Tumor mutational burden related classifier is predictive of response to PD-L1 blockade in locally advanced and metastatic urothelial carcinoma

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.

Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review

BACKGROUND

The widespread use of immune checkpoint inhibitors (ICIs) has revolutionised treatment of multiple cancer types. However, selecting patients who may benefit from ICI remains challenging. Artificial intelligence (AI) approaches allow exploitation of high-dimension oncological data in research and development of precision immuno-oncology.

MATERIALS AND METHODS

We conducted a systematic literature review of peer-reviewed original articles studying the ICI efficacy prediction in cancer patients across five data modalities: genomics (including genomics, transcriptomics, and epigenomics), radiomics, digital pathology (pathomics), and real-world and multimodality data.

RESULTS

A total of 90 studies were included in this systematic review, with 80% published in 2021-2022. Among them, 37 studies included genomic, 20 radiomic, 8 pathomic, 20 real-world, and 5 multimodal data. Standard machine learning (ML) methods were used in 72% of studies, deep learning (DL) methods in 22%, and both in 6%. The most frequently studied cancer type was non-small-cell lung cancer (36%), followed by melanoma (16%), while 25% included pan-cancer studies. No prospective study design incorporated AI-based methodologies from the outset; rather, all implemented AI as a post hoc analysis. Novel biomarkers for ICI in radiomics and pathomics were identified using AI approaches, and molecular biomarkers have expanded past genomics into transcriptomics and epigenomics. Finally, complex algorithms and new types of AI-based markers, such as meta-biomarkers, are emerging by integrating multimodal/multi-omics data.

CONCLUSION

AI-based methods have expanded the horizon for biomarker discovery, demonstrating the power of integrating multimodal data from existing datasets to discover new meta-biomarkers. While most of the included studies showed promise for AI-based prediction of benefit from immunotherapy, none provided high-level evidence for immediate practice change. A priori planned prospective trial designs are needed to cover all lifecycle steps of these software biomarkers, from development and validation to integration into clinical practice.

Assessment of Prostate and Bladder Cancer Genomic Biomarkers Using Artificial Intelligence: a Systematic Review

PURPOSE OF REVIEW

The aim of the systematic review is to assess AI's capabilities in the genetics of prostate cancer (PCa) and bladder cancer (BCa) to evaluate target groups for such analysis as well as to assess its prospects in daily practice.

RECENT FINDINGS

In total, our analysis included 27 articles: 10 articles have reported on PCa and 17 on BCa, respectively. The AI algorithms added clinical value and demonstrated promising results in several fields, including cancer detection, assessment of cancer development risk, risk stratification in terms of survival and relapse, and prediction of response to a specific therapy. Besides clinical applications, genetic analysis aided by the AI shed light on the basic urologic cancer biology. We believe, our results of the AI application to the analysis of PCa, BCa data sets will help to identify new targets for urological cancer therapy. The integration of AI in genomic research for screening and clinical applications will evolve with time to help personalizing chemotherapy, prediction of survival and relapse, aid treatment strategies such as reducing frequency of diagnostic cystoscopies, and clinical decision support, e.g., by predicting immunotherapy response. These factors will ultimately lead to personalized and precision medicine thereby improving patient outcomes.

Prognostic and therapeutic implications of iron-related cell death pathways in acute myeloid leukemia

Acute myeloid leukemia (AML) is a blood cancer that is diverse in terms of its molecular abnormalities and clinical outcomes. Iron homeostasis and cell death pathways play crucial roles in cancer pathogenesis, including AML. The objective of this study was to examine the clinical significance of genes involved in iron-related cell death and apoptotic pathways in AML, with the intention of providing insights that could have prognostic implications and facilitate the development of targeted therapeutic interventions. Gene expression profiles, clinical information, and molecular alterations were integrated from multiple datasets, including TCGA-LAML and GSE71014. Our analysis identified specific molecular subtypes of acute myeloid leukemia (AML) displaying varying outcomes, patterns of immune cell infiltration, and profiles of drug sensitivity for targeted therapies based on the expression of genes involved in iron-related apoptotic and cell death pathways. We further developed a risk model based on four genes, which demonstrated promising prognostic value in both the training and validation cohorts, indicating the potential of this model for clinical decision-making and risk stratification in AML. Subsequently, Western blot analysis showed that the expression levels of C-Myc and CyclinD1 were significantly reduced after CD4 expression levels were knocked down. The findings underscore the potential of iron-related cell death pathways as prognostic biomarkers and therapeutic targets in AML, paving the way for further research aimed at understanding the molecular mechanisms underlying the correlation between iron balance, apoptosis regulation, and immune modulation in the bone marrow microenvironment.

First-line Immune Checkpoint Inhibitor Versus Immune Checkpoint Inhibitor With Chemotherapy for Cisplatin-ineligible Metastatic Urothelial Carcinoma: Evidence From a Real-world, Multicenter Analysis

Immune checkpoint inhibitors (ICIs) are widely used for first-line cisplatin-ineligible patients with metastatic urothelial carcinoma (mUC). However, whether to use ICIs as monotherapy or in combination with chemotherapy is still uncertain. We retrospectively analyzed cisplatin-ineligible patients with mUC who underwent first-line ICI monotherapy or ICI plus chemotherapy at 2 medical centers in Taiwan from 2016 to 2021. We calculated the objective response rate, progression-free survival, and overall survival (OS) using the Kaplan-Meier method and Cox regression model for multivariable analysis. In total, 130 patients were enrolled and categorized into 2 groups: an ICI monotherapy group [immunotherapy (IO), n=101] and an ICI plus noncisplatin chemotherapy group [immunotherapy and chemotherapy (IC), n=29]. The median OS of patients in the IO and IC groups was 19.5 and 9.7 months ( P =0.33). Among patients with high programmed cell death ligand-1-expressing tumors, the median OS was significantly prolonged in the IO group compared with the IC group (not reached vs. 6.3 mo, P =0.02). First-line ICI monotherapy demonstrated robust antitumor activity in cisplatin-ineligible patients with mUC. Combining noncisplatin chemotherapy with ICI did not improve clinical outcomes.

Lower neutrophil-to-lymphocyte ratio and positive programmed cell death ligand-1 expression are favorable prognostic markers in patients treated with pembrolizumab for urothelial carcinoma

BACKGROUND

Immune checkpoint inhibitors (ICIs) are effective in some cancer patients; however, they may show no efficacy in others. Predictive biomarkers are crucial for appropriately selecting the patients who receive ICI therapy. This study aimed to clarify the predictors of disease progression in urothelial carcinoma (UC) patients treated with an ICI, pembrolizumab.

METHODS

We analyzed the response patterns of 50 UC patients who were treated with pembrolizumab, as well as the association between survival and clinicopathological factors. Clinical factors included age, sex, body mass index, clinical courses, laboratory data, metastases, and adverse events. Pathological factors included special variant, squamous differentiation, programmed cell death ligand-1 (PD-L1) expression, CD8-positive lymphocytes density, and CDKN2A/p16 homozygous deletion.

RESULTS

During pembrolizumab treatment, four (8%), 11 (22%), and eight (16%) patients achieved the best-case scenarios of complete response, partial response, and stable disease, respectively. Twenty-seven patients (54%) showed progressive disease. In this study, younger age, lower preoperative neutrophil-to-lymphocyte ratio (NLR), and positive PD-L1 expression were significantly correlated with longer progression-free survival and overall survival. Moreover, lower NLR and positive PD-L1 expression were independently associated with longer OS in multivariate analysis.

CONCLUSIONS

Based on our observations, lower NLR and positive PD-L1 expression may be independent favorable prognostic markers in UC patients treated with pembrolizumab. These results suggest that both host and tumor status can reflect the effectiveness of pembrolizumab among patients with UC.

Revealing potential diagnostic gene biomarkers of septic shock based on machine learning analysis

Background

Sepsis is an inflammatory response caused by infection with pathogenic microorganisms. The body shock caused by it is called septic shock. In view of this, we aimed to identify potential diagnostic gene biomarkers of the disease.

Material and methods

Firstly, mRNAs expression data sets of septic shock were retrieved and downloaded from the GEO (Gene Expression Omnibus) database for differential expression analysis. Functional enrichment analysis was then used to identify the biological function of DEmRNAs (differentially expressed mRNAs). Machine learning analysis was used to determine the diagnostic gene biomarkers for septic shock. Thirdly, RT-PCR (real-time polymerase chain reaction) verification was performed. Lastly, GSE65682 data set was utilized to further perform diagnostic and prognostic analysis of identified superlative diagnostic gene biomarkers.

Results

A total of 843 DEmRNAs, including 458 up-regulated and 385 down-regulated DEmRNAs were obtained in septic shock. 15 superlative diagnostic gene biomarkers (such as RAB13, KIF1B, CLEC5A, FCER1A, CACNA2D3, DUSP3, HMGN3, MGST1 and ARHGEF18) for septic shock were identified by machine learning analysis. RF (random forests), SVM (support vector machine) and DT (decision tree) models were used to construct classification models. The accuracy of the DT, SVM and RF models were very high. Interestingly, the RF model had the highest accuracy. It is worth mentioning that ARHGEF18 and FCER1A were related to survival. CACNA2D3 and DUSP3 participated in MAPK signaling pathway to regulate septic shock.

Conclusion

Identified diagnostic gene biomarkers may be helpful in the diagnosis and therapy of patients with septic shock.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07056-4.

Immune Signature-Based Risk Stratification and Prediction of Immunotherapy Efficacy for Bladder Urothelial Carcinoma

Immune-related genes (IRGs) are closely related to tumor progression and the immune microenvironment. Few studies have investigated the effect of tumor immune microenvironment on the survival and response to immune checkpoint inhibitors of patients with bladder urothelial carcinoma (BLCA). We constructed two IRG-related prognostic signatures based on gene–immune interaction for predicting risk stratification and immunotherapeutic responses. We also verified their predictive ability on internal and overall data sets. Patients with BLCA were divided into high- and low-risk groups. The high-risk group had poor survival, enriched innate immune-related cell subtypes, low tumor mutation burden, and poor response to anti-PD-L1 therapy. Our prognostic signatures can be used as reliable prognostic biomarkers, which may be helpful to screen the people who will benefit from immunotherapy and guide the clinical decision-making of patients with BLCA.

Potential role of a three-gene signature in predicting diagnosis in patients with myocardial infarction

In this study, we evaluated the diagnostic value of key genes in myocardial infarction (MI) based on data from the Gene Expression Omnibus (GEO) database. We used data from GSE66360 to identify a set of significant differentially expressed genes (DEGs) between MI and healthy controls. Logistic regression, least absolute shrinkage and selection operator (LASSO) regression, support vector machine recursive feature elimination (SVM-RFE), and SignalP 3.0 server were used to identify the potential role of genes in predicting diagnosis in patients with MI. Principal component analysis (PCA), receiver operating characteristic (ROC) curve analyses, area under the curve (AUC) analyses, and C-index were used to estimate the diagnostic value of genes in patients with MI. The association was validated using six other independent data sets. Subsequently, bioinformatics analysis was conducted based on the aforementioned potential genes. A meta-analysis was performed to evaluate the diagnostic value of the genes in MI. Forty-four DEGs were selected from the GSE66360 dataset. A three-gene signature consisting of CCL20, IL1R2, and ITLN1 could effectively distinguish patients with MI. The three-gene signature was validated in seven independent cohorts. Functional enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to reveal the involvement of the three-gene signature in inflammation-related biological processes and pathways. Moreover, diagnostic meta-analysis results of the three-gene signature showed that the pooled sensitivity, specificity, and AUC for MI were 0.80, 0.90, and 0.93, respectively. These results suggest that the three-gene signature is a novel candidate biomarker for distinguishing MI from healthy controls.