1st International and 10th National Iranian Conference on Bioinformatics
Home Accepted Papers
Prediction of protein aggregation tendency based on the support vector machine algorithm
Paper ID : 1038-ICB10
Authors:
Fatemeh Eshari *, Amirreza Farajnezhadi, Fahime Momeni, Mehran Habibi-Rezaei
آزمایشگاه بیوتکنولوژی پروتئین، دانشکده زیست، دانشکدگان علوم، دانشگاه تهران، تهران، ایران
Abstract:
Protein aggregation plays an important role in various diseases, for instance, type 2 diabetes (T2D), Alzheimer’s disease (AD), Parkinson’s disease (PD), prion encephalopathies, and Huntington’s disease. Moreover, it has been recognized as a field with increasing importance in the biopharmaceutical industries because of its occurrence during bioprocessing steps to ensure the drug's effectiveness and decrease associated risks, such as increased immunogenicity. Therefore, aggregation prediction of proteins under different conditions has great importance for successful biopharmaceutics’ development and theranostic approaches. In order to predict the aggregation propensity of proteins, a machine learning method was proposed to evaluate the aggregation propensity of hexapeptides of WALTZ-DB 2.0 databank, using the Support Vector Machine (SVM) algorithm based on the sequences of segments and beta-sheet formation propensity of residues as an intrinsic feature. To analyze the capability of the proposed method, two parameters were considered, which are F-measure and Matthews Correlation Coefficient (MCC), owing to their evaluative power. Finally, the applied approach was compared with the Pasta 2.0 server that uses similar inputs to make predictions. The mentioned parameters of the proposed method were resulted to be 0.830 and 0.633 for the proposed method, and 0.688 and 0.382 for the Pasta2 server, respectively. As a result, the new suggested strategy superiorly evaluates the aggregation propensity, which is essential for the basic and applied approaches.
Keywords:
Protein aggregation; Bioproducts engineering; Machine learning; SVM; Pasta 2.0
Status : Paper Accepted (Poster Presentation)