Pathological complete response (pCR) serves as a critical measure of the success of neoadjuvant chemotherapy (NAC) in breast cancer, directly influencing subsequent therapeutic decisions. With the continuous advancement of artificial intelligence, methods for early and accurate prediction of pCR are being extensively explored. In this study, we propose a cross-modal multi-pathway automated prediction model that integrates temporal and spatial information. This model fuses digital pathology images from biopsy specimens and multi-temporal ultrasound (US) images to predict pCR status early in NAC. The model demonstrates exceptional predictive efficacy. Our findings lay the foundation for developing personalized treatment paradigms based on individual responses. This approach has the potential to become a critical auxiliary tool for the early prediction of NAC response in breast cancer patients.
{"title":"Cross-modal deep learning model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer","authors":"Jianming Guo, Baihui Chen, Hongda Cao, Quan Dai, Ling Qin, Jinfeng Zhang, Youxue Zhang, Huanyu Zhang, Yuan Sui, Tianyu Chen, Dongxu Yang, Xue Gong, Dalin Li","doi":"10.1038/s41698-024-00678-8","DOIUrl":"10.1038/s41698-024-00678-8","url":null,"abstract":"Pathological complete response (pCR) serves as a critical measure of the success of neoadjuvant chemotherapy (NAC) in breast cancer, directly influencing subsequent therapeutic decisions. With the continuous advancement of artificial intelligence, methods for early and accurate prediction of pCR are being extensively explored. In this study, we propose a cross-modal multi-pathway automated prediction model that integrates temporal and spatial information. This model fuses digital pathology images from biopsy specimens and multi-temporal ultrasound (US) images to predict pCR status early in NAC. The model demonstrates exceptional predictive efficacy. Our findings lay the foundation for developing personalized treatment paradigms based on individual responses. This approach has the potential to become a critical auxiliary tool for the early prediction of NAC response in breast cancer patients.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00678-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142140685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Non-small cell lung cancer (NSCLC) constitutes the majority of lung cancer cases, accounting for over 80%. RNAs in EVs play a pivotal role in various biological and pathological processes mediated by extracellular vesicle (EV). Long non-coding RNAs (lncRNAs) are widely associated with cancer-related functions, including cell proliferation, migration, invasion, and drug resistance. Tumor-associated macrophages are recognized as pivotal contributors to tumorigenesis. Given these insights, this study aims to uncover the impact of lncRNA NORAD in EVs derived from M2 macrophages in NSCLC cell lines and xenograft mouse models of NSCLC. EVs were meticulously isolated and verified based on their morphology and specific biomarkers. The interaction between lncRNA NORAD and SMIM22 was investigated using immunoprecipitation. The influence of SMIM22/GALE or lncRNA NORAD in EVs on glycolysis was assessed in NSCLC cell lines. Additionally, we evaluated the effects of M2 macrophage-derived lncRNA NORAD in EVs on cell proliferation and apoptosis through colony formation and flow cytometry assays. Furthermore, the impact of M2 macrophage-derived lncRNA NORAD in EVs on tumor growth was confirmed using xenograft tumor animal models. The results underscored the potential role of M2 macrophage-derived lncRNA NORAD in EVs in NSCLC. SMIM22/GALE promoted glycolysis and the proliferation of NSCLC cells. Furthermore, lncRNA NORAD in EVs targeted SMIM22 and miR-520g-3p in NSCLC cells. Notably, lncRNA NORAD in EVs promoted the proliferation of NSCLC cells and facilitated NSCLC tumor growth through the miR-520g-3p axis. In conclusion, M2 macrophage-derived lncRNA NORAD in EVs promotes NSCLC progression through the miR-520g-3p/SMIM22/GALE axis.
{"title":"M2 macrophage-derived lncRNA NORAD in EVs promotes NSCLC progression via miR-520g-3p/SMIM22/GALE axis","authors":"Qingtao Zhao, Bin Li, Xiaopeng Zhang, Huanfen Zhao, Wenfei Xue, Zheng Yuan, Shun Xu, Guochen Duan","doi":"10.1038/s41698-024-00675-x","DOIUrl":"10.1038/s41698-024-00675-x","url":null,"abstract":"Non-small cell lung cancer (NSCLC) constitutes the majority of lung cancer cases, accounting for over 80%. RNAs in EVs play a pivotal role in various biological and pathological processes mediated by extracellular vesicle (EV). Long non-coding RNAs (lncRNAs) are widely associated with cancer-related functions, including cell proliferation, migration, invasion, and drug resistance. Tumor-associated macrophages are recognized as pivotal contributors to tumorigenesis. Given these insights, this study aims to uncover the impact of lncRNA NORAD in EVs derived from M2 macrophages in NSCLC cell lines and xenograft mouse models of NSCLC. EVs were meticulously isolated and verified based on their morphology and specific biomarkers. The interaction between lncRNA NORAD and SMIM22 was investigated using immunoprecipitation. The influence of SMIM22/GALE or lncRNA NORAD in EVs on glycolysis was assessed in NSCLC cell lines. Additionally, we evaluated the effects of M2 macrophage-derived lncRNA NORAD in EVs on cell proliferation and apoptosis through colony formation and flow cytometry assays. Furthermore, the impact of M2 macrophage-derived lncRNA NORAD in EVs on tumor growth was confirmed using xenograft tumor animal models. The results underscored the potential role of M2 macrophage-derived lncRNA NORAD in EVs in NSCLC. SMIM22/GALE promoted glycolysis and the proliferation of NSCLC cells. Furthermore, lncRNA NORAD in EVs targeted SMIM22 and miR-520g-3p in NSCLC cells. Notably, lncRNA NORAD in EVs promoted the proliferation of NSCLC cells and facilitated NSCLC tumor growth through the miR-520g-3p axis. In conclusion, M2 macrophage-derived lncRNA NORAD in EVs promotes NSCLC progression through the miR-520g-3p/SMIM22/GALE axis.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00675-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-28DOI: 10.1038/s41698-024-00673-z
Peter Truesdell, Jessica Chang, Doris Coto Villa, Meiou Dai, Yulei Zhao, Robin McIlwain, Stephanie Young, Shawna Hiley, Andrew W. Craig, Tomas Babak
Despite the clinical success of dozens of genetically targeted cancer therapies, the vast majority of patients with tumors caused by loss-of-function (LoF) mutations do not have access to these treatments. This is primarily due to the challenge of developing a drug that treats a disease caused by the absence of a protein target. The success of PARP inhibitors has solidified synthetic lethality (SL) as a means to overcome this obstacle. Recent mapping of SL networks using pooled CRISPR-Cas9 screens is a promising approach for expanding this concept to treating cancers driven by additional LoF drivers. In practice, however, translating signals from cell lines, where these screens are typically conducted, to patient outcomes remains a challenge. We developed a pharmacogenomic (PGx) approach called “Clinically Optimized Driver Associated-PGx” (CODA-PGX) that accurately predicts genetically targeted therapies with clinical-stage efficacy in specific LoF driver contexts. Using approved targeted therapies and cancer drugs with available real-world evidence and molecular data from hundreds of patients, we discovered and optimized the key screening principles predictive of efficacy and overall patient survival. In addition to establishing basic technical conventions, such as drug concentration and screening kinetics, we found that replicating the driver perturbation in the right context, as well as selecting patients where those drivers are genuine founder mutations, were key to accurate translation. We used CODA-PGX to screen a diverse collection of clinical stage drugs and report dozens of novel LoF genetically targeted opportunities; many validated in xenografts and by real-world evidence. Notable examples include treating STAG2-mutant tumors with Carboplatin, SMARCB1-mutant tumors with Oxaliplatin, and TP53BP1-mutant tumors with Etoposide or Bleomycin. We identified principles of pharmacogenomic screening that predict clinical efficacy in cancer patients with specific driver mutations.
{"title":"Pharmacogenomic discovery of genetically targeted cancer therapies optimized against clinical outcomes","authors":"Peter Truesdell, Jessica Chang, Doris Coto Villa, Meiou Dai, Yulei Zhao, Robin McIlwain, Stephanie Young, Shawna Hiley, Andrew W. Craig, Tomas Babak","doi":"10.1038/s41698-024-00673-z","DOIUrl":"10.1038/s41698-024-00673-z","url":null,"abstract":"Despite the clinical success of dozens of genetically targeted cancer therapies, the vast majority of patients with tumors caused by loss-of-function (LoF) mutations do not have access to these treatments. This is primarily due to the challenge of developing a drug that treats a disease caused by the absence of a protein target. The success of PARP inhibitors has solidified synthetic lethality (SL) as a means to overcome this obstacle. Recent mapping of SL networks using pooled CRISPR-Cas9 screens is a promising approach for expanding this concept to treating cancers driven by additional LoF drivers. In practice, however, translating signals from cell lines, where these screens are typically conducted, to patient outcomes remains a challenge. We developed a pharmacogenomic (PGx) approach called “Clinically Optimized Driver Associated-PGx” (CODA-PGX) that accurately predicts genetically targeted therapies with clinical-stage efficacy in specific LoF driver contexts. Using approved targeted therapies and cancer drugs with available real-world evidence and molecular data from hundreds of patients, we discovered and optimized the key screening principles predictive of efficacy and overall patient survival. In addition to establishing basic technical conventions, such as drug concentration and screening kinetics, we found that replicating the driver perturbation in the right context, as well as selecting patients where those drivers are genuine founder mutations, were key to accurate translation. We used CODA-PGX to screen a diverse collection of clinical stage drugs and report dozens of novel LoF genetically targeted opportunities; many validated in xenografts and by real-world evidence. Notable examples include treating STAG2-mutant tumors with Carboplatin, SMARCB1-mutant tumors with Oxaliplatin, and TP53BP1-mutant tumors with Etoposide or Bleomycin. We identified principles of pharmacogenomic screening that predict clinical efficacy in cancer patients with specific driver mutations.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00673-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-28DOI: 10.1038/s41698-024-00676-w
Rajat Thawani, Matteo Repetto, Clare Keddy, Katelyn Nicholson, Kristen Jones, Kevin Nusser, Catherine Z. Beach, Guilherme Harada, Alexander Drilon, Monika A. Davare
{"title":"Author Correction: TKI type switching overcomes ROS1 L2086F in ROS1 fusion-positive cancers","authors":"Rajat Thawani, Matteo Repetto, Clare Keddy, Katelyn Nicholson, Kristen Jones, Kevin Nusser, Catherine Z. Beach, Guilherme Harada, Alexander Drilon, Monika A. Davare","doi":"10.1038/s41698-024-00676-w","DOIUrl":"10.1038/s41698-024-00676-w","url":null,"abstract":"","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00676-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
While ferroptosis shows promise in anti-cancer strategy, the molecular mechanisms behind this process remain poorly understood. Our research aims to highlight the regulation of radiotherapy-induced ferroptosis in non-small cell lung cancer (NSCLC) via the NRF2/PHKG2 axis-mediated mechanism. To identify ferroptosis-associated genes associated with radioresistance in NSCLC, this study employed high-throughput transcriptome sequencing and Lasso risk regression analysis. Clinical samples were analyzed to confirm PHKG2 expression changes before and after radiotherapy. The study further examined ferritinophagy-related factors, intracellular iron levels, mitochondrial function, and ferroptosis in NSCLC cells undergoing radiation exposure to explore the effect of PHKG2 on radiosensitivity or radioresistance. The research also demonstrated the transcriptional inhibition of PHKG2 by NRF2 and created in situ transplantation tumor models of NSCLC to examine the role of NRF2/PHKG2 axis in NSCLC radiosensitivity and resistance in vivo. The Lasso risk regression model that incorporated ferroptosis-associated genes effectively predicted the prognosis of patients with NSCLC. Radiotherapy-sensitive tissues exhibited an increased expression of PHKG2. Overexpression of PHKG2 led to elevated intracellular iron levels by promoting ferritinophagy and increased mitochondrial stress-dependent ferroptosis induced by radiotherapy. PHKG2 transcription repression was achieved through NRF2. The FAGs-Lasso risk regression model can accurately predict the prognosis of NSCLC patients. Targeting Nrf2 upregulates the expression of PHKG2 and reverses radiotherapy resistance in NSCLC by promoting iron autophagy and inducing mitochondrial dysfunction, thereby increasing radiotherapy sensitivity.
{"title":"Targeting Nrf2/PHKG2 axis to enhance radiosensitivity in NSCLC","authors":"Fushi Han, Shuzhen Chen, Kangwei Zhang, Kunming Zhang, Meng Wang, Peijun Wang","doi":"10.1038/s41698-024-00629-3","DOIUrl":"10.1038/s41698-024-00629-3","url":null,"abstract":"While ferroptosis shows promise in anti-cancer strategy, the molecular mechanisms behind this process remain poorly understood. Our research aims to highlight the regulation of radiotherapy-induced ferroptosis in non-small cell lung cancer (NSCLC) via the NRF2/PHKG2 axis-mediated mechanism. To identify ferroptosis-associated genes associated with radioresistance in NSCLC, this study employed high-throughput transcriptome sequencing and Lasso risk regression analysis. Clinical samples were analyzed to confirm PHKG2 expression changes before and after radiotherapy. The study further examined ferritinophagy-related factors, intracellular iron levels, mitochondrial function, and ferroptosis in NSCLC cells undergoing radiation exposure to explore the effect of PHKG2 on radiosensitivity or radioresistance. The research also demonstrated the transcriptional inhibition of PHKG2 by NRF2 and created in situ transplantation tumor models of NSCLC to examine the role of NRF2/PHKG2 axis in NSCLC radiosensitivity and resistance in vivo. The Lasso risk regression model that incorporated ferroptosis-associated genes effectively predicted the prognosis of patients with NSCLC. Radiotherapy-sensitive tissues exhibited an increased expression of PHKG2. Overexpression of PHKG2 led to elevated intracellular iron levels by promoting ferritinophagy and increased mitochondrial stress-dependent ferroptosis induced by radiotherapy. PHKG2 transcription repression was achieved through NRF2. The FAGs-Lasso risk regression model can accurately predict the prognosis of NSCLC patients. Targeting Nrf2 upregulates the expression of PHKG2 and reverses radiotherapy resistance in NSCLC by promoting iron autophagy and inducing mitochondrial dysfunction, thereby increasing radiotherapy sensitivity.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00629-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142018186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-19DOI: 10.1038/s41698-024-00669-9
Govinda Sharma, James Round, Fei Teng, Zahra Ali, Chris May, Eric Yung, Robert A. Holt
Current tools for functionally profiling T cell receptors with respect to cytotoxic potency and cross-reactivity are hampered by difficulties in establishing model systems to test these proteins in the contexts of different HLA alleles and against broad arrays of potential antigens. We have implemented a granzyme-activatable sensor of T cell cytotoxicity in a universal prototyping platform which enables facile recombinant expression of any combination of TCR-, peptide-, and class I MHC-coding sequences and direct assessment of resultant responses. This system consists of an engineered cell platform based on the immortalized natural killer cell line, YT-Indy, and the MHC-null antigen-presenting cell line, K562. These cells were engineered to furnish the YT-Indy/K562 pair with appropriate protein domains required for recombinant TCR expression and function in a non-T cell chassis, integrate a fluorescence-based target-centric early detection reporter of cytotoxic function, and deploy a set of protective genetic interventions designed to preserve antigen-presenting cells for subsequent capture and downstream characterization. Our data show successful reconstitution of the surface TCR complex in the YT-Indy cell line at biologically relevant levels. We also demonstrate successful induction and highly sensitive detection of antigen-specific response in multiple distinct model TCRs. Additionally, we monitored destruction of targets in co-culture and found that our survival-optimized system allowed for complete preservation after 24 h exposure to cytotoxic effectors. With this bioplatform, we anticipate investigators will be empowered to rapidly express and characterize T cell receptor responses, generate knowledge regarding the patterns of T cell receptor recognition, and optimize therapeutic T cell receptors.
由于难以建立模型系统来测试这些蛋白在不同 HLA 等位基因背景下以及针对广泛的潜在抗原阵列的作用，目前用于分析 T 细胞受体细胞毒性效力和交叉反应性的工具受到了阻碍。我们在一个通用的原型平台上实现了一种粒酶激活的 T 细胞细胞毒性传感器，它能方便地重组表达 TCR、多肽和 I 类 MHC 编码序列的任何组合，并直接评估由此产生的反应。该系统包括一个基于永生化自然杀伤细胞株 YT-Indy 和 MHC 缺失的抗原递呈细胞株 K562 的工程细胞平台。设计这些细胞的目的是为 YT-Indy/K562 细胞对提供在非 T 细胞底盘中重组 TCR 表达和功能所需的适当蛋白质结构域，整合基于荧光的以靶点为中心的细胞毒性功能早期检测报告器，并部署一套保护性遗传干预措施，旨在保留抗原递呈细胞，以便后续捕获和下游鉴定。我们的数据显示，YT-Indy 细胞系中的表面 TCR 复合物在生物相关水平上成功重组。我们还证明了在多个不同的模型 TCR 中成功诱导和高灵敏度地检测抗原特异性反应。此外，我们还监测了共培养中靶点的破坏情况，发现我们的生存优化系统可以在暴露于细胞毒性效应物 24 小时后完全保存靶点。有了这个生物平台，我们预计研究人员将有能力快速表达和描述 T 细胞受体反应，生成有关 T 细胞受体识别模式的知识，并优化治疗性 T 细胞受体。
{"title":"A synthetic cytotoxic T cell platform for rapidly prototyping TCR function","authors":"Govinda Sharma, James Round, Fei Teng, Zahra Ali, Chris May, Eric Yung, Robert A. Holt","doi":"10.1038/s41698-024-00669-9","DOIUrl":"10.1038/s41698-024-00669-9","url":null,"abstract":"Current tools for functionally profiling T cell receptors with respect to cytotoxic potency and cross-reactivity are hampered by difficulties in establishing model systems to test these proteins in the contexts of different HLA alleles and against broad arrays of potential antigens. We have implemented a granzyme-activatable sensor of T cell cytotoxicity in a universal prototyping platform which enables facile recombinant expression of any combination of TCR-, peptide-, and class I MHC-coding sequences and direct assessment of resultant responses. This system consists of an engineered cell platform based on the immortalized natural killer cell line, YT-Indy, and the MHC-null antigen-presenting cell line, K562. These cells were engineered to furnish the YT-Indy/K562 pair with appropriate protein domains required for recombinant TCR expression and function in a non-T cell chassis, integrate a fluorescence-based target-centric early detection reporter of cytotoxic function, and deploy a set of protective genetic interventions designed to preserve antigen-presenting cells for subsequent capture and downstream characterization. Our data show successful reconstitution of the surface TCR complex in the YT-Indy cell line at biologically relevant levels. We also demonstrate successful induction and highly sensitive detection of antigen-specific response in multiple distinct model TCRs. Additionally, we monitored destruction of targets in co-culture and found that our survival-optimized system allowed for complete preservation after 24 h exposure to cytotoxic effectors. With this bioplatform, we anticipate investigators will be empowered to rapidly express and characterize T cell receptor responses, generate knowledge regarding the patterns of T cell receptor recognition, and optimize therapeutic T cell receptors.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00669-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142002634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep learning (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well as prognosis (primary task) in gliomas. Further, we aimed to provide the biological mechanisms underlying the model’s predictions. We collected multiscale data including baseline MRI images from 2776 glioma patients across two private (FAHZU and HPPH, n = 1931) and three public datasets (TCGA, n = 213; UCSF, n = 410; and EGD, n = 222). We trained and internally validated the MDL model using our private datasets, and externally validated it using the three public datasets. We used the model-predicted deep prognosis score (DPS) to stratify patients into low-DPS and high-DPS subtypes. Additionally, a radio-multiomics analysis was conducted to elucidate the biological basis of the DPS. In the external validation cohorts, the MDL model achieved average areas under the curve of 0.892–0.903, 0.710–0.894, and 0.850–0.879 for predicting IDH mutation status, 1p/19q co-deletion status, and tumor grade, respectively. Moreover, the MDL model yielded a C-index of 0.723 in the TCGA and 0.671 in the UCSF for the prediction of overall survival. The DPS exhibits significant correlations with activated oncogenic pathways, immune infiltration patterns, specific protein expression, DNA methylation, tumor mutation burden, and tumor-stroma ratio. Accordingly, our work presents an accurate and biologically meaningful tool for predicting molecular subtypes, tumor grade, and survival outcomes in gliomas, which provides personalized clinical decision-making in a global and non-invasive manner.
{"title":"Biologically interpretable multi-task deep learning pipeline predicts molecular alterations, grade, and prognosis in glioma patients","authors":"Xuewei Wu, Shuaitong Zhang, Zhenyu Zhang, Zicong He, Zexin Xu, Weiwei Wang, Zhe Jin, Jingjing You, Yang Guo, Lu Zhang, Wenhui Huang, Fei Wang, Xianzhi Liu, Dongming Yan, Jingliang Cheng, Jing Yan, Shuixing Zhang, Bin Zhang","doi":"10.1038/s41698-024-00670-2","DOIUrl":"10.1038/s41698-024-00670-2","url":null,"abstract":"Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep learning (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well as prognosis (primary task) in gliomas. Further, we aimed to provide the biological mechanisms underlying the model’s predictions. We collected multiscale data including baseline MRI images from 2776 glioma patients across two private (FAHZU and HPPH, n = 1931) and three public datasets (TCGA, n = 213; UCSF, n = 410; and EGD, n = 222). We trained and internally validated the MDL model using our private datasets, and externally validated it using the three public datasets. We used the model-predicted deep prognosis score (DPS) to stratify patients into low-DPS and high-DPS subtypes. Additionally, a radio-multiomics analysis was conducted to elucidate the biological basis of the DPS. In the external validation cohorts, the MDL model achieved average areas under the curve of 0.892–0.903, 0.710–0.894, and 0.850–0.879 for predicting IDH mutation status, 1p/19q co-deletion status, and tumor grade, respectively. Moreover, the MDL model yielded a C-index of 0.723 in the TCGA and 0.671 in the UCSF for the prediction of overall survival. The DPS exhibits significant correlations with activated oncogenic pathways, immune infiltration patterns, specific protein expression, DNA methylation, tumor mutation burden, and tumor-stroma ratio. Accordingly, our work presents an accurate and biologically meaningful tool for predicting molecular subtypes, tumor grade, and survival outcomes in gliomas, which provides personalized clinical decision-making in a global and non-invasive manner.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11329669/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141996230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-14DOI: 10.1038/s41698-024-00661-3
Devanjali Dutta, L. Francisco Lorenzo-Martín, François Rivest, Nicolas Broguiere, Lucie Tillard, Simone Ragusa, Nathalie Brandenberg, Sylke Höhnel, Damien Saugy, Sylvie Rusakiewicz, Krisztian Homicsko, George Coukos, Matthias P. Lutolf
Immunotherapy has emerged as a new standard of care for certain cancer patients with specific cellular and molecular makeups. However, there is still an unmet need for ex vivo models able to readily assess the effectiveness of immunotherapeutic treatments in a high-throughput and patient-specific manner. To address this issue, we have developed a microarrayed system of patient-derived tumoroids with recreated immune microenvironments that are optimized for the high-content evaluation of tumor-infiltrating lymphocyte functionality. Here we show that this system offers unprecedented opportunities to evaluate tumor immunogenicity, characterize the response to immunomodulators, and explore novel approaches for personalized immuno-oncology.
{"title":"Probing the killing potency of tumor-infiltrating lymphocytes on microarrayed colorectal cancer tumoroids","authors":"Devanjali Dutta, L. Francisco Lorenzo-Martín, François Rivest, Nicolas Broguiere, Lucie Tillard, Simone Ragusa, Nathalie Brandenberg, Sylke Höhnel, Damien Saugy, Sylvie Rusakiewicz, Krisztian Homicsko, George Coukos, Matthias P. Lutolf","doi":"10.1038/s41698-024-00661-3","DOIUrl":"10.1038/s41698-024-00661-3","url":null,"abstract":"Immunotherapy has emerged as a new standard of care for certain cancer patients with specific cellular and molecular makeups. However, there is still an unmet need for ex vivo models able to readily assess the effectiveness of immunotherapeutic treatments in a high-throughput and patient-specific manner. To address this issue, we have developed a microarrayed system of patient-derived tumoroids with recreated immune microenvironments that are optimized for the high-content evaluation of tumor-infiltrating lymphocyte functionality. Here we show that this system offers unprecedented opportunities to evaluate tumor immunogenicity, characterize the response to immunomodulators, and explore novel approaches for personalized immuno-oncology.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11324658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141982887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-14DOI: 10.1038/s41698-024-00674-y
Julia C. Kuehn, Patrick Metzger, Nicolas Neidert, Uta Matysiak, Linda Gräßel, Ulrike Philipp, Sabine Bleul, Thomas Pauli, Julia Falkenstein, Henriette Bertemes, Stepan Cysar, Maria Elena Hess, Anna Verena Frey, Jesús Duque-Afonso, Elisabeth Schorb, Marcia Machein, Jürgen Beck, Oliver Schnell, Nikolas von Bubnoff, Anna L. Illert, Christoph Peters, Tilman Brummer, Marco Prinz, Cornelius Miething, Heiko Becker, Silke Lassmann, Martin Werner, Melanie Börries, Justus Duyster, Dieter H. Heiland, Roman Sankowski, Florian Scherer
Despite major advances in molecular profiling and classification of primary brain tumors, personalized treatment remains limited for most patients. Here, we explored the feasibility of individual molecular profiling and the efficacy of biomarker-guided therapy for adult patients with primary brain cancers in the real-world setting within the molecular tumor board Freiburg, Germany. We analyzed genetic profiles, personalized treatment recommendations, and clinical outcomes of 102 patients with 21 brain tumor types. Alterations in the cell cycle, BRAF, and mTOR pathways most frequently led to personalized treatment recommendations. Molecularly informed therapies were recommended in 71% and implemented in 32% of patients with completed molecular diagnostics. The disease control rate following targeted treatment was 50% and the overall response rate was 30%, with a progression-free survival 2/1 ratio of at least 1.3 in 31% of patients. This study highlights the efficacy of molecularly guided treatment and the need for biomarker-stratified trials in brain cancers.
{"title":"Comprehensive genetic profiling and molecularly guided treatment for patients with primary CNS tumors","authors":"Julia C. Kuehn, Patrick Metzger, Nicolas Neidert, Uta Matysiak, Linda Gräßel, Ulrike Philipp, Sabine Bleul, Thomas Pauli, Julia Falkenstein, Henriette Bertemes, Stepan Cysar, Maria Elena Hess, Anna Verena Frey, Jesús Duque-Afonso, Elisabeth Schorb, Marcia Machein, Jürgen Beck, Oliver Schnell, Nikolas von Bubnoff, Anna L. Illert, Christoph Peters, Tilman Brummer, Marco Prinz, Cornelius Miething, Heiko Becker, Silke Lassmann, Martin Werner, Melanie Börries, Justus Duyster, Dieter H. Heiland, Roman Sankowski, Florian Scherer","doi":"10.1038/s41698-024-00674-y","DOIUrl":"10.1038/s41698-024-00674-y","url":null,"abstract":"Despite major advances in molecular profiling and classification of primary brain tumors, personalized treatment remains limited for most patients. Here, we explored the feasibility of individual molecular profiling and the efficacy of biomarker-guided therapy for adult patients with primary brain cancers in the real-world setting within the molecular tumor board Freiburg, Germany. We analyzed genetic profiles, personalized treatment recommendations, and clinical outcomes of 102 patients with 21 brain tumor types. Alterations in the cell cycle, BRAF, and mTOR pathways most frequently led to personalized treatment recommendations. Molecularly informed therapies were recommended in 71% and implemented in 32% of patients with completed molecular diagnostics. The disease control rate following targeted treatment was 50% and the overall response rate was 30%, with a progression-free survival 2/1 ratio of at least 1.3 in 31% of patients. This study highlights the efficacy of molecularly guided treatment and the need for biomarker-stratified trials in brain cancers.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11324882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141982886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1038/s41698-024-00671-1
Hannah L. Williams, Ana Leni Frei, Thibaud Koessler, Martin D. Berger, Heather Dawson, Olivier Michielin, Inti Zlobec
Enabling the examination of cell-cell relationships in tissue, spatially resolved omics technologies have revolutionised our perspectives on cancer biology. Clinically, the development of immune checkpoint inhibitors (ICI) has advanced cancer therapeutics. However, a major challenge of effective implementation is the identification of predictive biomarkers of response. In this review we examine the potential added predictive value of spatial biomarkers of response to ICI beyond current clinical benchmarks.
{"title":"The current landscape of spatial biomarkers for prediction of response to immune checkpoint inhibition","authors":"Hannah L. Williams, Ana Leni Frei, Thibaud Koessler, Martin D. Berger, Heather Dawson, Olivier Michielin, Inti Zlobec","doi":"10.1038/s41698-024-00671-1","DOIUrl":"10.1038/s41698-024-00671-1","url":null,"abstract":"Enabling the examination of cell-cell relationships in tissue, spatially resolved omics technologies have revolutionised our perspectives on cancer biology. Clinically, the development of immune checkpoint inhibitors (ICI) has advanced cancer therapeutics. However, a major challenge of effective implementation is the identification of predictive biomarkers of response. In this review we examine the potential added predictive value of spatial biomarkers of response to ICI beyond current clinical benchmarks.","PeriodicalId":19433,"journal":{"name":"NPJ Precision Oncology","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41698-024-00671-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141976265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：