Integrating Machine Learning and Tumor Immune Signature to Predict Oncologic Outcomes in Resected Biliary Tract Cancer

Modulating PCGF4/BMI1 Stability Is an Efficient Metastasis-Regulatory Strategy Used by Distinct Subtypes of Cancer-Associated Fibroblasts in Intrahepatic Cholangiocarcinoma

Intrahepatic cholangiocarcinoma (ICC) is a highly malignant neoplasm prone to metastasis. Whether cancer-associated fibroblasts (CAFs) affect the metastasis of ICC is unclear. Herein, ICC patient-derived CAF lines and related cancerous cell lines were established and the effects of CAFs on the tumor progressive properties of the ICC cancerous cells were analyzed. CAFs could be classified into cancer-restraining or cancer-promoting categories based on distinct tumorigenic effects. The RNA-sequencing analyses of ICC cancerous cell lines identified polycomb group ring finger 4 (PCGF4; alias BMI1) as a potential metastasis regulator. The changes of PCGF4 levels in ICC cells mirrored the restraining or promoting effects of CAFs on ICC migration. Immunohistochemical analyses on the ICC tissue microarrays indicated that PCGF4 was negatively correlated with overall survival of ICC. The promoting effects of PCGF4 on cell migration, drug resistance activity, and stemness properties were confirmed. Mechanistically, cancer-restraining CAFs triggered the proteasome-dependent degradation of PCGF4, whereas cancer-promoting CAFs enhanced the stability of PCGF4 via activating the IL-6/phosphorylated STAT3 pathway. In summary, the current data identified the role of CAFs in ICC metastasis and revealed a new mechanism of the CAFs on ICC progression in which PCGF4 acted as the key effector by both categories of CAFs. These findings shed light on developing comprehensive therapeutic strategies for ICC.

Low gamma-butyrobetaine dioxygenase (BBOX1) expression as a prognostic biomarker in patients with clear cell renal cell carcinoma: a machine learning approach

Gamma-butyrobetaine dioxygenase (BBOX1) is a catalyst for the conversion of gamma-butyrobetaine to l-carnitine, which is detected in normal renal tubules. The purpose of this study was to analyze the prognosis, immune response, and genetic alterations associated with low BBOX1 expression in patients with clear cell renal cell carcinoma (RCC). We analyzed the relative influence of BBOX1 on survival using machine learning and investigated drugs that can inhibit renal cancer cells with low BBOX1 expression. We analyzed clinicopathologic factors, survival rates, immune profiles, and gene sets according to BBOX1 expression in a total of 857 patients with kidney cancer from the Hanyang University Hospital cohort (247 cases) and The Cancer Genome Atlas (610 cases). We employed immunohistochemical staining, gene set enrichment analysis, in silico cytometry, pathway network analyses, in vitro drug screening, and gradient boosting machines. BBOX1 expression in RCC was decreased compared with that in normal tissues. Low BBOX1 expression was associated with poor prognosis, decreased CD8+ T cells, and increased neutrophils. In gene set enrichment analyses, low BBOX1 expression was related to gene sets with oncogenic activity and a weak immune response. In pathway network analysis, BBOX1 was linked to regulation of various T cells and programmed death-ligand 1. In vitro drug screening showed that midostaurin, BAY-61-3606, GSK690693, and linifanib inhibited the growth of RCC cells with low BBOX1 expression. Low BBOX1 expression in patients with RCC is related to short survival time and reduced CD8+ T cells; midostaurin, among other drugs, may have enhanced therapeutic effects in this context.

BiTNet: Hybrid deep convolutional model for ultrasound image analysis of human biliary tract and its applications

Certain life-threatening abnormalities, such as cholangiocarcinoma, in the human biliary tract are curable if detected at an early stage, and ultrasonography has been proven to be an effective tool for identifying them. However, the diagnosis often requires a second opinion from experienced radiologists, who are usually overwhelmed by many cases. Therefore, we propose a deep convolutional neural network model, named biliary tract network (BiTNet), developed to solve problems in the current screening system and to avoid overconfidence issues of traditional deep convolutional neural networks. Additionally, we present an ultrasound image dataset for the human biliary tract and demonstrate two artificial intelligence (AI) applications: auto-prescreening and assisting tools. The proposed model is the first AI model to automatically screen and diagnose upper-abdominal abnormalities from ultrasound images in real-world healthcare scenarios. Our experiments suggest that prediction probability has an impact on both applications, and our modifications to EfficientNet solve the overconfidence problem, thereby improving the performance of both applications and of healthcare professionals. The proposed BiTNet can reduce the workload of radiologists by 35% while keeping the false negatives to as low as 1 out of every 455 images. Our experiments involving 11 healthcare professionals with four different levels of experience reveal that BiTNet improves the diagnostic performance of participants of all levels. The mean accuracy and precision of the participants with BiTNet as an assisting tool (0.74 and 0.61, respectively) are statistically higher than those of participants without the assisting tool (0.50 and 0.46, respectively (p<0.001)). These experimental results demonstrate the high potential of BiTNet for use in clinical settings.

High PPFIA1 expression promotes cancer survival by suppressing CD8+ T cells in breast cancer: drug discovery and machine learning approach

BACKGROUND

PTPRF-interacting protein alpha 1 (PPFIA1) plays an important role as a regulator of cell motility and tumor cell invasion and is frequently amplified in breast cancer. The aim of this study was to investigate the clinicopathologic features, survival, anticancer immunities and specific gene sets related to high PPFIA1 expression in patients with breast cancer. We verified the importance of PPFIA1 and survival rates using machine learning and identified drugs that can effectively reduce breast cancer cells with high PPFIA1 expression.

METHODS

This study analyzed clinicopathologic factors, survival rates, immune profiles and gene sets according to PPFIA1 expression in 3457 patients with breast cancer from the Kangbuk Samsung Medical Center cohort (456 cases), Molecular Taxonomy of Breast Cancer International Consortium (1904 cases) and The Cancer Genome Atlas (1097 cases). We applied gene set enrichment analysis (GSEA), in silico cytometry, pathway network analyses, in vitro drug screening, and gradient boosting machine (GBM) analysis.

RESULTS

High PPFIA1 expression in breast cancer was associated with worse prognosis, with reduced tumor-infiltrating lymphocytes, especially CD8+ T cells, and increased PD-L1 expression. In pathway network analysis, PPFIA1 was linked directly to the tyrosine-protein phosphatase pathway and indirectly to immune pathways. The importance of PPFIA1's association with survival in GBM analysis was higher than that of perineural and lymphovascular invasion. In in vitro drug screening, expression of PPFIA1 on mRNA level positively correlated with sensitivity of cell lines to erlotinib.

CONCLUSION

High PPFIA1 in patients with breast cancer is related to poor prognosis and decreased anticancer immune response, and erlotinib may be promising for development of therapeutic approaches in patients with tumors overexpressing PPFIA1.

A Clinical-Radiomic Model for Predicting Indocyanine Green Retention Rate at 15 Min in Patients With Hepatocellular Carcinoma

Purpose:

The indocyanine green retention rate at 15 min (ICG-R15) is of great importance in the accurate assessment of hepatic functional reserve for safe hepatic resection. To assist clinicians to evaluate hepatic functional reserve in medical institutions that lack expensive equipment, we aimed to explore a novel approach to predict ICG-R15 based on CT images and clinical data in patients with hepatocellular carcinoma (HCC).

Methods

In this retrospective study, 350 eligible patients were enrolled and randomly assigned to the training cohort (245 patients) and test cohort (105 patients). Radiomics features and clinical factors were analyzed to pick out the key variables, and based on which, we developed the random forest regression, extreme gradient boosting regression (XGBR), and artificial neural network models for predicting ICG-R15, respectively. Pearson's correlation coefficient (R) was adopted to evaluate the performance of the models.

Results

We extracted 660 CT image features in total from each patient. Fourteen variables significantly associated with ICG-R15 were picked out for model development. Compared to the other two models, the XGBR achieved the best performance in predicting ICG-R15, with a mean difference of 1.59% (median, 1.53%) and an R-value of 0.90. Delong test result showed no significant difference in the area under the receiver operating characteristic (AUROCs) for predicting post hepatectomy liver failure between actual and estimated ICG-R15.

Conclusion

The proposed approach that incorporates the optimal radiomics features and clinical factors can allow for individualized prediction of ICG-R15 value of patients with HCC, regardless of the specific equipment and detection reagent (NO. ChiCTR2100053042; URL, http://www.chictr.org.cn).

MiR-206 suppresses the deterioration of intrahepatic cholangiocarcinoma and promotes sensitivity to chemotherapy by inhibiting interactions with stromal CAFs

Background: Intrahepatic cholangiocarcinoma (iCCA) is a highly malignant subtype of cholangiocarcinoma (CCA) with poor prognosis. In iCCA, the interplay between the stroma and tumor cells results in resistance to adjuvant chemotherapy. Increasing evidence indicates that miR-206 participates in tumor progression, but its role in iCCA is still unclear. The aim of this study was to identify dysregulated miR-206 expression in iCCA and to further explore the underlying mechanism.

Methods: MiR-206 expression was proven to be downregulated in iCCA tissues by qPCR, and its correlation with clinical characteristics and prognosis was investigated. iCCA-derived cancer-associated fibroblast cells (CAFs) and normal fibroblast cells (NFs) were isolated and identified. MiR-206 was knocked in or down in CAFs and CCA cells, respectively, to explore the role of miR-206, and coculture of these treated CCAs and CAFs was conducted to explore the effects of miR-206 on their mutual promoting effects. Exosomes carrying miR-206 and an orthotopic mouse model were used to determine the inhibitory effects of miR-206 on iCCA deterioration in vivo.

Results: We confirmed that miR-206 is a suppressor of iCCA. Overexpressing miR-206 in CCA cells inhibited cell proliferation, migration and invasion. When cocultured with CCA cells, NFs downregulated miR-206 expression, and NFs were susceptible to transforming into CAFs. Moreover, CAFs promoted CCA cell malignant behaviors and gemcitabine resistance. Overexpressing miR-206 in CAFs or CCA cells inhibited this mutual promoting effect. Additionally, when delivered by exosomes, miR-206 suppressed tumor deterioration. And combined with gemcitabine, this treatment resulted in a longer survival time.

Conclusion: Our study explained that the interaction between CCA cells and CAFs promoted iCCA deterioration. As a suppressive factor, miR-206 inhibited aggressive characteristics and gemcitabine resistance by interfering with this mutual promoting effect. This research elucidated the molecular mechanism underlying the unfavorable chemotherapeutic response of patients with iCCA, which provided a promising target for iCCA treatment.

A Study of the Recent Trends of Immunology: Key Challenges, Domains, Applications, Datasets, and Future Directions

The human immune system is very complex. Understanding it traditionally required specialized knowledge and expertise along with years of study. However, in recent times, the introduction of technologies such as AIoMT (Artificial Intelligence of Medical Things), genetic intelligence algorithms, smart immunological methodologies, etc., has made this process easier. These technologies can observe relations and patterns that humans do and recognize patterns that are unobservable by humans. Furthermore, these technologies have also enabled us to understand better the different types of cells in the immune system, their structures, their importance, and their impact on our immunity, particularly in the case of debilitating diseases such as cancer. The undertaken study explores the AI methodologies currently in the field of immunology. The initial part of this study explains the integration of AI in healthcare and how it has changed the face of the medical industry. It also details the current applications of AI in the different healthcare domains and the key challenges faced when trying to integrate AI with healthcare, along with the recent developments and contributions in this field by other researchers. The core part of this study is focused on exploring the most common classifications of health diseases, immunology, and its key subdomains. The later part of the study presents a statistical analysis of the contributions in AI in the different domains of immunology and an in-depth review of the machine learning and deep learning methodologies and algorithms that can and have been applied in the field of immunology. We have also analyzed a list of machine learning and deep learning datasets about the different subdomains of immunology. Finally, in the end, the presented study discusses the future research directions in the field of AI in immunology and provides some possible solutions for the same.

Applied machine learning in cancer research: A systematic review for patient diagnosis, classification and prognosis

Artificial Intelligence (AI) has recently altered the landscape of cancer research and medical oncology using traditional Machine Learning (ML) algorithms and cutting-edge Deep Learning (DL) architectures. In this review article we focus on the ML aspect of AI applications in cancer research and present the most indicative studies with respect to the ML algorithms and data used. The PubMed and dblp databases were considered to obtain the most relevant research works of the last five years. Based on a comparison of the proposed studies and their research clinical outcomes concerning the medical ML application in cancer research, three main clinical scenarios were identified. We give an overview of the well-known DL and Reinforcement Learning (RL) methodologies, as well as their application in clinical practice, and we briefly discuss Systems Biology in cancer research. We also provide a thorough examination of the clinical scenarios with respect to disease diagnosis, patient classification and cancer prognosis and survival. The most relevant studies identified in the preceding year are presented along with their primary findings. Furthermore, we examine the effective implementation and the main points that need to be addressed in the direction of robustness, explainability and transparency of predictive models. Finally, we summarize the most recent advances in the field of AI/ML applications in cancer research and medical oncology, as well as some of the challenges and open issues that need to be addressed before data-driven models can be implemented in healthcare systems to assist physicians in their daily practice.

Machine learning in gastrointestinal surgery

Machine learning (ML) is a collection of algorithms allowing computers to learn directly from data without predetermined equations. It is used widely to analyze "big data". In gastrointestinal surgery, surgeons deal with various data such as clinical parameters, surgical videos, and pathological images, to stratify surgical risk, perform safe surgery and predict patient prognosis. In the current "big data" era, the accelerating accumulation of a large amount of data drives studies using ML algorithms. Three subfields of ML are supervised learning, unsupervised learning, and reinforcement learning. In this review, we summarize applications of ML to surgical practice in the preoperative, intraoperative, and postoperative phases of care. Prediction and stratification using ML is promising; however, the current overarching concern is the availability of ML models. Information systems that can manage "big data" and integrate ML models into electronic health records are essential to incorporate ML into daily practice. ML is fundamental technology to meaningfully process data that exceeds the capacity of the human mind to comprehend. The accelerating accumulation of a large amount of data is changing the nature of surgical practice fundamentally. Artificial intelligence (AI), represented by ML, is being incorporated into daily surgical practice.

Cancer-associated fibroblasts are associated with poor prognosis in solid type of lung adenocarcinoma in a machine learning analysis

Cancer-associated fibroblasts (CAFs) participate in critical processes in the tumor microenvironment, such as extracellular matrix remodeling, reciprocal signaling interactions with cancer cells and crosstalk with infiltrating inflammatory cells. However, the relationships between CAFs and survival are not well known in lung cancer. The aim of this study was to reveal the correlations of CAFs with survival rates, genetic alterations and immune activities. This study reviewed the histological features of 517 patients with lung adenocarcinoma from The Cancer Genome Atlas (TCGA) database. We performed gene set enrichment analysis (GSEA), network-based analysis and survival analysis based on CAFs in four histological types of lung adenocarcinoma: acinar, papillary, micropapillary and solid. We found four hallmark gene sets, the epithelial-mesenchymal transition, angiogenesis, hypoxia, and inflammatory response gene sets, that were associated with the presence of CAFs. CAFs were associated with tumor proliferation, elevated memory CD4+T cells and high CD274 (encoding PD-L1) expression. In the pathway analyses, CAFs were related to blood vessel remodeling, matrix organization, negative regulation of apoptosis and transforming growth factor-β signaling. In the survival analysis of each histological type, CAFs were associated with poor prognosis in the solid type. These results may contribute to the development of therapeutic strategies against lung adenocarcinoma cases in which CAFs are present.

High BMI1 Expression with Low CD8+ and CD4+ T Cell Activity Could Promote Breast Cancer Cell Survival: A Machine Learning Approach

BMI1 is known to play a key role in the regulation of stem cell self-renewal in both endogenous and cancer stem cells. High BMI1 expression has been associated with poor prognosis in a variety of human tumors. The aim of this study was to reveal the correlations of BMI1 with survival rates, genetic alterations, and immune activities, and to validate the results using machine learning. We investigated the survival rates according to BMI1 expression in 389 and 789 breast cancer patients from Kangbuk Samsung Medical Center (KBSMC) and The Cancer Genome Atlas, respectively. We performed gene set enrichment analysis (GSEA) with pathway-based network analysis, investigated the immune response, and performed in vitro drug screening assays. The survival prediction model was evaluated through a gradient boosting machine (GBM) approach incorporating BMI1. High BMI1 expression was correlated with poor survival in patients with breast cancer. In GSEA and in in silico flow cytometry, high BMI1 expression was associated with factors indicating a weak immune response, such as decreased CD8+ T cell and CD4+ T cell counts. In pathway-based network analysis, BMI1 was directly linked to transcriptional regulation and indirectly linked to inflammatory response pathways, etc. The GBM model incorporating BMI1 showed improved prognostic performance compared with the model without BMI1. We identified telomerase inhibitor IX, a drug with potent activity against breast cancer cell lines with high BMI1 expression. We suggest that high BMI1 expression could be a therapeutic target in breast cancer. These results could contribute to the design of future experimental research and drug development programs for breast cancer.

High WHSC1L1 Expression Reduces Survival Rates in Operated Breast Cancer Patients with Decreased CD8+ T Cells: Machine Learning Approach

Nuclear receptor-binding SET domain protein (NSD), a histone methyltransferase, is known to play an important role in cancer pathogenesis. The WHSC1L1 (Wolf-Hirschhorn syndrome candidate 1-like 1) gene, encoding NSD3, is highly expressed in breast cancer, but its role in the development of breast cancer is still unknown. The purpose of this study was to analyze the survival rates and immune responses of breast cancer patients with high WHSC1L1 expression and to validate the results using gradient boosting machine (GBM) in breast cancer. We investigated the clinicopathologic parameters, proportions of immune cells, pathway networks and in vitro drug responses according to WHSC1L1 expression in 456, 1500 and 776 breast cancer patients from the Hanyang University Guri Hospital, METABRIC and TCGA, respectively. High WHSC1L1 expression was associated with poor prognosis, decreased CD8+ T cells and high CD274 expression (encoding PD-L1). In the pathway networks, WHSC1L1 was indirectly linked to the regulation of the lymphocyte apoptotic process. The GBM model with WHSC1L1 showed improved prognostic performance compared with the model without WHSC1L1. We found that VX-11e, CZC24832, LY2109761, oxaliplatin and erlotinib were effective in inhibiting breast cancer cell lines with high WHSC1L1 expression. High WHSC1L1 expression could play potential roles in the progression of breast cancer and targeting WHSC1L1 could be a potential strategy for the treatment of breast cancer.