Bioinformatics Research on Drug Sensitivity Prediction

Chen, Yaojia; Juan, Liran; Lv, Xiao; Shi, Lei

doi:10.3389/fphar.2021.799712

Cited by 4 publications

(4 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adoption of a biologically informed architecture has three main advantages: a) it allows to uncover the role of specific pathways in response to drug stimuli; b) it improves the trust in predictions, especially among non-ML experts and c) the efficient parameterization of our model can simplify the learning process rather than use arbitrarily overparameterized, architectures for prediction, simplifying interpretability. Most drug sensitivity prediction models only use gene expression data [12], however, the effect of single nucleotide mutations, DNA methylation and DNA copy number variation on drug sensitivity should also be considered. Here we have presented a visible neural with an improved accuracy level due to the use of multiple omics platforms and the better handling of imbalance of data.…”

Section: Discussionmentioning

confidence: 99%

MOViDA: Multi-Omics Visible Drug Activity Prediction with a Biologically Informed Neural Network Model

Ferraro

Scala

Cerulo

et al. 2023

Preprint

View full text Add to dashboard Cite

Drug discovery is a challenging task, characterized by a protracted period of time between initial development and market release, with a high rate of attrition at each stage. Computational virtual screening, powered by machine learning algorithms, has emerged as a promising approach for predicting therapeutic efficacy. However, the complex relationships between features learned by these algorithms can be challenging to decipher. We have devised a neural network model for the prediction of drug sensitivity, which employs a biologically-informed visible neural network (VNN), enabling a greater level of interpretability. The trained model can be scrutinized to investigate the biological pathways that play a fundamental role in prediction, as well as the chemical properties of drugs that influence sensitivity. The model leverages multi-omics data obtained from diverse tumor tissue sources and molecular descriptors that encode drug properties. We have extended the model to predict drug synergy, resulting in favorable outcomes while retaining interpretability. Given the often imbalanced nature of publicly available drug screening datasets, our model demonstrates superior performance compared to state-of-the-art visible machine learning algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

MOViDA: Multi-Omics Visible Drug Activity Prediction with a Biologically Informed Neural Network Model

Ferraro

Scala

Cerulo

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…One of the main obstacles in the treatment of cancer is its heterogeneity, which leads to a difference in the response of patients with the same cancer to the same drug [17,18]. In this context, computer-based approaches can be very powerful tools in order to identify in advance which drugs a patient is sensitive to and to which drugs does not respond instead [19]. To reach this goal, we proposed a network-based method which exploits Non-Negative Matrix Tri-Factorization algorithm for the prediction of the sensitiveness of a patient, which is represented by the cell line extracted from his tumor mass, to a drug.…”

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

A Non-Negative Matrix Tri-Factorization Based Method for Predicting Antitumor Drug Sensitivity

Testa

Pidò²,

Pinoli³

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Large annotated cell line collections have been proven to enable the prediction of drug response in the pre-clinical setting. We present an enhancement of Non-Negative Matrix Tri-Factorization method, which allows the integration of different data types for the prediction of missing associations. To test our method we retrieved a dataset from the Cancer Cell Line Encyclopedia (CCLE), containing the connections among cell lines and drugs by means of their IC50 values, and we integrated it by linking cell lines to their respective tissue of origin and genomic profile. We performed two different kind of experiments: a) prediction of missing values in the matrix, b) prediction of the complete drug profile of a new cell line, demonstrating the validity of the method in both scenarios.

show abstract

“…The prediction of metabolic pathways involves the utilization of bioinformatics techniques and databases to anticipate the potential metabolic transformations that a medication may undergo within the physiological context of the human body [14][15][16][17][18]. The aforementioned is crucial in evaluating the safety and effectiveness of a pharmaceutical compound under consideration [12,[19][20][21][22][23][24]. The utilization of bioinformatics facilitates the identification of distinct enzymes that play a role in the process of drug metabolism.…”

Section: Bioinformatics In Drug Metabolismmentioning

confidence: 99%

“…The amalgamation of pharmacology and bioinformatics exemplifies a potent synergy between conventional pharmacological methodologies and state-of-theart computational tools [23,25,[29][30][31][32]. The integration of bioinformatics in drug development pipeline has greatly improved our capacity to identify, create, and refine pharmaceuticals with heightened accuracy and effectiveness.…”

Section: Pharmacology and Bioinformatics Integrationmentioning

confidence: 99%

The Role of Bioinformatics in Drug Discovery: A Comprehensive Overview

Somda,

Wilson Kpordze,

Jerpkorir

et al. 2024

Pharmaceutical Science

View full text Add to dashboard Cite

Bioinformatics plays a crucial role in various aspects of drug discovery, drug metabolism, and pharmacology. In drug discovery, bioinformatics enables the efficient analysis and interpretation of large-scale biological data, facilitating target identification, lead compound optimization, and prediction of drug-target interactions. It aids in the identification and characterization of potential drug targets through genomic and proteomic analyses. Additionally, bioinformatics assists in the prediction of drug metabolism and pharmacokinetic properties, offering insights into the safety and efficacy of potential drug candidates. Furthermore, it contributes to pharmacology by enabling the analysis of drug-drug interactions, adverse drug reactions, and personalized medicine approaches. The integration of computational tools and algorithms with biological and chemical data has accelerated the drug discovery process, improved success rates, and reduced costs. Bioinformatics has become an indispensable tool in the development of novel therapeutics and the optimization of drug efficacy and safety. This book chapter elucidates the profound impact of bioinformatics in drug metabolism and pharmacology, emphasizing the transformative potential it holds for the future of pharmaceutical research, ultimately improving patient outcomes and bringing innovative therapies.

show abstract

Bioinformatics Research on Drug Sensitivity Prediction

Cited by 4 publications

References 81 publications

MOViDA: Multi-Omics Visible Drug Activity Prediction with a Biologically Informed Neural Network Model

MOViDA: Multi-Omics Visible Drug Activity Prediction with a Biologically Informed Neural Network Model

A Non-Negative Matrix Tri-Factorization Based Method for Predicting Antitumor Drug Sensitivity

The Role of Bioinformatics in Drug Discovery: A Comprehensive Overview

Contact Info

Product

Resources

About