Integrated Machine Learning and Bioinformatic Analyses Constructed a Novel Stemness-Related Classifier to Predict Prognosis and Immunotherapy Responses for Hepatocellular Carcinoma Patients

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

ChatGPT in Occupational Medicine: A Comparative Study with Human Experts

The objective of this study is to evaluate ChatGPT's accuracy and reliability in answering complex medical questions related to occupational health and explore the implications and limitations of AI in occupational health medicine. The study also provides recommendations for future research in this area and informs decision-makers about AI's impact on healthcare. A group of physicians was enlisted to create a dataset of questions and answers on Italian occupational medicine legislation. The physicians were divided into two teams, and each team member was assigned a different subject area. ChatGPT was used to generate answers for each question, with/without legislative context. The two teams then evaluated human and AI-generated answers blind, with each group reviewing the other group's work. Occupational physicians outperformed ChatGPT in generating accurate questions on a 5-point Likert score, while the answers provided by ChatGPT with access to legislative texts were comparable to those of professional doctors. Still, we found that users tend to prefer answers generated by humans, indicating that while ChatGPT is useful, users still value the opinions of occupational medicine professionals.

Online COVID-19 diagnosis prediction using complete blood count: an innovative tool for public health

BACKGROUND

COVID-19, caused by SARS-CoV-2, presents distinct diagnostic challenges due to its wide range of clinical manifestations and the overlapping symptoms with other common respiratory diseases. This study focuses on addressing these difficulties by employing machine learning (ML) methodologies, particularly the XGBoost algorithm, to utilize Complete Blood Count (CBC) parameters for predictive analysis.

METHODS

We performed a retrospective study involving 2114 COVID-19 patients treated between December 2022 and January 2023 at our healthcare facility. These patients were classified into fever (1057 patients) and pneumonia groups (1057 patients), based on their clinical symptoms. The CBC data were utilized to create predictive models, with model performance evaluated through metrics like Area Under the Receiver Operating Characteristics Curve (AUC), accuracy, sensitivity, specificity, and precision. We selected the top 10 predictive variables based on their significance in disease prediction. The data were then split into a training set (70% of patients) and a validation set (30% of patients) for model validation.

RESULTS

We identified 31 indicators with significant disparities. The XGBoost model outperformed others, with an AUC of 0.920 and high precision, sensitivity, specificity, and accuracy. The top 10 features (Age, Monocyte%, Mean Platelet Volume, Lymphocyte%, SIRI, Eosinophil count, Platelet count, Hemoglobin, Platelet Distribution Width, and Neutrophil count.) were crucial in constructing a more precise predictive model. The model demonstrated strong performance on both training (AUC = 0.977) and validation (AUC = 0.912) datasets, validated by decision curve analysis and calibration curve.

CONCLUSION

ML models that incorporate CBC parameters offer an innovative and effective tool for data analysis in COVID-19. They potentially enhance diagnostic accuracy and the efficacy of therapeutic interventions, ultimately contributing to a reduction in the mortality rate of this infectious disease.

WGCNA combined with machine learning to find potential biomarkers of liver cancer

The incidence of hepatocellular carcinoma (HCC) has been increasing in recent years. With the development of various detection technologies, machine learning is an effective method to screen disease characteristic genes. In this study, weighted gene co-expression network analysis (WGCNA) and machine learning are combined to find potential biomarkers of liver cancer, which provides a new idea for future prediction, prevention, and personalized treatment. In this study, the "limma" software package was used. P < .05 and log2 |fold-change| > 1 is the standard screening differential genes, and then the module genes obtained by WGCNA analysis are crossed to obtain the key module genes. Gene Ontology and Kyoto Gene and Genome Encyclopedia analysis was performed on key module genes, and 3 machine learning methods including lasso, support vector machine-recursive feature elimination, and RandomForest were used to screen feature genes. Finally, the validation set was used to verify the feature genes, the GeneMANIA (http://www.genemania.org) database was used to perform protein-protein interaction networks analysis on the feature genes, and the SPIED3 database was used to find potential small molecule drugs. In this study, 187 genes associated with HCC were screened by using the "limma" software package and WGCNA. After that, 6 feature genes (AADAT, APOF, GPC3, LPA, MASP1, and NAT2) were selected by RandomForest, Absolute Shrinkage and Selection Operator, and support vector machine-recursive feature elimination machine learning algorithms. These genes are also significantly different on the external dataset and follow the same trend as the training set. Finally, our findings may provide new insights into targets for diagnosis, prevention, and treatment of HCC. AADAT, APOF, GPC3, LPA, MASP1, and NAT2 may be potential genes for the prediction, prevention, and treatment of liver cancer in the future.

Targeting NAD+ metabolism of hepatocellular carcinoma cells by lenvatinib promotes M2 macrophages reverse polarization, suppressing the HCC progression

BACKGROUND

Lowered nicotinamide adenine dinucleotide (NAD+) levels in tumor cells drive tumor hyperprogression during immunotherapy, and its restoration activates immune cells. However, the effect of lenvatinib, a first-line treatment for unresectable hepatocellular carcinoma (HCC), on NAD+ metabolism in HCC cells, and the metabolite crosstalk between HCC and immune cells after targeting NAD+ metabolism of HCC cells remain unelucidated.

METHODS

Liquid chromatography-tandem mass spectrometry (LC-MS/MS) and ultra-high-performance liquid chromatography multiple reaction monitoring-mass spectrometry (UHPLC-MRM-MS) were used to detect and validate differential metabolites. RNA sequencing was used to explore mRNA expression in macrophages and HCC cells. HCC mouse models were used to validate the effects of lenvatinib on immune cells and NAD+ metabolism. The macrophage properties were elucidated using cell proliferation, apoptosis, and co-culture assays. In silico structural analysis and interaction assays were used to determine whether lenvatinib targets tet methylcytosine dioxygenase 2 (TET2). Flow cytometry was performed to assess changes in immune cells.

RESULTS

Lenvatinib targeted TET2 to synthesize and increase NAD+ levels, thereby inhibiting decomposition in HCC cells. NAD+ salvage increased lenvatinib-induced apoptosis of HCC cells. Lenvatinib also induced CD8+ T cells and M1 macrophages infiltration in vivo. And lenvatinib suppressed niacinamide, 5-Hydroxy-L-tryptophan and quinoline secretion of HCC cells, and increased hypoxanthine secretion, which contributed to proliferation, migration and polarization function of macrophages. Consequently, lenvatinib targeted NAD+ metabolism and elevated HCC-derived hypoxanthine to enhance the macrophages polarization from M2 to M1. Glycosaminoglycan binding disorder and positive regulation of cytosolic calcium ion concentration were characteristic features of the reverse polarization.

CONCLUSIONS

Targeting HCC cells NAD+ metabolism by lenvatinib-TET2 pathway drives metabolite crosstalk, leading to M2 macrophages reverse polarization, thereby suppressing HCC progression. Collectively, these novel insights highlight the role of lenvatinib or its combination therapies as promising therapeutic alternatives for HCC patients with low NAD+ levels or high TET2 levels.

Identification of Molecular Markers Predicting the Outcome of Anti-thrombotic Therapy After Percutaneous Coronary Intervention in Patients with Acute Coronary Syndrome and Atrial fibrillation: Evidence from a Meta-analysis and Experimental Study

Acute coronary syndrome (ACS) and atrial fibrillation (AF) often coexist in clinical practice, and patients with these conditions often have a critical illness with high risk of both ischemia and bleeding. This study aims to report potential molecular markers for predicting the efficacy based on a meta-analysis of microarray data from the GEO database. In 40 patients with acute coronary syndrome (ACS) and atrial fibrillation (AF) treated with PCI, P2RX1's effects on platelet aggregation, medication resistance, and predictive value were examined. Twenty up-regulated genes in peripheral blood samples of ACS and AF patients were down-regulated after PCI, while 7 down-regulated genes were up-regulated. ACS affected eight potential genes. P2RX1, one of the four LASSO analysis-retrieved disease characteristic genes, accurately predicted AF patients' thrombosis risk and PCI's anti-thrombotic impact. Therefore, P2RX1 may be a molecular marker to predict the effect of anti-thrombotic therapy in patients with ACS and AF after PCI.

Network pharmacology and bioinformatics to identify the molecular mechanisms of Gleditsiae Spina against colorectal cancer

Objective

In this study, network pharmacology, bioinformatics and molecular docking were used to explore the active phytochemicals, hub genes, and potential molecular mechanisms of Gleditsiae Spina in treating of colorectal cancer..

Methods

The targets of Gleditsiae Spina, and targets related to CRC were derived from databases. We identified the hub genes for Gleditsiae Spina anti-colorectal cancer following the protein-protein-interaction (PPI) network. Furthermore, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment were used to analyze the hub genes from a macro perspective. Finally, we verified the hub genes by molecular docking, GEPIA, HPA, and starBase database.

Results

We identified nine active phytochemicals and 36 intersection targets. The GO enrichment analysis results showed that Gleditsiae Spina may be involved in gene targets affecting multiple biological processes, including response to radiation, response to ionizing radiation, cyclin-dependent protein kinase holoenzyme complex, serine/threonine protein kinase complex, cyclin-dependent protein serine/threonine kinase regulator activity and protein kinase regulator activity. KEGG enrichment analysis results indicated that the P53 signaling pathway, IL-17 signaling pathway, Toll-like receptor signaling pathway, PI3K-Akt signaling pathway, and JAK-STAT signaling pathway were mainly related to the effect of Gleditsiae Spina on colorectal cancer. Molecular docking analysis suggested that the active phytochemicals of Gleditsiae Spina could combine well with hub genes (PTGS1, PIK3CG, CCND1, CXCL8 and ADRB2).

Conclusion

This study provides clues for further study of anti-CRC phytochemicals as well as their mechanisms of provides a basis for their development model.

Stemness signature and targeted therapeutic drugs identification for Triple Negative Breast Cancer

Triple-negative breast cancer (TNBC) is the most aggressive subtype of breast cancer and carries the worst prognosis, characterized by the lack of progesterone, estrogen, and HER2 gene expression. This study aimed to analyze cancer stemness-related gene signature to determine patients' risk stratification and prognosis feature with TNBC. Here one-class logistic regression (OCLR) algorithm was applied to compute the stemness index of TNBC patients. Cox and LASSO regression analysis was performed on stemness-index related genes to establish 16 genes-based prognostic signature, and their predictive performance was verified in TCGA and METABERIC merged data cohort. We diagnosed the expression level of prognostic genes signature in the tumor immune microenvironment, analyzed the TNBC scRNA-seq GSE176078 dataset, and further validated the expression level of prognostic genes using the HPA database. Finally, the small molecular compounds targeted at the anti-tumor effect of predictive genes were screened by molecular docking; this novel stemness-based prognostic genes signature study could facilitate the prognosis of patients with TNBC and thus provide a feasible therapeutic target for TNBC.

Prognostic clinical phenotypes associated with tumor stemness in the immune microenvironment of T-cell exhaustion for hepatocellular carcinoma

T-cell exhaustion (TEX) and high heterogeneity of cancer stem cells (CSCs) are associated with progression, metastasis, and treatment resistance in hepatocellular carcinoma (HCC). Here, we aim to characterize TEX-stemness-related genes (TEXSRGs) and screen for HCC patients who are more sensitive to immunotherapy. The immune cell abundance identifier (ImmuCellAI) was utilized to precisely evaluate the abundance of TEX and screen TEX-related genes. The stemness index (mRNAsi) of samples was analyzed through the one-class logistic regression (OCLR) algorithm. Application of the non-negative matrix decomposition algorithm (NMF) for subtype identification of HCC samples. The different subtypes were assessed for differences in prognosis, tumor microenvironment (TME) landscape, and immunotherapy treatment response. Then, the TEXSRGS-score, which can accurately forecast the survival outcome of HCC patients, was built by LASSO-Cox and multivariate Cox regression, and experimentally validated for the most important TEXSRGs. We also analyzed the expression of TEXSRGs and the infiltration of CD8+ T cells in clinical samples using qRT-PCR and immunohistochemistry (IHC). Based on 146 TEXSRGs, we found two distinct clinical phenotypes with different TEX infiltration abundance, tumor stemness index, enrichment pathways, mutational landscape, and immune cell infiltration through the non-negative matrix decomposition algorithm (NMF), which were confirmed in the ICGC dataset. Utilizing eight TEXSRGs linked to clinical outcome, we created a TEXSRGs-score model to further improve the clinical applicability. Patients can be divided into two groups with substantial differences in the characteristics of immune cell infiltration, TEX infiltration abundance, and survival outcomes. The results of qRT-PCR and IHC analysis showed that PAFAH1B3, ZIC2, and ESR1 were differentially expressed in HCC and normal tissues and that patients with high TEXSRGs-scores had higher TEX infiltration abundance and tumor stemness gene expression. Regarding immunotherapy reaction and immune cell infiltration, patients with various TEXSRGs-score levels had various clinical traits. The outcome and immunotherapy efficacy of patients with low TEXSRGs-score was favorable. In conclusion, we identified two clinical subtypes with different prognoses, TEX infiltration abundance, tumor cell stemness index, and immunotherapy response based on TEXSRGs, and developed and validated a TEXSRGs-score capable of accurately predicting survival outcomes in HCC patients by comprehensive bioinformatics analysis. We believe that the TEXSRGs-score has prospective clinical relevance for prognostic assessment and may help physicians select prospective responders in preference to current immune checkpoint inhibitors (ICIs).

Machine learning-based prediction models for parathyroid carcinoma using pre-surgery cognitive function and clinical features

Patients with parathyroid carcinoma (PC) are often diagnosed postoperatively, due to incomplete resection during the initial surgery, resulting in poor outcomes. The aim of our study was to investigate the pre-surgery indicators of PC and try to develop a predictive model for PC utilizing machine learning. Evaluation of pre-surgery neuropsychological function and confirmation of pathology were carried out in 133 patients with primary hyperparathyroidism in Beijing Chaoyang Hospital from December 2019 to January 2023. Patients were randomly divided into a training cohort (n = 93) and a validating cohort (n = 40). Analysis of the clinical dataset, two machine learning including the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression were utilized to develop the prediction model for PC. Logistic regression analysis was also conducted for comparison. Significant differences in elevated parathyroid hormone and decreased serum phosphorus in PC compared to (BP). The lower score of MMSE and MOCA was observed in PC and a cutoff of MMSE < 24 was the optimal threshold to stratify PC from BP (area under the curve AUC 0.699 vs 0.625). The predicted probability of PC by machine learning was similar to the observed probability in the test set, whereas the logistic model tended to overpredict the possibility of PC. The XGBoost model attained a higher AUC than the logistic algorithms and LASSO models. (0.835 vs 0.683 vs 0.607). Preoperative cognitive function may be a probable predictor for PC. The cognitive function-based prediction model based on the XGBoost algorithm outperformed LASSO and logistic regression, providing valuable preoperative assistance to surgeons in clinical decision-making for patients suspected PC.

Machine Learning in Cardio-Oncology: New Insights from an Emerging Discipline

A growing body of evidence on a wide spectrum of adverse cardiac events following oncologic therapies has led to the emergence of cardio-oncology as an increasingly relevant interdisciplinary specialty. This also calls for better risk-stratification for patients undergoing cancer treatment. Machine learning (ML), a popular branch discipline of artificial intelligence that tackles complex big data problems by identifying interaction patterns among variables, has seen increasing usage in cardio-oncology studies for risk stratification. The objective of this comprehensive review is to outline the application of ML approaches in cardio-oncology, including deep learning, artificial neural networks, random forest and summarize the cardiotoxicity identified by ML. The current literature shows that ML has been applied for the prediction, diagnosis and treatment of cardiotoxicity in cancer patients. In addition, role of ML in gender and racial disparities for cardiac outcomes and potential future directions of cardio-oncology are discussed. It is essential to establish dedicated multidisciplinary teams in the hospital and educate medical professionals to become familiar and proficient in ML in the future.

Machine learning model of imipenem-resistant Klebsiella pneumoniae based on MALDI-TOF-MS platform: An observational study

Background and Aim

Machine learning is an important branch and supporting technology of artificial intelligence, we established four machine learning model for the drug sensitivity of Klebsiella pneumoniae to imipenem based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF-MS) and compared their diagnostic effect.

Methods

The data of MALDI-TOF-MS and imipenem sensitivity of 174 cases of K. pneumoniae isolated from clinical specimens in the laboratory of microbiology department of Tianjin Haihe Hospital from 2019 January to 2020 December were collected. The mass spectrometry and imipenem sensitivity of 70 cases of imipenem-sensitive and 70 resistant cases were randomly selected to establish the training set model, 17 cases of sensitive and 17 cases of resistant cases were randomly selected to establish the test set model. Mass spectral peak data were subjected to orthogonal partial least squares discriminant analysis (OPLS-DA), the training set data model was established by machine learning least absolute shrinkage and selection operator (LASSO) algorithm, logistic regression (LR) algorithm, support vector machines (SVM) algorithm, neural network (NN) algorithm, the area under the curve (AUC) and confusion matrix of training set and test set model were calculated and selected by Grid search and 3-fold Cross-validation respectively, the accuracy of the prediction model was verified by test set confusion matrix.

Results

The R²Y and Q² of OPLS-DA were 0.546 and 0.0178. The AUC of the best training set and test set models were 0.9726 and 0.9100, 1.0000 and 0.8581, 0.8462 and 0.6263, 1.0000 and 0.7180 evaluated by LASSO, LR, SVM and NN model respectively. The accuracy of the LASSO, LR, SVM and NN model were 87%, 79%, 62%, and 68% in test set, respectively.

Conclusion

The LASSO prediction model of K. pneumoniae sensitivity to imipenem established in this study has a high accuracy rate and has potential clinical decision support ability.

Unleashing the efficacy of immune checkpoint inhibitors for advanced hepatocellular carcinoma: factors, strategies, and ongoing trials

Hepatocellular carcinoma (HCC) is a prevalent primary liver cancer, representing approximately 85% of cases. The diagnosis is often made in the middle and late stages, necessitating systemic treatment as the primary therapeutic option. Despite sorafenib being the established standard of care for advanced HCC in the past decade, the efficacy of systemic therapy remains unsatisfactory, highlighting the need for novel treatment modalities. Recent breakthroughs in immunotherapy have shown promise in HCC treatment, particularly with immune checkpoint inhibitors (ICIs). However, the response rate to ICIs is currently limited to approximately 15%-20% of HCC patients. Recently, ICIs demonstrated greater efficacy in "hot" tumors, highlighting the urgency to devise more effective approaches to transform "cold" tumors into "hot" tumors, thereby enhancing the therapeutic potential of ICIs. This review presented an updated summary of the factors influencing the effectiveness of immunotherapy in HCC treatment, identified potential combination therapies that may improve patient response rates to ICIs, and offered an overview of ongoing clinical trials focusing on ICI-based combination therapy.

Refining Liver Biopsy in Hepatocellular Carcinoma: An In-Depth Exploration of Shifting Diagnostic and Therapeutic Applications

The field of hepatocellular carcinoma (HCC) has faced significant change on multiple levels in the past few years. The increasing emphasis on the various HCC phenotypes and the emergence of novel, specific therapies have slowly paved the way for a personalized approach to primary liver cancer. In this light, the role of percutaneous liver biopsy of focal lesions has shifted from a purely confirmatory method to a technique capable of providing an in-depth characterization of any nodule. Cancer subtype, gene expression, the mutational profile, and tissue biomarkers might soon become widely available through biopsy. However, indications, expectations, and techniques might suffer changes as the aim of the biopsy evolves from providing minimal proof of the disease to high-quality specimens for extensive analysis. Consequently, a revamped position of tissue biopsy is expected in HCC, following the reign of non-invasive imaging-only diagnosis. Moreover, given the advances in techniques that have recently reached the spotlight, such as liquid biopsy, concomitant use of all the available methods might gather just enough data to improve therapy selection and, ultimately, outcomes. The current review aims to discuss the changing role of liver biopsy and provide an evidence-based rationale for its use in the era of precision medicine in HCC.

Machine learning-based identification of glycosyltransferase-related mRNAs for improving outcomes and the anti-tumor therapeutic response of gliomas

Background: Glycosyltransferase participates in glycosylation modification, and glycosyltransferase alterations are involved in carcinogenesis, progression, and immune evasion, leading to poor outcomes. However, in-depth studies on the influence of glycosyltransferase on clinical outcomes and treatments are lacking. Methods: The analysis of differentially expressed genes was performed using the Gene Expression Profiling Interactive Analysis 2 database. A total of 10 machine learning algorithms were introduced, namely, random survival forest, elastic network, least absolute shrinkage and selection operator, Ridge, stepwise Cox, CoxBoost, partial least squares regression for Cox, supervised principal components, generalized boosted regression modeling, and survival support vector machine. Gene Set Enrichment Analysis was performed to explore signaling pathways regulated by the signature. Cell-type identification by estimating relative subsets of RNA transcripts was used for estimating the fractions of immune cell types. Results: Here, we analyzed the genomic and expressive alterations in glycosyltransferase-related genes in gliomas. A combination of 80 machine learning algorithms was introduced to establish the glycosyltransferase-related mRNA signature (GRMS) based on 2,030 glioma samples from The Cancer Genome Atlas Program, Chinese Glioma Genome Atlas, Rembrandt, Gravendeel, and Kamoun cohorts. The GRMS was identified as an independent hazardous factor for overall survival and exhibited stable and robust performance. Notably, gliomas in the high-GRMS subgroup exhibited abundant tumor-infiltrating lymphocytes and tumor mutation burden values, increased expressive levels of hepatitis A virus cellular receptor 2 and CD274, and improved progression-free survival when subjected to anti-tumor immunotherapy. Conclusion: The GRMS may act as a powerful and promising biomarker for improving the clinical prognosis of glioma patients.

Integrated analysis revealing a novel stemness-metabolism-related gene signature for predicting prognosis and immunotherapy response in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a malignant lethal tumor and both cancer stem cells (CSCs) and metabolism reprogramming have been proven to play indispensable roles in HCC. This study aimed to reveal the connection between metabolism reprogramming and the stemness characteristics of HCC, established a new gene signature related to stemness and metabolism and utilized it to assess HCC prognosis and immunotherapy response. The clinical information and gene expression profiles (GEPs) of 478 HCC patients came from the Gene Expression Omnibus (GEO) and the Cancer Genome Atlas (TCGA). The one-class logistic regression (OCLR) algorithm was employed to calculate the messenger ribonucleic acid expression-based stemness index (mRNAsi), a new stemness index quantifying stemness features. Differentially expressed analyses were done between high- and low-mRNAsi groups and 74 differentially expressed metabolism-related genes (DEMRGs) were identified with the help of metabolism-related gene sets from Molecular Signatures Database (MSigDB). After integrated analysis, a risk score model based on the three most efficient prognostic DEMRGs, including Recombinant Phosphofructokinase Platelet (PFKP), phosphodiesterase 2A (PDE2A) and UDP-glucuronosyltransferase 1A5 (UGT1A5) was constructed and HCC patients were divided into high-risk and low-risk groups. Significant differences were found in pathway enrichment, immune cell infiltration patterns, and gene alterations between the two groups. High-risk group patients tended to have worse clinical outcomes and were more likely to respond to immunotherapy. A stemness-metabolism-related model composed of gender, age, the risk score model and tumor-node-metastasis (TNM) staging was generated and showed great discrimination and strong ability in predicting HCC prognosis and immunotherapy response.

From Reductionistic Approach to Systems Immunology Approach for the Understanding of Tumor Microenvironment

The tumor microenvironment (TME) is a complex and dynamic ecosystem that includes a variety of immune cells mutually interacting with tumor cells, structural/stromal cells, and each other. The immune cells in the TME can have dual functions as pro-tumorigenic and anti-tumorigenic. To understand such paradoxical functions, the reductionistic approach classifies the immune cells into pro- and anti-tumor cells and suggests the therapeutic blockade of the pro-tumor and induction of the anti-tumor immune cells. This strategy has proven to be partially effective in prolonging patients' survival only in a fraction of patients without offering a cancer cure. Recent advances in multi-omics allow taking systems immunology approach. This essay discusses how a systems immunology approach could revolutionize our understanding of the TME by suggesting that internetwork interactions of the immune cell types create distinct collective functions independent of the function of each cellular constituent. Such collective function can be understood by the discovery of the immunological patterns in the TME and may be modulated as a therapeutic means for immunotherapy of cancer.

Prognosis prediction and comparison between pancreatic signet ring cell carcinoma and pancreatic duct adenocarcinoma: a retrospective observational study

Background

Pancreatic signet ring cell carcinoma (PSRCC) is a rare and aggressive cancer that has been reported primarily as case reports. Due to limited large-scale epidemiological and prognostic analyses, the outcomes of PSRCC patients varies greatly in the absence of recognized first-line treatment strategies. This study aimed to compare the clinical features, treatment, and prognosis of PSRCC and pancreatic ductal cell carcinoma (PDAC), the most common subtype of pancreatic cancer, and to establish predictive models for these subtypes.

Methods

The data on PSRCC and PDAC patients from 1998 to 2018 was obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Thereafter, the clinical, demographic, and treatment characteristics of the two groups and the differences and influencing factors of the two groups were evaluated by propensity score matching (PSM), Kaplan-Meier survival curves, Cox risk regression analyses, and least absolute shrinkage and selection operator (LASSO) analysis. Next, prognosis models were constructed and validated by KM and ROC analysis. Finally, a nomogram was constructed, based on the results of these analyses, to predict survival outcomes of PSRCC and PDAC patients.

Results

A total of 84,789 patients (432 PSRCC and 84357 PDAC patients) were included in this study. The results of the study revealed that, compared to the PDAC patients, PSRCC patients were more likely to be male, aged between 58-72 years, have larger tumor masses, and less likely to undergo chemotherapy. Before PSM, the overall survival and cancer-specific survival of the PSRCC group were significantly lower than those PDAC group, but there was no difference in the prognosis of the two groups after PSM. Additionally, lymph node ratio (LNR), log odds of positive lymph node (LODDS), tumor size, age, T-stage, marital status, and summary stage were found to be independent prognostic factors for PSRCC. Lastly, the prediction model and nomogram based on these prognostic factors could accurately predict the survival rate of the patients in SEER datasets and external validation datasets.

Conclusion

The prognosis of PSRCC and PDAC patients is similar under the same conditions; however, PSRCC patients may have more difficulty in receiving better treatment, thus resulting in their poor prognosis.

Early warning and diagnosis of liver cancer based on dynamic network biomarker and deep learning

Background

Early detection of complex diseases like hepatocellular carcinoma remains challenging due to their network-driven pathology. Dynamic network biomarkers (DNB) based on monitoring changes in molecular correlations may enable earlier predictions. However, DNB analysis often overlooks disease heterogeneity.

Methods

We integrated DNB analysis with graph convolutional neural networks (GCN) to identify critical transitions during hepatocellular carcinoma development in a mouse model. A DNB-GCN model was constructed using transcriptomic data and gene expression levels as node features.

Results

DNB analysis identified a critical transition point at 7 weeks of age despite histological examinations being unable to detect cancerous changes at that time point. The DNB-GCN model achieved 100% accuracy in classifying healthy and cancerous mice, and was able to accurately predict the health status of newly introduced mice.

Conclusion

The integration of DNB analysis and GCN demonstrates potential for the early detection of complex diseases by capturing network structures and molecular features that conventional biomarker discovery methods overlook. The approach warrants further development and validation.

Current Understanding on Why Ovarian Cancer Is Resistant to Immune Checkpoint Inhibitors

The standard treatment of ovarian cancer (OC) patients, including debulking surgery and first-line chemotherapy, is unsatisfactory because of recurrent episodes in the majority (~70%) of patients with advanced OC. Clinical trials have shown only a modest (10-15%) response of OC individuals to treatment based on immune checkpoint inhibitors (ICIs). The resistance of OC to therapy is caused by various factors, including OC heterogeneity, low density of tumor-infiltrating lymphocytes (TILs), non-cellular and cellular interactions in the tumor microenvironment (TME), as well as a network of microRNA regulating immune checkpoint pathways. Moreover, ICIs are the most efficient in tumors that are marked by high microsatellite instability and high tumor mutation burden, which is rare among OC patients. The great challenge in ICI implementation is connected with distinguishing hyper-, pseudo-, and real progression of the disease. The understanding of the immunological, molecular, and genetic mechanisms of OC resistance is crucial to selecting the group of OC individuals in whom personalized treatment would be beneficial. In this review, we summarize current knowledge about the selected factors inducing OC resistance and discuss the future directions of ICI-based immunotherapy development for OC patients.

Characterization of stemness features and construction of a stemness subtype classifier to predict survival and treatment responses in lung squamous cell carcinoma

BACKGROUND

Cancer stemness has been proven to affect tumorigenesis, metastasis, and drug resistance in various cancers, including lung squamous cell carcinoma (LUSC). We intended to develop a clinically applicable stemness subtype classifier that could assist physicians in predicting patient prognosis and treatment response.

METHODS

This study collected RNA-seq data from TCGA and GEO databases to calculate transcriptional stemness indices (mRNAsi) using the one-class logistic regression machine learning algorithm. Unsupervised consensus clustering was conducted to identify a stemness-based classification. Immune infiltration analysis (ESTIMATE and ssGSEA algorithms) methods were used to investigate the immune infiltration status of different subtypes. Tumor Immune Dysfunction and Exclusion (TIDE) and Immunophenotype Score (IPS) were used to evaluate the immunotherapy response. The pRRophetic algorithm was used to estimate the efficiency of chemotherapeutic and targeted agents. Two machine learning algorithms (LASSO and RF) and multivariate logistic regression analysis were performed to construct a novel stemness-related classifier.

RESULTS

We observed that patients in the high-mRNAsi group had a better prognosis than those in the low-mRNAsi group. Next, we identified 190 stemness-related differentially expressed genes (DEGs) that could categorize LUSC patients into two stemness subtypes. Patients in the stemness subtype B group with higher mRNAsi scores exhibited better overall survival (OS) than those in the stemness subtype A group. Immunotherapy prediction demonstrated that stemness subtype A has a better response to immune checkpoint inhibitors (ICIs). Furthermore, the drug response prediction indicated that stemness subtype A had a better response to chemotherapy but was more resistant to epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs). Finally, we constructed a nine-gene-based classifier to predict patients' stemness subtype and validated it in independent GEO validation sets. The expression levels of these genes were also validated in clinical tumor specimens.

CONCLUSION

The stemness-related classifier could serve as a potential prognostic and treatment predictor and assist physicians in selecting effective treatment strategies for patients with LUSC in clinical practice.

The Role of Artificial Intelligence in the Detection and Implementation of Biomarkers for Hepatocellular Carcinoma: Outlook and Opportunities

Liver cancer is a leading cause of cancer-related death worldwide, and its early detection and treatment are crucial for improving morbidity and mortality. Biomarkers have the potential to facilitate the early diagnosis and management of liver cancer, but identifying and implementing effective biomarkers remains a major challenge. In recent years, artificial intelligence has emerged as a promising tool in the cancer sphere, and recent literature suggests that it is very promising in facilitating biomarker use in liver cancer. This review provides an overview of the status of AI-based biomarker research in liver cancer, with a focus on the detection and implementation of biomarkers for risk prediction, diagnosis, staging, prognostication, prediction of treatment response, and recurrence of liver cancers.

Basement membrane-related regulators for prediction of prognoses and responses to diverse therapies in hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma (HCC) remains a global health threat. Finding a novel biomarker for assessing the prognosis and new therapeutic targets is vital to treating this patient population. Our study aimed to explore the contribution of basement membrane-related regulators (BMR) to prognostic assessment and therapeutic response prediction in HCC.

MATERIAL AND METHODS

The RNA sequencing and clinical information of HCC were downloaded from TCGA-LIHC, ICGC-JP, GSE14520, GSE104580, and CCLE datasets. The BMR signature was created by the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm and used to separate HCC patients into low- and high-risk groups. We conducted analyses using various R 4.1.3 software packages to compare prognoses and responses to immunotherapy, transcatheter arterial chemoembolization (TACE), and chemotherapeutic drugs between the groups. Additionally, stemness indices, molecular functions, and somatic mutation analyses were further explored in these subgroups.

RESULTS

The BMR signature included 3 basement membrane-related genes (CTSA, P3H1, and ADAM9). We revealed that BMR signature was an independent risk contributor to poor prognosis in HCC, and high-risk group patients presented shorter overall survival. We discovered that patients in the high-risk group might be responsive to immunotherapy, while patients in the low-risk group may be susceptible to TACE therapy. Over 300 agents were screened to identify effective drugs for the two subgroups.

CONCLUSION

Overall, basement membrane-related regulators represent novel biomarkers in HCC for assessing prognosis, response to immunotherapy, the effectiveness of TACE therapy, and drug susceptibility.

Combined transcriptomics and proteomics forecast analysis for potential biomarker in the acute phase of temporal lobe epilepsy

Background

Temporal lobe epilepsy (TLE) is a common chronic episodic illness of the nervous system. However, the precise mechanisms of dysfunction and diagnostic biomarkers in the acute phase of TLE are uncertain and hard to diagnose. Thus, we intended to qualify potential biomarkers in the acute phase of TLE for clinical diagnostics and therapeutic purposes.

Methods

An intra-hippocampal injection of kainic acid was used to induce an epileptic model in mice. First, with a TMT/iTRAQ quantitative labeling proteomics approach, we screened for differentially expressed proteins (DEPs) in the acute phase of TLE. Then, differentially expressed genes (DEGs) in the acute phase of TLE were identified by linear modeling on microarray data (limma) and weighted gene co-expression network analysis (WGCNA) using the publicly available microarray dataset GSE88992. Co-expressed genes (proteins) in the acute phase of TLE were identified by overlap analysis of DEPs and DEGs. The least absolute shrinkage and selection operator (LASSO) regression and support vector machine recursive feature elimination (SVM-RFE) algorithms were used to screen Hub genes in the acute phase of TLE, and logistic regression algorithms were applied to develop a novel diagnostic model for the acute phase of TLE, and the sensitivity of the diagnostic model was validated using receiver operating characteristic (ROC) curves.

Results

We screened a total of 10 co-expressed genes (proteins) from TLE-associated DEGs and DEPs utilizing proteomic and transcriptome analysis. LASSO and SVM-RFE algorithms for machine learning were applied to identify three Hub genes: Ctla2a, Hapln2, and Pecam1. A logistic regression algorithm was applied to establish and validate a novel diagnostic model for the acute phase of TLE based on three Hub genes in the publicly accessible datasets GSE88992, GSE49030, and GSE79129.

Conclusion

Our study establishes a reliable model for screening and diagnosing the acute phase of TLE that provides a theoretical basis for adding diagnostic biomarkers for TLE acute phase genes.

Epithelial-mesenchymal transition-related gene prognostic index and phenotyping clusters for hepatocellular carcinoma patients

Epithelial-mesenchymal transition (EMT) contributes to high tumor heterogeneity and the immunosuppressive environment of the HCC tumor microenvironment (TME). Here, we developed EMT-related genes phenotyping clusters and systematically evaluated their impact on HCC prognosis, the TME, and drug efficacy prediction. We identified HCC specific EMT-related genes using weighted gene co-expression network analysis (WGCNA). An EMT-related genes prognostic index (EMT-RGPI) capable of effectively predicting HCC prognosis was then constructed. Consensus clustering of 12 HCC specific EMT-related hub genes uncovered two molecular clusters C1 and C2. Cluster C2 preferentially associated with unfavorable prognosis, higher stemness index (mRNAsi) value, elevated immune checkpoint expression, and immune cell infiltration. The TGF-β signaling, EMT, glycolysis, Wnt β-catenin signaling, and angiogenesis were markedly enriched in cluster C2. Moreover, cluster C2 exhibited higher TP53 and RB1 mutation rates. The TME subtypes and tumor immune dysfunction and exclusion (TIDE) score showed that cluster C1 patients responded well to immune checkpoint inhibitors (ICIs). Half-maximal inhibitory concentration (IC50) revealed that cluster C2 patients were more sensitive to chemotherapeutic and antiangiogenic agents. These findings may guide risk stratification and precision therapy for HCC patients.

Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models

Background: Currently, surgical decisions for hepatocellular carcinoma (HCC) resection are difficult and not sufficiently personalized. We aimed to develop and validate data driven prediction models to assist surgeons in selecting the optimal surgical procedure for patients. Methods: Retrospective data from 361 HCC patients who underwent radical resection in two institutions were included. End-to-end deep learning models were built to automatically segment lesions from the arterial phase (AP) of preoperative dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Clinical baseline characteristics and radiomic features were rigorously screened. The effectiveness of radiomic features and radiomic-clinical features was also compared. Three ensemble learning models were proposed to perform the surgical procedure decision and the overall survival (OS) and recurrence-free survival (RFS) predictions after taking different solutions, respectively. Results: SegFormer performed best in terms of automatic segmentation, achieving a Mean Intersection over Union (mIoU) of 0.8860. The five-fold cross-validation results showed that inputting radiomic-clinical features outperformed using only radiomic features. The proposed models all outperformed the other mainstream ensemble models. On the external test set, the area under the receiver operating characteristic curve (AUC) of the proposed decision model was 0.7731, and the performance of the prognostic prediction models was also relatively excellent. The application web server based on automatic lesion segmentation was deployed and is available online. Conclusions: In this study, we developed and externally validated the surgical decision-making procedures and prognostic prediction models for HCC for the first time, and the results demonstrated relatively accurate predictions and strong generalizations, which are expected to help clinicians optimize surgical procedures.

Pediatric Crohn's disease diagnosis aid via genomic analysis and machine learning

Introduction

Determination of pediatric Crohn's disease (CD) remains a major diagnostic challenge. However, the rapidly emerging field of artificial intelligence has demonstrated promise in developing diagnostic models for intractable diseases.

Methods

We propose an artificial neural network model of 8 gene markers identified by 4 classification algorithms based on Gene Expression Omnibus database for diagnostic of pediatric CD.

Results

The model achieved over 85% accuracy and area under ROC curve value in both training set and testing set for diagnosing pediatric CD. Additionally, immune infiltration analysis was performed to address why these markers can be integrated to develop a diagnostic model.

Conclusion

This study supports further clinical facilitation of precise disease diagnosis by integrating genomics and machine learning algorithms in open-access database.

Genes Modulating Butyrate Metabolism for Assessing Clinical Prognosis and Responses to Systematic Therapies in Hepatocellular Carcinoma

Butyrate, one of the major products of the gut microbiota, has played notable roles in diverse therapies for multiple tumors. Our study aimed to determine the roles of genes that modulate butyrate metabolism (BM) in predicting the clinical prognosis and responses to systemic therapies in hepatocellular carcinoma (HCC). The genes modulating BM were available from the GeneCard database, and gene expression and clinical information were obtained from TCGA-LIHC, GEO, ICGC-JP, and CCLE databases. Candidate genes from these genes that regulate BM were then identified by univariate Cox analysis. According to candidate genes, the patients in TCGA were grouped into distinct subtypes. Moreover, BM- related gene signature (BMGs) was created via the LASSO Cox algorithm. The roles of BMGs in identifying high-risk patients of HCC, assessing the prognoses, and predicting systematic therapies were determined in various datasets. The statistical analyses were fulfilled with R 4.1.3, GraphPad Prism 8.0 and Perl 5.30.0.1 software. In the TCGA cohort, most butyrate-related genes were over-expressed in the B cluster, and patients in the B cluster showed worse prognoses. BMGs constructed by LASSO were composed of eight genes. BMGs exhibited a strong performance in evaluating the prognoses of HCC patients in various datasets, which may be superior to 33 published biomarkers. Furthermore, BMGs may contribute to the early surveillance of HCC, and BMGs could play active roles in assessing the effectiveness of immunotherapy, TACE, ablation therapy, and chemotherapeutic drugs for HCC. BMGs may be served as novel promising biomarkers for early identifying high-risk groups of HCC, as well as assessing prognoses, drug sensitivity, and the responses to immunotherapy, TACE, and ablation therapy in patients with HCC.

Artificial intelligence for prediction of response to cancer immunotherapy

Artificial intelligence (AI) indicates the application of machines to imitate intelligent behaviors for solving complex tasks with minimal human intervention, including machine learning and deep learning. The use of AI in medicine improves health-care systems in multiple areas such as diagnostic confirmation, risk stratification, analysis, prognosis prediction, treatment surveillance, and virtual health support, which has considerable potential to revolutionize and reshape medicine. In terms of immunotherapy, AI has been applied to unlock underlying immune signatures to associate with responses to immunotherapy indirectly as well as predict responses to immunotherapy responses directly. The AI-based analysis of high-throughput sequences and medical images can provide useful information for management of cancer immunotherapy considering the excellent abilities in selecting appropriate subjects, improving therapeutic regimens, and predicting individualized prognosis. In present review, we aim to evaluate a broad framework about AI-based computational approaches for prediction of response to cancer immunotherapy on both indirect and direct manners. Furthermore, we summarize our perspectives about challenges and opportunities of further AI applications on cancer immunotherapy relating to clinical practicability.

Characteristic Genes and Immune Infiltration Analysis for Acute Rejection after Kidney Transplantation

Background

Renal transplantation can significantly improve the survival rate and quality of life of patients with end-stage renal disease, but the probability of acute rejection (AR) in adult renal transplant recipients is still approximately 12.2%. Machine learning (ML) is superior to traditional statistical methods in various clinical scenarios. However, the current AR model is constructed only through simple difference analysis or a single queue, which cannot guarantee the accuracy of prediction. Therefore, this study identified and validated new gene sets that contribute to the early prediction of AR and the prognosis prediction of patients after renal transplantation by constructing a more accurate AR gene signature through ML technology.

Methods

Based on the Gene Expression Omnibus (GEO) database and multiple bioinformatic analyses, we identified differentially expressed genes (DEGs) and built a gene signature via LASSO regression and SVM analysis. Immune cell infiltration and immunocyte association analyses were also conducted. Furthermore, we investigated the relationship between AR genes and graft survival status.

Results

Twenty-four DEGs were identified. A 5 gene signature (CPA6, EFNA1, HBM, THEM5, and ZNF683) were obtained by LASSO analysis and SVM analysis, which had a satisfied ability to differentiate AR and NAR in the training cohort, internal validation cohort and external validation cohort. Additionally, ZNF683 was associated with graft survival.

Conclusion

A 5 gene signature, particularly ZNF683, provided insight into a precise therapeutic schedule and clinical applications for AR patients.

Stemness analysis in hepatocellular carcinoma identifies an extracellular matrix gene–related signature associated with prognosis and therapy response

Background: Tumor stemness is the stem-like phenotype of cancer cells, as a hallmark for multiple processes in the development of hepatocellular carcinoma (HCC). However, comprehensive functions of the regulators of tumor cell’s stemness in HCC remain unclear.

Methods: Gene expression data and clinical information of HCC samples were downloaded from The Cancer Genome Atlas (TCGA) dataset as the training set, and three validation datasets were derived from Gene Expression Omnibus (GEO) and International Cancer Genome Consortium (ICGC). Patients were dichotomized according to median mRNA expression–based stemness index (mRNAsi) scores, and differentially expressed genes were further screened out. Functional enrichment analysis of these DEGs was performed to identify candidate extracellular matrix (ECM)–related genes in key pathways. A prognostic signature was constructed by applying least absolute shrinkage and selection operator (LASSO) to the candidate ECM genes. The Kaplan–Meier curve and receiver operating characteristic (ROC) curve were used to evaluate the prognostic value of the signature. Correlations between signatures and genomic profiles, tumor immune microenvironment, and treatment response were also explored using multiple bioinformatic methods.

Results: A prognostic prediction signature was established based on 10 ECM genes, including TRAPPC4, RSU1, ILK, LAMA1, LAMB1, FLNC, ITGAV, AGRN, ARHGEF6, and LIMS2, which could effectively distinguish patients with different outcomes in the training and validation sets, showing a good prognostic prediction ability. Across different clinicopathological parameter stratifications, the ECMs signature still retains its robust efficacy in discriminating patient with different outcomes. Based on the risk score, vascular invasion, α-fetoprotein (AFP), T stage, and N stage, we further constructed a nomogram (C-index = 0.70; AUCs at 1-, 3-, and 5-year survival = 0.71, 0.75, and 0.78), which is more practical for clinical prognostic risk stratification. The infiltration abundance of macrophages M0, mast cells, and Treg cells was significantly higher in the high-risk group, which also had upregulated levels of immune checkpoints PD-1 and CTLA-4. More importantly, the ECMs signature was able to distinguish patients with superior responses to immunotherapy, transarterial chemoembolization, and sorafenib.

Conclusion: In this study, we constructed an ECM signature, which is an independent prognostic biomarker for HCC patients and has a potential guiding role in treatment selection.