Related Experiment Video
Updated: Dec 2, 2025
Chick Heart Invasion Assay for Testing the Invasiveness of Cancer Cells and the Activity of Potentially Anti-invasive Compounds
Published on: June 6, 2015
Perturbation-Theory Machine Learning (PTML) Multilabel Model of the ChEMBL Dataset of Preclinical Assays for
Alejandro Cabrera-Andrade1,2,3, Andrés López-Cortés3,4, Cristian R Munteanu3,5,6
1Grupo de Bio-Quimioinformática, Universidad de Las Américas, de los Granados Avenue, Quito 170125, Ecuador.
Abstract:
Sarcomas are a group of malignant neoplasms of connective tissue with a different etiology than carcinomas. The efforts to discover new drugs with antisarcoma activity have generated large datasets of multiple preclinical assays with different experimental conditions. For instance, the ChEMBL database contains outcomes of 37,919 different antisarcoma assays with 34,955 different chemical compounds. Furthermore, the experimental conditions reported in this dataset include 157 types of biological activity parameters, 36 drug targets, 43 cell lines, and 17 assay organisms. Considering this information, we propose combining perturbation theory (PT) principles with machine learning (ML) to develop a PTML model to predict antisarcoma compounds. PTML models use one function of reference that measures the probability of a drug being active under certain conditions (protein, cell line, organism, etc.). In this paper, we used a linear discriminant analysis and neural network to train and compare PT and non-PT models. All the explored models have an accuracy of 89.19-95.25% for training and 89.22-95.46% in validation sets. PTML-based strategies have similar accuracy but generate simplest models. Therefore, they may become a versatile tool for predicting antisarcoma compounds.
Insights
Researchers developed a novel PTML model combining perturbation theory (PT) and machine learning (ML) to predict potential antisarcoma compounds. This approach offers a versatile tool for drug discovery with high accuracy.
Area of Science:
- Oncology
- Computational Chemistry
- Bioinformatics
Background:
- Sarcomas are malignant connective tissue neoplasms distinct from carcinomas.
- Drug discovery for sarcomas involves analyzing large preclinical assay datasets.
- Existing datasets contain numerous compounds, assays, and experimental variables.
Purpose of the Study:
- To develop a predictive model for identifying antisarcoma compounds.
- To combine perturbation theory (PT) principles with machine learning (ML) for enhanced prediction.
- To evaluate the efficacy of PTML models compared to traditional ML approaches.
Main Methods:
- Utilized perturbation theory (PT) principles integrated with machine learning (ML).
- Developed a PTML model using a reference function to assess drug activity probability.
- Trained and compared PTML models against non-PT models using linear discriminant analysis and neural networks.
Main Results:
- PTML models demonstrated high accuracy in both training (89.19-95.25%) and validation (89.22-95.46%) sets.
- PTML-based strategies achieved comparable accuracy to traditional models.
- PTML models generated simpler predictive models.
Conclusions:
- PTML strategies offer a versatile and accurate tool for predicting antisarcoma compounds.
- The integration of PT and ML simplifies model generation while maintaining predictive power.
- This approach holds promise for accelerating sarcoma drug discovery efforts.
More Related Videos
09:41An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells
Published on: July 15, 2015
09:53Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
