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

Abstract

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.

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

“…In our case, the TAMs had an M2-like polarization, with positivity of CSF1R, CD163, and IL-10 that is compatible with an M2c-like subtype of immune regulatory properties. Additionally, the tumor was IL-10 and RGS1, markers that we have described to be associated with poor prognosis in diffuse large B-cell lymphoma ( Figure A2 ) [ 18 , 19 , 32 , 33 , 34 ].…”

“…Histological analysis consisted of hematoxylin and eosin (H&E), Masson trichrome stain, immunohistochemical staining, and DNA in situ hybridization (FISH) with brake apart probes for BCL2 , BCL6 , and MYC (Vysis, Tokyo, Japan) [ 15 , 16 , 17 ]. Immunohistochemistry was performed following the manufacturer’s instructions (Leica Bond-Max autostainer, Leica Biosystems K.K., Tokyo, Japan) [ 18 ] and included a battery of primary antibodies as actin-SM, ALK-1, BCL2, BCL6, BTK D3H5, CD10, CD163, CD20 (L26), CD21, CD3, CD31, CD34, CD5, CD68, CD85A, CDK4, CK AE1/3, C-MYC, CSF1R, desmin, FOXP3, HLA-DP-DR, IL-10, MDM2, MIB-1, MUM1, p16, PD-1, PD-L1, PTEN, PTX3, RGS1, S100, and TNFRSF14 (HVEM). The primary antibodies were purchased or obtained from Novocasra (Leica), ThermoFisher, Perseus Proteomics, Abcam, and the Spanish National Cancer Research Center (CNIO).…”

“…The primary antibodies were purchased or obtained from Novocasra (Leica), ThermoFisher, Perseus Proteomics, Abcam, and the Spanish National Cancer Research Center (CNIO). Immunofluorescence was performed as described previously [ 18 , 19 ]. The slides were observed using an optical BX51 Olympus microscope, scanned using a Zeiss LSM700 confocal microscope, and visualized with Imaris Bitplane 3D rendering software (Oxford Instruments, Abingdon, Oxfordshire, UK) [ 18 , 20 ].…”

“…Immunofluorescence was performed as described previously [ 18 , 19 ]. The slides were observed using an optical BX51 Olympus microscope, scanned using a Zeiss LSM700 confocal microscope, and visualized with Imaris Bitplane 3D rendering software (Oxford Instruments, Abingdon, Oxfordshire, UK) [ 18 , 20 ].…”

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

“…We did not compare with DLBCL, which was not otherwise specified. Nevertheless, we have recently shown that cases with high gene expression of BCL2 , MYC , and ENO3 are associated with an unfavorable overall survival of the patients [ 47 , 55 , 56 ], and that HGBL accounts for around 10% of the cases [ 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 ] and is characterized by higher CD163 but lower PTX3 expression [ 57 ]. Therefore, this WHO subtype is being characterized progressively.…”