Granzyme A from killer lymphocytes cleaves gasdermin B (GSDMB) and triggers pyroptosis in targeted human tumor cells, eliciting antitumor immunity. However, GSDMB has a controversial role in pyroptosis and has been linked to both anti- and protumor functions. Here, we found that GSDMB splicing variants are functionally distinct. Cleaved N-terminal (NT) fragments of GSDMB isoforms 3 and 4 caused pyroptosis, but isoforms 1, 2, and 5 did not. The nonfunctional isoforms have a deleted or modified exon 6 and therefore lack a stable belt motif. The belt likely contributes to the insertion of oligomeric GSDMB-NTs into the membrane. Consistently, noncytotoxic GSDMB-NTs blocked pyroptosis caused by cytotoxic GSDMB-NTs in a dominant-negative manner. Upon natural killer (NK) cell attack, GSDMB3-expressing cells died by pyroptosis, whereas GSDMB4-expressing cells died by mixed pyroptosis and apoptosis, and GSDMB1/2-expressing cells died only by apoptosis. GSDMB4 partially resisted NK cell-triggered cleavage, suggesting that only GSDMB3 is fully functional. GSDMB1-3 were the most abundant isoforms in the tested tumor cell lines and were similarly induced by interferon-γ and the chemotherapy drug methotrexate. Expression of cytotoxic GSDMB3/4 isoforms, but not GSDMB1/2 isoforms that are frequently up-regulated in tumors, was associated with better outcomes in bladder and cervical cancers, suggesting that GSDMB3/4-mediated pyroptosis was protective in those tumors. Our study indicates that tumors may block and evade killer cell-triggered pyroptosis by generating noncytotoxic GSDMB isoforms. Therefore, therapeutics that favor the production of cytotoxic GSDMB isoforms by alternative splicing may improve antitumor immunity.

For cancer diagnosis, many DNA methylation markers have been identified. However, few studies have tried to identify DNA methylation markers to diagnose diverse cancer types simultaneously, i.e., pan-cancers. In this study, we tried to identify DNA methylation markers to differentiate cancer samples from the respective normal samples in pan-cancers. We collected whole genome methylation data of 27 cancer types containing 10,140 cancer samples and 3386 normal samples, and divided all samples into five data sets, including one training data set, one validation data set and three test data sets. We applied machine learning to identify DNA methylation markers, and specifically, we constructed diagnostic prediction models by deep learning. We identified two categories of markers: 12 CpG markers and 13 promoter markers. Three of 12 CpG markers and four of 13 promoter markers locate at cancer-related genes. With the CpG markers, our model achieved an average sensitivity and specificity on test data sets as 92.8% and 90.1%, respectively. For promoter markers, the average sensitivity and specificity on test data sets were 89.8% and 81.1%, respectively. Furthermore, in cell-free DNA methylation data of 163 prostate cancer samples, the CpG markers achieved the sensitivity as 100%, and the promoter markers achieved 92%. For both marker types, the specificity of normal whole blood was 100%. To conclude, we identified methylation markers to diagnose pan-cancers, which might be applied to liquid biopsy of cancers.

Effective and precise classification of glioma patients for their disease risks is critical to improving early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omics data types to efficiently and precisely subgroup glioma patients and predict survival prognosis is still lacking. In addition, effective therapeutic targets for treating glioma patients with poor prognoses are in dire need. To begin to resolve this difficulty, we developed i-Modern, an integrated Multi-omics deep learning network method, and optimized a sophisticated computational model in gliomas that can accurately stratify patients based on their prognosis. We built a survival-associated predictive framework integrating transcription profile, miRNA expression, somatic mutations, copy number variation (CNV), DNA methylation, and protein expression. This framework achieved promising performance in distinguishing high-risk glioma patients from those with good prognoses. Furthermore, we constructed multiple fully connected neural networks that are trained on prioritized multi-omics signatures or even only potential single-omics signatures, based on our customized scoring system. Together, the landmark multi-omics signatures we identified may serve as potential therapeutic targets in gliomas.

Abnormal accumulation of R-loops results in replication stress, genome instability, chromatin alterations and gene silencing. Little research has been done to characterize functional relationships among R-loops, histone marks, RNA polymerase II (RNAPII) transcription and gene regulation. We built extremely randomized trees (ETs) models to predict the genome-wide R-loops using RNAPII and multiple histone modifications chromatin immunoprecipitation (ChIP)-seq, DNase-seq, Global Run-On sequencing (GRO-seq) and R-loop profiling data. We compared the performance of ET models to multiple machine learning approaches, and the proposed ET models achieved the best and extremely robust performances. Epigenetic profiles are highly predictive of R-loops genome-widely and they are strongly associated with R-loop formation. In addition, the presence of R-loops is significantly correlated with RNAPII transcription activity, H3K4me3 and open chromatin around the transcription start site, and H3K9me1 and H3K9me3 around the transcription termination site. RNAPII pausing defects were correlated with 5′R-loops accumulation, and transcriptional termination defects and read-throughs were correlated with 3′R-loops accumulation. Furthermore, we found driver genes with 5′R-loops and RNAPII pausing defects express significantly higher and genes with 3′R-loops and read-through transcription express significantly lower than genes without R-loops. These driver genes are enriched with chromosomal instability, Hippo–Merlin signaling Dysregulation, DNA damage response and TGF-β pathways, indicating R-loops accumulating at the 5′ end of genes play oncogenic roles, whereas at the 3′ end of genes play tumor-suppressive roles in tumorigenesis.

Whole-genome bisulfite sequencing generates a comprehensive profiling of the gene methylation levels, but is limited by a high cost. Recent studies have partitioned the genes into landmark genes and target genes and suggested that the landmark gene expression levels capture adequate information to reconstruct the target gene expression levels. This inspired us to propose that the methylation level of the promoters in landmark genes might be adequate to reconstruct the promoter methylation level of target genes, which would eventually reduce the cost of promoter methylation profiling. Here, we propose a deep learning model called Deep-Gene Promoter Methylation (D-GPM) to predict the whole-genome promoter methylation level based on the promoter methylation profile of the landmark genes from The Cancer Genome Atlas (TCGA). D-GPM-15%-7000 × 5, the optimal architecture of D-GPM, acquires the least overall mean absolute error (MAE) and the highest overall Pearson correlation coefficient (PCC), with values of 0.0329 and 0.8186, respectively, when testing data. Additionally, the D-GPM outperforms the regression tree (RT), linear regression (LR), and the support vector machine (SVM) in 95.66%, 92.65%, and 85.49% of the target genes by virtue of its relatively lower MAE and in 98.25%, 91.00%, and 81.56% of the target genes based on its relatively higher PCC, respectively. More importantly, the D-GPM predominates in predicting 79.86% and 78.34% of the target genes according to the model distribution of the least MAE and the highest PCC, respectively.

Effective and precise classification of breast cancer patients for their disease risks is critical to improve early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omics data to subgroup cancer patients and predict survival prognosis is still lacking. In addition, effective therapeutic targets for treating breast cancer patients with poor prognoses are in dire need. To begin to resolve this difficulty, we developed and optimized a sophisticated deep learning-based model in breast cancer that can accurately stratify patients based on their prognosis. We built a survival-associated predictive framework integrating transcription profile, miRNA expression, somatic mutations, copy number variation, DNA methylation and protein expression. This framework achieved promising performance in distinguishing high-risk breast cancer patients from those with good prognoses. Furthermore, we constructed multiple fully connected neural networks that are trained on prioritized multi-omics signatures or even only potential single-omics signatures, based on our customized scoring system. Together, the landmark multi-omics signatures we identified may serve as potential therapeutic targets in breast cancer.