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

Abstract

Understanding of quorum-sensing peptides (QSPs) in their functional mechanism plays an essential role in finding new opportunities to combat bacterial infections by designing drugs. With the avalanche of the newly available peptide sequences in the post-genomic age, it is highly desirable to develop a computational model for efficient, rapid and high-throughput QSP identification purely based on the peptide sequence information alone. Although, few methods have been developed for predicting QSPs, their prediction accuracy and interpretability still requires further improvements. Thus, in this work, we proposed an accurate sequence-based predictor (called iQSP) and a set of interpretable rules (called IR-QSP) for predicting and analyzing QSPs. In iQSP, we utilized a powerful support vector machine (SVM) cooperating with 18 informative features from physicochemical properties (PCPs). Rigorous independent validation test showed that iQSP achieved maximum accuracy and MCC of 93.00% and 0.86, respectively. Furthermore, a set of interpretable rules IR-QSP was extracted by using random forest model and the 18 informative PCPs. Finally, for the convenience of experimental scientists, the iQSP web server was established and made freely available online. It is anticipated that iQSP will become a useful tool or at least as a complementary existing method for predicting and analyzing QSPs.

iPMI: Machine Learning-Aided Identification of Parametrial Invasion in Women with Early-Stage Cervical Cancer

“…where Ac, Sn, Sp and MCC are accuracy, sensitivity, specificity, and Matthews correlation coefficient, respectively. More details of these four standard metrics can be found in our previous studies [25,26,[41][42][43][44][45]. Furthermore, the area under the receiver operating characteristic (ROC) curve was used to assess the predictive performance, where AUC values of 0.5 and 1 were indicative of random and perfect models, respectively.…”

“…In order to make a fair comparison, the DT, LR, MLP, NB, XGB, and SVM models were constructed based on the same feature set (the combination of baseline+pelvicme+utmet) using Scikit-Learn package [46]. This package has been successfully applied to various domains [25,[41][42][43][44][45]. To demonstrate the comparative results clearly, we summarized the Ac, Sn, Sp, MCC and AUC values for iPMI-Power, iPMI-Econ and other ML classifiers assessed via 10-fold cross-validation (Table S2 and Figure 1E) and independent tests (Table 3 and Figure 1F).…”

PVPred-SCM: Improved Prediction and Analysis of Phage Virion Proteins Using a Scoring Card Method

“…PCPs are one of the most intuitive features associated with biophysical and biochemical reactions. Previously, our studies utilized these features for predicting and analyzing various functions of proteins and peptides from primary sequences [17,19,20,26,28,29,32,33,67]. In fact, there are 544 PCPs of amino acids extracted from the amino acid index database (AAindex) [37], which is a collection of published literature as well as different biochemical and biophysical properties of amino acids.…”

Extremely-randomized-tree-based Prediction of N6-methyladenosine Sites inSaccharomyces cerevisiae

“…We carried out 10-fold CV test to assess model performance. In 10-fold CV, the benchmark dataset was randomly separated into 10 subgroups with roughly equal size [54][55][56][57][58][59][60][61][62][63][64], with each subgroup containing the same number of m6A and non-m6A samples [65,66]. One of the subgroups was considered as the validation set to assess the trained model and the remaining subgroups were used to train the model.…”