DNA methylation-based classifier and gene expression signatures detect BRCAness in osteosarcoma

From biology to personalized medicine: Recent knowledge in osteosarcoma

High-grade osteosarcoma is the most common paediatric bone cancer. More than one third of patients relapse and die of osteosarcoma using current chemotherapeutic and surgical strategies. To improve outcomes in osteosarcoma, two crucial challenges need to be tackled: 1-the identification of hard-to-treat disease, ideally from diagnosis; 2- choosing the best combined or novel therapies to eradicate tumor cells which are resistant to current therapies leading to disease dissemination and metastasize as well as their favorable microenvironment. Genetic chaos, tumor complexity and heterogeneity render this task difficult. The development of new technologies like next generation sequencing has led to an improvement in osteosarcoma oncogenesis knownledge. This review summarizes recent biological and therapeutical advances in osteosarcoma, as well as the challenges that must be overcome in order to develop personalized medicine and new therapeutic strategies and ultimately improve patient survival.

The diagnostic value of machine learning for the classification of malignant bone tumor: a systematic evaluation and meta-analysis

Background

Malignant bone tumors are a type of cancer with varying malignancy and prognosis. Accurate diagnosis and classification are crucial for treatment and prognosis assessment. Machine learning has been introduced for early differential diagnosis of malignant bone tumors, but its performance is controversial. This systematic review and meta-analysis aims to explore the diagnostic value of machine learning for malignant bone tumors.

Methods

PubMed, Embase, Cochrane Library, and Web of Science were searched for literature on machine learning in the differential diagnosis of malignant bone tumors up to October 31, 2022. The risk of bias assessment was conducted using QUADAS-2. A bivariate mixed-effects model was used for meta-analysis, with subgroup analyses by machine learning methods and modeling approaches.

Results

The inclusion comprised 31 publications with 382,371 patients, including 141,315 with malignant bone tumors. Meta-analysis results showed machine learning sensitivity and specificity of 0.87 [95% CI: 0.81,0.91] and 0.91 [95% CI: 0.86,0.94] in the training set, and 0.83 [95% CI: 0.74,0.89] and 0.87 [95% CI: 0.79,0.92] in the validation set. Subgroup analysis revealed MRI-based radiomics was the most common approach, with sensitivity and specificity of 0.85 [95% CI: 0.74,0.91] and 0.87 [95% CI: 0.81,0.91] in the training set, and 0.79 [95% CI: 0.70,0.86] and 0.79 [95% CI: 0.70,0.86] in the validation set. Convolutional neural networks were the most common model type, with sensitivity and specificity of 0.86 [95% CI: 0.72,0.94] and 0.92 [95% CI: 0.82,0.97] in the training set, and 0.87 [95% CI: 0.51,0.98] and 0.87 [95% CI: 0.69,0.96] in the validation set.

Conclusion

Machine learning is mainly applied in radiomics for diagnosing malignant bone tumors, showing desirable diagnostic performance. Machine learning can be an early adjunctive diagnostic method but requires further research and validation to determine its practical efficiency and clinical application prospects.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42023387057.

Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network

DNA methylation takes on critical significance to the regulation of gene expression by affecting the stability of DNA and changing the structure of chromosomes. DNA methylation modification sites should be identified, which lays a solid basis for gaining more insights into their biological functions. Existing machine learning-based methods of predicting DNA methylation have not fully exploited the hidden multidimensional information in DNA gene sequences, such that the prediction accuracy of models is significantly limited. Besides, most models have been built in terms of a single methylation type. To address the above-mentioned issues, a deep learning-based method was proposed in this study for DNA methylation site prediction, termed the MEDCNN model. The MEDCNN model is capable of extracting feature information from gene sequences in three dimensions (i.e., positional information, biological information, and chemical information). Moreover, the proposed method employs a convolutional neural network model with double convolutional layers and double fully connected layers while iteratively updating the gradient descent algorithm using the cross-entropy loss function to increase the prediction accuracy of the model. Besides, the MEDCNN model can predict different types of DNA methylation sites. As indicated by the experimental results,the deep learning method based on coding from multiple dimensions outperformed single coding methods, and the MEDCNN model was highly applicable and outperformed existing models in predicting DNA methylation between different species. As revealed by the above-described findings, the MEDCNN model can be effective in predicting DNA methylation sites.

Epigenetic Changes Associated with Osteosarcoma: A Comprehensive Review

Osteosarcoma is the most common malignant primary bone tumor in children and adolescents. While clinical outcomes have improved, the 5-year survival rate is only around 60% if discovered early and can require debilitating treatments, such as amputations. A better understanding of the disease could lead to better clinical outcomes for patients with osteosarcoma. One promising avenue of osteosarcoma research is in the field of epigenetics. This research investigates changes in genetic expression that occur above the genome rather than in the genetic code itself. The epigenetics of osteosarcoma is an active area of research that is still not fully understood. In a narrative review, we examine recent advances in the epigenetics of osteosarcoma by reporting biomarkers of DNA methylation, histone modifications, and non-coding RNA associated with disease progression. We also show how cancer tumor epigenetic profiles are being used to predict and improve patient outcomes. The papers in this review cover a large range of epigenetic target genes and pathways that modulate many aspects of osteosarcoma, including but not limited to metastases and chemotherapy resistance. Ultimately, this review will shed light on the recent advances in the epigenetics of osteosarcoma and illustrate the clinical benefits of this field of research.

Unravelling homologous recombination repair deficiency and therapeutic opportunities in soft tissue and bone sarcoma

Defects in homologous recombination repair (HRR) in tumors correlate with poor prognosis and metastases development. Determining HRR deficiency (HRD) is of major clinical relevance as it is associated with therapeutic vulnerabilities and remains poorly investigated in sarcoma. Here, we show that specific sarcoma entities exhibit high levels of genomic instability signatures and molecular alterations in HRR genes, while harboring a complex pattern of chromosomal instability. Furthermore, sarcomas carrying HRDness traits exhibit a distinct SARC-HRD transcriptional signature that predicts PARP inhibitor sensitivity in patient-derived sarcoma cells. Concomitantly, HRD^high sarcoma cells lack RAD51 nuclear foci formation upon DNA damage, further evidencing defects in HRR. We further identify the WEE1 kinase as a therapeutic vulnerability for sarcomas with HRDness and demonstrate the clinical benefit of combining DNA damaging agents and inhibitors of DNA repair pathways ex vivo and in the clinic. In summary, we provide a personalized oncological approach to treat sarcoma patients successfully.

Osteosarcoma: Novel prognostic biomarkers using circulating and cell-free tumour DNA

AIM

Osteosarcoma (OS) is the most common primary bone tumour in children and adolescents. Circulating free (cfDNA) and circulating tumour DNA (ctDNA) are promising biomarkers for disease surveillance and prognostication in several cancer types; however, few such studies are reported for OS. The purpose of this study was to discover and validate methylation-based biomarkers to detect plasma ctDNA in patients with OS and explore their utility as prognostic markers.

METHODS

Candidate CpG markers were selected through analysis of methylation array data for OS, non-OS tumours and germline samples. Candidates were validated in two independent OS datasets (n = 162, n = 107) and the four top-performing markers were selected. Methylation-specific digital droplet PCR (ddPCR) assays were designed and experimentally validated in OS tumour samples (n = 20) and control plasma samples. Finally, ddPCR assays were applied to pre-operative plasma and where available post-operative plasma from 72 patients with OS, and findings correlated with outcome.

RESULTS

Custom ddPCR assays detected ctDNA in 69% and 40% of pre-operative plasma samples (n = 72), based on thresholds of one or two positive markers respectively. ctDNA was detected in 5/17 (29%) post-operative plasma samples from patients, which in four cases were associated with or preceded disease relapse. Both pre-operative cfDNA levels and ctDNA detection independently correlated with overall survival (p = 0.0015 and p = 0.0096, respectively).

CONCLUSION

Our findings illustrate the potential of mutation-independent methylation-based ctDNA assays for OS. This study lays the foundation for multi-institutional collaborative studies to explore the utility of plasma-derived biomarkers in the management of OS.