Hemopred: A Web Server for Predicting the Hemolytic Activity of Peptides

Abstract

A sequence-based predictor which is publicly available as the web service of HemoPred, is proposed to predict and analyze the hemolytic activity of peptides.

Unraveling the bioactivity of anticancer peptides as deduced from machine learning

“…data collection, feature representation, model construction and model evaluation (Shoombuatong et al, 2012[76], 2015[78][79], 2016[77], 2017[80][81]; Win et al, 2017[102]; Pratiwi et al, 2017[70]; Nantasenamat et al, 2015)[58]. In the point of view of machine learning, the use of reliable dataset plays a crucial role to obtain an efficient and generalized model.…”

“…Overall, most research articles showed encouraging results with having satisfied accuracies of more than 90 %. Nevertheless, there is still room for development to improve the existing methods as useful and interpretable models for facilitating experimental scientists and related researchers as demonstrated by a series of recent publications (Shoombuatong et al, 2012[76], 2015[78][79], 2016[77], 2017[80][81]; Win et al, 2017[102]; Pratiwi et al, 2017[70]; Nantasenamat et al, 2015[58]) and summarized in comprehensive reviews (Nantasenamat et al, 2015[58]; Shoombuatong et al, 2017[80][81]).…”

iQSP: A Sequence-Based Tool for the Prediction and Analysis of Quorum Sensing Peptides Using Informative Physicochemical Properties

“…. , 100) and fixing the ntree parameter with 500 [36,39,42,45]. Finally, the average value of MDGI on 100 runs of feature importance estimations were used in this study.…”

“…However, previous studies [28,29,48] performed these two datasets using a single random sampling procedure. As elaborated in [39,40,42,43,45,49,50], this procedure might find a possible bias of the random sampling process and provided a good predictive result by chance. Therefore, we repeated this construction procedure with ten independent rounds to alleviate the aforementioned problems [36,39,[41][42][43]45].…”

Towards understanding aromatase inhibitory activity via QSAR modeling

“…Breiman (2001[14]) developed the RF method by growing many weak decision trees for enhancing the prediction performance of CART. The last decade has witnessed the significant achievement of RF model in applications of drug developments and related works (Win et al, 2017[100]; Worachartcheewan et al, 2015[102]; Pratiwi et al, 2017[73]; Simeon et al, 2016[87]; Phanus-umporn et al, 2018[69]; Suvannang et al, 2018[94]). RF model takes advantage of two efficient machine learning techniques: bagging and random feature selection.…”