Deep Neural Network Modeling Identifies Biomarkers of Response to Immune-checkpoint Therapy

Virtual patient analysis identifies strategies to improve the performance of predictive biomarkers for PD-1 blockade

Patients with metastatic triple-negative breast cancer (TNBC) show variable responses to PD-1 inhibition. Efficient patient selection by predictive biomarkers would be desirable, but is hindered by the limited performance of existing biomarkers. Here, we leveraged in-silico patient cohorts generated using a quantitative systems pharmacology model of metastatic TNBC, informed by transcriptomic and clinical data, to explore potential ways to improve patient selection. We tested 90 biomarker candidates, including various cellular and molecular species, by a cutoff-based biomarker testing algorithm combined with machine learning-based feature selection. Combinations of pre-treatment biomarkers improved the specificity compared to single biomarkers at the cost of reduced sensitivity. On the other hand, early on-treatment biomarkers, such as the relative change in tumor diameter from baseline measured at two weeks after treatment initiation, achieved remarkably higher sensitivity and specificity. Further, blood-based biomarkers had a comparable ability to tumor- or lymph node-based biomarkers in identifying a subset of responders, potentially suggesting a less invasive way for patient selection.

BERNN: Enhancing classification of Liquid Chromatography Mass Spectrometry data with batch effect removal neural networks

Liquid Chromatography Mass Spectrometry (LC-MS) is a powerful method for profiling complex biological samples. However, batch effects typically arise from differences in sample processing protocols, experimental conditions, and data acquisition techniques, significantly impacting the interpretability of results. Correcting batch effects is crucial for the reproducibility of omics research, but current methods are not optimal for the removal of batch effects without compressing the genuine biological variation under study. We propose a suite of Batch Effect Removal Neural Networks (BERNN) to remove batch effects in large LC-MS experiments, with the goal of maximizing sample classification performance between conditions. More importantly, these models must efficiently generalize in batches not seen during training. A comparison of batch effect correction methods across five diverse datasets demonstrated that BERNN models consistently showed the strongest sample classification performance. However, the model producing the greatest classification improvements did not always perform best in terms of batch effect removal. Finally, we show that the overcorrection of batch effects resulted in the loss of some essential biological variability. These findings highlight the importance of balancing batch effect removal while preserving valuable biological diversity in large-scale LC-MS experiments.

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.

Mapping the tumor microenvironment in clear cell renal carcinoma by single-cell transcriptome analysis

Introduction: Clear cell renal cell carcinoma (ccRCC) is associated with unfavorable clinical outcomes. To identify viable therapeutic targets, a comprehensive understanding of intratumoral heterogeneity is crucial. In this study, we conducted bioinformatic analysis to scrutinize single-cell RNA sequencing data of ccRCC tumor and para-tumor samples, aiming to elucidate the intratumoral heterogeneity in the ccRCC tumor microenvironment (TME). Methods: A total of 51,780 single cells from seven ccRCC tumors and five para-tumor samples were identified and grouped into 11 cell lineages using bioinformatic analysis. These lineages included tumor cells, myeloid cells, T-cells, fibroblasts, and endothelial cells, indicating a high degree of heterogeneity in the TME. Copy number variation (CNV) analysis was performed to compare CNV frequencies between tumor and normal cells. The myeloid cell population was further re-clustered into three major subgroups: monocytes, macrophages, and dendritic cells. Differential expression analysis, gene ontology, and gene set enrichment analysis were employed to assess inter-cluster and intra-cluster functional heterogeneity within the ccRCC TME. Results: Our findings revealed that immune cells in the TME predominantly adopted an inflammatory suppression state, promoting tumor cell growth and immune evasion. Additionally, tumor cells exhibited higher CNV frequencies compared to normal cells. The myeloid cell subgroups demonstrated distinct functional properties, with monocytes, macrophages, and dendritic cells displaying diverse roles in the TME. Certain immune cells exhibited pro-tumor and immunosuppressive effects, while others demonstrated antitumor and immunostimulatory properties. Conclusion: This study contributes to the understanding of intratumoral heterogeneity in the ccRCC TME and provides potential therapeutic targets for ccRCC treatment. The findings emphasize the importance of considering the diverse functional roles of immune cells in the TME for effective therapeutic interventions.

Enhancing Classification of liquid chromatography mass spectrometry data with Batch Effect Removal Neural Networks (BERNN)

Liquid Chromatography Mass Spectrometry (LC-MS) is a powerful method for profiling complex biological samples. However, batch effects typically arise from differences in sample processing protocols, experimental conditions and data acquisition techniques, significantlyimpacting the interpretability of results. Correcting batch effects is crucial for the reproducibility of proteomics research, but current methods are not optimal for removal of batch effects without compressing the genuine biological variation under study. We propose a suite of Batch Effect Removal Neural Networks (BERNN) to remove batch effects in large LC-MS experiments, with the goal of maximizing sample classification performance between conditions. More importantly, these models must efficiently generalize in batches not seen during training. Comparison of batch effect correction methods across three diverse datasets demonstrated that BERNN models consistently showed the strongest sample classification performance. However, the model producing the greatest classification improvements did not always perform best in terms of batch effect removal. Finally, we show that overcorrection of batch effects resulted in the loss of some essential biological variability. These findings highlight the importance of balancing batch effect removal while preserving valuable biological diversity in large-scale LC-MS experiments.