NeoDL: a novel neoantigen intrinsic feature-based deep learning model identifies IDH wild-type glioblastomas with the longest survival.
Ontology highlight
ABSTRACT: Background
Neoantigen based personalized immune therapies achieve promising results in melanoma and lung cancer, but few neoantigen based models perform well in IDH wild-type GBM, and the association between neoantigen intrinsic features and prognosis remain unclear in IDH wild-type GBM. We presented a novel neoantigen intrinsic feature-based deep learning model (neoDL) to stratify IDH wild-type GBMs into subgroups with different survivals.Results
We first derived intrinsic features for each neoantigen associated with survival, followed by applying neoDL in TCGA data cohort(AUC = 0.988, p value < 0.0001). Leave one out cross validation (LOOCV) in TCGA demonstrated that neoDL successfully classified IDH wild-type GBMs into different prognostic subgroups, which was further validated in an independent data cohort from Asian population. Long-term survival IDH wild-type GBMs identified by neoDL were found characterized by 12 protective neoantigen intrinsic features and enriched in development and cell cycle.Conclusions
The model can be therapeutically exploited to identify IDH wild-type GBM with good prognosis who will most likely benefit from neoantigen based personalized immunetherapy. Furthermore, the prognostic intrinsic features of the neoantigens inferred from this study can be used for identifying neoantigens with high potentials of immunogenicity.
SUBMITTER: Sun T
PROVIDER: S-EPMC8299600 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Glioblastoma (GBM) is resistant to multimodality therapeutic approaches. A high burden of tumor-specific mutant peptides (neoantigens) correlates with better survival and response to immunotherapies in selected solid tumors but how neoantigens impact clinical outcome in GBM remains unclear. Here, we exploit the similarity between tumor neoantigens and infectious disease-derived immune epitopes and apply a neoantigen fitness model for identifying high-quality neoantigens in a human pan-glioma dataset. We find that the neoantigen quality fitness model stratifies GBM patients with more favorable clinical outcome and, together with CD8+ T lymphocytes tumor infiltration, identifies a GBM subgroup with the longest survival, which displays distinct genomic and transcriptomic features. Conversely, neither tumor neoantigen burden from a quantitative model nor the isolated enrichment of CD8+ T lymphocytes were able to predict survival of GBM patients. This approach may guide optimal stratification of GBM patients for maximum response to immunotherapy.
| S-EPMC6478916 | biostudies-literature
Project description:This study aimed to investigate the potential of quantitative radiomic data extracted from conventional MR images in discriminating IDH-mutant grade 4 astrocytomas from IDH-wild-type glioblastomas (GBMs). A cohort of 57 treatment-naïve patients with IDH-mutant grade 4 astrocytomas (n = 23) and IDH-wild-type GBMs (n = 34) underwent anatomical imaging on a 3T MR system with standard parameters. Post-contrast T1-weighted and T2-FLAIR images were co-registered. A semi-automatic segmentation approach was used to generate regions of interest (ROIs) from different tissue components of neoplasms. A total of 1050 radiomic features were extracted from each image. The data were split randomly into training and testing sets. A deep learning-based data augmentation method (CTGAN) was implemented to synthesize 200 datasets from the training sets. A total of 18 classifiers were used to distinguish two genotypes of grade 4 astrocytomas. From generated data using 80% training set, the best discriminatory power was obtained from core tumor regions overlaid on post-contrast T1 using the K-best feature selection algorithm and a Gaussian naïve Bayes classifier (AUC = 0.93, accuracy = 0.92, sensitivity = 1, specificity = 0.86, PR_AUC = 0.92). Similarly, high diagnostic performances were obtained from original and generated data using 50% and 30% training sets. Our findings suggest that conventional MR imaging-based radiomic features combined with machine/deep learning methods may be valuable in discriminating IDH-mutant grade 4 astrocytomas from IDH-wild-type GBMs.
| S-EPMC9913426 | biostudies-literature
Project description:Telomerase reverse transcriptase (TERT) promoter (pTERT) mutation has often been described as a late event in gliomagenesis and it has been suggested as a prognostic biomarker in gliomas other than 1p19q codeleted tumors. However, the characteristics of isocitrate dehydrogenase (IDH) wild type (wt) (IDHwt), pTERTwt glioblastomas are not well known. We recruited 72 adult IDHwt, pTERTwt glioblastomas and performed methylation profiling, targeted sequencing, and fluorescence in situ hybridization (FISH) for TERT structural rearrangement and ALT (alternative lengthening of telomeres). There was no significant difference in overall survival (OS) between our cohort and a the Cancer Genome Atlas (TCGA) cohort of IDHwt, pTERT mutant (mut) glioblastomas, suggesting that pTERT mutation on its own is not a prognostic factor among IDHwt glioblastomas. Epigenetically, the tumors clustered into classic-like (11%), mesenchymal-like (32%), and LGm6-glioblastoma (GBM) (57%), the latter far exceeding the corresponding proportion seen in the TCGA cohort of IDHwt, pTERTmut glioblastomas. LGm6-GBM-clustered tumors were enriched for platelet derived growth factor receptor alpha (PDGFRA) amplification or mutation (p = 0.008), and contained far fewer epidermal growth factor receptor (EGFR) amplification (p < 0.01), 10p loss (p = 0.001) and 10q loss (p < 0.001) compared with cases not clustered to this group. LGm6-GBM cases predominantly showed ALT (p = 0.038). In the whole cohort, only 35% cases showed EGFR amplification and no case showed combined chromosome +7/-10. Since the cases were already pTERTwt, so the three molecular properties of EGFR amplification, +7/-10, and pTERT mutation may not cover all IDHwt glioblastomas. Instead, EGFR and PDGFRA amplifications covered 67% and together with their mutations covered 71% of cases of this cohort. Homozygous deletion of cyclin dependent kinase inhibitor 2A (CDKN2A)/B was associated with a worse OS (p = 0.031) and was an independent prognosticator in multivariate analysis (p = 0.032). In conclusion, adult IDHwt, pTERTwt glioblastomas show epigenetic clustering different from IDHwt, pTERTmut glioblastomas, and IDHwt glioblastomas which are pTERTwt may however not show EGFR amplification or +7/-10 in a significant proportion of cases. CDKN2A/B deletion is a poor prognostic biomarker in this group.
| S-EPMC9616088 | biostudies-literature
Project description:PurposePoor outcomes in IDH wild-type (IDHwt) glioblastomas indicate the need to determine which genetic alterations can indicate poor survival and guidance of patient specific treatment options. We sought to identify the genetic alterations in these patients that predict for survival when adjusting particularly for treatments and other genetic alterations.MethodsA cohort of 167 patients with pathologically confirmed IDHwt glioblastomas treated at our institution was retrospectively reviewed. Next generation sequencing was performed for each patient to determine tumor genetic alterations. Multivariable cox proportional hazards analysis for overall survival (OS) was performed to control for patient variables.ResultsCDKN2A, CDKN2B, and MTAP deletion predict for worse OS independently of other genetic alterations and patient characteristics (hazard ratio [HR] 2.192, p = 0.0017). Patients with CDKN2A copy loss (HR 2.963, p = 0.0037) or TERT mutated (HR 2.815, p = 0.0008) glioblastomas exhibited significant associations between radiation dose and OS, while CDKN2A and TERT wild type patients did not. CDKN2A deleted patients with NF1 mutations had worse OS (HR 1.990, p = 0.0540), while CDKN2A wild type patients had improved OS (HR 0.229, p = 0.0723). Patients with TERT mutated glioblastomas who were treated with radiation doses < 45 Gy (HR 3.019, p = 0.0010) but not those treated with ≥ 45 Gy exhibited worse OS compared to those without TERT mutations.ConclusionIn IDHwt glioblastomas, CDKN2A, CDKN2B, and MTAP predict for poor prognosis. TERT and CDKN2A mutations are associated with worse survival only when treated with lower radiation doses, thus potentially providing a genetic marker that can inform clinicians on proper dose-fractionation schemes.
| S-EPMC9666584 | biostudies-literature
Project description:Isocitrate dehydrogenase (IDH) mutant and wildtype glioblastoma multiforme (GBM) often show overlapping features on magnetic resonance imaging (MRI), representing a diagnostic challenge. Deep learning showed promising results for IDH identification in mixed low/high grade glioma populations; however, a GBM-specific model is still lacking in the literature. Our aim was to develop a GBM-tailored deep-learning model for IDH prediction by applying convoluted neural networks (CNN) on multiparametric MRI. We selected 100 adult patients with pathologically demonstrated WHO grade IV gliomas and IDH testing. MRI sequences included: MPRAGE, T1, T2, FLAIR, rCBV and ADC. The model consisted of a 4-block 2D CNN, applied to each MRI sequence. Probability of IDH mutation was obtained from the last dense layer of a softmax activation function. Model performance was evaluated in the test cohort considering categorical cross-entropy loss (CCEL) and accuracy. Calculated performance was: rCBV (accuracy 83%, CCEL 0.64), T1 (accuracy 77%, CCEL 1.4), FLAIR (accuracy 77%, CCEL 1.98), T2 (accuracy 67%, CCEL 2.41), MPRAGE (accuracy 66%, CCEL 2.55). Lower performance was achieved on ADC maps. We present a GBM-specific deep-learning model for IDH mutation prediction, with a maximal accuracy of 83% on rCBV maps. Highest predictivity achieved on perfusion images possibly reflects the known link between IDH and neoangiogenesis through the hypoxia inducible factor.
| S-EPMC8069494 | biostudies-literature
Project description:Little is known about the mutational processes that shape the genetic landscape of gliomas. Numerous mutational processes leave marks on the genome in the form of mutations, copy number alterations, rearrangements or their combinations. To explore gliomagenesis, we hypothesized that gliomas with different underlying oncogenic mechanisms would have differences in the burden of various forms of these genomic alterations. This was an analysis on adult diffuse gliomas, but IDH-mutant gliomas as well as diffuse midline gliomas H3-K27M were excluded to search for the possible presence of new entities among the very heterogenous group of IDH-WT glioblastomas. The cohort was divided into two molecular subsets: (1) Molecularly-defined GBM (mGBM) as those that carried molecular features of glioblastomas (including TERT promoter mutations, 7/10 pattern, or EGFR-amplification), and (2) those who did not (others). Whole exome sequencing was performed for 37 primary tumors and matched blood samples as well as 8 recurrences. Single nucleotide variations (SNV), short insertion or deletions (indels) and copy number alterations (CNA) were quantified using 5 quantitative metrics (SNV burden, indel burden, copy number alteration frequency-wGII, chromosomal arm event ratio-CAER, copy number amplitude) as well as 4 parameters that explored underlying oncogenic mechanisms (chromothripsis, double minutes, microsatellite instability and mutational signatures). Findings were validated in the TCGA pan-glioma cohort. mGBM and "Others" differed significantly in their SNV (only in the TCGA cohort) and CNA metrics but not indel burden. SNV burden increased with increasing age at diagnosis and at recurrences and was driven by mismatch repair deficiency. On the contrary, indel and CNA metrics remained stable over increasing age at diagnosis and with recurrences. Copy number alteration frequency (wGII) correlated significantly with chromothripsis while CAER and CN amplitude correlated significantly with the presence of double minutes, suggesting separate underlying mechanisms for different forms of CNA.
| S-EPMC7762325 | biostudies-literature
Project description:Glioblastomas (GBMs) are classified into isocitrate dehydrogenase (IDH) mutant (IDH MT) and wild-type (IDH WT) subtypes, and each is associated with distinct tumor behavior and prognosis. The present study aimed to investigate differentially expressed long non-coding (lnc)RNAs and mRNAs between IDH MT and IDH WT GBMs, as well as to explore the interaction and potential functions of these RNAs. A total of 132 GBM samples with RNA profiling data (10 IDH MT and 122 IDH WT cases) were obtained from The Cancer Genome Atlas, and 62/78 and 142/219 up/downregulated lncRNAs and mRNAs between IDH MT and IDH WT GBMs were identified, respectively. Multivariate Cox analysis of the dysregulated lncRNAs/mRNAs identified three-lncRNA and fifteen-mRNA signatures with independent prognostic value, indicating that these RNAs may serve roles in determining distinct tumor behaviors and prognosis of patients with IDH MT/WT GBMs. Functional analysis of the three lncRNAs revealed that they were primarily associated with cell stemness or differentiation. Pearson's correlation analysis revealed that the protective lncRNA AC068643.1 was significantly positively correlated with two key bone morphogenetic protein (BMP) signaling-associated mRNAs, Bone morphogenetic protein 2 (BMP2) and Myostatin (MSTN), from the 15 mRNAs. Further in vitro studies demonstrated that BMP2 and MSTN directly stimulated AC068643.1 expression. In conclusion, the present study identified a BMP signaling pathway-regulated lncRNA AC068643.1, which may contribute to the different tumor behaviors observed between IDH MT and IDH WT GBMs.
| S-EPMC7285920 | biostudies-literature
Project description:Glioblastoma (GBM) is the most common and malignant brain tumor in adults. Genomic and epigenomic alterations of multiple cancer-driving genes are frequent in GBM. To identify molecular alterations associated with epigenetic aberrations, we performed whole exome sequencing-based analysis of DNA copy number variations in 55 adult patients with IDH-wild-type GBM. Beside mutations in common GBM driver genes such as TERTp (76%), TP53 (22%) and PTEN (20%), 67% of patients were affected by amplifications of genes associated with RTK/Rb/p53 cell signaling, including EGFR (45%), CDK4 (13%), and MDM2/4 (both 7%). The minimal deleted region at chromosome 10 was detected at the DNA demethylase TET1 (93%), mainly due to a loss-of-heterozygosity of complete chromosome 10 (53%) or by a mono-allelic microdeletion at 10q21.3 (7%). In addition, bi-allelic TET1 deletions, detected in 18 patients (33%), frequently co-occurred with EGFR amplification and were associated with low levels of TET1 mRNA expression, pointing at loss of TET1 activity. Bi-allelic TET1 loss was not associated with global concentrations of 5-hydroxymethylcytosine, indicating a site-specific effect of TET1 for DNA (de)methylation. Focal amplification of EGFR positively correlated with overall mutational burden, tumor size, and poor long-term survival. Bi-allelic TET1 loss was not an independent prognostic factor, but significantly associated with poor survival in patients with concomitant EGFR amplification. Rates of genomic TET1 deletion were significantly lower in a cohort of IDH1-mutated patients. Despite the relevance of TET1 for DNA demethylation and as potential therapeutic target, a frequent genomic loss of TET1 has not previously been reported in GBM.
| S-EPMC7642757 | biostudies-literature
Project description:Giant cell glioblastoma (GC-GBM) is a rare variant of IDH-wt GBM histologically characterized by the presence of numerous multinucleated giant cells and molecularly considered a hybrid between IDH-wt and IDH-mutant GBM. The lack of an objective definition, specifying the percentage of giant cells required for this diagnosis, may account for the absence of a definite molecular profile of this variant. This study aimed to clarify the molecular landscape of GC-GBM, exploring the mutations and copy number variations of 458 cancer-related genes, tumor mutational burden (TMB), and microsatellite instability (MSI) in 39 GBMs dichotomized into having 30-49% (15 cases) or ≥ 50% (24 cases) GCs. The type and prevalence of the genetic alterations in this series was not associated with the GCs content (< 50% or ≥ 50%). Most cases (82% and 51.2%) had impairment in TP53/MDM2 and PTEN/PI3K pathways, but a high proportion also featured TERT promoter mutations (61.5%) and RB1 (25.6%) or NF1 (25.6%) alterations. EGFR amplification was detected in 18% cases in association with a shorter overall survival (P = 0.004). Sixteen (41%) cases had a TMB > 10 mut/Mb, including two (5%) that harbored MSI and one with a POLE mutation. The frequency of RB1 and NF1 alterations and TMB counts were significantly higher compared to 567 IDH wild type (P < 0.0001; P = 0.0003; P < 0.0001) and 26 IDH-mutant (P < 0.0001; P = 0.0227; P < 0.0001) GBMs in the TCGA PanCancer Atlas cohort. These findings demonstrate that the molecular landscape of GBMs with at least 30% giant cells is dominated by the impairment of TP53/MDM2 and PTEN/PI3K pathways, and additionally characterized by frequent RB1 alterations and hypermutation and by EGFR amplification in more aggressive cases. The high frequency of hypermutated cases suggests that GC-GBMs might be candidates for immune check-point inhibitors clinical trials.
| S-EPMC8709962 | biostudies-literature
Project description:Isocitrate dehydrogenase (IDH) mutant glioblastoma (GBM), accounts for ~10% GBMs, arises from lower grade diffuse glioma and preferentially appears in younger patients. Here, we aim to establish a robust gene expression-based molecular classification of IDH-mutant GBM. A total of 33 samples from the Chinese Glioma Genome Atlas RNA-sequencing data were selected as training set, and 21 cases from Chinese Glioma Genome Atlas microarray data were used as validation set. Consensus clustering identified three groups with distinguished prognostic and molecular features. G1 group, with a poorer clinical outcome, mainly contained TERT promoter wild-type and male cases. G2 and G3 groups had better prognosis differed in gender. Gene ontology analysis showed that genes enriched in G1 group were involved in DNA replication, cell division and cycle. On the basis of the differential genes between G1 and G2/G3 groups, a six-gene signature was developed with a Cox proportional hazards model. Kaplan-Meier analysis found that the acquired signature could differentiate the outcome of low- and high-risk cases. Moreover, the signature could also serve as an independent prognostic factor for IDH-mutant GBM in the multivariate Cox regression analysis. Gene ontology and gene set enrichment analyses revealed that gene sets correlated with high-risk group were involved in cell cycle, cell proliferation, DNA replication and repair. These finding highlights heterogeneity within IDH-mutant GBMs and will advance our molecular understanding of this lethal cancer.
| S-EPMC6642368 | biostudies-literature