Artificial Neural Networks Predicted the Overall Survival and Molecular Subtypes of Diffuse Large B-Cell Lymphoma Using a Pancancer Immune-Oncology Panel

Artificial intelligence-based prognostic model accurately predicts the survival of patients with diffuse large B-cell lymphomas: analysis of a large cohort in China

BACKGROUND

Diffuse large B-cell lymphomas (DLBCLs) display high molecular heterogeneity, but the International Prognostic Index (IPI) considers only clinical indicators and has not been updated to include molecular data. Therefore, we developed a widely applicable novel scoring system with molecular indicators screened by artificial intelligence (AI) that achieves accurate prognostic stratification and promotes individualized treatments.

METHODS

We retrospectively enrolled a cohort of 401 patients with DLBCL from our hospital, covering the period from January 2015 to January 2019. We included 22 variables in our analysis and assigned them weights using the random survival forest method to establish a new predictive model combining bidirectional long-short term memory (Bi-LSTM) and logistic hazard techniques. We compared the predictive performance of our "molecular-contained prognostic model" (McPM) and the IPI. In addition, we developed a simplified version of the McPM (sMcPM) to enhance its practical applicability in clinical settings. We also demonstrated the improved risk stratification capabilities of the sMcPM.

RESULTS

Our McPM showed superior predictive accuracy, as indicated by its high C-index and low integrated Brier score (IBS), for both overall survival (OS) and progression-free survival (PFS). The overall performance of the McPM was also better than that of the IPI based on receiver operating characteristic (ROC) curve fitting. We selected five key indicators, including extranodal involvement sites, lactate dehydrogenase (LDH), MYC gene status, absolute monocyte count (AMC), and platelet count (PLT) to establish the sMcPM, which is more suitable for clinical applications. The sMcPM showed similar OS results (P < 0.0001 for both) to the IPI and significantly better PFS stratification results (P < 0.0001 for sMcPM vs. P = 0.44 for IPI).

CONCLUSIONS

Our new McPM, including both clinical and molecular variables, showed superior overall stratification performance to the IPI, rendering it more suitable for the molecular era. Moreover, our sMcPM may become a widely used and effective stratification tool to guide individual precision treatments and drive new drug development.

Artificial intelligence and classification of mature lymphoid neoplasms

Hematologists, geneticists, and clinicians came to a multidisciplinary agreement on the classification of lymphoid neoplasms that combines clinical features, histological characteristics, immunophenotype, and molecular pathology analyses. The current classification includes the World Health Organization (WHO) Classification of tumours of haematopoietic and lymphoid tissues revised 4th edition, the International Consensus Classification (ICC) of mature lymphoid neoplasms (report from the Clinical Advisory Committee 2022), and the 5th edition of the proposed WHO Classification of haematolymphoid tumours (lymphoid neoplasms, WHO-HAEM5). This article revises the recent advances in the classification of mature lymphoid neoplasms. Artificial intelligence (AI) has advanced rapidly recently, and its role in medicine is becoming more important as AI integrates computer science and datasets to make predictions or classifications based on complex input data. Summarizing previous research, it is described how several machine learning and neural networks can predict the prognosis of the patients, and classified mature B-cell neoplasms. In addition, new analysis predicted lymphoma subtypes using cell-of-origin markers that hematopathologists use in the clinical routine, including CD3, CD5, CD19, CD79A, MS4A1 (CD20), MME (CD10), BCL6, IRF4 (MUM-1), BCL2, SOX11, MNDA, and FCRL4 (IRTA1). In conclusion, although most categories are similar in both classifications, there are also conceptual differences and differences in the diagnostic criteria for some diseases. It is expected that AI will be incorporated into the lymphoma classification as another bioinformatics tool.

Advanced insights on tumor-associated macrophages revealed by single-cell RNA sequencing: The intratumor heterogeneity, functional phenotypes, and cellular interactions

Single-cell RNA sequencing (scRNA-seq) is an emerging technology used for cellular transcriptome analysis. The application of scRNA-seq has led to profoundly advanced oncology research, continuously optimizing novel therapeutic strategies. Intratumor heterogeneity extensively consists of all tumor components, contributing to different tumor behaviors and treatment responses. Tumor-associated macrophages (TAMs), the core immune cells linking innate and adaptive immunity, play significant roles in tumor progression and resistance to therapies. Moreover, dynamic changes occur in TAM phenotypes and functions subject to the regulation of the tumor microenvironment. The heterogeneity of TAMs corresponding to the state of the tumor microenvironment has been comprehensively recognized using scRNA-seq. Herein, we reviewed recent research and summarized variations in TAM phenotypes and functions from a developmental perspective to better understand the significance of TAMs in the tumor microenvironment.

Construction of disulfidptosis-based immune response prediction model with artificial intelligence and validation of the pivotal grouping oncogene c-MET in regulating T cell exhaustion

Background

Given the lack of research on disulfidptosis, our study aimed to dissect its role in pan-cancer and explore the crosstalk between disulfidptosis and cancer immunity.

Methods

Based on TCGA, ICGC, CGGA, GSE30219, GSE31210, GSE37745, GSE50081, GSE22138, GSE41613, univariate Cox regression, LASSO regression, and multivariate Cox regression were used to construct the rough gene signature based on disulfidptosis for each type of cancer. SsGSEA and Cibersort, followed by correlation analysis, were harnessed to explore the linkage between disulfidptosis and cancer immunity. Weighted correlation network analysis (WGCNA) and Machine learning were utilized to make a refined prognosis model for pan-cancer. In particular, a customized, enhanced prognosis model was made for glioma. The siRNA transfection, FACS, ELISA, etc., were employed to validate the function of c-MET.

Results

The expression comparison of the disulfidptosis-related genes (DRGs) between tumor and nontumor tissues implied a significant difference in most cancers. The correlation between disulfidptosis and immune cell infiltration, including T cell exhaustion (Tex), was evident, especially in glioma. The 7-gene signature was constructed as the rough model for the glioma prognosis. A pan-cancer suitable DSP clustering was made and validated to predict the prognosis. Furthermore, two DSP groups were defined by machine learning to predict the survival and immune therapy response in glioma, which was validated in CGGA. PD-L1 and other immune pathways were highly enriched in the core blue gene module from WGCNA. Among them, c-MET was validated as a tumor driver gene and JAK3-STAT3-PD-L1/PD1 regulator in glioma and T cells. Specifically, the down-regulation of c-MET decreased the proportion of PD1+ CD8+ T cells.

Conclusion

To summarize, we dissected the roles of DRGs in the prognosis and their relationship with immunity in pan-cancer. A general prognosis model based on machine learning was constructed for pan-cancer and validated by external datasets with a consistent result. In particular, a survival-predicting model was made specifically for patients with glioma to predict its survival and immune response to ICIs. C-MET was screened and validated for its tumor driver gene and immune regulation function (inducing t-cell exhaustion) in glioma.

In silico study of polyphenols as potential inhibitors of MALT1 protein in non-Hodgkin lymphoma

Non-Hodgkin lymphoma (NHL) is one of the most common cancer types. Deregulated signaling pathways can trigger certain NHL subtypes, including Diffuse Large B-cell lymphoma. NF-ĸB signaling pathway, which is responsible for the proliferation, growth, and survival of cells, has an essential role in lymphoma development. Although different signals control NF-ĸB activation in various lymphoid malignancies, the characteristic one is the CARD11-BCL10-MALT1 (CBM) complex. The CBM complex is responsible for the initiation of adaptive immune response. Our study is focused on the molecular docking of ten polyphenols as potential CARD11-BCL10-MALT1 complex inhibitors, essentially through MALT1 inhibition. Molecular docking was performed by Auto Dock Tools and AutoDock Vina tool, while SwissADME was used for drug-likeness and absorption, distribution, metabolism, excretion, and toxicity (ADMET) analysis of the ligands. Out of 66 ligands that were used in this study, we selected and visualized five. Selection criteria were based on the binding energy score and position of the ligands on the used protein. 2D and 3D visualizations showed interactions of ligands with the protein. Five ligands are considered potential inhibitors of MALT1, thus affecting NF-ĸB signaling pathway. However, additional in vivo and in vitro studies are required to confirm their mechanism of inhibition.

Integrative analysis of lysine acetylation-related genes and identification of a novel prognostic model for oral squamous cell carcinoma

Introduction: Oral squamous cell carcinoma (OSCC), which accounts for a high proportion of oral cancers, is characterized by high aggressiveness and rising incidence. Lysine acetylation is associated with cancer pathogenesis. Lysine acetylation-related genes (LARGs) are therapeutic targets and potential prognostic indicators in various tumors, including oral squamous cell carcinoma. However, systematic bioinformatics analysis of the Lysine acetylation-related genes in Oral squamous cell carcinoma is still unexplored. Methods: We analyzed the expression of 33 Lysine acetylation-related genes in oral squamous cell carcinoma and the effects of their somatic mutations on oral squamous cell carcinoma prognosis. Consistent clustering analysis identified two lysine acetylation patterns and the differences between the two patterns were further evaluated. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to develop a lysine acetylation-related prognostic model using TCGA oral squamous cell carcinoma datasets, which was then validated using gene expression omnibus (GEO) dataset GSE41613. Results: Patients with lower risk scores had better prognoses, in both the overall cohort and within the subgroups These patients also had "hot" immune microenvironments and were more sensitive to immunotherapy. Disscussion: Our findings offer a new model for classifying oral squamous cell carcinoma and determining its prognosis and offer novel insights into oral squamous cell carcinoma diagnosis and treatment.

miR-141-3p accelerates ovarian cancer progression and promotes M2-like macrophage polarization by targeting the Keap1-Nrf2 pathway

The miR-141-3p has been reported to participate in regulating autophagy and tumor-stroma interactions in ovarian cancer (OC). We aim to investigate whether miR-141-3p accelerates the progression of OC and its effect on macrophage 2 polarization by targeting the Kelch-like ECH-associated protein1-Nuclear factor E2-related factor2 (Keap1-Nrf2) pathway. SKOV3 and A2780 cells were transfected with miR-141-3p inhibitor and negative control to confirm the regulation of miR-141-3p on OC development. Moreover, the growth of tumors in xenograft nude mice treated by cells transfected with miR-141-3p inhibitor was established to further testify the role of miR-141-3p in OC. The expression of miR-141-3p was higher in OC tissue compared with non-cancerous tissue. Downregulation of miR-141-3p inhibited the proliferation, migration, and invasion of ovarian cells. Furthermore, miR-141-3p inhibition also suppressed M2-like macrophage polarization and in vivo OC progression. Inhibition of miR-141-3p significantly enhanced the expression of Keap1, the target gene of miR-141-3p, and thus downregulated Nrf2, while activation of Nrf2 reversed the reduction in M2 polarization by miR-141-3p inhibitor. Collectively, miR-141-3p contributes to tumor progression, migration, and M2 polarization of OC by activating the Keap1-Nrf2 pathway. Inhibition of miR-141-3p attenuates the malignant biological behavior of ovarian cells by inactivating the Keap1-Nrf2 pathway.

Surface TREM2 on circulating M-MDSCs as a novel prognostic factor for adults with treatment-naïve diffuse large B-cell lymphoma

INTRODUCTION

Circulating monocytic myeloid-derived suppressive cells (M-MDSCs) are implicated as a poor prognostic factor and cause CAR T-cell failure in diffuse large B-cell lymphoma (DLBCL). Triggering receptors expressed on myeloid cells 2 (TREM2) are a transmembrane glycoprotein that polarize macrophages to anti-inflammation phenotype but have never been explored on M-MDSCs. This study aims to elucidate the expression and clinical impact of surface TREM2 on circulating M-MDSCs derived from DLBCL adults.

METHODS

This prospective, observational study enrolled 100 adults with newly diagnosed and treatment-naïve DLBCL from May 2019 to October 2021. Human circulating M-MDSCs were obtained from freshly isolated peripheral blood, and each patient's surface-TREM2 level on M-MDSCs was normalized via a healthy control at the same performance of flow-cytometry analysis. Murine MDSCs derived from bone marrow (BM-MDSCs) were adopted to assess the link between Trem2 and cytotoxic T lymphocytes.

RESULTS

More circulating M-MDSCs at diagnosis of DLBCL predicted worse progression-free (PFS) and overall survival (OS). Patients with higher IPI scores, bone marrow involvement, or lower absolute counts of CD4⁺ or CD8⁺ T cells in PB had significantly higher normalized TREM2 levels on M-MDSCs. Additionally, normalized TREM2 levels on M-MDSCs could be grouped into low (< 2%), medium (2-44%), or high (> 44%) levels, and a high normalized TREM2 level on M-MDSCs was proven as an independent prognostic factor for both PFS and OS via multivariate Cox regression analysis and associated with worst PFS and OS. Interestingly, normalized levels of surface TREM2 on M-MDSCs were negatively associated with absolute counts of PB CD8⁺ T cells and positively correlated with levels of intracellular arginase 1 (ARG1) within M-MDSCs. Wild-type BM-MDSCs had significantly higher mRNA levels of Arg1 and showed more prominent ability to suppress the proliferation of co-cultured CD8⁺ T cells than BM-MDSCs from Trem2 knockout mice, and the suppressive ability could be impaired by adding Arg1 inhibitors (CB1158) or supplementing L-arginine.

CONCLUSION

In treatment-naïve DLBCL adults, a high surface-TREM2 level on circulating M-MDSCs is a poor prognostic factor for both PFS and OS and warrants further investigation for its potential as a novel target in immunotherapy.

Mutational Profile and Pathological Features of a Case of Interleukin-10 and RGS1-Positive Spindle Cell Variant Diffuse Large B-Cell Lymphoma

Diffuse large B-cell lymphoma with spindle cell morphology is a rare variant. We present the case of a 74-year-old male who initially presented with a right supraclavicular (lymph) node enlargement. Histological analysis showed a proliferation of spindle-shaped cells with narrow cytoplasms. An immunohistochemical panel was used to exclude other tumors, such as melanoma, carcinoma, and sarcoma. The lymphoma was characterized by a cell-of-origin subtype of germinal center B-cell-like (GCB) based on Hans’ classifier (CD10-negative, BCL6-positive, and MUM1-negative); EBER negativity, and the absence of BCL2, BCL6, and MYC rearrangements. Mutational profiling using a custom panel of 168 genes associated with aggressive B-cell lymphomas confirmed mutations in ACTB, ARID1B, DUSP2, DTX1, HLA-B, PTEN, and TNFRSF14. Based on the LymphGen 1.0 classification tool, this case had an ST2 subtype prediction. The immune microenvironment was characterized by moderate infiltration of M2-like tumor-associated macrophages (TMAs) with positivity of CD163, CSF1R, CD85A (LILRB3), and PD-L1; moderate PD-1 positive T cells, and low FOXP3 regulatory T lymphocytes (Tregs). Immunohistochemical expression of PTX3 and TNFRSF14 was absent. Interestingly, the lymphoma cells were positive for HLA-DP-DR, IL-10, and RGS1, which are markers associated with poor prognosis in DLBCL. The patient was treated with R-CHOP therapy, and achieved a metabolically complete response.

Feature selection combined with top-down and bottom-up strategies for survival analysis: A case of prognostic prediction in glioblastoma

Over the last decades, molecular signatures have attracted extensive attention in cancer research. However, most of the reported biomarkers show a weak distinguishing ability in predicting the survival risks of patients. Actually, univariate analysis is generally considered in regression analysis, which makes the existing statistical methods ineffective. Furthermore, there is too much human involvement in the ways of classifying patients with high and low risk. Last but not least, the participation of therapy after conservative surgery also makes the survival analysis more complex. In order to solve these problems, we propose a solid method of feature selection which combines top-down and bottom-up strategies. The top-down strategy is to randomly extract some genes each time and select candidate genes through cumulative voting. The bottom-up strategy is to fully enumerate the selected genes and to use a clustering algorithm to classify samples. We analyzed glioblastoma data from the Cancer Genome Atlas (TCGA) and got candidate signatures. The results of simulation data, as well as an independent test set the Chinese Glioma Genome Atlas (CGGA), verified the reliability of the method and validity of the selected features.

Identification of novel biomarkers involved in doxorubicin-induced acute and chronic cardiotoxicity, respectively, by integrated bioinformatics

Background

The mechanisms of doxorubicin (DOX) cardiotoxicity were complex and controversial, with various contradictions between experimental and clinical data. Understanding the differences in the molecular mechanism between DOX-induced acute and chronic cardiotoxicity may be an ideal entry point to solve this dilemma.

Methods

Mice were injected intraperitoneally with DOX [(20 mg/kg, once) or (5 mg/kg/week, three times)] to construct acute and chronic cardiotoxicity models, respectively. Survival record and ultrasound monitored the cardiac function. The corresponding left ventricular (LV) myocardium tissues were analyzed by RNA-seq to identify differentially expressed genes (DEGs). Gene Ontology (GO), Kyoto Encyclopedia of Gene and Genome (KEGG), and Gene Set Enrichment Analysis (GSEA) found the key biological processes and signaling pathways. DOX cardiotoxicity datasets from the Gene expression omnibus (GEO) database were combined with RNA-seq to identify the common genes. Cytoscape analyzed the hub genes, which were validated by quantitative real-time PCR. ImmuCo and ImmGen databases analyzed the correlations between hub genes and immunity-relative markers in immune cells. Cibersort analyzed the immune infiltration and correlations between the hub genes and the immune cells. Logistic regression, receiver operator characteristic curve, and artificial neural network analysis evaluated the diagnosis ability of hub genes for clinical data in the GEO dataset.

Results

The survival curves and ultrasound monitoring demonstrated that cardiotoxicity models were constructed successfully. In the acute model, 788 DEGs were enriched in the activated metabolism and the suppressed immunity-associated signaling pathways. Three hub genes (Alas1, Atp5g1, and Ptgds) were upregulated and were negatively correlated with a colony of immune-activating cells. However, in the chronic model, 281 DEGs showed that G protein-coupled receptor (GPCR)-related signaling pathways were the critical events. Three hub genes (Hsph1, Abcb1a, and Vegfa) were increased in the chronic model. Furthermore, Hsph1 combined with Vegfa was positively correlated with dilated cardiomyopathy (DCM)-induced heart failure (HF) and had high accuracy in the diagnosis of DCM-induced HF (AUC = 0.898, P = 0.000).

Conclusion

Alas1, Atp5g1, and Ptgds were ideal biomarkers in DOX acute cardiotoxicity. However, Hsph1 and Vegfa were potential biomarkers in the myocardium in the chronic model. Our research, first, provided bioinformatics and clinical evidence for the discovery of the differences in mechanism and potential biomarkers of DOX-induced acute and chronic cardiotoxicity to find a therapeutic strategy precisely.

Copy Number Alteration and Mutational Profile of High-Grade B-Cell Lymphoma with MYC and BCL2 and/or BCL6 Rearrangements, Diffuse Large B-Cell Lymphoma with MYC-Rearrangement, and Diffuse Large B-Cell Lymphoma with MYC-Cluster Amplification

Diffuse large B-cell lymphoma (DLBCL) with MYC alteration is classified as high-grade B-cell lymphoma with MYC and BCL2 and/or BCL6 rearrangements (double/triple-hit lymphoma; DHL/THL), DLBCL with MYC rearrangement (single-hit lymphoma; SHL) and DLBCL with MYC-cluster amplification (MCAD). To elucidate the genetic features of DHL/THL, SHL, and MCAD, 23 lymphoma cases from Tokai University Hospital were analyzed. The series included 10 cases of DHL/THL, 10 cases of SHL and 3 cases of MCAD. The analysis used whole-genome copy number microarray analysis (OncoScan) and a custom-made next-generation sequencing (NGS) panel of 115 genes associated with aggressive B-cell lymphomas. The copy number alteration (CNA) profiles were similar between DHL/THL and SHL. MCAD had fewer CNAs than those of DHL/THL and SHL, except for +8q24. The NGS profile characterized DHL/THL with a higher "mutation burden" than SHL (17 vs. 10, p = 0.010), and the most relevant genes for DHL/THL were BCL2 and SOCS1, and for SHL was DTX1. MCAD was characterized by mutations of DDX3X, TCF3, HLA-A, and TP53, whereas MYC was unmutated. In conclusion, DHL/THL, SHL, and MCAD have different profiles.

Small Tweaks, Major Changes: Post-Translational Modifications That Occur within M2 Macrophages in the Tumor Microenvironment

The majority of proteins are subjected to post-translational modifications (PTMs), regardless of whether they occur in or after biosynthesis of the protein. Capable of altering the physical and chemical properties and functions of proteins, PTMs are thus crucial. By fostering the proliferation, migration, and invasion of cancer cells with which they communicate in the tumor microenvironment (TME), M2 macrophages have emerged as key cellular players in the TME. Furthermore, growing evidence illustrates that PTMs can occur in M2 macrophages as well, possibly participating in molding the multifaceted characteristics and physiological behaviors in the TME. Hence, there is a need to review the PTMs that have been reported to occur within M2 macrophages. Although there are several reviews available regarding the roles of M2 macrophages, the majority of these reviews overlooked PTMs occurring within M2 macrophages. Considering this, in this review, we provide a review focusing on the advancement of PTMs that have been reported to take place within M2 macrophages, mainly in the TME, to better understand the performance of M2 macrophages in the tumor microenvironment. Incidentally, we also briefly cover the advances in developing inhibitors that target PTMs and the application of artificial intelligence (AI) in the prediction and analysis of PTMs at the end of the review.

Artificial Intelligence Predicted Overall Survival and Classified Mature B-Cell Neoplasms Based on Immuno-Oncology and Immune Checkpoint Panels

Artificial intelligence (AI) can identify actionable oncology biomarkers. This research integrates our previous analyses of non-Hodgkin lymphoma. We used gene expression and immunohistochemical data, focusing on the immune checkpoint, and added a new analysis of macrophages, including 3D rendering. The AI comprised machine learning (C5, Bayesian network, C&R, CHAID, discriminant analysis, KNN, logistic regression, LSVM, Quest, random forest, random trees, SVM, tree-AS, and XGBoost linear and tree) and artificial neural networks (multilayer perceptron and radial basis function). The series included chronic lymphocytic leukemia, mantle cell lymphoma, follicular lymphoma, Burkitt, diffuse large B-cell lymphoma, marginal zone lymphoma, and multiple myeloma, as well as acute myeloid leukemia and pan-cancer series. AI classified lymphoma subtypes and predicted overall survival accurately. Oncogenes and tumor suppressor genes were highlighted (MYC, BCL2, and TP53), along with immune microenvironment markers of tumor-associated macrophages (M2-like TAMs), T-cells and regulatory T lymphocytes (Tregs) (CD68, CD163, MARCO, CSF1R, CSF1, PD-L1/CD274, SIRPA, CD85A/LILRB3, CD47, IL10, TNFRSF14/HVEM, TNFAIP8, IKAROS, STAT3, NFKB, MAPK, PD-1/PDCD1, BTLA, and FOXP3), apoptosis (BCL2, CASP3, CASP8, PARP, and pathway-related MDM2, E2F1, CDK6, MYB, and LMO2), and metabolism (ENO3, GGA3). In conclusion, AI with immuno-oncology markers is a powerful predictive tool. Additionally, a review of recent literature was made.

Artificial Intelligence Analysis of Celiac Disease Using an Autoimmune Discovery Transcriptomic Panel Highlighted Pathogenic Genes including BTLA

Celiac disease is a common immune-related inflammatory disease of the small intestine caused by gluten in genetically predisposed individuals. This research is a proof-of-concept exercise focused on using Artificial Intelligence (AI) and an autoimmune discovery gene panel to predict and model celiac disease. Conventional bioinformatics, gene set enrichment analysis (GSEA), and several machine learning and neural network techniques were used on a publicly available dataset (GSE164883). Machine learning and deep learning included C5, logistic regression, Bayesian network, discriminant analysis, KNN algorithm, LSVM, random trees, SVM, Tree-AS, XGBoost linear, XGBoost tree, CHAID, Quest, C&R tree, random forest, and neural network (multilayer perceptron). As a result, the gene panel predicted celiac disease with high accuracy (95–100%). Several pathogenic genes were identified, some of the immune checkpoint and immuno-oncology pathways. They included CASP3, CD86, CTLA4, FASLG, GZMB, IFNG, IL15RA, ITGAX, LAG3, MMP3, MUC1, MYD88, PRDM1, RGS1, etc. Among them, B and T lymphocyte associated (BTLA, CD272) was highlighted and validated at the protein level by immunohistochemistry in an independent series of cases. Celiac disease was characterized by high BTLA, expressed by inflammatory cells of the lamina propria. In conclusion, artificial intelligence predicted celiac disease using an autoimmune discovery gene panel.

Artificial Intelligence Analysis of Ulcerative Colitis Using an Autoimmune Discovery Transcriptomic Panel

Ulcerative colitis is a bowel disease of unknown cause. This research is a proof-of-concept exercise focused on determining whether it is possible to identify the genes associated with ulcerative colitis using artificial intelligence. Several machine learning and artificial neural networks analyze using an autoimmune discovery transcriptomic panel of 755 genes to predict and model ulcerative colitis versus healthy donors. The dataset GSE38713 of 43 cases from the Hospital Clinic of Barcelona was selected, and 16 models were used, including C5, logistic regression, Bayesian network, discriminant analysis, KNN algorithm, LSVM, random trees, SVM, Tree-AS, XGBoost linear, XGBoost tree, CHAID, Quest, C&R tree, random forest, and neural network. Conventional analysis, including volcano plot and gene set enrichment analysis (GSEA), were also performed. As a result, ulcerative colitis was successfully predicted with several machine learning techniques and artificial neural networks (multilayer perceptron), with an overall accuracy of 95–100%, and relevant pathogenic genes were highlighted. One of them, programmed cell death 1 ligand 1 (PD-L1, CD274, PDCD1LG1, B7-H1) was validated in a series from the Tokai University Hospital by immunohistochemistry. In conclusion, artificial intelligence analysis of transcriptomic data of ulcerative colitis is a feasible analytical strategy.

Integrating artificial intelligence into haematology training and practice: Opportunities, threats and proposed solutions

There remains a limited emphasis on the use beyond the research domain of artificial intelligence (AI) in haematology and it does not feature significantly in postgraduate medical education and training. This perspective article considers recent developments in the field of AI research in haematology and anticipates the potential benefits and risks associated with its deeper integration into the specialty. Anxiety towards the greater use of AI in healthcare stems from legitimate concerns surrounding data protection, lack of transparency in clinical decision-making, and erosion of the doctor-patient relationship. The specialty of haematology has successfully embraced multiple disruptive innovations. We are at the cusp of a new era of closer integration of AI into routine haematology practice that will ultimately benefit patient care but to harness its benefits the next generation of haematologists will need access to bespoke learning opportunities with input from data scientists.

Artificial Intelligence Analysis of Gene Expression Predicted the Overall Survival of Mantle Cell Lymphoma and a Large Pan-Cancer Series

Mantle cell lymphoma (MCL) is a subtype of mature B-cell non-Hodgkin lymphoma characterized by a poor prognosis. First, we analyzed a series of 123 cases (GSE93291). An algorithm using multilayer perceptron artificial neural network, radial basis function, gene set enrichment analysis (GSEA), and conventional statistics, correlated 20,862 genes with 28 MCL prognostic genes for dimensionality reduction, to predict the patients' overall survival and highlight new markers. As a result, 58 genes predicted survival with high accuracy (area under the curve = 0.9). Further reduction identified 10 genes: KIF18A, YBX3, PEMT, GCNA, and POGLUT3 that associated with a poor survival; and SELENOP, AMOTL2, IGFBP7, KCTD12, and ADGRG2 with a favorable survival. Correlation with the proliferation index (Ki67) was also made. Interestingly, these genes, which were related to cell cycle, apoptosis, and metabolism, also predicted the survival of diffuse large B-cell lymphoma (GSE10846, n = 414), and a pan-cancer series of The Cancer Genome Atlas (TCGA, n = 7289), which included the most relevant cancers (lung, breast, colorectal, prostate, stomach, liver, etcetera). Secondly, survival was predicted using 10 oncology panels (transcriptome, cancer progression and pathways, metabolic pathways, immuno-oncology, and host response), and TYMS was highlighted. Finally, using machine learning, C5 tree and Bayesian network had the highest accuracy for prediction and correlation with the LLMPP MCL35 proliferation assay and RGS1 was made. In conclusion, artificial intelligence analysis predicted the overall survival of MCL with high accuracy, and highlighted genes that predicted the survival of a large pan-cancer series.