Machine learning modeling of genome-wide copy number alteration signatures reliably predicts IDH mutational status in adult diffuse glioma

Knowledge of 1p/19q-codeletion and IDH1/2 mutational status is necessary to interpret any investigational study of diffuse gliomas in the modern era. While DNA sequencing is the gold standard for determining IDH mutational status, genome-wide methylation arrays and gene expression profiling have been used for surrogate mutational determination. Previous studies by our group suggest that 1p/19q-codeletion and IDH mutational status can be predicted by genome-wide somatic copy number alteration (SCNA) data alone, however a rigorous model to accomplish this task has yet to be established. In this study, we used SCNA data from 786 adult diffuse gliomas in The Cancer Genome Atlas (TCGA) to develop a two-stage classification system that identifies 1p/19q-codeleted oligodendrogliomas and predicts the IDH mutational status of astrocytic tumors using a machine-learning model. Cross-validated results on TCGA SCNA data showed near perfect classification results. Furthermore, our astrocytic IDH mutation model validated well on four additional datasets (AUC = 0.97, AUC = 0.99, AUC = 0.95, AUC = 0.96) as did our 1p/19q-codeleted oligodendroglioma screen on the two datasets that contained oligodendrogliomas (MCC = 0.97, MCC = 0.97). We then retrained our system using data from these validation sets and applied our system to a cohort of REMBRANDT study subjects for whom SCNA data, but not IDH mutational status, is available. Overall, using genome-wide SCNAs, we successfully developed a system to robustly predict 1p/19q-codeletion and IDH mutational status in diffuse gliomas. This system can assign molecular subtype labels to tumor samples of retrospective diffuse glioma cohorts that lack 1p/19q-codeletion and IDH mutational status, such as the REMBRANDT study, recasting these datasets as validation cohorts for diffuse glioma research.

TB-8 Genetic and molecular properties of long-term proliferating tumorsphere -forming glioma derived cells

Long-term proliferating tumorsphere-forming glioma derived cells (LTP-TS-GDCs) and patient derived xenografts (PDXs) are essential tools for translational research for glioma. However, only small subsets of glioma samples are established as LTP-TS and/or PDXs and little is known about the genetics and molecular properties of LTP-TS -forming GDCs and PDX. In this study, we aim to analyze the characteristics of LTP-TS -forming GDCs and PDXs. We tried primary sphere cultures from 56 glioma patient-derived samples and established 11 LTP-TS-GDCs out of 45 glioblastoma samples and no long-term sphere culture was isolated from grade3 and grade 2 gliomas. LTP-TS-GDCs had self-renewal ability and possessed certain multipotency. However, they significantly less expressed SOX1 FOXG1 and TUBB3, whereas they expressed LGALS1 and EN1 significantly higher than normal neural stem/progenitor cells. In addition, we found that LTP-TS-GDCs shared the same genetic profiles with original patients’ tumors. Furthermore, we investigated the genetic differences between the glioma tissues which were successfully established as LTP-TS-GDCs and those which were not. We found that glioma tissues with TERT promotor mutations and triple copy number alteration (CNA) [EGFR, CDKN2A, and PTEN loci] are significantly established as LTP-TS-GDCs. Lastly, we next investigated in vivo characteristics of glioma PDXs. We have injected glioma PDXs lines into immunodeficient mice brains and histopathologically analyzed the characteristics of xenografts. Each xenograft well recapitulated histological features of original patients’ tumors and tumor cells remarkably invade through subventricular zone. In conclusion, each LTP-TS-GDCs and PDXs had various gene expression profiles, reflecting intratumoral and interpatient heterogeneities of glioma. In addition, TERT promotor mutations and triple CNA significantly correlated with success rate of LTP-TS-GDCs. These findings will be of use and advance the preclinical and translational researches of glioma.

Identification of Tumor Mutation Burden, Microsatellite Instability, and Somatic Copy Number Alteration derived 9-gene Signatures to Predict Clinical Outcomes in STAD

Background: Genomic features including tumor mutation burden (TMB), microsatellite instability (MSI) and somatic copy number alteration (SCNA), had been demonstrated to be involved with the tumor microenvironment (TME) and outcome of gastric cancer (GC). Methods: We obtained profiles of TMB, MSI and SCNA by processing 405 GC data from The Cancer Genome Atlas (TCGA), then conducted a comprehensive analysis though “iClusterPlus”. Another independent Gene Expression Omnibus (GEO) contained specimens from 109 GC patients was designed as an external validation. Results: Two subgroups were generated, with distinguished prognosis, somatic mutation burden, copy number changes and immune landscape. We revealed that Cluster1 was marked by a better prognosis, accompanied by higher TMB, MSIsensor score, TMEscore, and lower SCNA burden. Based on these clusters, we screened 196 differentially expressed genes (DEGs), which were subsequently projected into univariate Cox survival analysis. Thus, we constructed a 9-gene immune risk score (IRS) model using lasso penalized logistic regression. Moreover, the prognostic prediction of IRS was verified by receiver operating characteristic (ROC) curve analysis and nomogram plot.Conclusions: Our works suggested that the 9‐gene‐signature prediction model, which derived from TMB, MSI, SCNA was a promising predictive tool for clinical outcome in GC patients. This novel methodology may help clinicians uncover the underlying mechanisms and guide future treatment strategies.

A Multimodal Affinity Fusion Network for Predicting the Survival of Breast Cancer Patients

Accurate survival prediction of breast cancer holds significant meaning for improving patient care. Approaches using multiple heterogeneous modalities such as gene expression, copy number alteration, and clinical data have showed significant advantages over those with only one modality for patient survival prediction. However, existing survival prediction methods tend to ignore the structured information between patients and multimodal data. We propose a multimodal data fusion model based on a novel multimodal affinity fusion network (MAFN) for survival prediction of breast cancer by integrating gene expression, copy number alteration, and clinical data. First, a stack-based shallow self-attention network is utilized to guide the amplification of tiny lesion regions on the original data, which locates and enhances the survival-related features. Then, an affinity fusion module is proposed to map the structured information between patients and multimodal data. The module endows the network with a stronger fusion feature representation and discrimination capability. Finally, the fusion feature embedding and a specific feature embedding from a triple modal network are fused to make the classification of long-term survival or short-term survival for each patient. As expected, the evaluation results on comprehensive performance indicate that MAFN achieves better predictive performance than existing methods. Additionally, our method can be extended to the survival prediction of other cancer diseases, providing a new strategy for other diseases prognosis.

Immune and stromal scoring system associated with tumor microenvironment and prognosis: a gene-based multi-cancer analysis

Background Tumor microenvironment (TME) is associated with tumor progression and prognosis. Previous studies provided tools to estimate immune and stromal cell infiltration in TME. However, there is still a lack of single index to reflect both immune and stromal status associated with prognosis and immunotherapy responses. Methods A novel immune and stromal scoring system named ISTMEscore was developed. A total of 15 datasets were used to train and validate this system, containing 2965 samples from lung adenocarcinoma, skin cutaneous melanoma and head and neck squamous cell carcinoma. Results The patients with high immune and low stromal scores (HL) were associated with low ratio of T cell co-inhibitory/stimulatory molecules and low levels of angiogenesis markers, while the patients with low immune and high stromal scores (LH) had the opposite characteristics. The HL patients had immune-centered networks, while the patients with low immune and low stromal scores (LL) had desert-like networks. Moreover, copy number alteration burden was decreased in the HL patients. For the clinical characteristics, our TME classification was an independent prognostic factor. In the 5 cohorts with immunotherapy, the LH patients were linked to the lowest response rate. Conclusions ISTMEscore system could reflect the TME status and predict the prognosis. Compared to previous TME scores, our ISTMEscore was superior in the prediction of prognosis and immunotherapy response.