Predict Drug Response Research Articles

QPGx-CARES: Qatar pharmacogenetics clinical applications and research enhancement strategies.

Pharmacogenetic (PGx)-informed medication prescription is a cutting-edge genomic application in contemporary medicine, offering the potential to overcome the conventional "trial-and-error" approach in drug prescription. The ability to use an individual's genetic profile to predict drug responses allows for personalized drug and dosage selection, thereby enhancing the safety and efficacy of treatments. However, despite significant scientific and clinical advancements in PGx, its integration into routine healthcare practices remains limited. To address this gap, the Qatar Genome Program (QGP) has embarked on an ambitious initiative known as QPGx-CARES (Qatar Pharmacogenetics Clinical Applications and Research Enhancement Strategies), which aims to set a roadmap for optimizing PGx research and clinical implementation on a national scale. The goal of QPGx-CARES initiative is to integrate PGx testing into clinical settings with the aim of improving patient health outcomes. In 2022, QGP initiated several implementation projects in various clinical settings. These projects aimed to evaluate the clinical utility of PGx testing, gather valuable insights into the effective dissemination of PGx data to healthcare professionals and patients, and identify the gaps and the challenges for wider adoption. QPGx-CARES strategy aimed to integrate evidence-based PGx findings into clinical practice, focusing on implementing PGx testing for cardiovascular medications, supported by robust scientific evidence. The current initiative sets a precedent for the nationwide implementation of precision medicine across diverse clinical domains.

Opioid Monitoring in Clinical Settings: Strategies and Implications of Tailored Approaches for Therapy.

This review emphasises the importance of opioid monitoring in clinical practice and advocates for a personalised approach based on pharmacogenetics. Beyond effectively managing pain, meticulous oversight is required to address concerns about side effects, specially due to opioid-crisis-related abuse and dependence. Various monitoring techniques, along with pharmacogenetic considerations, are critical for personalising treatment and optimising pain relief while reducing misuse and addiction risks. Future perspectives reveal both opportunities and challenges, with advances in analytical technologies holding promise for increasing monitoring efficiency. The integration of pharmacogenetics has the potential to transform pain management by allowing for a precise prediction of drug responses. Nevertheless, challenges such as prominent pharmacogenetic testing and guideline standardisation persist. Collaborative efforts are critical for transforming scientific advances into tangible improvements in patient care. Standardised protocols and interdisciplinary collaboration are required to ensure consistent and evidence-based opioid monitoring. Future research should look into the long-term effects of opioid therapy, as well as the impact of genetic factors on individual responses, to help guide personalised treatment plans and reduce adverse events. Lastly, embracing innovation and collaboration can improve the standard of care in chronic pain management by striking a balance between pain relief and patient safety.

Progress and application of lung-on-a-chip for lung cancer

Lung cancer is a malignant tumour with the highest incidence and mortality worldwide. Clinically effective therapy strategies are underutilized owing to the lack of efficient models for evaluating drug response. One of the main reasons for failure of anticancer drug therapy is development of drug resistance. Anticancer drugs face severe challenges such as poor biodistribution, restricted solubility, inadequate absorption, and drug accumulation. In recent years, “organ-on-a-chip” platforms, which can directly regulate the microenvironment of biomechanics, biochemistry and pathophysiology, have been developed rapidly and have shown great potential in clinical drug research. Lung-on-a-chip (LOC) is a new 3D model of bionic lungs with physiological functions created by micromachining technology on microfluidic chips. This approach may be able to partially replace animal and 2D cell culture models. To overcome drug resistance, LOC realizes personalized prediction of drug response by simulating the lung-related microenvironment in vitro, significantly enhancing therapeutic effectiveness, bioavailability, and pharmacokinetics while minimizing side effects. In this review, we present an overview of recent advances in the preparation of LOC and contrast it with earlier in vitro models. Finally, we describe recent advances in LOC. The combination of this technology with nanomedicine will provide an accurate and reliable treatment for preclinical evaluation.

A comprehensive benchmarking of machine learning algorithms and dimensionality reduction methods for drug sensitivity prediction.

A major challenge of precision oncology is the identification and prioritization of suitable treatment options based on molecular biomarkers of the considered tumor. In pursuit of this goal, large cancer cell line panels have successfully been studied to elucidate the relationship between cellular features and treatment response. Due to the high dimensionality of these datasets, machine learning (ML) is commonly used for their analysis. However, choosing a suitable algorithm and set of input features can be challenging. We performed a comprehensive benchmarking of ML methods and dimension reduction (DR) techniques for predicting drug response metrics. Using the Genomics of Drug Sensitivity in Cancer cell line panel, we trained random forests, neural networks, boosting trees and elastic nets for 179 anti-cancer compounds with feature sets derived from nine DR approaches. We compare the results regarding statistical performance, runtime and interpretability. Additionally, we provide strategies for assessing model performance compared with a simple baseline model and measuring the trade-off between models of different complexity. Lastly, we show that complex ML models benefit from using an optimized DR strategy, and that standard models-even when using considerably fewer features-can still be superior in performance.

A hierarchical attention network integrating multi-scale relationship for drug response prediction

Anticancer drug response prediction with deep learning technology has become the foundation of precision medicine. It is essential for anticancer drug response prediction to incorporate multi-scale relationships within feature items and biomedical entities. Therefore, we propose MultiDRP that develops the hierarchical attention networks integrating multi-scale relationship for drug response prediction. MultiDRP can fuse both internal correlation of feature items and external relationship of biomedical entities by hierarchically integrating graph attention and self-attention networks to improve the anticancer drug response prediction. A variety of results showed that MultiDRP generated the great representation by integrating multi-scale relationships, and achieved higher performance compared to existing methods on various prediction scenarios. The results of network proximity, gene ontology biological process (GOBP) enrichment, and drug pathway association analysis show that MultiDRP can accurately screen the sensitive and resistant drugs for cancer cell lines. In vitro experiments, eight novel drugs predicted by MultiDRP exhibited high sensitivity to lung cancer cell line NCI-H23, seven of which showed IC50 values of less than 10 nM. These results further suggest that MultiDRP can serve as a powerful tool for anticancer drug response prediction. The source data and code are available at https://github.com/pengsl-lab/MultiDRP.git.

Predicting Drug Resistance in Gastric Cancer with Mutation in the Human Epidermal Growth Factor Receptor 2 (HER2) And Machine Learning Technique

Gastric cancer with mutations in the human epidermal growth factor receptor (HER2) can be regarded as one of the leading causes of cancer mortality in the world. Targeted tyrosine kinase inhibitors (TKIs) developed against HER2 yielded optimistic results in improving patients' survival rates and life quality. Nevertheless, drug resistance can influence the critical supportive documents of treatment plans and decrease the treatment effectiveness after about one year. Predicting the efficacy of HER2-TKI drugs or therapies for patients with HER2-mutated gastric cancer is a critical research field. In the present study, a personalized drug response prediction model based on molecular dynamics simulations and machine learning is presented to predict response to first-generation drugs approved by the Ministry of Health in patients with gastric cancer. In the molecular dynamics simulation, the patient's mutation status is considered. The patient's unique mutation status was modeled using molecular dynamics simulations to extract geometric features at the molecular level.Furthermore, additional clinical features are incorporated into the machine learning model to predict drug response. The complete features encompass demographic and clinical characteristics, geometrical properties of the drug-target binding site, and binding free energy (RBFE) of the drug-target complex from molecular dynamics simulations. Drug response prediction utilizes the XGBoost classifier, which achieved leading-edge performance for a 4-level drug response prediction task (PDRP) with 97.5% accuracy, 93% sensitivity, 96.5% specificity, and 94% F1 score. The present research has demonstrated that modeling the binding cavity geometry, in tandem with the binding free energy, can effectively predict drug response. Interestingly, the clinical information, while significant, did not significantly influence the model's performance. This exciting finding opens up new avenues for testing the proposed model on various types of cancers, potentially revolutionizing drug development strategies. DOI: https://doi.org/10.52783/pst.391

Improving Anticancer Drug Selection and Prioritization via Neural Learning to Rank.

Personalized cancer treatment requires a thorough understanding of complex interactions between drugs and cancer cell lines in varying genetic and molecular contexts. To address this, high-throughput screening has been used to generate large-scale drug response data, facilitating data-driven computational models. Such models can capture complex drug-cell line interactions across various contexts in a fully data-driven manner. However, accurately prioritizing the most effective drugs for each cell line still remains a significant challenge. To address this, we developed multiple neural ranking approaches that leverage large-scale drug response data across multiple cell lines from diverse cancer types. Unlike existing approaches that primarily utilize regression and classification techniques for drug response prediction, we formulated the objective of drug selection and prioritization as a drug ranking problem. In this work, we proposed multiple pairwise and listwise neural ranking methods that learn latent representations of drugs and cell lines and then use those representations to score drugs in each cell line via a learnable scoring function. Specifically, we developed neural pairwise and listwise ranking methods, Pair-PushC and List-One on top of the existing methods, pLETORg and ListNet, respectively. Additionally, we proposed a novel listwise ranking method, List-All, that focuses on all the effective drugs instead of the top effective drug, unlike List-One. We also provide an exhaustive empirical evaluation with state-of-the-art regression and ranking baselines on large-scale data sets across multiple experimental settings. Our results demonstrate that our proposed ranking methods mostly outperform the best baselines with significant improvements of as much as 25.6% in terms of selecting truly effective drugs within the top 20 predicted drugs (i.e., hit@20) across 50% test cell lines. Furthermore, our analyses suggest that the learned latent spaces from our proposed methods demonstrate informative clustering structures and capture relevant underlying biological features. Moreover, our comprehensive evaluation provides a thorough and objective comparison of the performance of different methods (including our proposed ones).

Prediction of anticancer drug sensitivity using an interpretable model guided by deep learning

BackgroundThe prediction of drug sensitivity plays a crucial role in improving the therapeutic effect of drugs. However, testing the effectiveness of drugs is challenging due to the complex mechanism of drug reactions and the lack of interpretability in most machine learning and deep learning methods. Therefore, it is imperative to establish an interpretable model that receives various cell line and drug feature data to learn drug response mechanisms and achieve stable predictions between available datasets.ResultsThis study proposes a new and interpretable deep learning model, DrugGene, which integrates gene expression, gene mutation, gene copy number variation of cancer cells, and chemical characteristics of anticancer drugs to predict their sensitivity. This model comprises two different branches of neural networks, where the first involves a hierarchical structure of biological subsystems that uses the biological processes of human cells to form a visual neural network (VNN) and an interpretable deep neural network for human cancer cells. DrugGene receives genotype input from the cell line and detects changes in the subsystem states. We also employ a traditional artificial neural network (ANN) to capture the chemical structural features of drugs. DrugGene generates final drug response predictions by combining VNN and ANN and integrating their outputs into a fully connected layer. The experimental results using drug sensitivity data extracted from the Cancer Drug Sensitivity Genome Database and the Cancer Treatment Response Portal v2 reveal that the proposed model is better than existing prediction methods. Therefore, our model achieves higher accuracy, learns the reaction mechanisms between anticancer drugs and cell lines from various features, and interprets the model’s predicted results.ConclusionsOur method utilizes biological pathways to construct neural networks, which can use genotypes to monitor changes in the state of network subsystems, thereby interpreting the prediction results in the model and achieving satisfactory prediction accuracy. This will help explore new directions in cancer treatment. More available code resources can be downloaded for free from GitHub (https://github.com/pangweixiong/DrugGene).

Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data.

Multi-omics data provide a comprehensive view of gene regulation at multiple levels, which is helpful in achieving accurate diagnosis of complex diseases like cancer. However, conventional integration methods rarely utilize prior biological knowledge and lack interpretability. To integrate various multi-omics data of tissue and liquid biopsies for disease diagnosis and prognosis, we developed a biological pathway informed Transformer, Pathformer. It embeds multi-omics input with a compacted multi-modal vector and a pathway-based sparse neural network. Pathformer also leverages criss-cross attention mechanism to capture the crosstalk between different pathways and modalities. We first benchmarked Pathformer with 18 comparable methods on multiple cancer datasets, where Pathformer outperformed all the other methods, with an average improvement of 6.3%-14.7% in F1 score for cancer survival prediction, 5.1%-12% for cancer stage prediction, and 8.1%-13.6% for cancer drug response prediction. Subsequently, for cancer prognosis prediction based on tissue multi-omics data, we used a case study to demonstrate the biological interpretability of Pathformer by identifying key pathways and their biological crosstalk. Then, for cancer early diagnosis based on liquid biopsy data, we used plasma and platelet datasets to demonstrate Pathformer's potential of clinical applications in cancer screening. Moreover, we revealed deregulation of interesting pathways (e.g. scavenger receptor pathway) and their crosstalk in cancer patients' blood, providing potential candidate targets for cancer microenvironment study. Pathformer is implemented and freely available at https://github.com/lulab/Pathformer.

PBAC: A pathway-based attention convolution neural network for predicting clinical drug treatment responses.

Precise and personalized drug application is crucial in the clinical treatment of complex diseases. Although neural networks offer a new approach to improving drug strategies, their internal structure is difficult to interpret. Here, we propose PBAC (Pathway-Based Attention Convolution neural network), which integrates a deep learning framework and attention mechanism to address the complex biological pathway information, thereby provide a biology function-based robust drug responsiveness prediction model. PBAC has four layers: gene-pathway layer, attention layer, convolution layer and fully connected layer. PBAC improves the performance of predicting drug responsiveness by focusing on important pathways, helping us understand the mechanism of drug action in diseases. We validated the PBAC model using data from four chemotherapy drugs (Bortezomib, Cisplatin, Docetaxel and Paclitaxel) and 11 immunotherapy datasets. In the majority of datasets, PBAC exhibits superior performance compared to traditional machine learning methods and other research approaches (area under curve = 0.81, the area under the precision-recall curve = 0.73). Using PBAC attention layer output, we identified some pathways as potential core cancer regulators, providing good interpretability for drug treatment prediction. In summary, we presented PBAC, a powerful tool to predict drug responsiveness based on the biology pathway information and explore the potential cancer-driving pathways.

Pharmacogenomics as a Tool in Addressing Genetic VariationDependent Adverse Drug Reactions

Adverse drug reactions (ADRs) are a cause of discontinuing drug development and withdrawal from market, as well as a very common source of morbidity and mortality. Genetic variables may be the primary predictor of drug response for certain medications, but they are estimated to account for 15– 30% of the variability in drug response. Many factors can contribute to adverse drug reactions, including genetics and drug targeting/delivery. Genetic markers, such as single nucleotide polymorphisms (SNPs) in drug-metabolizing enzymes, drug targets, and human leukocyte antigen (HLA) genotypes, have been associated with an increased risk of ADRs. Pharmacogenomics is the study of the genetic variation in the way that different people react to different pharmaceuticals, including variations in the risk of adverse drug reactions, dose requirements, and efficacy. The implementation of genetic data for predicting responses to medications and ADRs is becoming a reality in clinical practice, offering the potential to reduce the incidence of ADRs and improve patient outcomes. As pharmacogenomic research continues to advance, it holds great promise for enhancing drug safety and efficacy, ultimately leading to more tailored and effective therapeutic interventions.

Contradiction in Star-Allele Nomenclature of Pharmacogenes between Common Haplotypes and Rare Variants.

The nomenclature of star alleles has been widely used in pharmacogenomics to enhance treatment outcomes, predict drug response variability, and reduce adverse reactions. However, the discovery of numerous rare functional variants through genome sequencing introduces complexities into the star-allele system. This study aimed to assess the nature and impact of the rapid discovery of numerous rare functional variants in the traditional haplotype-based star-allele system. We developed a new method to construct haplogroups, representing a common ancestry structure, by iteratively excluding rare and functional variants of the 25 representative pharmacogenes using the 2504 genomes from the 1000 Genomes Project. In total, 192 haplogroups and 288 star alleles were identified, with an average of 7.68 ± 4.2 cross-ethnic haplogroups per gene. Most of the haplogroups (70.8%, 136/192) were highly aligned with their corresponding classical star alleles (VI = 1.86 ± 0.78), exhibiting higher genetic diversity than the star alleles. Approximately 41.3% (N = 119) of the star alleles in the 2504 genomes did not belong to any of the haplogroups, and most of them (91.3%, 105/116) were determined by a single variant according to the allele-definition table provided by CPIC. These functional single variants had low allele frequency (MAF < 1%), high evolutionary conservation, and variant deleteriousness, which suggests significant negative selection. It is suggested that the traditional haplotype-based naming system for pharmacogenetic star alleles now needs to be adjusted by balancing both traditional haplotyping and newly emerging variant-sequencing approaches to reduce naming complexity.

Mutation Patterns Predict Drug Sensitivity in Acute Myeloid Leukemia.

The inherent genetic heterogeneity of acute myeloid leukemia (AML) has challenged the development of precise and effective therapies. The objective of this study was to elucidate the genomic basis of drug resistance or sensitivity, identify signatures for drug response prediction, and provide resources to the research community. We performed targeted sequencing, high-throughput drug screening, and single-cell genomic profiling on leukemia cell samples derived from patients with AML. Statistical approaches and machine learning models were applied to identify signatures for drug response prediction. We also integrated large public datasets to understand the co-occurring mutation patterns and further investigated the mutation profiles in the single cells. The features revealed in the co-occurring or mutual exclusivity pattern were further subjected to machine learning models. We detected genetic signatures associated with sensitivity or resistance to specific agents, and identified five co-occurring mutation groups. The application of single-cell genomic sequencing unveiled the co-occurrence of variants at the individual cell level, highlighting the presence of distinct subclones within patients with AML. Using the mutation pattern for drug response prediction demonstrates high accuracy in predicting sensitivity to some drug classes, such as MEK inhibitors for RAS-mutated leukemia. Our study highlights the importance of considering the gene mutation patterns for the prediction of drug response in AML. It provides a framework for categorizing patients with AML by mutations that enable drug sensitivity prediction.

Prediction of immunochemotherapy response for diffuse large B-cell lymphoma using artificial intelligence digital pathology.

Diffuse large B-cell lymphoma (DLBCL) is a heterogeneous and prevalent subtype of aggressive non-Hodgkin lymphoma that poses diagnostic and prognostic challenges, particularly in predicting drug responsiveness. In this study, we used digital pathology and deep learning to predict responses to immunochemotherapy in patients with DLBCL. We retrospectively collected 251 slide images from 216 DLBCL patients treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP), with their immunochemotherapy response labels. The digital pathology images were processed using contrastive learning for feature extraction. A multi-modal prediction model was developed by integrating clinical data and pathology image features. Knowledge distillation was employed to mitigate overfitting on gigapixel histopathology images to create a model that predicts responses based solely on pathology images. Based on the importance derived from the attention mechanism of the model, we extracted histological features that were considered key textures associated with drug responsiveness. The multi-modal prediction model achieved an impressive area under the ROC curve of 0.856, demonstrating significant associations with clinical variables such as Ann Arbor stage, International Prognostic Index, and bulky disease. Survival analyses indicated their effectiveness in predicting relapse-free survival. External validation using TCGA datasets supported the model's ability to predict survival differences. Additionally, pathology-based predictions show promise as independent prognostic indicators. Histopathological analysis identified centroblastic and immunoblastic features to be associated with treatment response, aligning with previous morphological classifications and highlighting the objectivity and reproducibility of artificial intelligence-based diagnosis. This study introduces a novel approach that combines digital pathology and clinical data to predict the response to immunochemotherapy in patients with DLBCL. This model shows great promise as a diagnostic and prognostic tool for clinical management of DLBCL. Further research and genomic data integration hold the potential to enhance its impact on clinical practice, ultimately improving patient outcomes.

Abstract LB435: Large panel organoid drug testing combined with biomarker analysis: Unveiling prospects for mechanism of action identification and preclinical patient stratification

Abstract Introduction The development of oncology drugs has a persistently high attrition rate of greater than 95%, requiring the development and implementation of novel models and technologies aimed at better predictive abilities during the preclinical phase. Among these, organoid technologies, which involve propagating tumor stem cells in a near-native state, have proven to markedly advance drug testing with enhanced precision. Our previously developed assay-ready organoid technology has paved the way for large panel organoid screening, allowing organoids to augment the efficiency of drug development pipelines, boost patient-derived model usage in preclinical studies, and facilitate accurate predictions of drug action mechanisms. Here, we present a proof-of-concept (POC) large scale organoid experiment, studying the responses of 50 models to the cytotoxic agent paclitaxel, using next generation sequencing data to analyze the drug mechanism of action (MOA) and identify biomarkers that predict drug responses. Methods A panel of 50 organoid models was characterized for paclitaxel response in 9-dose-response curves by measuring ATP levels after a 5-day exposure. Models were genomically profiled by whole-exome sequencing (n = 47) and whole-transcriptome sequencing (n = 44) to analyze the association between organoid pharmacology data and genomic information and elucidate genes and pathways that may be related with, or predictive of, the treatment responses. We performed biomarker analysis on gene expression, mutation, and copy number alteration levels. Results By assessing organoid sensitivity to paclitaxel, we observed no significant indication-specific difference in organoid responses across 7 cancer types. The 50 models were then categorized into responders (AUC &amp;lt; 1.5; n=15) and non-responders (AUC &amp;gt; 2.6; n=14) for biomarker discovery. Differential expression analysis and pathway activation analysis revealed genes and pathways involved in the cell cycle and DNA replication. DNA recombination differentiates responders from non-responders, while genes involved in epithelial cell proliferation, differentiation, and wound healing are associated with drug resistance. Mutation of proto-oncogene RB Transcriptional Corepressor 1, RB1 (a negative regulator of the cell cycle), was found to be a biomarker enriched in non-responders to paclitaxel, corroborating earlier clinical findings. Using the identified profile, we predicted responses for non-tested models in our biobank and validated our approach. Conclusion Large panel organoid drug screening in combination with biomarker analysis brings great opportunities for increasing drug pipeline efficiency. The POC here presented highlights how such a screen can identify MOAs and identify relevant biomarker profiles to be used in clinical trial patient stratification. Citation Format: Linda Xue, Liza Wijler, Marten Hornsveld, Sheng Guo, Leo Price, Marrit Putker, Ludovic Bourre. Large panel organoid drug testing combined with biomarker analysis: Unveiling prospects for mechanism of action identification and preclinical patient stratification [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB435.

DBDNMF: A Dual Branch Deep Neural Matrix Factorization method for drug response prediction.

Anti-cancer response of cell lines to drugs is in urgent need for individualized precision medical decision-making in the era of precision medicine. Measurements with wet-experiments is time-consuming and expensive and it is almost impossible for wide ranges of application. The design of computational models that can precisely predict the responses between drugs and cell lines could provide a credible reference for further research. Existing methods of response prediction based on matrix factorization or neural networks have revealed that both linear or nonlinear latent characteristics are applicable and effective for the precise prediction of drug responses. However, the majority of them consider only linear or nonlinear relationships for drug response prediction. Herein, we propose a Dual Branch Deep Neural Matrix Factorization (DBDNMF) method to address the above-mentioned issues. DBDNMF learns the latent representation of drugs and cell lines through flexible inputs and reconstructs the partially observed matrix through a series of hidden neural network layers. Experimental results on the datasets of Cancer Cell Line Encyclopedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC) show that the accuracy of drug prediction exceeds state-of-the-art drug response prediction algorithms, demonstrating its reliability and stability. The hierarchical clustering results show that drugs with similar response levels tend to target similar signaling pathway, and cell lines coming from the same tissue subtype tend to share the same pattern of response, which are consistent with previously published studies.

New role of platelets in schizophrenia: predicting drug response

BackgroundElevated platelet count (PLTc) is associated with first-episode schizophrenia and adverse outcomes in individuals with precursory psychosis. However, the impact of antipsychotic medications on PLTc and its association with symptom...

Drug Response Prediction Using XGBOOST

Abstract: An essential issue in computational personalised medicine is the prediction of drug responses. There have been several proposals for approaches to this problem that rely on machine learning, particularly deep learning. Nevertheless, these approaches often portray the medications as strings, an implausible representation of molecules. Furthermore, there has been a lack of comprehensive consideration of interpretation, such as whether mutations or copy number aberrations contribute to the medication response. Graph DRP, a new approach based on graph convolution networks, is suggested as a solution to the issue in this research. Cell lines were displayed as double vectors of genetic abnormalities in Graph DRP, whereas medications were shown as sub-atomic chartsthat straightforwardly caught the bonds among particles.

Hi-GeoMVP: a hierarchical geometry-enhanced deep learning model for drug response prediction.

Personalized cancer treatments require accurate drug response predictions. Existing deep learning methods show promise but higher accuracy is needed to serve the purpose of precision medicine. The prediction accuracy can be improved with not only topology but geometrical information of drugs. A novel deep learning methodology for drug response prediction is presented, named Hi-GeoMVP. It synthesizes hierarchical drug representation with multi-omics data, leveraging graph neural networks and variational autoencoders for detailed drug and cell line representations. Multi-task learning is employed to make better prediction, while both 2D and 3D molecular representations capture comprehensive drug information. Testing on the GDSC dataset confirms Hi-GeoMVP's enhanced performance, surpassing prior state-of-the-art methods by improving the Pearson correlation coefficient from 0.934 to 0.941 and decreasing the root mean square error from 0.969 to 0.931. In the case of blind test, Hi-GeoMVP demonstrated robustness, outperforming the best previous models with a superior Pearson correlation coefficient in the drug-blind test. These results underscore Hi-GeoMVP's capabilities in drug response prediction, implying its potential for precision medicine. The source code is available at https://github.com/matcyr/Hi-GeoMVP.

Novel peripheral blood mononuclear cell mRNA signature for IFN-beta therapy responsiveness prediction in multiple sclerosis

Interferon-beta (IFN- β ) is one of the classical drugs for immunomodulatory therapy in relapsing-remitting multiple sclerosis (RRMS) patients, but the drug responsiveness of different patients varies. Currently, there is no valid model to predict IFN- β responsiveness. This research attempted to develop an IFN- β responsiveness prediction model based on mRNA expression in RRMS patient peripheral blood mononuclear cells. Peripheral blood mononuclear cell mRNA expression datasets including 50 RRMS patients receiving IFN- β treatment were obtained from GEO. Among the datasets, 24 cases from GSE24427 were included in a training set, and 18 and 9 cases from GSE19285 and GSE33464, respectively, were adopted as two independent test sets. In the training set, blood samples were collected immediately before first, second, month 1, 12, and 24 IFN- β injection, and the mRNA expression data at four time points, namely, two days, one month, one year and two years after the onset of IFN- β treatment, were compared with pre-treatment data to identify IFN-stimulated genes (ISGs). The ISGs at the one-month time point were used to construct the drug responsiveness prediction model. Next, the drug responsiveness model was verified in the two independent test sets to examine the performance of the model in predicting drug responsiveness. Finally, we used CIBERSORTx to estimate the content of cell subtypes in samples and evaluated whether differences in the proportions of cell subtypes were related to differences in IFN- β responsiveness. Among the four time points, one month was the time point when the training set GSE24427 and test set GSE33464 had the highest number of ISGs. Functional analysis showed that these one-month ISGs were enriched in biological functions such as the innate immune response, type-I interferon signalling pathway, and other IFN- β -associated functions. Based on these ISGs, we obtained a four-factor prediction model for IFN- β responsiveness including MX1, MX2, XAF1, and LAMP3. In addition, the model demonstrated favourable predictive performance within the training set and two external test sets. A higher proportion of activated NK cells and lower naive CD4/total CD4 ratio might indicate better drug responsiveness. This research developed a polygene-based biomarker model that could predict RRMS patient IFN- β responsiveness in the early treatment period. This model could probably help doctors screen out patients who would not benefit from IFN- β treatment early and determine whether a current treatment plan should be continued.