1
|
Arulraj T, Wang H, Deshpande A, Varadhan R, Emens LA, Jaffee EM, Fertig EJ, Santa-Maria CA, Popel AS. Virtual patient analysis identifies strategies to improve the performance of predictive biomarkers for PD-1 blockade. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.05.21.595235. [PMID: 38826266 PMCID: PMC11142158 DOI: 10.1101/2024.05.21.595235] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2024]
Abstract
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.
Collapse
|
2
|
Pelletier SJ, Leclercq M, Roux-Dalvai F, de Geus MB, Leslie S, Wang W, Lam TT, Nairn AC, Arnold SE, Carlyle BC, Precioso F, Droit A. BERNN: Enhancing classification of Liquid Chromatography Mass Spectrometry data with batch effect removal neural networks. Nat Commun 2024; 15:3777. [PMID: 38710683 PMCID: PMC11074280 DOI: 10.1038/s41467-024-48177-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Accepted: 04/24/2024] [Indexed: 05/08/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Simon J Pelletier
- Computational Biology Laboratory, CHU de Québec - Université Laval Research Center, Québec City, QC, Canada
| | - Mickaël Leclercq
- Computational Biology Laboratory, CHU de Québec - Université Laval Research Center, Québec City, QC, Canada
| | - Florence Roux-Dalvai
- Computational Biology Laboratory, CHU de Québec - Université Laval Research Center, Québec City, QC, Canada
- Proteomics Platform, CHU de Québec - Université Laval Research Center, Québec City, QC, Canada
| | - Matthijs B de Geus
- Massachusetts General Hospital Department of Neurology, Charlestown, MA, USA
- Leiden University Medical Center, Leiden, The Netherlands
| | - Shannon Leslie
- Yale Department of Psychiatry, New Haven, CT, USA
- Janssen Pharmaceuticals, San Diego, CA, USA
| | - Weiwei Wang
- Keck MS & Proteomics Resource, Yale School of Medicine, New Haven, CT, USA
| | - TuKiet T Lam
- Keck MS & Proteomics Resource, Yale School of Medicine, New Haven, CT, USA
- Yale School of Medicine, Department of Molecular Biophysics and Biochemistry, New Haven, CT, USA
| | | | - Steven E Arnold
- Massachusetts General Hospital Department of Neurology, Charlestown, MA, USA
| | - Becky C Carlyle
- Massachusetts General Hospital Department of Neurology, Charlestown, MA, USA
- Oxford University Department of Physiology Anatomy and Genetics, Oxford, UK
- Kavli Institute for Nanoscience Discovery, Oxford, UK
| | - Frédéric Precioso
- Université Côte d'Azur, CNRS, INRIA, I3S, Sophia Antipolis, Nice, France
| | - Arnaud Droit
- Computational Biology Laboratory, CHU de Québec - Université Laval Research Center, Québec City, QC, Canada.
- Proteomics Platform, CHU de Québec - Université Laval Research Center, Québec City, QC, Canada.
| |
Collapse
|
3
|
Li Y, Wu X, Fang D, Luo Y. Informing immunotherapy with multi-omics driven machine learning. NPJ Digit Med 2024; 7:67. [PMID: 38486092 PMCID: PMC10940614 DOI: 10.1038/s41746-024-01043-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Accepted: 02/14/2024] [Indexed: 03/18/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Yawei Li
- Department of Preventive Medicine, Northwestern University, Feinberg School of Medicine, Chicago, IL, 60611, USA
- Center for Collaborative AI in Healthcare, Northwestern University, Feinberg School of Medicine, Chicago, IL, 60611, USA
| | - Xin Wu
- Department of Medicine, University of Illinois at Chicago, Chicago, IL, 60612, USA
| | - Deyu Fang
- Department of Pathology, Northwestern University Feinberg School of Medicine, Chicago, IL, 60611, USA
| | - Yuan Luo
- Department of Preventive Medicine, Northwestern University, Feinberg School of Medicine, Chicago, IL, 60611, USA.
- Center for Collaborative AI in Healthcare, Northwestern University, Feinberg School of Medicine, Chicago, IL, 60611, USA.
| |
Collapse
|
4
|
Wang Y, Wang Y, Liu B, Gao X, Li Y, Li F, Zhou H. Mapping the tumor microenvironment in clear cell renal carcinoma by single-cell transcriptome analysis. Front Genet 2023; 14:1207233. [PMID: 37533434 PMCID: PMC10392130 DOI: 10.3389/fgene.2023.1207233] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Accepted: 07/06/2023] [Indexed: 08/04/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Yuxiong Wang
- Department of Urology, The First Hospital of Jilin University, Jilin, China
| | - Yishu Wang
- Key Laboratory of Pathobiology, Ministry of Education, Jilin University, Jilin, China
| | - Bin Liu
- Department of Urology, The First Hospital of Jilin University, Jilin, China
| | - Xin Gao
- Department of Urology, The First Hospital of Jilin University, Jilin, China
| | - Yunkuo Li
- Department of Urology, The First Hospital of Jilin University, Jilin, China
| | - Faping Li
- Department of Urology, The First Hospital of Jilin University, Jilin, China
| | - Honglan Zhou
- Department of Urology, The First Hospital of Jilin University, Jilin, China
| |
Collapse
|
5
|
Droit A, Pelletier S, Leclerq M, Roux-Dalvai F, de Geus M, Leslie S, Wang W, Lam T, Nairn A, Arnold S, Carlyle B, Precioso F. Enhancing Classification of liquid chromatography mass spectrometry data with Batch Effect Removal Neural Networks (BERNN). RESEARCH SQUARE 2023:rs.3.rs-3112514. [PMID: 37461653 PMCID: PMC10350225 DOI: 10.21203/rs.3.rs-3112514/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/28/2023]
Abstract
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.
Collapse
Affiliation(s)
- Arnaud Droit
- Centre de Recherche du CHU de Québec - Université Laval, Axe Endocrinologie et Néphrologie, Québec, Canada
| | | | | | | | | | | | - Weiwei Wang
- 7. Keck MS & Proteomics Resource, Yale School of Medicine
| | - TuKiet Lam
- 7. Keck MS & Proteomics Resource, Yale School of Medicine
| | | | - Steven Arnold
- 3. Massachusetts General Hospital Department of Neurology
| | - Becky Carlyle
- 3. Massachusetts General Hospital Department of Neurology
| | | |
Collapse
|
6
|
Ma A, Wang J, Xu D, Ma Q. Deep learning analysis of single-cell data in empowering clinical implementation. Clin Transl Med 2022; 12:e950. [PMID: 35858171 PMCID: PMC9299757 DOI: 10.1002/ctm2.950] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Revised: 06/07/2022] [Accepted: 06/13/2022] [Indexed: 11/12/2022] Open
Affiliation(s)
- Anjun Ma
- Department of Biomedical Informatics, College of MedicineThe Ohio State UniversityColumbusOhioUSA
- Pelotonia Institute for Immuno‐Oncology, The James Comprehensive Cancer CenterThe Ohio State UniversityColumbusOhioUSA
| | - Juexin Wang
- Department of Electrical Engineering and Computer Science, and Christopher S. Bond Life Sciences CenterUniversity of MissouriColumbiaMissouriUSA
| | - Dong Xu
- Department of Electrical Engineering and Computer Science, and Christopher S. Bond Life Sciences CenterUniversity of MissouriColumbiaMissouriUSA
| | - Qin Ma
- Department of Biomedical Informatics, College of MedicineThe Ohio State UniversityColumbusOhioUSA
- Pelotonia Institute for Immuno‐Oncology, The James Comprehensive Cancer CenterThe Ohio State UniversityColumbusOhioUSA
| |
Collapse
|