The development of digital pathology and progression of state-of-the-art algorithms for computer vision have led to increasing interest in the use of artificial intelligence (AI), especially deep learning (DL)-based AI, in tumor pathology. The DL-based algorithms have been developed to conduct all kinds of work involved in tumor pathology, including tumor diagnosis, subtyping, grading, staging, and prognostic prediction, as well as the identification of pathological features, biomarkers and genetic changes. The applications of AI in pathology not only contribute to improve diagnostic accuracy and objectivity but also reduce the workload of pathologists and subsequently enable them to spend additional time on high-level decision-making tasks. In addition, AI is useful for pathologists to meet the requirements of precision oncology. However, there are still some challenges relating to the implementation of AI, including the issues of algorithm validation and interpretability, computing systems, the unbelieving attitude of pathologists, clinicians and patients, as well as regulators and reimbursements. Herein, we present an overview on how AI-based approaches could be integrated into the workflow of pathologists and discuss the challenges and perspectives of the implementation of AI in tumor pathology.

Primary biliary cholangitis (PBC) is an autoimmune liver disease with a strong hereditary component. Here, we report a genome-wide association study that included 1,122 PBC cases and 4,036 controls of Han Chinese descent, with subsequent replication in a separate cohort of 907 PBC cases and 2,127 controls. Our results show genome-wide association of 14 PBC risk loci including previously identified 6p21 (HLA-DRA and DPB1), 17q12 (ORMDL3), 3q13.33 (CD80), 2q32.3 (STAT1/STAT4), 3q25.33 (IL12A), 4q24 (NF-κB) and 22q13.1 (RPL3/SYNGR1). We also identified variants in IL21, IL21R, CD28/CTLA4/ICOS, CD58, ARID3A and IL16 as novel PBC risk loci. These new findings and histochemical studies showing enhanced expression of IL21 and IL21R in PBC livers (particularly in the hepatic portal tracks) support a disease mechanism in which the deregulation of the IL21 signalling pathway, in addition to CD4 T-cell activation and T-cell co-stimulation are critical components in the development of PBC.

Background The expression of CYP4Z1 and the pseudogene CYP4Z2P has been shown to be specifically increased in breast cancer by our group and others. Additionally, we previously revealed the roles of the competitive endogenous RNA (ceRNA) network mediated by these genes (ceRNET_CC) in breast cancer angiogenesis, apoptosis, and tamoxifen resistance. However, the roles of ceRNET_CC in regulating the stemness of breast cancer cells and the mechanisms through which ceRNET_CC is regulated remain unclear. Methods Transcriptional factor six2, CYP4Z1-3′UTR, and CYP4Z2P-3′UTR were stably overexpressed or knocked down in breast cancer cells via lentivirus infection. ChIP-sequencing and RNA-sequencing analysis were performed to reveal the mechanism through which ceRNET_CC is regulated and the transcriptome change mediated by ceRNET_CC. Clinical samples were used to validate the correlation between six2 and ceRNET_CC. Finally, the effects of the six2/ceRNET_CC axis on the stemness of breast cancer cells and chemotherapy sensitivity were evaluated by in vitro and in vivo experiments. Results We revealed that ceRNET_CC promoted the stemness of breast cancer cells. Mechanistically, six2 activated ceRNET_CC by directly binding to their promoters, thus activating the downstream PI3K/Akt and ERK1/2 pathways. Finally, we demonstrated that the six2/ceRNET_CC axis was involved in chemoresistance. Conclusions Our results uncover the mechanism through which ceRNET_CC is regulated, identify novel roles for the six2/ceRNET_CC axis in regulating the stemness of breast cancer cells, and propose the possibility of targeting the six2/ceRNET_CC axis to inhibit breast cancer stem cell (CSC) traits. Electronic supplementary material The online version of this article (10.1186/s13045-019-0697-6) contains supplementary material, which is available to authorized users.

No abstract

Background : Epigenetic regulation has been verified as a key mechanism in tumorigenesis. SET and MYND domain-containing protein 3 (SMYD3), a histone methyltransferase, is a promising epigenetic therapeutic target and is overexpressed in numerous human tumors. SMYD3 can promote oncogenic progression by methylating lysines to integrate cytoplasmic kinase signaling cascades or by methylating histone lysines to regulate specific gene transcription. However, the exact role of SMYD3 in the progression of ovarian cancer is still unknown. Methods : Immunohistochemistry was employed to test SMYD3 expression in ovarian cancer tissues from clinical patients. CCK-8 assay, Real-time cell analysis (RTCA), colony formation assay, cell cycle and apoptosis tested by Flow cytometer were employed to test the effects of SMYD3 on cell proliferation and apoptosis in ovarian cancer cell lines. A PCR array was used to identify the downstream targets of SMYD3. And, PCR and Western blot were used to verify their expression. The binding of SMYD3 on the promoter of target genes were tested by ChIP assays. We also use nude mice subcutaneous tumor model and patient-derived xenograft (PDX) model to investigate the tumor promotive function of SMYD3 in vivo . Results : SMYD3 expression was higher in ovarian cancer tissues and cell lines than in normal ovarian epithelial tissue and human ovarian surface epithelial cells (HOSEpiC). After silencing SMYD3, the proliferation of ovarian cancer cells was significantly inhibited in vitro . In addition, the SMYD3-specific small-molecule inhibitor BCI-121 suppressed ovarian cancer cell proliferation. Downregulation of SMYD3 led to S phase arrest and increased the cell apoptosis rate. Furthermore, a PCR array revealed that SMYD3 knockdown caused the upregulation of the cyclin-dependent kinase (CDK) inhibitors CDKN2A (p16 INK4 ), CDKN2B (p15 INK4B ), CDKN3 and CDC25A, which may be responsible for the S phase arrest. In addition, the upregulation of CD40LG and downregulation of BIRC3 may explain the increased cell apoptosis rate after silencing SMYD3. We also discovered that SMYD3 bound on the promoter of CDKN2A and down-regulated its expression by triple-methylating H4K20. In addition, SMYD3 bound on the promoter of BIRC3 and up-regulated its expression by triple-methylating H3K4. Finally, knocking down SMYD3 could inhibit ovarian cancer growth in nude mice subcutaneous tumor model and PDX model. Conclusion : Our results demonstrated that SMYD3 was overexpressed in ovarian cancer and contributes to the regulation of tumor proliferation and apoptosis via SMYD3-H4K20me3-CDKN2A pathway and SMYD3-H3K4me3-BIRC3 pathway. Thus, SMYD3 is a promising epigenetic therapeutic target for ovarian cancer.