PMC:2667511 / 3200-4082 JSONTXT

{"project":"2_test","denotations":[{"id":"19173748-17586545-8336728","span":{"begin":127,"end":128},"obj":"17586545"},{"id":"19173748-9299342-8336729","span":{"begin":221,"end":222},"obj":"9299342"},{"id":"19173748-11093265-8336729","span":{"begin":221,"end":222},"obj":"11093265"},{"id":"19173748-15050833-8336729","span":{"begin":221,"end":222},"obj":"15050833"},{"id":"19173748-15657096-8336730","span":{"begin":251,"end":252},"obj":"15657096"},{"id":"19173748-8143162-8336731","span":{"begin":278,"end":279},"obj":"8143162"},{"id":"19173748-11331240-8336732","span":{"begin":388,"end":389},"obj":"11331240"},{"id":"19173748-15047913-8336732","span":{"begin":388,"end":389},"obj":"15047913"},{"id":"19173748-15613384-8336732","span":{"begin":388,"end":389},"obj":"15613384"},{"id":"19173748-16423290-8336732","span":{"begin":388,"end":389},"obj":"16423290"},{"id":"19173748-16234318-8336733","span":{"begin":411,"end":413},"obj":"16234318"},{"id":"19173748-14564010-8336734","span":{"begin":436,"end":438},"obj":"14564010"},{"id":"19173748-1153006-8336735","span":{"begin":583,"end":585},"obj":"1153006"},{"id":"19173748-8552589-8336736","span":{"begin":586,"end":588},"obj":"8552589"},{"id":"19173748-9299342-8336737","span":{"begin":589,"end":590},"obj":"9299342"}],"text":"The prediction of protein interaction sites has gained much attention in recent years with over 20 different methods proposed [3]. Interaction regions can be characterized by a diverse set of physico-chemical properties [4-6], topological properties [7] and conserved residues [8]. A variety of studies have employed different classification approaches including Support Vector Machines [9-12], Random Forests [13] and Neural Networks [14]. These studies have shown that the interfaces of interaction sites share common properties that distinguish them from the rest of the protein [15,16,4]. Despite their good performance in the prediction of protein interaction sites, these machine learning approaches generate final prediction models which do not provide users with explicit rules and thus result in low interpretability of the results and poor knowledge extraction capability."}