Trends in Phase II Trials for Cancer Therapies

DDSBC: A Stacking Ensemble Classifier-Based Approach for Breast Cancer Drug-Pair Cell Synergy Prediction

Breast cancer (BC) ranks as a leading cause of mortality among women worldwide, with incidence rates continuing to rise. The quest for effective treatments has led to the adoption of drug combination therapy, aiming to enhance drug efficacy. However, identifying synergistic drug combinations remains a daunting challenge due to the myriad of potential drug pairs. Current research leverages machine learning (ML) and deep learning (DL) models for drug-pair synergy prediction and classification. Nevertheless, these models often underperform on specific cancer types, including BC, as they are trained on data spanning various cancers without any specialization. Here, we introduce a stacking ensemble classifier, the drug-drug synergy for breast cancer (DDSBC), tailored explicitly for BC drug-pair cell synergy classification. Unlike existing models that generalize across cancer types, DDSBC is exclusively developed for BC, offering a more focused approach. Our comparative analysis against classical ML methods as well as DL models developed for drug synergy prediction highlights DDSBC's superior performance across test and independent datasets on BC data. Despite certain metrics where other methods narrowly surpass DDSBC by 1-2%, DDSBC consistently emerges as the top-ranked model, showcasing significant differences in scoring metrics and robust performance in ablation studies. DDSBC's performance and practicality position it as a preferred choice or an adjunctive validation tool for identifying synergistic or antagonistic drug pairs in BC, providing valuable insights for treatment strategies.

Evaluation of the tumor-targeting specific imaging and killing effect of a CEA-targeting nanoparticle in colorectal cancer

INTRODUCTION

Colorectal cancer (CRC) is a prevalent digestive malignancy with significant global mortality and morbidity rates. Improving diagnostic capabilities for CRC and investigating novel therapeutic approaches are pressing clinical imperatives. Additionally, carcinoembryonic antigen (CEA) has emerged as a highly promising candidate for both colorectal tumor imaging and treatment.

METHODS

A novel active CEA-targeting nanoparticle, CEA(Ab)-MSNs-ICG-Pt, was designed and synthesized, which served as a tumor-specific fluorescence agent to help in CRC near-infrared (NIR) fluorescence imaging. In cell studies, CEA(Ab)-MSNs-ICG-Pt exhibited specific targeting to RKO cells through specific antibody-antigen binding of CEA, resulting in distribution both within and around these cells. The tumor-targeting-specific imaging capabilities of the nanoparticle were determined through in vivo fluorescence imaging experiments. Furthermore, the efficacy of the nanoparticle in delivering chemotherapeutics and its killing effect were evaluated both in vitro and in vivo.

RESULTS

The CEA(Ab)-MSNs-ICG-Pt nanoparticle, designed as a novel targeting agent for carcinoembryonic antigen (CEA), exhibited dual functionality as a targeting fluorescent agent. This CEA-targeting nanoparticle showed exceptional efficacy in eradicating CRC cells in comparison to individual treatment modalities. Furthermore, it exhibits exceptional biosafety and biocompatibility properties. CEA(Ab)-MSNs-ICG-Pt exhibits significant promise due to its ability to selectively target tumors through NIR fluorescence imaging and effectively eradicate CRC cells with minimal adverse effects in both laboratory and in vivo environments.

CONCLUSION

The favorable characteristics of CEA(Ab)-MSNs-ICG-Pt offer opportunities for its application in chemotherapeutic interventions, tumor-specific NIR fluorescence imaging, and fluorescence-guided surgical procedures.

Deep graph contrastive learning model for drug-drug interaction prediction

Drug-drug interaction (DDI) is the combined effects of multiple drugs taken together, which can either enhance or reduce each other's efficacy. Thus, drug interaction analysis plays an important role in improving treatment effectiveness and patient safety. It has become a new challenge to use computational methods to accelerate drug interaction time and reduce its cost-effectiveness. The existing methods often do not fully explore the relationship between the structural information and the functional information of drug molecules, resulting in low prediction accuracy for drug interactions, poor generalization, and other issues. In this paper, we propose a novel method, which is a deep graph contrastive learning model for drug-drug interaction prediction (DeepGCL for brevity). DeepGCL incorporates a contrastive learning component to enhance the consistency of information between different views (molecular structure and interaction network), which means that the DeepGCL model predicts drug interactions by integrating molecular structure features and interaction network topology features. Experimental results show that DeepGCL achieves better performance than other methods in all datasets. Moreover, we conducted many experiments to analyze the necessity of each component of the model and the robustness of the model, which also showed promising results. The source code of DeepGCL is freely available at https://github.com/jzysj/DeepGCL.

PermuteDDS: a permutable feature fusion network for drug-drug synergy prediction

MOTIVATION

Drug combination therapies have shown promise in clinical cancer treatments. However, it is hard to experimentally identify all drug combinations for synergistic interaction even with high-throughput screening due to the vast space of potential combinations. Although a number of computational methods for drug synergy prediction have proven successful in narrowing down this space, fusing drug pairs and cell line features effectively still lacks study, hindering current algorithms from understanding the complex interaction between drugs and cell lines.

RESULTS

In this paper, we proposed a Permutable feature fusion network for Drug-Drug Synergy prediction, named PermuteDDS. PermuteDDS takes multiple representations of drugs and cell lines as input and employs a permutable fusion mechanism to combine drug and cell line features. In experiments, PermuteDDS exhibits state-of-the-art performance on two benchmark data sets. Additionally, the results on independent test set grouped by different tissues reveal that PermuteDDS has good generalization performance. We believed that PermuteDDS is an effective and valuable tool for identifying synergistic drug combinations. It is publicly available at https://github.com/littlewei-lazy/PermuteDDS .

SCIENTIFIC CONTRIBUTION

First, this paper proposes a permutable feature fusion network for predicting drug synergy termed PermuteDDS, which extract diverse information from multiple drug representations and cell line representations. Second, the permutable fusion mechanism combine the drug and cell line features by integrating information of different channels, enabling the utilization of complex relationships between drugs and cell lines. Third, comparative and ablation experiments provide evidence of the efficacy of PermuteDDS in predicting drug-drug synergy.

Risk and benefit for umbrella trials in oncology: a systematic review and meta-analysis

BACKGROUND

Umbrella clinical trials in precision oncology are designed to tailor therapies to the specific genetic changes within a tumor. Little is known about the risk/benefit ratio for umbrella clinical trials. The aim of our systematic review with meta-analysis was to evaluate the efficacy and safety profiles in cancer umbrella trials testing targeted drugs or a combination of targeted therapy with chemotherapy.

METHODS

Our study was prospectively registered in PROSPERO (CRD42020171494). We searched Embase and PubMed for cancer umbrella trials testing targeted agents or a combination of targeted therapies with chemotherapy. We included solid tumor studies published between 1 January 2006 and 7 October 2019. We measured the risk using drug-related grade 3 or higher adverse events (AEs), and the benefit by objective response rate (ORR), progression-free survival (PFS), and overall survival (OS). When possible, data were meta-analyzed.

RESULTS

Of the 6207 records identified, we included 31 sub-trials or arms of nine umbrella trials (N = 1637). The pooled overall ORR was 17.7% (95% confidence interval [CI] 9.5-25.9). The ORR for targeted therapies in the experimental arms was significantly lower than the ORR for a combination of targeted therapy drugs with chemotherapy: 13.3% vs 39.0%; p = 0.005. The median PFS was 2.4 months (95% CI 1.9-2.9), and the median OS was 7.1 months (95% CI 6.1-8.4). The overall drug-related death rate (drug-related grade 5 AEs rate) was 0.8% (95% CI 0.3-1.4), and the average drug-related grade 3/4 AE rate per person was 0.45 (95% CI 0.40-0.50).

CONCLUSIONS

Our findings suggest that, on average, one in five cancer patients in umbrella trials published between 1 January 2006 and 7 October 2019 responded to a given therapy, while one in 125 died due to drug toxicity. Our findings do not support the expectation of increased patient benefit in cancer umbrella trials. Further studies should investigate whether umbrella trial design and the precision oncology approach improve patient outcomes.

DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations

MOTIVATION

Drug combination therapy has become an increasingly promising method in the treatment of cancer. However, the number of possible drug combinations is so huge that it is hard to screen synergistic drug combinations through wet-lab experiments. Therefore, computational screening has become an important way to prioritize drug combinations. Graph neural network has recently shown remarkable performance in the prediction of compound-protein interactions, but it has not been applied to the screening of drug combinations.

RESULTS

In this paper, we proposed a deep learning model based on graph neural network and attention mechanism to identify drug combinations that can effectively inhibit the viability of specific cancer cells. The feature embeddings of drug molecule structure and gene expression profiles were taken as input to multilayer feedforward neural network to identify the synergistic drug combinations. We compared DeepDDS (Deep Learning for Drug-Drug Synergy prediction) with classical machine learning methods and other deep learning-based methods on benchmark data set, and the leave-one-out experimental results showed that DeepDDS achieved better performance than competitive methods. Also, on an independent test set released by well-known pharmaceutical enterprise AstraZeneca, DeepDDS was superior to competitive methods by more than 16% predictive precision. Furthermore, we explored the interpretability of the graph attention network and found the correlation matrix of atomic features revealed important chemical substructures of drugs. We believed that DeepDDS is an effective tool that prioritized synergistic drug combinations for further wet-lab experiment validation.

AVAILABILITY AND IMPLEMENTATION

Source code and data are available at https://github.com/Sinwang404/DeepDDS/tree/master.

Risk and Benefit for Targeted Therapy Agents in Pediatric Phase II Trials in Oncology: A Systematic Review with a Meta-Analysis

BACKGROUND

For research with human participants to be ethical, risk must be in a favorable balance with potential benefits. Little is known about the risk/benefit ratio for pediatric cancer phase II trials testing targeted therapies.

OBJECTIVE

Our aim was to conduct a systematic review of preliminary efficacy and safety profiles of phase II targeted therapy clinical trials in pediatric oncology.

METHODS

Our protocol was prospectively registered in PROSPERO (CRD42020146491). We searched EMBASE and PubMed for phase II pediatric cancer trials testing targeted agents. We included solid and hematological malignancy studies published between 1 January, 2015 and 27 February, 2020. We measured risk using drug-related grade 3 or higher adverse events, and benefit by response rates. When possible, data were meta-analyzed. All statistical tests were two-sided.

RESULTS

We identified 34 clinical trials (1202 patients) that met our eligibility criteria. The pooled overall response rate was 24.4% (95% confidence interval [CI] 14.5-34.2) and was lower in solid tumors, 6.4% (95% CI 3.2-9.6), compared with hematological malignancies, 55.1% (95% CI 35.9-74.3); p < 0.001. The overall fatal drug-related (grade 5) adverse event rate was 1.6% (95% CI 0.6-2.5), and the average drug-related grade 3/4 adverse event rate per person was 0.66 (95% CI 0.55-0.78).

CONCLUSIONS

We provide an estimate for the risks and benefits of participation in pediatric phase II cancer trials. These data may be used as an empirical basis for informed communication about benefits and burdens in pediatric oncology research.