{"?xml":{"@version":"1.0"},"edm:RDF":{"@xmlns:dc":"http://purl.org/dc/elements/1.1/","@xmlns:edm":"http://www.europeana.eu/schemas/edm/","@xmlns:wgs84_pos":"http://www.w3.org/2003/01/geo/wgs84_pos","@xmlns:foaf":"http://xmlns.com/foaf/0.1/","@xmlns:rdaGr2":"http://rdvocab.info/ElementsGr2","@xmlns:oai":"http://www.openarchives.org/OAI/2.0/","@xmlns:owl":"http://www.w3.org/2002/07/owl#","@xmlns:rdf":"http://www.w3.org/1999/02/22-rdf-syntax-ns#","@xmlns:ore":"http://www.openarchives.org/ore/terms/","@xmlns:skos":"http://www.w3.org/2004/02/skos/core#","@xmlns:dcterms":"http://purl.org/dc/terms/","edm:WebResource":[{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-MUHRKBFA/9ea3dc19-d688-4a9c-ab4b-2f351de8e1ff/HTML","dcterms:extent":"34 KB"},{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-MUHRKBFA/eecceae5-834c-41fe-a5ef-4ead029455a3/PDF","dcterms:extent":"143 KB"},{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-MUHRKBFA/71d3a42c-4324-44e0-a101-a28c4077e4ce/TEXT","dcterms:extent":"27 KB"}],"edm:TimeSpan":{"@rdf:about":"1998-2025","edm:begin":{"@xml:lang":"en","#text":"1998"},"edm:end":{"@xml:lang":"en","#text":"2025"}},"edm:ProvidedCHO":{"@rdf:about":"URN:NBN:SI:doc-MUHRKBFA","dcterms:isPartOf":[{"@rdf:resource":"https://www.dlib.si/details/URN:NBN:SI:spr-KC6O72BG"},{"@xml:lang":"sl","#text":"Acta chimica slovenica"}],"dcterms:issued":"2011","dc:creator":["Zupan, Jure","Župerl, Špela"],"dc:format":[{"@xml:lang":"sl","#text":"številka:3"},{"@xml:lang":"sl","#text":"letnik:58"},{"@xml:lang":"sl","#text":"str. 485-491"}],"dc:identifier":["ISSN:1318-0207","COBISSID:4798490","URN:URN:NBN:SI:doc-MUHRKBFA"],"dc:language":"en","dc:publisher":[{"@xml:lang":"sl","#text":"Slovenian Chemical Society"},{"@xml:lang":"sl","#text":"Slovensko kemijsko društvo"}],"dc:subject":[{"@xml:lang":"sl","#text":"genski algoritmi"},{"@xml:lang":"sl","#text":"inhibitorji"},{"@xml:lang":"sl","#text":"modeliranje"},{"@xml:lang":"sl","#text":"struktura snovi"},{"@xml:lang":"sl","#text":"tripsin"}],"dcterms:temporal":{"@rdf:resource":"1998-2025"},"dc:title":{"@xml:lang":"sl","#text":"Linear vs. non-linear modelling| case study| modelling of binding affinity of inhibitors to trypsin|"},"dc:description":[{"@xml:lang":"sl","#text":"On the set of 53 trypsin inhibitors the affinity to the covalent bound ligandsis modeled using linear (MLR) and non-linear (ANN) methods. Each compound is represented by 343 chemical descriptors. The hypothesis was that linear models are not sufficiently flexible to yield the best model, because in MLR (multiple regression analysis) the number of variables (descriptors) is limited by the number of objects in the training set. On the other hand the CP-ANN (counterpropagation- artificial neural network) is not limited by this restriction and can thus involve larger number of variables than there are compounds in the training set. Both methods are applied on the same division of 53 compounds on the training, test, and validation sets. In a systematic GA (genetic algorithm) search the MLR models containing all possible forms of linear polynomials, i.e., from 3 to 25 variables were scanned and no better model that one obtained by the CP-ANN model was found"},{"@xml:lang":"sl","#text":"Na nizu 53 tripsinsih inhibitorjev smo z linearnimi (MLR) in nelinearnimi metodami (ANN) modelirali njihovo afiniteto do kovalentno vezanih ligandov. Vsaka spojina je bila predstavljena s 343 molekulskimi deskriptorji. Preverjali smo hipotezo, da linearno modeliranje (MLR) zaradi premajhnega števila spojin v učnem nizu ne nudi možnosti izbire tolikšnega števila deskriptorjev, da bi to zadostovalo, za izdelavo dovolj dobrega modela. Po drugi strani pa modeliranje s protitočnimi nevronskimi mrežami (CP ANN) nima te omejitve in zaradi tega lahko pri njej uporabimo predstavitve spojin z večjim številom deskriptorjev, kot je število spojin v učenem nizu. Obe modelni metodi sta bili uporabljeni na povsem enaki delitvi niza 53 spojin na tri skupine, na učno, testno in validacijsko. S pomočjo genetskega algoritma (GA) smo preiskali vse možne oblike linearnih polinomov, ki jih dovoljuje velikost učnega niza, tj., vse velikosti sistema enačb s tremi do petindvajsetimi deskriptorji. Sistematičen pregled z modeli narejenimi z metodo MLR ni dal boljšega modela od tistega, ki jo je dal CP ANN model"}],"edm:type":"TEXT","dc:type":[{"@xml:lang":"sl","#text":"znanstveno časopisje"},{"@xml:lang":"en","#text":"journals"},{"@rdf:resource":"http://www.wikidata.org/entity/Q361785"}]},"ore:Aggregation":{"@rdf:about":"http://www.dlib.si/?URN=URN:NBN:SI:doc-MUHRKBFA","edm:aggregatedCHO":{"@rdf:resource":"URN:NBN:SI:doc-MUHRKBFA"},"edm:isShownBy":{"@rdf:resource":"http://www.dlib.si/stream/URN:NBN:SI:doc-MUHRKBFA/eecceae5-834c-41fe-a5ef-4ead029455a3/PDF"},"edm:rights":{"@rdf:resource":"http://creativecommons.org/licenses/by/4.0/"},"edm:provider":"Slovenian National E-content Aggregator","edm:intermediateProvider":{"@xml:lang":"en","#text":"National and University Library of Slovenia"},"edm:dataProvider":{"@xml:lang":"sl","#text":"Slovensko kemijsko društvo"},"edm:object":{"@rdf:resource":"http://www.dlib.si/streamdb/URN:NBN:SI:doc-MUHRKBFA/maxi/edm"},"edm:isShownAt":{"@rdf:resource":"http://www.dlib.si/details/URN:NBN:SI:doc-MUHRKBFA"}}}}