Aug 2026· Pharmaceuticals· Vol 19, pp. 1363· 0 citations· 43 references
TL;DR
The BIRC5-NAMPT-TOP1 combination showed reproducible phenotypic activity in the tested genetic and pharmacological models and support the use of DeepMDS as a hypothesis-generation tool for higher-order target prioritization.
Abstract
Background/Objectives: Breast cancer exhibits substantial molecular heterogeneity, resulting in diverse therapeutic vulnerabilities and limiting the efficacy of single-agent therapies. Although multi-target strategies may offer improved therapeutic benefit, the systematic identification of synergistic higher-order target combinations remains challenging. This study aimed to identify and validate effective higher-order target combinations for heterogeneous breast cancer. Methods: DeepMDS, a previously developed deep learning-based multi-compound synergy prediction model, was used to prioritize candidate target combinations for breast cancer. Exhaustive two-target and three-target combinations were ranked in the gene-expression contexts of ER-positive luminal-like MCF-7 and triple-negative MDA-MB-231 breast cancer cells. The top-ranked target combinations were evaluated using single, pairwise, and triple small interfering RNA (siRNA) perturbations. Representative inhibitors were subsequently assessed in fixed-ratio combinations in MCF-7, MDA-MB-231, and 4T1 cells and in a 4T1 syngeneic mouse experiment. Results: BIRC5-NAMPT-TOP1 ranked first in both cell lines. Triple siRNA co-transfection targeting BIRC5, NAMPT, and TOP1 produced the strongest antiproliferative effects, with inhibition rates of 62.94% in MCF-7 cells and 55.62% in MDA-MB-231 cells. The corresponding inhibitors, LQZ-7I, FK866, and topotecan, exhibited synergistic antiproliferative activity at multiple molar ratios, with combination index values below 1. The optimized 2.5:10:1 molar ratio showed strong synergy in MCF-7, MDA-MB-231, and 4T1 cells, with combination index values of 0.26, 0.19, and 0.15, respectively. In tumor-bearing mice model, the triple-inhibitor regimen achieved a tumor inhibition rate of 62.05%. Topotecan-containing groups showed hematological alterations, whereas no statistically detectable elevations were observed in the measured terminal serum hepatic or renal biomarkers. Conclusions: The BIRC5-NAMPT-TOP1 combination showed reproducible phenotypic activity in the tested genetic and pharmacological models. These findings support the use of DeepMDS as a hypothesis-generation tool for higher-order target prioritization.
This study demonstrates the viability of the deep learning models to discover structurally novel anticancer agents that are distinct from conventional drugs, thereby expanding the therapeutic arsenal for TNBC patients.
Yiyue Xu, Taotao Dong, Butuo Li et al.· Journal of Chemical Informat...· 0 citations
Breast cancer is a complex and heterogeneous disease that remains a major global health challenge. Recent progress in molecular biology, artificial intelligence (AI), and precision medicine has transformed its diagnosis and treatment. Conventional biomarkers such as ER, PR, HER2, and BRCA mutations continue to guide therapeutic decisions, while emerging biomarkers including TP53, PTEN, and STK11 offer new insights into tumor behavior and drug resistance. AI-based technologies, including machine learning and deep learning, have improved early detection and diagnostic accuracy through advanced medical imaging and multimodal analysis. Current treatment strategies extend beyond conventional chemotherapy and surgery to include targeted therapy, endocrine therapy, immunotherapy, antibody-drug conjugates, and gene-based approaches. Novel therapeutics such as CDK4/6 inhibitors, PARP inhibitors, PI3K inhibitors, and selective estrogen receptor degraders have demonstrated promising clinical outcomes in advanced breast cancer. Additionally, emerging technologies such as CRISPR/Cas9 gene editing and nanotechnology-based drug delivery systems show significant potential for personalized cancer therapy. This review summarizes recent advancements in breast cancer biomarkers, AI-assisted diagnostics, and modern therapeutic strategies aimed at improving precision medicine and patient outcomes.
Divya Sharma, Peeyush Bhardwaj, Kaushalendra Kumar Mishra et al.· Cancer Treatment and Researc...· 0 citations
MOTIVATION
As unique drugs positioned between small and macro molecules, anticancer peptides (ACPs) hold great potential in oncotherapy owing to their high selectivity and low toxicity. Nowadays, computational ACP prediction has emerged as a cost-effective alternative to bioassay screening, but most methods are limited to identifying bioactivity and fail to resolve tumor cell-specific targeting, primarily because of the sparse annotated data.
RESULTS
To fill this gap, we integrate a hybrid dataset compiled from five well-established peptide databases and propose TargetPC, a deep learning method tailored for cell line-targeted ACP prediction. TargetPC encodes multimodal representations of ACPs and cell lines via pretrained protein and omics models, and combines them via hierarchical intra- and inter-modal fusion for targeting prediction. This combination is further augmented by a mutual learning paradigm that distills domain knowledge from both ACP and cell line, enabling improved generalization under sparse supervision. Experimental results on the hybrid dataset demonstrate the effectiveness of TargetPC, which outperforms the state-of-the-art baselines in terms of prediction accuracy, and maintains strong generalization to unseen ACPs and cell lines. When extended to out-of-distribution samples, TargetPC has successfully screened dozens of novel ACPs targeted to breast cancer cells and uncovered biological motifs underlying its predictions. As a result, our TargetPC is expected to serve as a versatile tool for lead ACP discovery at a lower burden.
AVAILABILITY
The source code and data are available at GitHub (https://github.com/liuxuan666/TargetPC).
Xuan Liu, Jian Zhang, Chong-Yang Chen et al.· Bioinformatics· 0 citations
Colorectal cancer (CRC) exhibits high genetic heterogeneity and frequent resistance to single-agent therapies, highlighting the need for rationally designed drug combinations. We apply a mechanistic modelling framework to prioritise synergistic combinations in 16 CRC cell lines. Simulations of 210 double perturbations among 21 targeted inhibitors guided the selection of 17 combinations for experimental validation. Of 704 tested conditions, 68% showed synergy, most involving PI3K/AKT/MTOR-related inhibitors. We report six novel compound combinations that inhibit CRC cell-line growth by targeting MTOR and ERK, or MTOR and BCL2. In silico analysis indicates that feedback suppression via S6K–FOXO3 mediates the MTORi–ERKi synergy, whereas apoptotic reinforcement explains the MTORi–BCL2i effect. These results demonstrate that model-guided prioritisation enables the efficient discovery of synergistic drug pairs, mechanistic insight into their action, and a scalable route to rational combination-therapy design in CRC.
Viviam Solangeli Bermúdez Paiva, H. Bwanika, M.S. Sigfúsdóttir et al.· npj Systems Biology and Appl...· 0 citations
Background: Chemotherapy is a fundamental and rapidly acting modality for cancer treatment that employs specific anticancer agents such as cyclophosphamide, 5-fluorouracil, and methotrexate. It is administered either with curative intent, typically through defined drug combinations, or with palliative intent, aiming to prolong survival and alleviate symptoms. Aim: This work highlights the transformative synergy between artificial intelligence (AI) and quantum biology in advancing the detection and treatment of breast cancer. Recent clinical research in chemotherapy underscores the expanding role of AI-driven deep learning (DL) frameworks and machine learning (ML) applications in OMIC-based precision diagnostics, rational drug design, and personalized therapeutic strategies enabled through biomarker discovery. The integration of intelligent medical engineering with quantum biological principles and deep learning methodologies offers significant advancements in targeted drug delivery, minimizes the adverse effects and toxicity associated with chemotherapeutic agents, and enables robust real-time monitoring of treatment responses. Collectively, these innovations demonstrate substantial potential to enhance therapeutic efficacy and improve clinical outcomes in breast cancer (BC) management. Methodology: We simulated a series of anti-breast-cancer agents including cyclophosphamide, 5-fluorouracil, and methotrexate combined via a polyethylene glycol (PEG) linker using QM/MM methods. This approach aims to improve therapeutic effectiveness while reducing side effects, guided by deep learning and AI-based optimization strategies. Finally, this study provides an overview of current trends in AI-based healthcare nanotechnologies and concludes that the integration of AI into healthcare offers significant benefits, paving the way toward a more advanced and effective future in medicine. Results: PEG conjugation in CP–[PEG(n)]–5-FU conjugates represents a strategy to extend circulation time and reduce immunogenicity by increasing hydrodynamic size and shielding epitopes from immune surveillance .The amino acids from the ligand {CP–[PEG(n)]–5-FU (n = 2–18)} that interact with 1JNX are Cys1697, Arg1699, and Asp1739 in the H–M interaction, Asp1692 and Cys1692 in the V–M interaction, Glu1698 and Val1740 in the V–S interaction, and finally only one residue (Glu1698) in the H–S interaction. These residues are also completely located within the active site of 1JNX, which represents the crystal structure of the BRCT region associated with BC. Conclusions: Up to now, biotechnology in medical Artificial intelligence (AI) has immense potential for various applications in the pharmaceutical industry. AI enables the design of novel drugs for delivery to tissue and cell targets based on the discovery of specific chemical structures. A subfield of AI known as machine learning is commonly used in disease analysis and detection. Obviously, the results of predicting experimental help improve the precision of the testing output, significantly. Based on machine learning analysis, the systems {CP–[PEG(n)]–5-FU (n = 30–35)} were identified as the most favorable candidates for these simulations.
Majid Monajjemi, Oktay Bıyıklıoğlu, F. Mollaamin et al.· Revista Colombiana de Cienci...· 0 citations
Breast cancer is characterized by marked heterogeneity and redundant signaling networks, which leave single-target treatments susceptible to adaptive resistance. Traditional combination treatments are often limited by inconsistent pharmacokinetic profiles and cumulative systemic toxicity. In contrast, dual-target inhibitors enable concurrent regulation of two functionally related biological targets within a single molecular framework, effectively overcoming target-specific drug resistance and addressing the pharmacokinetic asynchrony characteristic of multi-drug regimens. Consequently, the design of dual-target drugs has become a prominent area of research in anticancer drug development. From a rational molecular design perspective, this review systematically summarizes advancements over the past five years (2020-2025) in the construction of dual-target anticancer agents using mainstream strategies, including pharmacophore fusion and scaffold hopping. Additionally, we highlight typical dual-target candidates involved in epigenetic remodeling, synthetic lethality coupled with DNA damage repair, synergistic inhibition of kinase pathways, and modulation of the tumor microenvironment, emphasizing their design principles, structure-activity relationships (SAR), and underlying pharmacological mechanisms. Overall, the perspectives presented herein aim to provide a theoretical framework to support the rational development of highly effective, low-toxicity anticancer agents with promising potential for clinical translation.
Guang-Huan Shen, Yong-Hui Wang, Shihao Li et al.· Bioorganic chemistry (Print)· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
