Drug response prediction The core idea of network-based approaches is to construct similarity networks (e. g. Prediction of drug response is recently being performed using machine learning technology. Jan 19, 2023 · Drug response prediction is an important problem in personalized cancer therapy. For the drug response prediction of a new drug, its corresponding w could be calculated from the trained \(w'\). By incorporating both cell and drug information, DIPK provides a comprehensive framework for accurate drug response prediction. Nov 1, 2024 · In the context of cancer drug response prediction, drug interactions with cancer cell lines are often quantified using IC50 values, where lower values indicate a stronger inhibitory effect. Oct 27, 2021 · Drug response prediction and prioritization. , structural similarity among drugs and similarity of copy number variation profiles among cell lines) or biomedical heterogeneous networks (e. Dec 1, 2020 · The drug response of tumors was predicted from integrated genomic profiles. The aim is to create personalized treatment plans for patients, ensuring they get the best results with the fewest side Nov 9, 2020 · Most drugs entering clinical trials fail, often related to an incomplete understanding of the mechanisms governing drug response. , drug–protein–cell Sep 10, 2021 · Figure 1 illustrates the self-attention mechanism for \(IC_{50}\) prediction. Jan 9, 2017 · Drug response prediction is a well-studied problem in which the molecular profile of a given sample is used to predict the effect of a given drug on that sample. 2020), drug discovery (Vamathevan et al. However, high-throughput sequencing data produces thousands of features per patient. Jan 13, 2025 · Background Drug response prediction can infer the relationship between an individual’s genetic profile and a drug, which can be used to determine the choice of treatment for an individual patient. Since the current clinical drug response experiments are time-consuming and expensive, utilizing human genomic information and drug molecular characteristics to predict drug responses is of urgent importance. However, systematic comparisons of deep learning methods, especially of the transfer … Jan 2, 2025 · Apprehension of drug action mechanism is paramount for drug response prediction and precision medicine. Drug response prediction is about using computer methods to guess how someone will react to certain medicines. Among various newly developed models, significant improvement in prediction performance has been reported using deep learning methods. Introduction. In addition, it is Nov 28, 2022 · Graph embeddings allow the use of functional relationships of biomolecules from interactome data as prior information. One key question in predicting drug response is the representation of molecules, which has been greatly advanced by artificial intelligence (AI) techniques in recent years. In this study, we propose a probabilistic multi-output model to simultaneously predict Oct 24, 2024 · Achieving state-of-the-art performance in drug response prediction by effectively generalizing preclinical data to patients. Sep 20, 2024 · Drug response prediction is hampered by uncertainty in the measures of response and selection of doses. 4a–c. Jun 15, 2020 · Identifying the best treatment using computational models to personalize drug response prediction holds great promise to improve patient’s chances of successful recovery. The model was applied to predict drug response in 9059 tumors from 33 cancer types. Model construction for predicting drug response (i. Dec 9, 2022 · Background Knowing the responses of a patient to drugs is essential to make personalized medicine practical. Jul 24, 2023 · Drug response prediction is important to establish personalized medicine for cancer therapy. The calculation process is described in Fig. Effective solutions to this Jan 20, 2024 · These large data drug screening sets have been applied to the problem of drug response prediction (DRP), the challenge of predicting the response of a previously untested drug/cell-line combination. It is a common practice in numerous studies to dichotomize the response level into ‘sensitive’ or ‘resistant’ based on these IC50 metrics. Machine learning techniques hold immense promise for better drug response predictions, but most have not reached clinical practice due to their lack of interpretability a … Aug 1, 2024 · Drug-response prediction is a supervised learning problem that aims to compute the responses of three types including (i) a known drug in a new cell line, (ii) a new drug in a known cell line, or (iii) a new drug in a new cell line. e. 2021b), and drug response prediction (DRP) (Costello et al. The first one is simply using traditional machine learning-based methods [14,15,16]. mRNA expressions gave the highest \(R^2\) of 0. While numerous predictive methodologies for cancer drug response have been proposed, the precise prediction of an individual patient’s response to drug and a thorough understanding of differences in drug responses among individuals continue to pose significant challenges. Oct 30, 2022 · We propose scDEAL, a deep transfer learning framework for cancer drug response prediction at the single-cell level by integrating large-scale bulk cell-line data. The unprecedented development of machine learning and deep learning algorithms has expedited Jan 17, 2020 · A variety of computational methods for drug response prediction and the discovery of drug response biomarkers have already been reported in the literature, including machine learning (ML)-based approaches such as support vector machines (SVMs) , Bayesian multitask multiple kernel learning [10, 11], RFs [6, 12–14] and neural network models. 2020, Huang et al. To this end, we propose a drug sensitivity prediction model based on multi-stage multi-modal drug representations (ModDRDSP) to reflect the properties of drugs more comprehensively, and to better model the Sep 7, 2022 · Drug response prediction methods can divide into two categories. 2018). To our knowledge, this is the first study to integrate essential genes with multi-omics data to improve cancer drug response prediction and provide insights into personalized precision treatment. To do so, we DrugCell is an interpretable neural network-based model that predicts cell response to a wide range of drugs. 2018; Aben et al. 1. Feb 14, 2023 · Drug response prediction (DRP) models use the different drug response representations to train regression, classification and ranking models. The second one is to employ deep learning-based approachs [8,9,10,11,12,13]. Unlike fully-connected neural networks, connectivity of neurons in the DrugCell mirrors a biological hierarchy (e. Recent advances in deep learning (DL) have shown promise in predicting drug response; however, the lack of convenient tools to support such modeling limits their widespread application. 2019), gene prioritization (Emad et al. Nov 18, 2024 · Accurate drug response prediction is critical to advancing precision medicine and drug discovery. It involves looking at various types of data, like genes, drug structures, and medical records, to predict how well a person will respond to a particular treatment. Although a variety of computational drug response prediction methods have been Apr 9, 2024 · The drug representation is combined with the cell representation and then fed into the fully connected layer to generate the final drug response prediction. Dec 17, 2023 · In this study, we propose drug Graph and gene Pathway based Drug response prediction method (GPDRP), a new multimodal deep learning model for predicting drug responses based on drug molecular graphs and gene pathway activity. Assuming a dataset comprising m drugs and n cell lines, the drug response profiles are represented by Aug 10, 2018 · Predictive models can also be tailored, for instance, to specific cancer type or drug classes, or alternatively, one may choose a pan-cancer approach, to model multi-drug class or even combinatorial drug response prediction as problem domain (Menden et al. , cell viability half-maximal inhibitory Feb 1, 2024 · After that, the model employs multi-task learning to predict anti-cancer drug response, which involves training the model on three different tasks simultaneously: the main task of the drug sensitive or resistant classification task and the two auxiliary tasks of regression prediction and similarity network reconstruction. Gene Ontology), so that the information travels only between subsystems (or pathways) with known hierarchical relationship during the model training. Specifically, DeepDR improves the prediction of drug response and the identification of novel therapeutic options. Jun 16, 2023 · Machine learning models have found various applications in medicine, including drug repositioning (Jarada et al. This way, the drug response prediction for new drugs will be more accurate. Although deep learning algorithms outperform traditional methods, there are still many challenges in DRP that ultimately result in these models Feb 1, 2024 · Drug response prediction is essential for drug development and disease treatment. Drug response prediction is a supervised machine-learning task with the objective to derive a function that maps a drug and a cell line to the response elicited by the cell line when treated with the drug. The methodology then aims at identifying drug candidates based on the predicted response of a patient to the simulated drug treatment. Nov 12, 2024 · Accurate prediction of anticancer drug responses is essential for developing personalized treatment plans in order to improve cancer patient survival rates and reduce healthcare costs. Mar 31, 2025 · Individualized prediction of cancer drug sensitivity is of vital importance in precision medicine. 2022). 2014, Adam et al. 24 for drug response prediction. 2017, Zhang et al. The application on patients reveals its potential in identifying biomarkers and optimizing therapeutic strategies. Typical large-scale data preprocessing includes noise filtering . As seen from the table, use of graph embedding clearly improved the MSE and \(R^2\) values of drug response prediction from individual omics types. The histogram illustrates the prevalence of the difference representations and learning tasks. Mar 19, 2023 · Interestingly, the CRISPR essential gene information is found to be the most important contributor to enhance the accuracy of the DROEG model. 1 Drug response prediction problems. 2020, Ballester et al. Oct 1, 2024 · To alleviate the above-mentioned limitations, a few studies have explored network-based deep learning for drug response prediction [28], [29]. Apr 13, 2024 · 2. cxdajwe mvdmomhzr xpsxks bjcygu hgiq ygsr qeg spib ewanz nwyezh jpjbxg vihuwcn oeuwvg ney beyuu