Identification of Anticancer and Anti-inflammatory Drugs from Drug-target Interaction Descriptors by Machine Learning..

Background: Drug repositioning is an important subject in drug-disease research. In the past, most studies simply used drug descriptors as the feature vector to classify drugs or targets, or used qualitative data about drug-target or drug-disease to predict drug-target interactions. These data provide limited information for drug repositioning. Objective: Considering both drugs and targets and constructing quantitative drug-target interaction descriptors as a method of drug characteristics are of great significance to the study of drug repositioning. Methods: Taking anticancer and anti-inflammatory drugs as research objects, the interaction sites between drugs and targets were determined by molecular docking. Sixty-seven drug-target interaction descriptors were calculated to describe the drug-target interactions, and 22 important descriptors were screened for drug classification by SVM, LightGBM and MLP. Results: The accuracy of SVM, LightGBM and MLP reached 93.29%, 92.68% and 94.51%, their Matthews correlation coefficients reached 0.852, 0.840 and 0.882, and their areas under the ROC curve reached 0.977, 0.969 and 0.968, respectively. Conclusion: Using drug-target interaction descriptors to build machine learning models can obtain better results for drug classification. Number of atom pairs, force field, hydrophobic interactions and bSASA are the four types of key features for the classification of anticancer and anti-inflammatory drugs.

Drug Classification using Black-box models and Interpretability

The focus of this study is on drug categorization utilising Machine Learning models, as well as interpretability utilizing LIME and SHAP to get a thorough understanding of the ML models. To do this, the researchers used machine learning models such as random forest, decision tree, and logistic regression to classify drugs. Then, using LIME and SHAP, they determined if these models were interpretable, which allowed them to better understand their results. It may be stated at the conclusion of this paper that LIME and SHAP can be utilised to get insight into a Machine Learning model and determine which attribute is accountable for the divergence in the outcomes. According to the LIME and SHAP results, it is also discovered that Random Forest and Decision Tree ML models are the best models to employ for drug classification, with Na to K and BP being the most significant characteristics for drug classification. Keywords: Machine Learning, Back-box models, LIME, SHAP, Decision Tree

Analisys Of Demand and Optimization Of Medicine Prediction Using ABC Analysis and SVR Method In The “MORBIS” Aplication

The problem that occurs in hospitals regarding the processing of drug supplies is about the condition of out of stock medicines because hospitals spend around 33% of the total investment in one year only for the investment costs of drugs. To deal with the above problems the hospital must have good logistics management, one way of managing it is by doing good planning. In this research, the writer will use ABC Analysis and Support Vector Regression (SVR) algorithm. For the use of these methods, the following ABC Analysis will be used for the drug classification process, namely by dividing the torch into three main groups based on interests, namely groups A, B and C. Henceforth, the writer will use the SVR motedo to calculate drug predictions. The results that the authors get from this study are ABC analyys classify drugs. Into three groups namely group A with a total of 276 items with a percentage of 22.96% of the total number of items, group B with a total of 396 items with a percentage of 33.11% and C with a total of 528 with a percentage of 43.94% with a total of 1202 drug items. Prediction testing is done by taking a sample of five drugs derived from group classification. The SVR calculation process is done by comparing linear scaling and z normalization preprocessing methods. The result of this research is that MAPE shows that preprocessing with linear scaling produces a better value than compared to z nomrlization and calculation with ABC analysis.