "numChildren": 0 }, "data": { "key": "6CZZKDRB", "version": 1, "itemType": "journalArticle", "title": "Pathogenic or not? And if so, then how? Studying the effects of missense mutations using bioinformatics methods", "creators": [ { "creatorType": "author", "firstName": "Janita", "lastName": "Thusberg" }, { "creatorType": "author", "firstName": "Mauno", "lastName": "Vihinen" } ], "abstractNote": "Many gene defects are relatively easy to identify experimentally, but obtaining information about the effects of sequence variations and elucidation of the detailed molecular mechanisms of genetic diseases will be among the next major efforts in mutation research. Amino acid substitutions may have diverse effects on protein structure and function; thus, a detailed analysis of the mutations is essential. Experimental study of the molecular effects of mutations is laborious, whereas useful and reliable information about the effects of amino acid substitutions can readily be obtained by theoretical methods. Experimentally defined structures and molecular modeling can be used as a basis for interpretation of the mutations. The effects of missense mutations can be analyzed even when the 3D structure of the protein has not been determined, although structure-based analyses are more reliable. Structural analyses include studies of the contacts between residues, their implication for the stability of the protein, and the effects of the introduced residues. Investigations of steric and stereochemical consequences of substitutions provide insights on the molecular fit of the introduced residue. Mutations that change the electrostatic surface potential of a protein have wide-ranging effects. Analyses of the effects of mutations on interactions with ligands and partners have been performed for elucidation of functional mutations. We have employed numerous methods for predicting the effects of amino acid substitutions. We discuss the applicability of these methods in the analysis of genes, proteins, and diseases to reveal protein structure-function relationships, which is essential to gain insights into disease genotype-phenotype correlations.", "publicationTitle": "Human Mutation", "publisher": "", "place": "", "date": "May 2009", "volume": "30", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "703-714", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Hum. Mutat", "DOI": "10.1002/humu.20938", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/19267389", "accessDate": "2011-01-08T10:55:50Z", "PMID": "", "PMCID": "", "ISSN": "1098-1004", "archive": "", "archiveLocation": "", "shortTitle": "Pathogenic or not?", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 19267389", "tags": [ { "tag": "Computational Biology", "type": 1 }, { "tag": "Humans", "type": 1 }, { "tag": "Mutation, Missense", "type": 1 }, { "tag": "Protein Structure, Secondary", "type": 1 } ], "collections": [ "CT9IKJRE" ], "relations": {}, "dateAdded": "2011-01-08T10:55:50Z", "dateModified": "2011-01-08T10:55:50Z" } }, { "key": "WXZFFGWX", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/WXZFFGWX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/WXZFFGWX", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/13757/items/B2S3NKSC", "type": "application/json" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } } }, "data": { "key": "WXZFFGWX", "version": 1, "parentItem": "B2S3NKSC", "itemType": "attachment", "linkMode": "linked_url", "title": "PubMed Central Link", "accessDate": "2010-11-01T17:12:15Z", "url": "http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2832822/", "note": "", "contentType": "text/html", "charset": "", "tags": [], "relations": {}, "dateAdded": "2010-11-01T17:25:51Z", "dateModified": "2010-11-01T17:25:51Z" } }, { "key": "B2S3NKSC", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/B2S3NKSC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/B2S3NKSC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Mottaz et al.", "parsedDate": "2010-03-15", "numChildren": 1 }, "data": { "key": "B2S3NKSC", "version": 1, "itemType": "journalArticle", "title": "Easy retrieval of single amino-acid polymorphisms and phenotype information using SwissVar", "creators": [ { "creatorType": "author", "firstName": "Anaïs", "lastName": "Mottaz" }, { "creatorType": "author", "firstName": "Fabrice P.A.", "lastName": "David" }, { "creatorType": "author", "firstName": "Anne-Lise", "lastName": "Veuthey" }, { "creatorType": "author", "firstName": "Yum L.", "lastName": "Yip" } ], "abstractNote": "Summary: The SwissVar portal provides access to a comprehensive collection of single amino acid polymorphisms and diseases in the UniProtKB/Swiss-Prot database via a unique search engine. In particular, it gives direct access to the newly improved Swiss-Prot variant pages. The key strength of this portal is that it provides a possibility to query for similar diseases, as well as the underlying protein products and the molecular details of each variant. In the context of the recently proposed molecular view on diseases, the SwissVar portal should be in a unique position to provide valuable information for researchers and to advance research in this area.\n\nAvailability: The SwissVar portal is available at www.expasy.org/swissvar\n\nContact: anais.mottaz@isb-sib.ch; lina.yip@isb-sib.ch\n\nSupplementary information: Supplementary data are available at Bioinformatics online.", "publicationTitle": "", "publisher": "", "place": "", "date": "2010-3-15", "volume": "26", "issue": "6", "section": "", "partNumber": "", "partTitle": "", "pages": "851-852", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Bioinformatics", "DOI": "10.1093/bioinformatics/btq028", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1367-4803", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "PubMed Central", "callNumber": "", "rights": "", "extra": "PMID: 20106818\nPMCID: 2832822", "tags": [], "collections": [ "EVK3AVCT" ], "relations": {}, "dateAdded": "2010-11-01T17:25:51Z", "dateModified": "2010-11-01T17:25:51Z" } }, { "key": "QMUQZUBN", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/QMUQZUBN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/QMUQZUBN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Braga-Neto", "parsedDate": "2007-01", "numChildren": 0 }, "data": { "key": "QMUQZUBN", "version": 1, "itemType": "journalArticle", "title": "Fads and fallacies in the name of small-sample microarray classification", "creators": [ { "creatorType": "author", "firstName": "U", "lastName": "Braga-Neto" } ], "abstractNote": "", "publicationTitle": "IEEE SIGNAL PROCESSING MAGAZINE", "publisher": "", "place": "", "date": "JAN 2007", "volume": "24", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "91-99", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=3&SID=T2AK6ekpND5pJNCFGg5&page=1&doc=1", "accessDate": "2010-05-08T16:43:06Z", "PMID": "", "PMCID": "", "ISSN": "1053-5888", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "DTQVKQ2F" ], "relations": {}, "dateAdded": "2010-05-08T16:43:06Z", "dateModified": "2010-05-08T16:43:06Z" } }, { "key": "6PKQFTM3", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/6PKQFTM3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/6PKQFTM3", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Larranaga et al.", "parsedDate": "2006-03-01", "numChildren": 0 }, "data": { "key": "6PKQFTM3", "version": 1, "itemType": "journalArticle", "title": "Machine learning in bioinformatics", "creators": [ { "creatorType": "author", "firstName": "Pedro", "lastName": "Larranaga" }, { "creatorType": "author", "firstName": "Borja", "lastName": "Calvo" }, { "creatorType": "author", "firstName": "Roberto", "lastName": "Santana" }, { "creatorType": "author", "firstName": "Concha", "lastName": "Bielza" }, { "creatorType": "author", "firstName": "Josu", "lastName": "Galdiano" }, { "creatorType": "author", "firstName": "Inaki", "lastName": "Inza" }, { "creatorType": "author", "firstName": "Jose A.", "lastName": "Lozano" }, { "creatorType": "author", "firstName": "Ruben", "lastName": "Armananzas" }, { "creatorType": "author", "firstName": "Guzman", "lastName": "Santafe" }, { "creatorType": "author", "firstName": "Aritz", "lastName": "Perez" }, { "creatorType": "author", "firstName": "Victor", "lastName": "Robles" } ], "abstractNote": "This article reviews machine learning methods for bioinformatics. It presents modelling methods, such as supervised classification, clustering and probabilistic graphical models for knowledge discovery, as well as deterministic and stochastic heuristics for optimization. Applications in genomics, proteomics, systems biology, evolution and text mining are also shown.", "publicationTitle": "Brief Bioinform", "publisher": "", "place": "", "date": "March 1, 2006", "volume": "7", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "86-112", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/bib/bbk007", "citationKey": "", "url": "http://bib.oxfordjournals.org/cgi/content/abstract/7/1/86", "accessDate": "2010-05-08T16:21:18Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "HighWire", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "HRAIU9FW" ], "relations": {}, "dateAdded": "2010-05-08T16:21:18Z", "dateModified": "2010-05-08T16:21:18Z" } }, { "key": "3JHCDP55", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/3JHCDP55", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/3JHCDP55", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Mathe et al.", "parsedDate": "2002-10-01", "numChildren": 0 }, "data": { "key": "3JHCDP55", "version": 1, "itemType": "journalArticle", "title": "Current methods of gene prediction, their strengths and weaknesses", "creators": [ { "creatorType": "author", "firstName": "Catherine", "lastName": "Mathe" }, { "creatorType": "author", "firstName": "Marie-France", "lastName": "Sagot" }, { "creatorType": "author", "firstName": "Thomas", "lastName": "Schiex" }, { "creatorType": "author", "firstName": "Pierre", "lastName": "Rouze" } ], "abstractNote": "While the genomes of many organisms have been sequenced over the last few years, transforming such raw sequence data into knowledge remains a hard task. A great number of prediction programs have been developed that try to address one part of this problem, which consists of locating the genes along a genome. This paper reviews the existing approaches to predicting genes in eukaryotic genomes and underlines their intrinsic advantages and limitations. The main mathematical models and computational algorithms adopted are also briefly described and the resulting software classified according to both the method and the type of evidence used. Finally, the several difficulties and pitfalls encountered by the programs are detailed, showing that improvements are needed and that new directions must be considered.", "publicationTitle": "Nucl. Acids Res.", "publisher": "", "place": "", "date": "October 1, 2002", "volume": "30", "issue": "19", "section": "", "partNumber": "", "partTitle": "", "pages": "4103-4117", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/nar/gkf543", "citationKey": "", "url": "http://nar.oxfordjournals.org/cgi/content/abstract/30/19/4103", "accessDate": "2010-05-08T16:20:46Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "HighWire", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "GTASR3JS" ], "relations": {}, "dateAdded": "2010-05-08T16:20:46Z", "dateModified": "2010-05-08T16:20:46Z" } }, { "key": "VUVJ5ANT", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/VUVJ5ANT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/VUVJ5ANT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Ozen et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "VUVJ5ANT", "version": 1, "itemType": "journalArticle", "title": "Machine learning integration for predicting the effect of single amino acid substitutions on protein stability", "creators": [ { "creatorType": "author", "firstName": "Ayşegül", "lastName": "Ozen" }, { "creatorType": "author", "firstName": "Mehmet", "lastName": "Gönen" }, { "creatorType": "author", "firstName": "Ethem", "lastName": "Alpaydan" }, { "creatorType": "author", "firstName": "Türkan", "lastName": "Haliloğlu" } ], "abstractNote": "BACKGROUND: Computational prediction of protein stability change due to single-site amino acid substitutions is of interest in protein design and analysis. We consider the following four ways to improve the performance of the currently available predictors: (1) We include additional sequence- and structure-based features, namely, the amino acid substitution likelihoods, the equilibrium fluctuations of the alpha- and beta-carbon atoms, and the packing density. (2) By implementing different machine learning integration approaches, we combine information from different features or representations. (3) We compare classification vs. regression methods to predict the sign vs. the output of stability change. (4) We allow a reject option for doubtful cases where the risk of misclassification is high. RESULTS: We investigate three different approaches: early, intermediate and late integration, which respectively combine features, kernels over feature subsets, and decisions. We perform simulations on two data sets: (1) S1615 is used in previous studies, (2) S2783 is the updated version (as of July 2, 2009) extracted also from ProTherm. For S1615 data set, our highest accuracy using both sequence and structure information is 0.842 on cross-validation and 0.904 on testing using early integration. Newly added features, namely, local compositional packing and the mobility extent of the mutated residues, improve accuracy significantly with intermediate integration. For S2783 data set, we also train regression methods to estimate not only the sign but also the amount of stability change and apply risk-based classification to reject when the learner has low confidence and the loss of misclassification is high. The highest accuracy is 0.835 on cross-validation and 0.832 on testing using only sequence information. The percentage of false positives can be decreased to less than 0.005 by rejecting 10 per cent using late integration. CONCLUSION: We find that in both early and late integration, combining inputs or decisions is useful in increasing accuracy. Intermediate integration allows assessing the contributions of individual features by looking at the assigned weights. Overall accuracy of regression is not better than that of classification but it has less false positives, especially when combined with the reject option. The server for stability prediction for three integration approaches and the data sets are available at http://www.prc.boun.edu.tr/appserv/prc/mlsta.", "publicationTitle": "BMC Structural Biology", "publisher": "", "place": "", "date": "2009", "volume": "9", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "66", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "BMC Struct. Biol", "DOI": "10.1186/1472-6807-9-66", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/19840377", "accessDate": "2010-05-02T16:47:05Z", "PMID": "", "PMCID": "", "ISSN": "1472-6807", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "NCBI PubMed", "callNumber": "", "rights": "", "extra": "PMID: 19840377", "tags": [ { "tag": "Amino Acid Substitution", "type": 1 }, { "tag": "Artificial Intelligence", "type": 1 }, { "tag": "Computational Biology", "type": 1 }, { "tag": "Databases, Protein", "type": 1 }, { "tag": "Mutagenesis, Site-Directed", "type": 1 }, { "tag": "Protein Stability", "type": 1 }, { "tag": "Proteins", "type": 1 }, { "tag": "Software", "type": 1 }, { "tag": "Thermodynamics", "type": 1 } ], "collections": [ "4BKSTXKI" ], "relations": {}, "dateAdded": "2010-05-02T16:47:05Z", "dateModified": "2010-05-02T16:47:05Z" } }, { "key": "BFVJU922", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/BFVJU922", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/BFVJU922", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Muggleton et al.", "parsedDate": "1992-10-01", "numChildren": 0 }, "data": { "key": "BFVJU922", "version": 1, "itemType": "journalArticle", "title": "Protein secondary structure prediction using logic-based machine learning", "creators": [ { "creatorType": "author", "firstName": "Stephen", "lastName": "Muggleton" }, { "creatorType": "author", "firstName": "Ross D.", "lastName": "King" }, { "creatorType": "author", "firstName": "Michael J.E.", "lastName": "Stenberg" } ], "abstractNote": "Many attempts have been made to solve the problem of predicting protein secondary structure from the primary sequence but the best performance results are still disappointing. In this paper, the use of a machine learning algorithm which allows relational descriptions is shown to lead to improved performance. The Inductive Logic Programming computer program, Golem, was applied to learning secondary structure prediction rules for {alpha}/{alpha} domain type proteins. The input to the program consisted of 12 non-homologous proteins (1612 residues) of known structure, together with a background knowledge describing the chemical and physical properties of the residues. Golem learned a small set of rules that predict which residues are part of the {alpha}-helices--based on their positional relationships and chemical and physical properties. The rules were tested on four independent non-homologous proteins (416 residues) giving an accuracy of 81% ({+/-}2%). This is an improvement, on identical data, over the previously reported result of 73% by King and Sternberg (1990, J. Mol. Biol., 216, 441-457) using the machine learning program PROMIS, and of 72% using the standard Gamier-Osguthorpe-Robson method. The best previously reported result in the literature for the {alpha}/{alpha} domain type is 76%, achieved using a neural net approach. Machine learning also has the advantage over neural network and statistical methods in producing more understandable results.", "publicationTitle": "Protein Eng.", "publisher": "", "place": "", "date": "October 1, 1992", "volume": "5", "issue": "7", "section": "", "partNumber": "", "partTitle": "", "pages": "647-657", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/protein/5.7.647", "citationKey": "", "url": "http://peds.oxfordjournals.org/cgi/content/abstract/5/7/647", "accessDate": "2010-03-30T08:03:36Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "HighWire", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "X5369XN3" ], "relations": {}, "dateAdded": "2010-03-30T08:03:36Z", "dateModified": "2010-03-30T08:03:36Z" } }, { "key": "X955V5JQ", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/X955V5JQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/X955V5JQ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Danziger et al.", "parsedDate": "2006-06", "numChildren": 0 }, "data": { "key": "X955V5JQ", "version": 1, "itemType": "journalArticle", "title": "Functional census of mutation sequence spaces: The example of p53 cancer rescue mutants", "creators": [ { "creatorType": "author", "firstName": "SA", "lastName": "Danziger" }, { "creatorType": "author", "firstName": "SJ", "lastName": "Swamidass" }, { "creatorType": "author", "firstName": "J", "lastName": "Zeng" }, { "creatorType": "author", "firstName": "LR", "lastName": "Dearth" }, { "creatorType": "author", "firstName": "Q", "lastName": "Lu" }, { "creatorType": "author", "firstName": "JH", "lastName": "Chen" }, { "creatorType": "author", "firstName": "JL", "lastName": "Cheng" }, { "creatorType": "author", "firstName": "VP", "lastName": "Hoang" }, { "creatorType": "author", "firstName": "H", "lastName": "Saigo" }, { "creatorType": "author", "firstName": "R", "lastName": "Luo" }, { "creatorType": "author", "firstName": "P", "lastName": "Baldi" }, { "creatorType": "author", "firstName": "RK", "lastName": "Brachmann" }, { "creatorType": "author", "firstName": "RH", "lastName": "Lathrop" } ], "abstractNote": "Many biomedical problems relate to mutant functional properties across a sequence space of interest, e. g., flu, cancer, and HIV. Detailed knowledge of mutant properties and function improves medical treatment and prevention. A functional census of p53 cancer rescue mutants would aid the search for cancer treatments from p53 mutant rescue. We devised a general methodology for conducting a functional census of a mutation sequence space by choosing informative mutants early. The methodology was tested in a double-blind predictive test on the functional rescue property of 71 novel putative p53 cancer rescue mutants iteratively predicted in sets of three ( 24 iterations). The first double-blind 15-point moving accuracy was 47 percent and the last was 86 percent; r = 0.01 before an epiphanic 16th iteration and r = 0.92 afterward. Useful mutants were chosen early ( overall r = 0.80). Code and data are freely available (http://www.igb.uci.edu/research/research.html, corresponding authors: R. H. L. for computation and R. K. B. for biology).", "publicationTitle": "IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS", "publisher": "", "place": "", "date": "APR-JUN 2006", "volume": "3", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "114-125", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=7&SID=S2mCe4kof6p15P2ljBb&page=1&doc=1", "accessDate": "2010-03-27T10:14:11Z", "PMID": "", "PMCID": "", "ISSN": "1545-5963", "archive": "", "archiveLocation": "", "shortTitle": "Functional census of mutation sequence spaces", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "5UUNGDD2" ], "relations": {}, "dateAdded": "2010-03-27T10:14:11Z", "dateModified": "2010-03-27T10:14:11Z" } }, { "key": "HSN3CSIC", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/HSN3CSIC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/HSN3CSIC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Danziger et al.", "parsedDate": "2007-07-01", "numChildren": 0 }, "data": { "key": "HSN3CSIC", "version": 1, "itemType": "journalArticle", "title": "Choosing where to look next in a mutation sequence space: Active Learning of informative p53 cancer rescue mutants", "creators": [ { "creatorType": "author", "firstName": "SA", "lastName": "Danziger" }, { "creatorType": "author", "firstName": "J", "lastName": "Zeng" }, { "creatorType": "author", "firstName": "Y", "lastName": "Wang" }, { "creatorType": "author", "firstName": "RK", "lastName": "Brachmann" }, { "creatorType": "author", "firstName": "RH", "lastName": "Lathrop" } ], "abstractNote": "Motivation: Many biomedical projects would benefit from reducing the time and expense of in vitro experimentation by using computer models for in silico predictions. These models may help determine which expensive biological data are most useful to acquire next. Active Learning techniques for choosing the most informative data enable biologists and computer scientists to optimize experimental data choices for rapid discovery of biological function. To explore design choices that affect this desirable behavior, five novel and five existing Active Learning techniques, together with three control methods, were tested on 57 previously unknown p53 cancer rescue mutants for their ability to build classifiers that predict protein function. The best of these techniques, Maximum Curiosity, improved the baseline accuracy of 56-77%. This article shows that Active Learning is a useful tool for biomedical research, and provides a case study of interest to others facing similar discovery challenges.", "publicationTitle": "BIOINFORMATICS", "publisher": "", "place": "", "date": "JUL 1 2007", "volume": "23", "issue": "13", "section": "", "partNumber": "", "partTitle": "", "pages": "I104-I114", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/bioinformatics/btm166", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=4&SID=S2mCe4kof6p15P2ljBb&page=1&doc=1", "accessDate": "2010-03-27T10:13:31Z", "PMID": "", "PMCID": "", "ISSN": "1367-4803", "archive": "", "archiveLocation": "", "shortTitle": "Choosing where to look next in a mutation sequence space", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "5UUNGDD2" ], "relations": {}, "dateAdded": "2010-03-27T10:13:31Z", "dateModified": "2010-03-27T10:13:31Z" } }, { "key": "AGQSKFIT", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/AGQSKFIT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/AGQSKFIT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Danziger et al.", "parsedDate": "2009-09", "numChildren": 0 }, "data": { "key": "AGQSKFIT", "version": 1, "itemType": "journalArticle", "title": "Predicting Positive p53 Cancer Rescue Regions Using Most Informative Positive (MIP) Active Learning", "creators": [ { "creatorType": "author", "firstName": "SA", "lastName": "Danziger" }, { "creatorType": "author", "firstName": "R", "lastName": "Baronio" }, { "creatorType": "author", "firstName": "L", "lastName": "Ho" }, { "creatorType": "author", "firstName": "L", "lastName": "Hall" }, { "creatorType": "author", "firstName": "K", "lastName": "Salmon" }, { "creatorType": "author", "firstName": "GW", "lastName": "Hatfield" }, { "creatorType": "author", "firstName": "P", "lastName": "Kaiser" }, { "creatorType": "author", "firstName": "RH", "lastName": "Lathrop" } ], "abstractNote": "Many protein engineering problems involve finding mutations that produce proteins with a particular function. Computational active learning is an attractive approach to discover desired biological activities. Traditional active learning techniques have been optimized to iteratively improve classifier accuracy, not to quickly discover biologically significant results. We report here a novel active learning technique, Most Informative Positive (MIP), which is tailored to biological problems because it seeks novel and informative positive results. MIP active learning differs from traditional active learning methods in two ways: (1) it preferentially seeks Positive (functionally active) examples; and (2) it may be effectively extended to select gene regions suitable for high throughput combinatorial mutagenesis. We applied MIP to discover mutations in the tumor suppressor protein p53 that reactivate mutated p53 found in human cancers. This is an important biomedical goal because p53 mutants have been implicated in half of all human cancers, and restoring active p53 in tumors leads to tumor regression. MIP found Positive (cancer rescue) p53 mutants in silico using 33% fewer experiments than traditional non-MIP active learning, with only a minor decrease in classifier accuracy. Applying MIP to in vivo experimentation yielded immediate Positive results. Ten different p53 mutations found in human cancers were paired in silico with all possible single amino acid rescue mutations, from which MIP was used to select a Positive Region predicted to be enriched for p53 cancer rescue mutants. In vivo assays showed that the predicted Positive Region: (1) had significantly more (p < 0.01) new strong cancer rescue mutants than control regions (Negative, and non-MIP active learning); (2) had slightly more new strong cancer rescue mutants than an Expert region selected for purely biological considerations; and (3) rescued for the first time the previously unrescuable p53 cancer mutant P152L.", "publicationTitle": "PLOS COMPUTATIONAL BIOLOGY", "publisher": "", "place": "", "date": "SEP 2009", "volume": "5", "issue": "9", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1371/journal.pcbi.1000498", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=1&SID=S2mCe4kof6p15P2ljBb&page=1&doc=1", "accessDate": "2010-03-27T10:13:05Z", "PMID": "", "PMCID": "", "ISSN": "1553-734X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "5UUNGDD2" ], "relations": {}, "dateAdded": "2010-03-27T10:13:05Z", "dateModified": "2010-03-27T10:13:05Z" } }, { "key": "25DTB8TT", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/25DTB8TT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/25DTB8TT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Bromberg and Rost", "parsedDate": "2007-06", "numChildren": 0 }, "data": { "key": "25DTB8TT", "version": 1, "itemType": "journalArticle", "title": "SNAP: predict effect of non-synonymous polymorphisms on function", "creators": [ { "creatorType": "author", "firstName": "Y", "lastName": "Bromberg" }, { "creatorType": "author", "firstName": "B", "lastName": "Rost" } ], "abstractNote": "Many genetic variations are single nucleotide polymorphisms (SNPs). Non-synonymous SNPs are 'neutral' if the resulting point-mutated protein is not functionally discernible from the wild type and 'non-neutral' otherwise. The ability to identify non-neutral substitutions could significantly aid targeting disease causing detrimental mutations, as well as SNPs that increase the fitness of particular phenotypes. Here, we introduced comprehensive data sets to assess the performance of methods that predict SNP effects. Along we introduced SNAP (screening for non-acceptable polymorphisms), a neural network-based method for the prediction of the functional effects of non-synonymous SNPs. SNAP needs only sequence information as input, but benefits from functional and structural annotations, if available. In a cross-validation test on over 80 000 mutants, SNAP identified 80% of the non-neutral substitutions at 77% accuracy and 76% of the neutral substitutions at 80% accuracy. This constituted an important improvement over other methods; the improvement rose to over ten percentage points for mutants for which existing methods disagreed. Possibly even more importantly SNAP introduced a well-calibrated measure for the reliability of each prediction. This measure will allow users to focus on the most accurate predictions and/or the most severe effects.", "publicationTitle": "NUCLEIC ACIDS RESEARCH", "publisher": "", "place": "", "date": "JUN 2007", "volume": "35", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "3823-3835", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/nar/gkm238", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=13&SID=U1mNpcMe5dMpog5DjgO&page=1&doc=2", "accessDate": "2010-03-23T19:47:36Z", "PMID": "", "PMCID": "", "ISSN": "0305-1048", "archive": "", "archiveLocation": "", "shortTitle": "SNAP", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "8AIDSATA" ], "relations": {}, "dateAdded": "2010-03-23T19:47:36Z", "dateModified": "2010-03-23T19:47:36Z" } }, { "key": "IPTB2SQB", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/IPTB2SQB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/IPTB2SQB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Bromberg et al.", "parsedDate": "2008-10-15", "numChildren": 0 }, "data": { "key": "IPTB2SQB", "version": 1, "itemType": "journalArticle", "title": "SNAP predicts effect of mutations on protein function", "creators": [ { "creatorType": "author", "firstName": "Y", "lastName": "Bromberg" }, { "creatorType": "author", "firstName": "G", "lastName": "Yachdav" }, { "creatorType": "author", "firstName": "B", "lastName": "Rost" } ], "abstractNote": "Many non-synonymous single nucleotide polymor-phisms (nsSNPs) in humans are suspected to impact protein function. Here, we present a publicly available server implementation of the method SNAP (screening for non-acceptable polymorphisms) that predicts the functional effects of single amino acid substitutions. SNAP identifies over 80% of the non-neutral mutations at 77% accuracy and over 76% of the neutral mutations at 80% accuracy at its default threshold. Each prediction is associated with a reliability index that correlates with accuracy and thereby enables experimentalists to zoom into the most promising predictions.", "publicationTitle": "BIOINFORMATICS", "publisher": "", "place": "", "date": "OCT 15 2008", "volume": "24", "issue": "20", "section": "", "partNumber": "", "partTitle": "", "pages": "2397-2398", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/bioinformatics/btn435", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=13&SID=U1mNpcMe5dMpog5DjgO&page=1&doc=1", "accessDate": "2010-03-23T19:47:32Z", "PMID": "", "PMCID": "", "ISSN": "1367-4803", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "8AIDSATA" ], "relations": {}, "dateAdded": "2010-03-23T19:47:32Z", "dateModified": "2010-03-23T19:47:32Z" } }, { "key": "2JPVK4TH", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/2JPVK4TH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/2JPVK4TH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Ozen et al.", "parsedDate": "2009-10-19", "numChildren": 0 }, "data": { "key": "2JPVK4TH", "version": 1, "itemType": "journalArticle", "title": "Machine learning integration for predicting the effect of single amino acid substitutions on protein stability", "creators": [ { "creatorType": "author", "firstName": "A", "lastName": "Ozen" }, { "creatorType": "author", "firstName": "M", "lastName": "Gonen" }, { "creatorType": "author", "firstName": "E", "lastName": "Alpaydin" }, { "creatorType": "author", "firstName": "T", "lastName": "Haliloglu" } ], "abstractNote": "Background: Computational prediction of protein stability change due to single-site amino acid substitutions is of interest in protein design and analysis. We consider the following four ways to improve the performance of the currently available predictors: (1) We include additional sequence-and structure-based features, namely, the amino acid substitution likelihoods, the equilibrium fluctuations of the alpha- and beta-carbon atoms, and the packing density. (2) By implementing different machine learning integration approaches, we combine information from different features or representations. (3) We compare classification vs. regression methods to predict the sign vs. the output of stability change. (4) We allow a reject option for doubtful cases where the risk of misclassification is high. Results: We investigate three different approaches: early, intermediate and late integration, which respectively combine features, kernels over feature subsets, and decisions. We perform simulations on two data sets: (1) S1615 is used in previous studies, (2) S2783 is the updated version (as of July 2, 2009) extracted also from ProTherm. For S1615 data set, our highest accuracy using both sequence and structure information is 0.842 on cross-validation and 0.904 on testing using early integration. Newly added features, namely, local compositional packing and the mobility extent of the mutated residues, improve accuracy significantly with intermediate integration. For S2783 data set, we also train regression methods to estimate not only the sign but also the amount of stability change and apply risk-based classification to reject when the learner has low confidence and the loss of misclassification is high. The highest accuracy is 0.835 on cross-validation and 0.832 on testing using only sequence information. The percentage of false positives can be decreased to less than 0.005 by rejecting 10 per cent using late integration. Conclusion: We find that in both early and late integration, combining inputs or decisions is useful in increasing accuracy. Intermediate integration allows assessing the contributions of individual features by looking at the assigned weights. Overall accuracy of regression is not better than that of classification but it has less false positives, especially when combined with the reject option. The server for stability prediction for three integration approaches and the data sets are available at http://www.prc.boun.edu.tr/appserv/prc/mlsta.", "publicationTitle": "BMC STRUCTURAL BIOLOGY", "publisher": "", "place": "", "date": "OCT 19 2009", "volume": "9", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1186/1472-6807-9-66", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=9&SID=U1mNpcMe5dMpog5DjgO&page=1&doc=1", "accessDate": "2010-03-23T19:46:35Z", "PMID": "", "PMCID": "", "ISSN": "1471-2237", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "4BKSTXKI" ], "relations": {}, "dateAdded": "2010-03-23T19:46:35Z", "dateModified": "2010-03-23T19:46:35Z" } }, { "key": "828B46UQ", "version": 1, "library": { "type": "group", "id": 13757, "name": "Data mining in bioinformatics", "links": { "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/13757/items/828B46UQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/data_mining_in_bioinformatics/items/828B46UQ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 98165, "username": "tonda", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/tonda", "type": "text/html" } } }, "creatorSummary": "Heath et al.", "parsedDate": "2002-06", "numChildren": 0 }, "data": { "key": "828B46UQ", "version": 1, "itemType": "journalArticle", "title": "Studying the functional genomics of stress responses in loblolly pine with the Expresso microarray experiment management system", "creators": [ { "creatorType": "author", "firstName": "LS", "lastName": "Heath" }, { "creatorType": "author", "firstName": "N", "lastName": "Ramakrishnan" }, { "creatorType": "author", "firstName": "RR", "lastName": "Sederoff" }, { "creatorType": "author", "firstName": "RW", "lastName": "Whetten" }, { "creatorType": "author", "firstName": "BI", "lastName": "Chevone" }, { "creatorType": "author", "firstName": "CA", "lastName": "Struble" }, { "creatorType": "author", "firstName": "VY", "lastName": "Jouenne" }, { "creatorType": "author", "firstName": "DW", "lastName": "Chen" }, { "creatorType": "author", "firstName": "L", "lastName": "van Zyl" }, { "creatorType": "author", "firstName": "R", "lastName": "Grene" } ], "abstractNote": "Conception, design, and implementation of cDNA microarray experiments present a variety of bioinformatics challenges for biologists and computational scientists. The multiple stages of data acquisition and analysis have motivated the design of Expresso, a system for microarray experiment management. Salient aspects of Expresso include support for clone replication and randomized placement; automatic gridding, extraction of expression data from each spot, and quality monitoring; flexible methods of combining data from individual spots into information about clones and functional categories; and the use of inductive logic programming for higher-level data analysis and mining. The development of Expresso is occurring in parallel with several generations of microarray experiments aimed at elucidating genomic responses to drought stress in loblolly pine seedlings. The current experimental design incorporates 384 pine cDNAs replicated and randomly placed in two specific microarray layouts. We describe the design of Expresso as well as results of analysis with Expresso that suggest the importance of molecular chaperones and membrane transport proteins in mechanisms conferring successful adaptation to long-term drought stress. Copyright (C) 2002 John Wiley Sons, Ltd.", "publicationTitle": "COMPARATIVE AND FUNCTIONAL GENOMICS", "publisher": "", "place": "", "date": "JUN 2002", "volume": "3", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "226-243", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/cfg.169", "citationKey": "", "url": "http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=76&SID=N2jBP2OkB8FK@cfo36H&page=1&doc=2", "accessDate": "2010-03-23T08:54:47Z", "PMID": "", "PMCID": "", "ISSN": "1531-6912", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ISI Web of Knowledge", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "X5369XN3" ], "relations": {}, "dateAdded": "2010-03-23T08:54:47Z", "dateModified": "2010-03-23T08:54:47Z" } } ]