SVMDLF: A novel R‐based Web application for prediction of dipeptidyl peptidase 4 inhibitors

Niu

et al. 2020

Preprint

Strategies to screen antihypertensive peptides with high throughput and rapid speed will be doubtlessly contributed to the treatment of hypertension. The food-derived antihypertensive peptides can reduce blood pressure without side effects. In present study, a novel model based on Extreme Gradient Boosting (XGBoost) algorithm was developed using the primary structural features of the food-derived peptides, and its performance in the prediction of antihypertensive peptides was compared with the dominating machine learning models. To further reflect the reliability of the method in real situation, the optimized XGBoost model was utilized to predict the antihypertensive degree of k-mer peptides cutting from 6 key proteins in bovine milk and the peptide-protein docking technology was introduced to verify the findings. The results showed that the XGBoost model achieved outstanding performance with the accuracy of 0.9841 and the area under the receiver operating characteristic curve of 0.9428, which were better than the other models. Using the XGBoost model, the prediction of antihypertensive peptides derived from milk protein was consistent with the peptide-protein docking results, and was more efficient. Our results indicate that using XGBoost algorithm as a novel auxiliary tool is feasible for screening antihypertensive peptide derived from food with high throughput and high efficiency.

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Machine Learning Strategy for Prediction of Antihypertensive Peptides Derived from Food with High Efficiency

Niu

et al. 2020

Preprint

“…It has been proved to be very effective in terms of reducing cost as well as time of a drug discovery program. Various success stories of CADD including virtual screening highlights its virtue for the identification of numerous inhibitors against various protein targets . However, as discussed only a limited number of in‐silico studies have been previously reported that identified HAT inhibitors.…”

Section: Introductionmentioning

confidence: 99%

“…Various success stories of CADD including virtual screening highlights its virtue for the identification of numerous inhibitors against various protein targets. [18][19][20][21][22] However, as discussed only a limited number of in-silico studies have been previously reported that identified HAT inhibitors. In one of the study, novel inhibitors in the form of rhodanine carboxylic acids were identified for PCAF HAT using docking-based virtual screening.…”

Section: Introductionmentioning

confidence: 99%

Multiple Machine Learning Based‐Chemoinformatics Models for Identification of Histone Acetyl Transferase Inhibitors

Krishna

Kumar

Singh

et al. 2018

Molecular Informatics

Self Cite

The histone acetyl transferase (HAT) are involved in acetylation of histones that lead to transcription activation in numerous gene regulatory mechanisms. There are very few GCN5 HAT inhibitors reported despite of their role in cancer progression. In this study, we have utilized in-silico virtual screening approaches based on various machine learning algorithm to identify potent inhibitors of GCN5 HAT from commercially available Maybridge library. We have generated predictive chemoinformatics models based on k-Nearest neighbour, naïve Bayesian, Random Forest and Support Vector Machine. Based on statistical parameters, the RF and SVM models have shown comparative performance. Therefore, we performed the virtual screening with these two models and the consensus hits were selected for further evaluation using molecular docking into the active site of GCN-5 HAT. Finally, a set of 10 molecules were selected and subjected to biological evaluation. Subsequently, inhibition of acetylation shown by three out of the ten molecules in the in-vitro experiments validated their utility as potential HAT inhibitors. Furthermore, the selected hits have also shown weak cell growth decrease in MCF-7 cancer cell lines, which suggests that after subsequent structural optimization the identified molecules may further be explored for the development of anti-cancer agents.

A Novel Machine Learning Strategy for the Prediction of Antihypertensive Peptides Derived from Food with High Efficiency

Niu

et al. 2021

Foods

Strategies to screen antihypertensive peptides with high throughput and rapid speed will doubtlessly contribute to the treatment of hypertension. Food-derived antihypertensive peptides can reduce blood pressure without side effects. In the present study, a novel model based on the eXtreme Gradient Boosting (XGBoost) algorithm was developed and compared with the dominating machine learning models. To further reflect on the reliability of the method in a real situation, the optimized XGBoost model was utilized to predict the antihypertensive degree of the k-mer peptides cutting from six key proteins in bovine milk, and the peptide–protein docking technology was introduced to verify the findings. The results showed that the XGBoost model achieved outstanding performance, with an accuracy of 86.50% and area under the receiver operating characteristic curve of 94.11%, which were better than the other models. Using the XGBoost model, the prediction of antihypertensive peptides derived from milk protein was consistent with the peptide–protein docking results, and was more efficient. Our results indicate that using the XGBoost algorithm as a novel auxiliary tool is feasible to screen for antihypertensive peptides derived from food, with high throughput and high efficiency.