A Pan-Cancer Approach to Predict Responsiveness to Immune Checkpoint Inhibitors by Machine Learning

Informing immunotherapy with multi-omics driven machine learning

Progress in sequencing technologies and clinical experiments has revolutionized immunotherapy on solid and hematologic malignancies. However, the benefits of immunotherapy are limited to specific patient subsets, posing challenges for broader application. To improve its effectiveness, identifying biomarkers that can predict patient response is crucial. Machine learning (ML) play a pivotal role in harnessing multi-omic cancer datasets and unlocking new insights into immunotherapy. This review provides an overview of cutting-edge ML models applied in omics data for immunotherapy analysis, including immunotherapy response prediction and immunotherapy-relevant tumor microenvironment identification. We elucidate how ML leverages diverse data types to identify significant biomarkers, enhance our understanding of immunotherapy mechanisms, and optimize decision-making process. Additionally, we discuss current limitations and challenges of ML in this rapidly evolving field. Finally, we outline future directions aimed at overcoming these barriers and improving the efficiency of ML in immunotherapy research.

A nomogram model for predicting 5-year risk of prediabetes in Chinese adults

Early identification is crucial to effectively intervene in individuals at high risk of developing pre-diabetes. This study aimed to create a personalized nomogram to determine the 5-year risk of pre-diabetes among Chinese adults. This retrospective cohort study included 184,188 participants without prediabetes at baseline. Training cohorts (92,177) and validation cohorts (92,011) were randomly assigned (92,011). We compared five prediction models on the training cohorts: full cox proportional hazards model, stepwise cox proportional hazards model, multivariable fractional polynomials (MFP), machine learning, and least absolute shrinkage and selection operator (LASSO) models. At the same time, we validated the above five models on the validation set. And we chose the LASSO model as the final risk prediction model for prediabetes. We presented the model with a nomogram. The model's performance was evaluated in terms of its discriminative ability, clinical utility, and calibration using the area under the receiver operating characteristic (ROC) curve, decision curve analysis, and calibration analysis on the training cohorts. Simultaneously, we also evaluated the above nomogram on the validation set. The 5-year incidence of prediabetes was 10.70% and 10.69% in the training and validation cohort, respectively. We developed a simple nomogram that predicted the risk of prediabetes by using the parameters of age, body mass index (BMI), fasting plasma glucose (FBG), triglycerides (TG), systolic blood pressure (SBP), and serum creatinine (Scr). The nomogram's area under the receiver operating characteristic curve (AUC) was 0.7341 (95% CI 0.7290-0.7392) for the training cohort and 0.7336 (95% CI 0.7285-0.7387) for the validation cohort, indicating good discriminative ability. The calibration curve showed a perfect fit between the predicted prediabetes risk and the observed prediabetes risk. An analysis of the decision curve presented the clinical application of the nomogram, with alternative threshold probability spectrums being presented as well. A personalized prediabetes prediction nomogram was developed and validated among Chinese adults, identifying high-risk individuals. Doctors and others can easily and efficiently use our prediabetes prediction model when assessing prediabetes risk.

Identification of cancer types from gene expressions using learning techniques

Tumor is the major cause of death all around the world in recent days. Early detection and prediction of a cancer type are important for a patient's well-being. Functional genomic data has recently been used in the effective and early detection of cancer. According to previous research, the use of microarray data in cancer prediction has evidenced two main problems as high dimensionality and limited sample size. Several researchers have used numerous statistical and machine learning-based methods to classify cancer types but still, limitations are there which makes cancer classification a difficult job. Deep Learning (DL) and Convolutional Neural Networks (CNN) have been proven with effective analyses of unstructured data including gene expression data. In the proposed method gene expression data for five types of cancer is collected from The Cancer Genome Atlas (TCGA). Prominent features are selected using a hybrid Particle Swarm Optimization (PSO) and Random Forest (RF) algorithm followed by the use of Principal Component Analysis (PCA) for dimensionality reduction. Finally, for classification blend of Convolutional Neural Network (CNN) and Bi-directional Long Short Term Memory (Bi-LSTM) is used to predict the target type of cancer. Experimental results demonstrate that accuracy of the proposed method is 96.89%. As compared to existing work, our method outperformed with better results.

Machine Learning Approaches for Assessing Risk Factors of Adrenal Insufficiency in Patients Undergoing Immune Checkpoint Inhibitor Therapy

Adrenal insufficiency is a rare, yet life-threatening immune-related adverse event of immune checkpoint inhibitors (ICIs). This study aimed to establish a risk scoring system for adrenal insufficiency in patients receiving anti-programmed cell death 1 (PD-1) or anti-programmed cell death-ligand 1 (PD-L1) agents. Moreover, several machine learning methods were utilized to predict such complications. This study included 209 ICI-treated patients from July 2015 to February 2021, excluding those with prior adrenal insufficiency, previous steroid therapy, or incomplete data to ensure data integrity. Patients were continuously followed up at Gyeongsang National University Hospital, with morning blood samples taken for basal cortisol level measurements, facilitating a comprehensive analysis of their adrenal insufficiency risk. Using a chi-squared test and logistic regression model, we derived the odds ratio and adjusted odds ratio (AOR) through univariate and multivariable analyses. This study utilized machine learning algorithms, such as decision trees, random forests, support vector machines (SVM), and logistic regression to predict adrenal insufficiency in patients treated with ICIs. The performance of each algorithm was evaluated using metrics like accuracy, sensitivity, specificity, precision, and the area under the receiver operating characteristic curve (AUROC), ensuring rigorous assessment and reproducibility. A risk scoring system was developed from the multivariable and machine learning analyses. In a multivariable analysis, proton pump inhibitors (PPIs) (AOR 4.5), and α-blockers (AOR 6.0) were significant risk factors for adrenal insufficiency after adjusting for confounders. Among the machine learning models, logistic regression and elastic net showed good predictions, with AUROC values of 0.75 (0.61-0.90) and 0.76 (0.64-0.89), respectively. Based on multivariable and machine learning analyses, females (1 point), age ≥ 65 (1 point), PPIs (1 point), α-blockers (2 points), and antipsychotics (3 points) were integrated into the risk scoring system. From the logistic regression curve, patients with 0, 1, 2, 4, 5, and 6 points showed approximately 1.1%, 2.8%, 7.3%, 17.6%, 36.8%, 61.3%, and 81.2% risk for adrenal insufficiency, respectively. The application of our scoring system could prove beneficial in patient assessment and clinical decision-making while administering PD-1/PD-L1 inhibitors.

Machine learning to improve interpretability of clinical, radiological and panel-based genomic data of glioma grade 4 patients undergoing surgical resection

BACKGROUND

Glioma grade 4 (GG4) tumors, including astrocytoma IDH-mutant grade 4 and the astrocytoma IDH wt are the most common and aggressive primary tumors of the central nervous system. Surgery followed by Stupp protocol still remains the first-line treatment in GG4 tumors. Although Stupp combination can prolong survival, prognosis of treated adult patients with GG4 still remains unfavorable. The introduction of innovative multi-parametric prognostic models may allow refinement of prognosis of these patients. Here, Machine Learning (ML) was applied to investigate the contribution in predicting overall survival (OS) of different available data (e.g. clinical data, radiological data, or panel-based sequencing data such as presence of somatic mutations and amplification) in a mono-institutional GG4 cohort.

METHODS

By next-generation sequencing, using a panel of 523 genes, we performed analysis of copy number variations and of types and distribution of nonsynonymous mutations in 102 cases including 39 carmustine wafer (CW) treated cases. We also calculated tumor mutational burden (TMB). ML was applied using eXtreme Gradient Boosting for survival (XGBoost-Surv) to integrate clinical and radiological information with genomic data.

RESULTS

By ML modeling (concordance (c)- index = 0.682 for the best model), the role of predicting OS of radiological parameters including extent of resection, preoperative volume and residual volume was confirmed. An association between CW application and longer OS was also showed. Regarding gene mutations, a role in predicting OS was defined for mutations of BRAF and of other genes involved in the PI3K-AKT-mTOR signaling pathway. Moreover, an association between high TMB and shorter OS was suggested. Consistently, when a cutoff of 1.7 mutations/megabase was applied, cases with higher TMB showed significantly shorter OS than cases with lower TMB.

CONCLUSIONS

The contribution of tumor volumetric data, somatic gene mutations and TBM in predicting OS of GG4 patients was defined by ML modeling.

Decision Support System and Web-Application Using Supervised Machine Learning Algorithms for Easy Cancer Classifications

Using a decision support system (DSS) that classifies various cancers provides support to the clinicians/researchers to make better decisions that can aid in early cancer diagnosis, thereby reducing chances of incorrect disease diagnosis. Thus, this work aimed at designing a classification model that can predict accurately for 5 different cancer types comprising of 20 cancer exomes, using the mutations identified from whole exome cancer analysis. Initially, a basic model was designed using supervised machine learning classification algorithms such as K-nearest neighbor (KNN), support vector machine (SVM), decision tree, naïve bayes and random forest (RF), among which decision tree and random forest performed better in terms of preliminary model accuracy. However, output predictions were incorrect due to less training scores. Thus, 16 essential features were then selected for model improvement using 2 approaches. All imbalanced datasets were balanced using SMOTE. In the first approach, all features from 20 cancer exome datasets were trained and models were designed using decision tree and random forest. Balanced datasets for decision tree model showed an accuracy of 77%, while with the RF model, the accuracy improved to 82% where all 5 cancer types were predicted correctly. Area under the curve for RF model was closer to 1, than decision tree model. In the second approach, all 15 datasets were trained, while 5 were tested. However, only 2 cancer types were predicted correctly. To cross validate RF model, Matthew's correlation co-efficient (MCC) test was performed. For method 1, the MCC test and MCC cross validation was found to be 0.7796 and 0.9356 respectively. Likewise, for second approach, MCC was observed to be 0.9365, corroborating the accuracy of the designed model. The model was successfully deployed using Streamlit as a web application for easy use. This study presents insights for allowing easy cancer classifications.

Bioinformatics reveal elevated levels of Myosin Vb in uterine corpus endometrial carcinoma patients which correlates to increased cell metabolism and poor prognosis

Carcinoma of the endometrium of the uterus is the most common female pelvic malignancy. Although uterine corpus endometrial cancer (UCEC) has a favorable prognosis if removed early, patients with advanced tumor stages have a low survival rate. These facts highlight the importance of understanding UCEC biology. Computational analysis of RNA-sequencing data from UCEC patients revealed that the molecular motor Myosin Vb (MYO5B) was elevated in the beginning stages of UCEC and occurred in all patients regardless of tumor stage, tumor type, age, menopause status or ethnicity. Although several mutations were identified in the MYO5B gene in UCEC patients, these mutations did not correlate with mRNA expression. Examination of MYO5B methylation revealed that UCEC patients had undermethylated MYO5B and undermethylation was positively correlated with increased mRNA and protein levels. Immunostaining confirmed elevated levels of apical MYO5B in UCEC patients compared to adjacent tissue. UCEC patients with high expressing MYO5B tumors had far worse prognosis than UCEC patients with low expressing MYO5B tumors, as reflected by survival curves. Metabolic pathway analysis revealed significant alterations in metabolism pathways in UCE patients and key metabolism genes were positively correlated with MYO5B mRNA. These data provide the first evidence that MYO5B may participate in UCEC tumor development.

Immune-related pan-cancer gene expression signatures of patient survival revealed by NanoString-based analyses

The immune system plays a central role in the onset and progression of cancer. A better understanding of transcriptional changes in immune cell-related genes associated with cancer progression, and their significance in disease prognosis, is therefore needed. NanoString-based targeted gene expression profiling has advantages for deployment in a clinical setting over RNA-seq technologies. We analysed NanoString PanCancer Immune Profiling panel gene expression data encompassing 770 genes, and overall survival data, from multiple previous studies covering 10 different cancer types, including solid and blood malignancies, across 515 patients. This analysis revealed an immune gene signature comprising 39 genes that were upregulated in those patients with shorter overall survival; of these 39 genes, three (MAGEC2, SSX1 and ULBP2) were common to both solid and blood malignancies. Most of the genes identified have previously been reported as relevant in one or more cancer types. Using Cibersort, we investigated immune cell levels within individual cancer types and across groups of cancers, as well as in shorter and longer overall survival groups. Patients with shorter survival had a higher proportion of M2 macrophages and γδ T cells. Patients with longer overall survival had a higher proportion of CD8+ T cells, CD4+ T memory cells, NK cells and, unexpectedly, T regulatory cells. Using a transcriptomics platform with certain advantages for deployment in a clinical setting, our multi-cancer meta-analysis of immune gene expression and overall survival data has identified a specific transcriptional profile associated with poor overall survival.

Collaborative study from the Bladder Cancer Advocacy Network for the genomic analysis of metastatic urothelial cancer

Urothelial Cancer - Genomic Analysis to Improve Patient Outcomes and Research (NCT02643043), UC-GENOME, is a genomic analysis and biospecimen repository study in 218 patients with metastatic urothelial carcinoma. Here we report on the primary outcome of the UC-GENOME-the proportion of subjects who received next generation sequencing (NGS) with treatment options-and present the initial genomic analyses and clinical correlates. 69.3% of subjects had potential treatment options, however only 5.0% received therapy based on NGS. We found an increased frequency of TP53E285K mutations as compared to non-metastatic cohorts and identified features associated with benefit to chemotherapy and immune checkpoint inhibition, including: Ba/Sq and Stroma-rich subtypes, APOBEC mutational signature (SBS13), and inflamed tumor immune phenotype. Finally, we derive a computational model incorporating both genomic and clinical features predictive of immune checkpoint inhibitor response. Future work will utilize the biospecimens alongside these foundational analyses toward a better understanding of urothelial carcinoma biology.

Identification of phenocopies improves prediction of targeted therapy response over DNA mutations alone

DNA mutations in specific genes can confer preferential benefit from drugs targeting those genes. However, other molecular perturbations can “phenocopy” pathogenic mutations, but would not be identified using standard clinical sequencing, leading to missed opportunities for other patients to benefit from targeted treatments. We hypothesized that RNA phenocopy signatures of key cancer driver gene mutations could improve our ability to predict response to targeted therapies, despite not being directly trained on drug response. To test this, we built gene expression signatures in tissue samples for specific mutations and found that phenocopy signatures broadly increased accuracy of drug response predictions in-vitro compared to DNA mutation alone, and identified additional cancer cell lines that respond well with a positive/negative predictive value on par or better than DNA mutations. We further validated our results across four clinical cohorts. Our results suggest that routine RNA sequencing of tumors to identify phenocopies in addition to standard targeted DNA sequencing would improve our ability to accurately select patients for targeted therapies in the clinic.

Expression Analysis of Ligand-Receptor Pairs Identifies Cell-to-Cell Crosstalk between Macrophages and Tumor Cells in Lung Adenocarcinoma

Background

Lung adenocarcinoma is one of the most commonly diagnosed malignancies worldwide. Macrophage plays crucial roles in the tumor microenvironment, but its autocrine network and communications with tumor cell are still unclear.

Methods

We acquired single-cell RNA sequencing (scRNA-seq) (n = 30) and bulk RNA sequencing (n = 1480) samples of lung adenocarcinoma patients from previous literatures and publicly available databases. Various cell subtypes were identified, including macrophages. Differentially expressed ligand-receptor gene pairs were obtained to explore cell-to-cell communications between macrophages and tumor cells. Furthermore, a machine-learning predictive model based on ligand-receptor interactions was built and validated.

Results

A total of 159,219 single cells (18,248 tumor cells and 29,520 macrophages) were selected in this study. We identified significantly correlated autocrine ligand-receptor gene pairs in tumor cells and macrophages, respectively. Furthermore, we explored the cell-to-cell communications between macrophages and tumor cells and detected significantly correlated ligand-receptor signaling pairs. We determined that some of the hub gene pairs were associated with patient prognosis and constructed a machine-learning model based on the intercellular interaction network.

Conclusion

We revealed significant cell-to-cell communications (both autocrine and paracrine network) within macrophages and tumor cells in lung adenocarcinoma. Hub genes with prognostic significance in the network were also identified.

An artificial intelligence model to predict survival and chemotherapy benefits for gastric cancer patients after gastrectomy development and validation in international multicenter cohorts

BACKGROUND

Gastric cancer (GC) is a major health problem worldwide, with high prevalence and mortality. The present GC staging system provides inadequate prognostic information and does not reflect the chemotherapy benefit of GC.

METHODS

Two hundred fifty-five patients who underwent surgical resection were enrolled in our study (training cohort = 212, internal validation cohort = 43). Nine clinicopathologic features were obtained to construct an support vector machine (SVM) model. The cohorts from 4 domestic centres and The Cancer Genome Atlas (TCGA) were used for external validation.

RESULTS

In the training cohort, the AUCs were 0.773 (95% CI 0.708-0.838) for 5-year overall survival (OS) and 0.751 (95% CI 0.683-0.820) for 5-year disease-free survival (DFS); in the domestic validation cohort, the AUCs were 0.852 (95% CI 0.810-0.894) and 0.837 (95% CI 0.792-0.882), respectively. The model performed better than the TNM staging system according to the receiver operator characteristic(ROC) curve. GC patients were significantly divided into low, moderate and high risk based on the SVM. High-risk TNM stage Ⅱ and Ⅲ patients were more likely to benefit from adjuvant chemotherapy than low-risk patients.

CONCLUSIONS

The SVM-based model may be used to predict OS and DFS in GC patients and the benefit of adjuvant chemotherapy in TNM stage Ⅱ and Ⅲ GC patients.

An artificial intelligence method to assess the tumor microenvironment with treatment outcomes for gastric cancer patients after gastrectomy

Background

The tumor microenvironment (TME) plays an important role in the occurrence and development of gastric cancer (GC) and is widely used to assess the treatment outcomes of GC patients. Immunohistochemistry (IHC) and gene sequencing are the main analysis methods for the TME but are limited due to the subjectivity of observers, the high cost of equipment and the need for professional analysts.

Methods

The ImmunoScore (IS) was developed in the TCGA cohort and validated in GEO cohorts. The Radiomic ImmunoScore (RIS) was developed in the TCGA cohort and validated in the Nanfang cohort. A nomogram was developed and validated in the Nanfang cohort based on RIS and clinical features.

Results

For IS, the area under the curves (AUCs) were 0.798 for 2-year overall survival (OS) and 0.873 for 4-year overall survival. For RIS, in the TCGA cohort, the AUCs distinguishing High-IS or Low-IS and predicting prognosis were 0.85 and 0.81, respectively; in the Nanfang cohort, the AUC predicting prognosis was 0.72. The nomogram performed better than the TNM staging system according to the ROC curve (all P < 0.01). Patients with TNM stage II and III in the High-nomogram group were more likely to benefit from adjuvant chemotherapy than Low-nomogram group patients.

Conclusions

The RIS and the nomogram can be used to assess the TME, prognosis and adjuvant chemotherapy benefit of GC patients after radical gastrectomy and are valuable additions to the current TNM staging system. High-nomogram GC patients may benefit more from adjuvant chemotherapy than Low-nomogram GC patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03298-7.

Engineering Cancer Antigen-Specific T Cells to Overcome the Immunosuppressive Effects of TGF-β

Adoptive T cell therapy with T cells expressing affinity-enhanced TCRs has shown promising results in phase 1/2 clinical trials for solid and hematological tumors. However, depth and durability of responses to adoptive T cell therapy can suffer from an inhibitory tumor microenvironment. A common immune-suppressive agent is TGF-β, which is secreted by tumor cells and cells recruited to the tumor. We investigated whether human T cells could be engineered to be resistant to inhibition by TGF-β. Truncating the intracellular signaling domain from TGF-β receptor (TGFβR) II produces a dominant-negative receptor (dnTGFβRII) that dimerizes with endogenous TGFβRI to form a receptor that can bind TGF-β but cannot signal. We previously generated specific peptide enhanced affinity receptor TCRs recognizing the HLA-A*02-restricted peptides New York esophageal squamous cell carcinoma 1 (NY-ESO-1)_157-165/l-Ag family member-1A (TCR: GSK3377794, formerly NY-ESO-1^c259) and melanoma Ag gene A10_254-262 (TCR: ADP-A2M10, formerly melanoma Ag gene A10^c796). In this article, we show that exogenous TGF-β inhibited in vitro proliferation and effector functions of human T cells expressing these first-generation high-affinity TCRs, whereas inhibition was reduced or abolished in the case of second-generation TCRs coexpressed with dnTGFβRII (e.g., GSK3845097). TGF-β isoforms and a panel of TGF-β-associated genes are overexpressed in a range of cancer indications in which NY-ESO-1 is commonly expressed, particularly in synovial sarcoma. As an example, immunohistochemistry/RNAscope identified TGF-β-positive cells close to T cells in tumor nests and stroma, which had low frequencies of cells expressing IFN-γ in a non-small cell lung cancer setting. Coexpression of dnTGFβRII may therefore improve the efficacy of TCR-transduced T cells.

A Pan-Cancer Analysis of Predictive Methylation Signatures of Response to Cancer Immunotherapy

Recently, tumor immunotherapy based on immune checkpoint inhibitors (ICI) has been introduced and widely adopted for various tumor types. Nevertheless, tumor immunotherapy has a few drawbacks, including significant uncertainty of outcome, the possibility of severe immune-related adverse events for patients receiving such treatments, and the lack of effective biomarkers to determine the ICI treatments' responsiveness. DNA methylation profiles were recently identified as an indicator of the tumor immune microenvironment. They serve as a potential hot spot for predicting responses to ICI treatment for their stability and convenience of measurement by liquid biopsy. We demonstrated the possibility of DNA methylation profiles as a predictor for responses to the ICI treatments at the pan-cancer level by analyzing DNA methylation profiles considered responsive and non-responsive to the treatments. An SVM model was built based on this differential analysis in the pan-cancer levels. The performance of the model was then assessed both at the pan-cancer level and in specific tumor types. It was also compared to the existing gene expression profile-based method. DNA methylation profiles were shown to be predictable for the responses to the ICI treatments in the TCGA cases in pan-cancer levels. The proposed SVM model was shown to have high performance in pan-cancer and specific cancer types. This performance was comparable to that of gene expression profile-based one. The combination of the two models had even higher performance, indicating the potential complementarity of the DNA methylation and gene expression profiles in the prediction of ICI treatment responses.

Exploring Prognosis-Associated Biomarkers of Estrogen-Independent Uterine Corpus Endometrial Carcinoma by Bioinformatics Analysis

Background

Uterine corpus endometrial carcinoma (UCEC) is one of the most common female cancers with high incidence and mortality rates. In particular, the prognosis of type II UCEC is poorer than that of type I. However, the molecular mechanism underlying type II UCEC remains unclear.

Methods

RNA-seq data and corresponding clinical information on UCEC patients were downloaded from The Cancer Genome Atlas database, which were then separated into mRNA, lncRNA, and miRNA gene expression profile matrix to perform differentially expressed gene analysis. Weighted gene co-expression network analysis (WGCNA) was used to identify key modules associated with different UCEC subtypes based on mRNA and lncRNA expression matrix. Following that, a subtype-associated competing endogenous RNA (ceRNA) regulatory network was constructed. In addition, GO functional annotation and KEGG pathway analysis were performed on subtype-related DE mRNAs, and STRING database was utilized to predict the interaction network between proteins and their biological functions. The key mRNAs were validated at the protein and gene expression levels in endometrial cancerous tissues as compared with normal tissues.

Results

In summary, we identified 4611 mRNA, 3568 lncRNAs, and 47 miRNAs as differentially expressed between endometrial cancerous tissues and normal endometrial tissues. WGCNA demonstrated that 72 mRNAs and 55 lncRNAs were correlated with pathological subtypes. In the constructed ceRNA regulatory network, LINC02418, RASGRF1, and GCNT1 were screened for their association with poor prognosis of type II UCEC. These DE mRNAs were linked to Wnt signaling pathway, and lower expression of LEF1 and NKD1 predicted advanced clinical stages and worse prognosis of UCEC patients.

Conclusion

This study revealed five prognosis-associated biomarkers that can be used to predict the worst prognosis of type II UCEC.

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.

Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles

(1) Background: Inter-tumour heterogeneity is one of cancer’s most fundamental features. Patient stratification based on drug response prediction is hence needed for effective anti-cancer therapy. However, single-gene markers of response are rare and/or may fail to achieve a significant impact in the clinic. Machine Learning (ML) is emerging as a particularly promising complementary approach to precision oncology. (2) Methods: Here we leverage comprehensive Patient-Derived Xenograft (PDX) pharmacogenomic data sets with dimensionality-reducing ML algorithms with this purpose. (3) Results: Combining multiple gene alterations via ML leads to better discrimination between sensitive and resistant PDXs in 19 of the 26 analysed cases. Highly predictive ML models employing concise gene lists were found for three cases: paclitaxel (breast cancer), binimetinib (breast cancer) and cetuximab (colorectal cancer). Interestingly, each of these multi-gene ML models identifies some treatment-responsive PDXs not harbouring the best actionable mutation for that case. Thus, ML multi-gene predictors generally have much fewer false negatives than the corresponding single-gene marker. (4) Conclusions: As PDXs often recapitulate clinical outcomes, these results suggest that many more patients could benefit from precision oncology if ML algorithms were also applied to existing clinical pharmacogenomics data, especially those algorithms generating classifiers combining data-selected gene alterations.

Predicting cancer drug TARGETS - TreAtment Response Generalized Elastic-neT Signatures

We are now in an era of molecular medicine, where specific DNA alterations can be used to identify patients who will respond to specific drugs. However, there are only a handful of clinically used predictive biomarkers in oncology. Herein, we describe an approach utilizing in vitro DNA and RNA sequencing and drug response data to create TreAtment Response Generalized Elastic-neT Signatures (TARGETS). We trained TARGETS drug response models using Elastic-Net regression in the publicly available Genomics of Drug Sensitivity in Cancer (GDSC) database. Models were then validated on additional in-vitro data from the Cancer Cell Line Encyclopedia (CCLE), and on clinical samples from The Cancer Genome Atlas (TCGA) and Stand Up to Cancer/Prostate Cancer Foundation West Coast Prostate Cancer Dream Team (WCDT). First, we demonstrated that all TARGETS models successfully predicted treatment response in the separate in-vitro CCLE treatment response dataset. Next, we evaluated all FDA-approved biomarker-based cancer drug indications in TCGA and demonstrated that TARGETS predictions were concordant with established clinical indications. Finally, we performed independent clinical validation in the WCDT and found that the TARGETS AR signaling inhibitors (ARSI) signature successfully predicted clinical treatment response in metastatic castration-resistant prostate cancer with a statistically significant interaction between the TARGETS score and PSA response (p = 0.0252). TARGETS represents a pan-cancer, platform-independent approach to predict response to oncologic therapies and could be used as a tool to better select patients for existing therapies as well as identify new indications for testing in prospective clinical trials.

A New Epigenetic Model to Stratify Glioma Patients According to Their Immunosuppressive State

Gliomas are the most common primary neoplasm of the central nervous system. A promising frontier in the definition of glioma prognosis and treatment is represented by epigenetics. Furthermore, in this study, we developed a machine learning classification model based on epigenetic data (CpG probes) to separate patients according to their state of immunosuppression. We considered 573 cases of low-grade glioma (LGG) and glioblastoma (GBM) from The Cancer Genome Atlas (TCGA). First, from gene expression data, we derived a novel binary indicator to flag patients with a favorable immune state. Then, based on previous studies, we selected the genes related to the immune state of tumor microenvironment. After, we improved the selection with a data-driven procedure, based on Boruta. Finally, we tuned, trained, and evaluated both random forest and neural network classifiers on the resulting dataset. We found that a multi-layer perceptron network fed by the 338 probes selected by applying both expert choice and Boruta results in the best performance, achieving an out-of-sample accuracy of 82.8%, a Matthews correlation coefficient of 0.657, and an area under the ROC curve of 0.9. Based on the proposed model, we provided a method to stratify glioma patients according to their epigenomic state.

Machine Learning for Predicting the 3-Year Risk of Incident Diabetes in Chinese Adults

Purpose: We aimed to establish and validate a risk assessment system that combines demographic and clinical variables to predict the 3-year risk of incident diabetes in Chinese adults. Methods: A 3-year cohort study was performed on 15,928 Chinese adults without diabetes at baseline. All participants were randomly divided into a training set (n = 7,940) and a validation set (n = 7,988). XGBoost method is an effective machine learning technique used to select the most important variables from candidate variables. And we further established a stepwise model based on the predictors chosen by the XGBoost model. The area under the receiver operating characteristic curve (AUC), decision curve and calibration analysis were used to assess discrimination, clinical use and calibration of the model, respectively. The external validation was performed on a cohort of 11,113 Japanese participants. Result: In the training and validation sets, 148 and 145 incident diabetes cases occurred. XGBoost methods selected the 10 most important variables from 15 candidate variables. Fasting plasma glucose (FPG), body mass index (BMI) and age were the top 3 important variables. And we further established a stepwise model and a prediction nomogram. The AUCs of the stepwise model were 0.933 and 0.910 in the training and validation sets, respectively. The Hosmer-Lemeshow test showed a perfect fit between the predicted diabetes risk and the observed diabetes risk (p = 0.068 for the training set, p = 0.165 for the validation set). Decision curve analysis presented the clinical use of the stepwise model and there was a wide range of alternative threshold probability spectrum. And there were almost no the interactions between these predictors (most P-values for interaction >0.05). Furthermore, the AUC for the external validation set was 0.830, and the Hosmer-Lemeshow test for the external validation set showed no statistically significant difference between the predicted diabetes risk and observed diabetes risk (P = 0.824). Conclusion: We established and validated a risk assessment system for characterizing the 3-year risk of incident diabetes.

Emerging Therapies in Pheochromocytoma and Paraganglioma: Immune Checkpoint Inhibitors in the Starting Blocks

Pheochromocytoma and paraganglioma are neuroendocrine neoplasms, originating in the adrenal medulla and in parasympathetic and sympathetic autonomic nervous system ganglia, respectively. They usually present as localized tumours curable with surgery. However, these tumours may exhibit heterogeneous clinical course, ranging from no/minimal progression to aggressive (progressive/metastatic) behavior. For this setting of patients, current therapies are unsatisfactory. Immune checkpoint inhibitors have shown outstanding results for several types of solid cancers. We therefore aimed to summarize and discuss available data on efficacy and safety of current FDA-approved immune checkpoint inhibitors in patients with pheochromocytoma and paraganglioma. After an extensive search, we found 15 useful data sources (four full-published articles, four supplements of scientific journals, seven ongoing registered clinical trials). The data we detected, even with the limit of the small number of patients treated, make a great expectation on the therapeutic use of immune checkpoint inhibitors. Besides, the newly detected predictors of response will (hopefully) be of great helps in selecting the subset of patients that might benefit the most from this class of drugs. Finally, new trials are in the starting blocks, and they are expected to shed in the next future new light on a therapy, which is considered a milestone in oncology.

Multi-Approach Bioinformatics Analysis of Curated Omics Data Provides a Gene Expression Panorama for Multiple Cancer Types

Studies describing the expression patterns and biomarkers for the tumoral process increase in number every year. The availability of new datasets, although essential, also creates a confusing landscape where common or critical mechanisms are obscured amidst the divergent and heterogeneous nature of such results. In this work, we manually curated the Gene Expression Omnibus using rigorous filtering criteria to select the most homogeneous and highest quality microarray and RNA-seq datasets from multiple types of cancer. By applying systems biology approaches, combined with machine learning analysis, we investigated possible frequently deregulated molecular mechanisms underlying the tumoral process. Our multi-approach analysis of 99 curated datasets, composed of 5,406 samples, revealed 47 differentially expressed genes in all analyzed cancer types, which were all in agreement with the validation using TCGA data. Results suggest that the tumoral process is more related to the overexpression of core deregulated machinery than the underexpression of a given gene set. Additionally, we identified gene expression similarities between different cancer types not described before and performed an overall survival analysis using 20 cancer types. Finally, we were able to suggest a core regulatory mechanism that could be frequently deregulated.

Identification of a five-gene signature for predicting the progression and prognosis of stage I endometrial carcinoma

Uterine corpus endometrial carcinoma (UCEC) is often diagnosed at an early clinical stage based on abnormal vaginal bleeding. However, the prognosis of UCEC is poor. The present study was conducted to identify novel tumor grade-related genes with the potential to predict the prognosis and progression of UCEC. A total of three gene expression microarray datasets were downloaded from the Gene Expression Omnibus database, and one RNA-sequencing dataset with corresponding clinical information of patients with UCEC was obtained from The Cancer Genome Atlas database. In summary, 1,447 differentially expressed genes (DEGs) were identified between endometrial cancerous tissues and normal endometrial tissues. Weighted gene co-expression network analysis was performed to assess the associations between DEGs and clinical traits. In total, five genes were found to be highly associated with the tumorigenesis and prognosis of UCEC. Among them, BUB1 mitotic checkpoint serine/threonine kinase B, cyclin B1, cell-division cycle protein 20 and non-SMC condensing I complex subunit G were involved in cell cycle regulation pathways, and DLG-associated protein 5 was involved in the Notch receptor 3 signaling pathway based on functional enrichment analyses. Of the five genes, four were highly expressed in endometrial cancerous tissues compared with normal endometrial tissues at the protein level. In addition, the higher expression of these genes predicted a higher tumor grade and worse overall survival. In conclusion, the present study revealed a 5-gene signature that can be used to predict the progression of UCEC.

Machine Learning to Predict the 1-Year Mortality Rate After Acute Anterior Myocardial Infarction in Chinese Patients

A formal risk assessment for identifying high-risk patients is essential in clinical practice and promoted in guidelines for the management of anterior acute myocardial infarction. In this study, we sought to evaluate the performance of different machine learning models in predicting the 1-year mortality rate of anterior ST-segment elevation myocardial infarction (STEMI) patients and to compare the utility of these models to the conventional Global Registry of Acute Coronary Events (GRACE) risk scores. We enrolled all of the patients aged >18 years with discharge diagnoses of anterior STEMI in the Western China Hospital, Sichuan University, from January 2011 to January 2017. A total of 1244 patients were included in this study. The mean patient age was 63.8±12.9 years, and the proportion of males was 78.4%. The majority (75.18%) received revascularization therapy. In the prediction of the 1-year mortality rate, the areas under the curve (AUCs) of the receiver operating characteristic curves (ROCs) of the six models ranged from 0.709 to 0.942. Among all models, XGBoost achieved the highest accuracy (92%), specificity (99%) and f1 score (0.72) for predictions with the full variable model. After feature selection, XGBoost still obtained the highest accuracy (93%), specificity (99%) and f1 score (0.73). In conclusion, machine learning algorithms can accurately predict the rate of death after a 1-year follow-up of anterior STEMI, especially the XGBoost model.