Development of machine learning classifiers to predict compound activity on prostate cancer cell lines

Abstract

Prostate cancer is the most common type of cancer in men. The disease presents good survival rates if treated at the early stages. However, the evolution of the disease in its most aggressive variant remains without effective therapeutic answers. Therefore, the identification of novel effective therapeutics is urgently needed. On these premises, we developed a series of machine learning models, based on compounds with reported highly homogeneous cell-based antiproliferative assay data, able to predict the activity of ligands towards the PC-3 and DU-145 prostate cancer cell lines. The data employed in the development of the computational models was finely-tuned according to a series of thresholds for the classification of active/inactive compounds, to the number of features to be implemented, and by using 10 different machine learning algorithms. Models’ evaluation allowed us to identify the best combination of activity thresholds and ML algorithms for the classification of active compounds, achieving prediction performances with MCC values above 0.60 for PC-3 and DU-145 cells. Moreover, in silico models based on the combination of PC-3 and DU-145 data were also developed, demonstrating excellent precision performances. Finally, an analysis of the activity annotations reported for the ligands in the curated datasets were conducted, suggesting associations between cellular activity and biological targets that might be explored in the future for the design of more effective prostate cancer antiproliferative agents.

Improving Anticancer Drug Selection and Prioritization via Neural Learning to Rank

“…This enables such approaches to capture the interactions among multiple drugs, among multiple cell lines, and between drugs and cell lines. Typically, these approaches focus either on regression, which estimates the drug responses for a given cell line, or on classification, which predicts whether a drug is effective or not in a given cell line. These approaches employ various machine learning techniques such as kernel methods, matrix factorization, decision trees, recommendation-based methods, , ensemble learning, , and deep learning. − We refer the readers to comprehensive surveys , for a broader coverage of the existing literature in this area.…”

Profiling Chemobiological Connection between Natural Product and Target Space Based on Systematic Analysis

“…Concentration-response activity values, such as IC 50 , EC 50 , XC 50 , AC 50 , K i , K d , and potency, are expressed as a negative logarithm known as pChEMBL. In constructing many machine learning models for predicting activity [13], pChEMBL is often used to classify compounds as active or inactive. Based on the available activity records in the ChEMBL and the chemical items in the LOTUS database, the number of natural products with documented high activity (pChEMBL > 8) in the ChEMBL database was 841 (Figure 3A), including activity results tested on animals, tissues, cells, mixed enzymes and single proteins.…”