The Machine-Learning-Mediated Interface of Microbiome and Genetic Risk Stratification in Neuroblastoma Reveals Molecular Pathways Related to Patient Survival

Risk of developing neuroblastoma influenced by maternal stressful life events during pregnancy and congenital pathologies

OBJECTIVE

A retrospective multicenter study to investigate the potential association between descriptive information related to pregnancy history and perinatal features and the risk of neuroblastoma (NB) in children.

STUDY DESIGN

Data from 56 mothers during 105 pregnancies (56 cases of NB, 49 control siblings) were collected through face-to-face or telephone interviews with mothers of children diagnosed with NB, along with information extracted from Health System databases. Descriptive information related to (a) pregnancy history as maternal stressful life events with perceived distress during pregnancy, weight gain, alcohol and tobacco consumption, mode of delivery and gestational age; and (b) perinatal features as congenital pathologies, weight at birth and type of feeding were examined to identify potential risk factors for NB.

RESULTS

Stressful life events during pregnancy and certain congenital pathologies were independently associated with NB risk. No significant associations were found between other features. Breastfeeding rates were similar between cases and controls.

CONCLUSION

Our results underscore the importance of providing support and care to pregnant women to reduce potential stressors. Further research is needed to better understand the influence of dysbiosis and mitochondrial-nuclear communication impairment as underlying mechanisms of maternal stress during pregnancy and presence of congenital pathologies in order to confirm them as potential risk factors for NB.

Intratumoral Microbiome: Foe or Friend in Reshaping the Tumor Microenvironment Landscape?

The role of the microbiome in cancer and its crosstalk with the tumor microenvironment (TME) has been extensively studied and characterized. An emerging field in the cancer microbiome research is the concept of the intratumoral microbiome, which refers to the microbiome residing within the tumor. This microbiome primarily originates from the local microbiome of the tumor-bearing tissue or from translocating microbiome from distant sites, such as the gut. Despite the increasing number of studies on intratumoral microbiome, it remains unclear whether it is a driver or a bystander of oncogenesis and tumor progression. This review aims to elucidate the intricate role of the intratumoral microbiome in tumor development by exploring its effects on reshaping the multileveled ecosystem in which tumors thrive, the TME. To dissect the complexity and the multitude of layers within the TME, we distinguish six specialized tumor microenvironments, namely, the immune, metabolic, hypoxic, acidic, mechanical and innervated microenvironments. Accordingly, we attempt to decipher the effects of the intratumoral microbiome on each specialized microenvironment and ultimately decode its tumor-promoting or tumor-suppressive impact. Additionally, we portray the intratumoral microbiome as an orchestrator in the tumor milieu, fine-tuning the responses in distinct, specialized microenvironments and remodeling the TME in a multileveled and multifaceted manner.

A review of machine learning methods for cancer characterization from microbiome data

Recent studies have shown that the microbiome can impact cancer development, progression, and response to therapies suggesting microbiome-based approaches for cancer characterization. As cancer-related signatures are complex and implicate many taxa, their discovery often requires Machine Learning approaches. This review discusses Machine Learning methods for cancer characterization from microbiome data. It focuses on the implications of choices undertaken during sample collection, feature selection and pre-processing. It also discusses ML model selection, guiding how to choose an ML model, and model validation. Finally, it enumerates current limitations and how these may be surpassed. Proposed methods, often based on Random Forests, show promising results, however insufficient for widespread clinical usage. Studies often report conflicting results mainly due to ML models with poor generalizability. We expect that evaluating models with expanded, hold-out datasets, removing technical artifacts, exploring representations of the microbiome other than taxonomical profiles, leveraging advances in deep learning, and developing ML models better adapted to the characteristics of microbiome data will improve the performance and generalizability of models and enable their usage in the clinic.

Predicting Neuroblastoma Patient Risk Groups, Outcomes, and Treatment Response Using Machine Learning Methods: A Review

Neuroblastoma, a paediatric malignancy with high rates of cancer-related morbidity and mortality, is of significant interest to the field of paediatric cancers. High-risk NB tumours are usually metastatic and result in survival rates of less than 50%. Machine learning approaches have been applied to various neuroblastoma patient data to retrieve relevant clinical and biological information and develop predictive models. Given this background, this study will catalogue and summarise the literature that has used machine learning and statistical methods to analyse data such as multi-omics, histological sections, and medical images to make clinical predictions. Furthermore, the question will be turned on its head, and the use of machine learning to accurately stratify NB patients by risk groups and to predict outcomes, including survival and treatment response, will be summarised. Overall, this study aims to catalogue and summarise the important work conducted to date on the subject of expression-based predictor models and machine learning in neuroblastoma for risk stratification and patient outcomes including survival, and treatment response which may assist and direct future diagnostic and therapeutic efforts.

Intratumor microbiome: selective colonization in the tumor microenvironment and a vital regulator of tumor biology

The polymorphic microbiome has been proposed as a new hallmark of cancer. Intratumor microbiome has been revealed to play vital roles in regulating tumor initiation and progression, but the regulatory mechanisms have not been fully uncovered. In this review, we illustrated that similar to other components in the tumor microenvironment, the reside and composition of intratumor microbiome are regulated by tumor cells and the surrounding microenvironment. The intratumor hypoxic, immune suppressive, and highly permeable microenvironment may select certain microbiomes, and tumor cells may directly interact with microbiome via molecular binding or secretions. Conversely, the intratumor microbiomes plays vital roles in regulating tumor initiation and progression via regulating the mutational landscape, the function of genes in tumor cells and modulating the tumor microenvironment, including immunity, inflammation, angiogenesis, stem cell niche, etc. Moreover, intratumor microbiome is regulated by anti-cancer therapies and actively influences therapy response, which could be a therapeutic target or engineered to be a therapy weapon in the clinic. This review highlights the intratumor microbiome as a vital component in the tumor microenvironment, uncovers potential mutual regulatory mechanisms between the tumor microenvironment and intratumor microbiome, and points out the ongoing research directions and drawbacks of the research area, which should broaden our view of microbiome and enlighten further investigation directions.

Mastering the craft: Creating an insightful and widely-cited literature review

The art of constructing an insightful literature review manuscript has witnessed an exemplar in the work of Oz et al (2023), wherein concept progression harmoniously merges with figures and tables. Reflecting on retrospective data science, it is evident that well-cited articles can wield a transformative influence on the Journal Citation Reports Impact Factor score, as exemplified by Robert Weinberg's landmark on cancer (Hanahan and Weinberg, 2011). Here, we aim to spotlight a commendable contribution by Tuba Oz, Ajeet Kaushik, and Małgorzata Kujawska in this issue while pivoting towards identifying the hallmarks of a subpar literature review-elements that hinder rather than promote advancement. The hurdles and roadblocks encountered within subpar literature reviews are multifold. Anticipation of emerging trends, identification of challenges, and exploration of solutions remain conspicuously absent. Original Contributions fail to surface amidst the vast sea of pre-existing literature, with noticeable gaps amplified by the lack of illustrative figures and tables. The manuscript, at times, assumes a skeletal form, reflecting an attempt to accommodate an excess of references, leading to convoluted sentences laden with citations. In contrast, a potent solution lies in adopting a comprehensive approach. A nuanced and critical evaluation of sources can culminate in a robust discussion, surpassing the mere summarization of conclusions drawn by others. This approach, often dismissed, holds the potential to elevate clarity, coherence, and logical flow, ultimately inviting engaged readership and coveted citations. The critical necessity of integrating visionary insights is underscored and achieved through a rigorous analysis of pivotal concepts and innovative ideas. Examples can be harnessed to elucidate the application of these solutions. We advocate a paradigm shift, urging literature review writers to embrace the readers' perspective. A literature review's purpose extends beyond providing a comprehensive panorama; it should illuminate avenues for concept development within a specific field of interest. By achieving this balance, literature reviews stand to captivate a devoted readership, paving the way for manuscripts that are both widely read and frequently cited. The pathway forward requires a fusion of astute analysis and visionary insights, shaping the future of literature review composition.

Prospect of bacteria for tumor diagnosis and treatment

In recent decades, the comprehensive cancer treatments including surgery, chemotherapy, and radiotherapy have improved the overall survival rate and quality of life of many cancer patients. However, we are still facing many difficult problems in the cancer treatment, such as unpredictable side effects, high recurrence rate, and poor curative effect. Therefore, the better intervention strategies are needed in this field. In recent years, the role and importance of microbiota in a variety of diseases were focused on as a hot research topic, and the role of some intracellular bacteria of cancer cells in carcinogenesis has recently been discovered. The impact of bacteria on cancer is not limited to their contribution to tumorigenesis, but the overall susceptibility of bacteria to subsequent tumor progression, the development of concurrent infections, and the response to anti-cancer therapy have also been found to be affected. Concerns about the contribution of bacteria in the anti-cancer response have inspired researchers to develop bacteria-based anti-cancer treatments. In this paper, we reviewed the main roles of bacteria in the occurrence and development of tumors, and summarized the mechanism of bacteria in the occurrence, development, and clinical anti-tumor treatment of tumors, providing new insights for the in-depth study of the role of bacteria in tumor diagnosis and treatment. This review aims to provide a new perspective for the development of new technologies based on bacteria to enhance anti-tumor immunotherapy.