Mining the interpretable prognostic features from pathological image of intrahepatic cholangiocarcinoma using multi-modal deep learning.

BACKGROUND: The advances in deep learning-based pathological image analysis have invoked tremendous insights into cancer prognostication. Still, lack of interpretability remains a significant barrier to clinical application. METHODS: We established an integrative prognostic neural network for intrahepatic cholangiocarcinoma (iCCA), towards a comprehensive evaluation of both architectural and fine-grained information from whole-slide images. Then, leveraging on multi-modal data, we conducted extensive interrogative approaches to the models, to extract and visualize the morphological features that most correlated with clinical outcome and underlying molecular alterations. RESULTS: The models were developed and optimized on 373 iCCA patients from our center and demonstrated consistent accuracy and robustness on both internal (n = 213) and external (n = 168) cohorts. The occlusion sensitivity map revealed that the distribution of tertiary lymphoid structures, the geometric traits of the invasive margin, the relative composition of tumor parenchyma and stroma, the extent of necrosis, the presence of the disseminated foci, and the tumor-adjacent micro-vessels were the determining architectural features that impacted on prognosis. Quantifiable morphological vector extracted by CellProfiler demonstrated that tumor nuclei from high-risk patients exhibited significant larger size, more distorted shape, with less prominent nuclear envelope and textural contrast. The multi-omics data (n = 187) further revealed key molecular alterations left morphological imprints that could be attended by the network, including glycolysis, hypoxia, apical junction, mTORC1 signaling, and immune infiltration. CONCLUSIONS: We proposed an interpretable deep-learning framework to gain insights into the biological behavior of iCCA. Most of the significant morphological prognosticators perceived by the network are comprehensible to human minds.

Identification and validation of a lactate metabolism-related six-gene prognostic signature in intrahepatic cholangiocarcinoma.

PURPOSE: Intrahepatic cholangiocarcinoma (iCCA) is a highly malignant and fatal liver tumor with increasing incidence worldwide. Lactate metabolism has been recently reported as a crucial contributor to tumor progression and immune regulation in the tumor microenvironment. However, it remains poorly identified about the biological functions of lactate metabolism in iCCA, which hinders the development of prognostic tools and therapeutic interventions. METHODS: The univariate Cox regression analysis and Boruta algorithm were utilized to identify key lactate metabolism-related genes (LMRGs), and a prognostic signature was constructed based on LMRG scores. Genomic variations and immune cell infiltration were evaluated in the high and low LMRG score groups. Finally, the biological functions of key LMRGs were verified with in vitro and in vivo experiments. RESULTS: Patients in the high LMRG score group exhibit a poor prognosis compared to those in the low LMRG score group, with a high frequency of TP53 and KRAS mutations. Moreover, the infiltration and function of NK cells were compromised in the high LMRG score group, consistent with the results from two independent single-cell RNA sequencing datasets and immunohistochemistry of tissue microarrays. Experimental data revealed that lactate dehydrogenase A (LDHA) knockdown inhibited proliferation and migration in iCCA cell lines and tumor growth in immunocompetent mice. CONCLUSION: Our study revealed the biological roles of LDHA in iCCA and developed a reliable lactate metabolism-related prognostic signature for iCCA, offering promising therapeutic targets for iCCA in the clinic.

Whole-Genome DNA Methylation Profiling of Intrahepatic Cholangiocarcinoma Reveals Prognostic Subtypes with Distinct Biological Drivers.

Intrahepatic cholangiocarcinoma (iCCA) is the second most prevalent primary liver cancer. Although the genetic characterization of iCCA has led to targeted therapies for treating tumors with FGFR2 alterations and IDH1/2 mutations, only a limited number of patients can benefit from these strategies. Epigenomic profiles have emerged as potential diagnostic and prognostic biomarkers for improving the treatment of cancers. In this study, we conducted whole-genome bisulfite sequencing on 331 iCCAs integrated with genetic, transcriptomic, and proteomic analyses, demonstrating the existence of four DNA methylation subtypes of iCCAs (S1-S4) that exhibited unique postoperative clinical outcomes. The S1 group was an IDH1/2 mutation-specific subtype with moderate survival. The S2 subtype was characterized by the lowest methylation level and the highest mutational burden among the four subtypes and displayed upregulation of a gene-expression pattern associated with cell cycle/DNA replication. The S3 group was distinguished by high interpatient heterogeneity of tumor immunity, a gene-expression pattern associated with carbohydrate metabolism, and an enrichment of KRAS alterations. Patients with the S2 and S3 subtypes had the shortest survival among the four subtypes. Tumors in the S4 subtype, which had the best prognosis, showed global methylation levels comparable to normal controls, increased FGFR2 fusions/BAP1 mutations, and the highest copy-number variant burdens. Further integrative and functional analyses identified GBP4 demethylation, which is highly prevalent in the S2 and S3 groups, as an epigenetic oncogenic factor that regulates iCCA proliferation, migration, and invasion. Together, this study identifies prognostic methylome alterations and epigenetic drivers in iCCA. SIGNIFICANCE: Characterization of the DNA methylome of intrahepatic cholangiocarcinoma integrated with genomic, transcriptomic, and proteomic analyses uncovers molecular mechanisms affected by genome-wide DNA methylation alterations, providing a resource for identifying potential therapeutic targets.