Machine learning-powered discovery of a novel berberine derivative inducing SCD-dependent ferroptosis in osteosarcoma

He et al. Journal of Translational Medicine (2025) 23:1328 https://doi.org/10.1186/s12967-025-07358-6 Journal of Translational Medicine Open Access RESEARCH Machine learning-powered discovery of a novel berberine derivative inducing SCDdependent ferroptosis in osteosarcoma Mingyu He1†, Yanyan Liu1†, Tao Li2, Ying Liu2, Xinyue Wang2, Jiajie Xie3, Ao Wang2, Yanquan Wang2, Ye Yuan3,4*, Min Cui1* and Zhimin Du1,5* Abstract Background Despite decades of therapeutic development, osteosarcoma survival remains poor. Although berberine (BBR) shows anti-tumor activity, its efficacy is limited. We addressed this through structural modification and machine learning-guided discovery, developing a novel derivative: 9-O-methoxyethylberberrubine bromide (B1). Methods In vivo, subcutaneous and orthotopic models were established in BALB/c nude mice using 143B cells. Treatment groups received daily B1 (0.1-5 mg/kg) or berberine (5, 50 mg/kg); a positive control group received doxorubicin (1 mg/kg). Tumor growth was assessed by volume and weight; tissue necrosis, proliferation, and apoptosis were analyzed. In vitro, human osteosarcoma cells (143B, U2OS, HOS) and human bone marrow mesenchymal stem cells (hBMSCs) were treated with B1, and anti-proliferation was evaluated via CCK-8, EdU, colony formation, and transwell assays. We integrated machine learning into our proteomic discovery pipeline to prioritize critical targets. Proteomic sequencing was followed by multi-algorithm feature selection including least absolute shrinkage and selection operator (LASSO), Ridge, Elastic Net, mRMR, and univariate filtering. Mechanistic validations employed molecular docking, thermal shift assays, surface plasmon resonance (SPR), co-immunoprecipitation, ubiquitination assays, and lipidomics. single-cell RNA sequencing compared malignant osteosarcoma cells with normal bone microenvironment components. Results B1 exhibited dose-dependent anti-tumor effects superior to BBR. Machine learning-driven integration of proteomic profiles unanimously nominated Sterol CoA desaturase (SCD) as the key target across all feature selection algorithms, showing both maximal relevance and minimal redundancy. Mechanistically, B1 acts as a molecular glue that recruits the E3 ligase neural precursor cell expressed, developmentally down-regulated 4-like (NEDD4L) to SCD, inducing its ubiquitination and degradation. Single-cell RNA sequencing confirmed significant overexpression of † Mingyu He and Yanyan Liu are contributed equally to this work. *Correspondence: Ye Yuan Min Cui Zhimin Du Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. He et al. Journal of Translational Medicine (2025) 23:1328 Page 2 of 23 SCD in malignant osteosarcoma cells, further highlighting its therapeutic relevance. Computationally prioritized SCD targeting disrupted lipid metabolism, causing saturated lipid accumulation, mitochondrial damage, and oxidative stress. This ultimately promoted glutathione peroxidase 4 (GPX4)-mediated lipid peroxidation and ferroptosis. Resistance to B1 occurred with SCD overexpression, while arachidonic acid supplementation partially restored tumor survival. Conclusions By incorporating machine learning into drug target discovery, we established B1 as a ferroptosis inducer targeting the NEDD4L-SCD axis. Our study provides both a robust therapeutic strategy against chemoresistant osteosarcoma and a compelling blueprint for AI-augmented oncology drug development. Graphical Abstract Keywords Berberine derivative, 9-O-methoxyethylberberrubine bromide, Osteosarcoma, Machine learning, SCD, NEDD4L, Ferroptosis Background Osteosarcoma (OS), a primary malignant tumor originating in the bone marrow, poses a significant health threat to young adults aged 10 to 25 years [1]. Over the past 30 years, improvements in patient survival rates for osteosarcoma have been largely incremental [2]. Currently, the MAP regimen, which includes high-dose methotrexate, cisplatin, and doxorubicin, is the standard first-line treatment for patients diagnosed with osteosarcoma [3]. As treatment strategies evolve, the combination of neoadjuvant chemotherapy and surgical intervention has contributed to an enhanced overall survival rate. However, clinical outcomes for osteosarcoma patients have not demonstrated substantial improvements in recent decades. Additionally, chemotherapy resistance is a prevalent issue, with the 5-year survival rate remaining below 70% 2. Consequently, addressing chemotherapy resistance and developing novel therapeutic agents for osteosarcoma are critical to improving treatment efficacy. Berberine (BBR), an alkaloid derived from the traditional Chinese medicinal plant Coptis chinensis, possesses various pharmacological properties, such as antidiarrheal [4], antibacterial [5], anti-hypertensive [6]. Recent studies have suggested that BBR may act as a potent anti-tumor agent in various cancers [7]. Notably, BBR derivatives have shown enhanced potency as antitumor He et al. Journal of Translational Medicine (2025) 23:1328 agents, exhibiting greater inhibition of cell proliferation and increased apoptosis-inducing activity compared to their parent compound, BBR [8], suggesting that berberine derivatives could serve as promising candidates for tumor chemotherapy. Recent studies have demonstrated that both fatty acid synthesis and glycolysis are crucial for the energy supply in cancer cells [9]. Fatty acids play a crucial role in the synthesis of phospholipids in cancer cell membranes and contribute to the activation of important signaling pathways [10]. In terms of energy production, cancer cells predominantly depend on ATP generated via fatty acid β-oxidation to satisfy their energy needs, while also utilizing nicotinamide adenine dinucleotide phosphate (NADPH) to preserve redox homeostasis [11, 12]. SCD is an enzyme involved in lipid modification, and its expression is often elevated in various cancers, including ovarian, liver, and breast cancers [13–15]. This enzyme facilitates the conversion of saturated fatty acids (SFAs) to monounsa (...truncated)