Development of QSAR machine learning-based models to forecast the effect of substances on malignant melanoma cells

Abstract

SK-MEL-5 is a human melanoma cell line that has been used in various studies to explore new therapies against melanoma in different in vitro experiments. Based on this study we report on the development of quantitative structure-activity relationship (QSAR) models able to predict the cytotoxic effect of diverse chemical compounds on this cancer cell line. The dataset of cytotoxic and inactive compounds were downloaded from the PubChem database. It contains the data for all chemical compounds for which cytotoxicity results expressed by GI 50 was recorded. In total 13 blocks of molecular descriptors were computed and used, after appropriate pre-processing in building QSAR models with four machine learning classifiers: Random forest (RF), gradient boosting, support vector machine and random k-nearest neighbors. Among the 186 models reported none had a positive predictive value (PPV) higher than 0.90 in both nested cross-validation and on an external dataset testing, but 7 models had a PPV higher than 0.85 in both evaluations, all seven using the RFs algorithm as a classifier, and topological descriptors, information indices, 2D-autocorrelation descriptors, P-VSA-like descriptors, and edge-adjacency descriptors as sets of features used for classification. The y-scrambling test was associated with considerably worse performance (confirming the non-random character of the models) and the applicability domain was assessed through three different methods.

Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

“…Random forests (RF) are a widespread classification algorithm in a variety of fields, including QSAR [80,81]. They assemble a large number of decision trees with the help of a simple majority vote to resolve the most probable class for each data point.…”

Mitochondrial nanotargeting in malignancies (Review)

“…In recent years, impressive progress was recorded in the nano-oncology field, with the development of NPs which can be used in the diagnosis and treatment of cancer. The newly developed nanosystems may have decisive influence in cancer therapy in the next decade through new formulas for early detection of cancer, highly sensitive and selective imagistic agents, targeted therapies with minimal systemic side effects and development of minimal invasive techniques (4,5,16,17).…”

“…Functionalized NPs can be built with high precision to make them capable of absorbance, binding or transport with high effectiveness of different types of molecules (drugs, fluorescent molecules or groups, DNA, RNA, proteins, glycans). These NPs can be designed in order to be compatible with different ways of administration (4,5,16,18).…”

“…Nanoparticles (NPs) are currently used in physics, material sciences, chemistry, biology and also medicine. The nano-oncology field has registered an impressive progress since NPs can be used in the diagnosis and treatment of cancer (1)(2)(3)(4)(5).…”

Use of QSAR Global Models and Molecular Docking for Developing New Inhibitors of c-Src Tyrosine Kinase

“…Based on an arbitrary number of decision trees used as an ensemble with a majority vote to decide on the most probable class assigned to each data point, random forests (RF) are a popular classification algorithm often used with very good performance in QSAR models (35)(36)(37). Each decision tree is constructed using bootstrap sets of the training set and subsets of descriptors that are selected in a random manner (38).…”