Multimodal data fusion AI model uncovers tumor microenvironment immunotyping heterogeneity and enhanced risk stratification of breast cancer

Abstract

Breast cancer is the leading cancer among women, with a significant number experiencing recurrence and metastasis, thereby reducing survival rates. This study focuses on the role of long noncoding RNAs (lncRNAs) in breast cancer immunotherapy response. We conducted an analysis involving 1027 patients from Sun Yat-sen Memorial Hospital, Sun Yat-sen University, and The Cancer Genome Atlas, utilizing RNA sequencing and pathology whole-slide images. We employed unsupervised clustering to identify distinct lncRNA expression patterns and developed an AI-based pathology model using convolutional neural networks to predict immune–metabolic subtypes. Additionally, we created a multimodal model integrating lncRNA data, immune-cell scores, clinical information, and pathology images for prognostic prediction. Our findings revealed four unique immune–metabolic subtypes, and the AI model demonstrated high predictive accuracy, highlighting the significant impact of lncRNAs on antitumor immunity and metabolic states within the tumor microenvironment. The AI-based pathology model, DeepClinMed-IM, exhibited high accuracy in predicting these subtypes. Additionally, the multimodal model, DeepClinMed-PGM, integrating pathology images, lncRNA data, immune-cell scores, and clinical information, showed superior prognostic performance. In conclusion, these AI models provide a robust foundation for precise prognostication and the identification of potential candidates for immunotherapy, advancing breast cancer research and treatment strategies.

Keywords

artificial intelligence / breast cancer / immune–metabolic subtypes / prognostic prediction / tumor microenvironment

References

[1] Waks AG, Winer EP. Breast cancer treatment. JAMA. 2019; 321(3): 288.

[2] Derks MGM, van de Velde CJH. Neoadjuvant chemotherapy in breast cancer: more than just downsizing. Lancet Oncol. 2018; 19(1): 2-3.

[3] Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022; 72(1): 7-33.

[4] Fulton-Ward T, Middleton G. The impact of genomic context on outcomes of solid cancer patients treated with genotype-matched targeted therapies: a comprehensive review. Ann Oncol. 2023; 34(12): 1113-1130.

[5] Ye F, Dewanjee S, Li Y, et al. Advancements in clinical aspects of targeted therapy and immunotherapy in breast cancer. Mol Cancer. 2023; 22(1): 105.

[6] Kansara S, Singh A, Badal AK, et al. The emerging regulatory roles of non-coding RNAs associated with glucose metabolism in breast cancer. Semin Cancer Biol. 2023; 95: 1-12.

[7] Miraghel SA, Ebrahimi N, Khani L, et al. Crosstalk between non-coding RNAs expression profile, drug resistance and immune response in breast cancer. Pharmacol Res. 2022; 176: 106041.

[8] Yang J, Liu F, Wang Y, Qu L, Lin A. LncRNAs in tumor metabolic reprogramming and immune microenvironment remodeling. Cancer Lett. 2022; 543: 215798.

[9] Yu Y, Zhang W, Li A, et al. Association of long noncoding RNA biomarkers with clinical immune subtype and prediction of immunotherapy response in patients with cancer. JAMA Netw Open. 2020; 3(4): e202149.

[10] Lin Q, Liu T, Wang X, et al. Long noncoding RNA HITT coordinates with RGS2 to inhibit PD-L1 translation in T cell immunity. J Clin Invest. 2023; 133(11): e162951.

[11] Toker J, Iorgulescu JB, Ling AL, et al. Clinical importance of the lncRNA NEAT1 in cancer patients treated with immune checkpoint inhibitors. Clin Cancer Res. 2023; 29(12): 2226-2238.

[12] Hanahan D. Hallmarks of cancer: new dimensions. Cancer Discov. 2022; 12(1): 31-46.

[13] Zeng W, Li F, Jin S, Ho P-C, Liu P-S, Xie X. Functional polarization of tumor-associated macrophages dictated by metabolic reprogramming. Journal of Experimental (Clinical Cancer Research). 2023; 42(1): 245.

[14] Borde S, Matosevic S. Metabolic adaptation of NK cell activity and behavior in tumors: challenges and therapeutic opportunities. Trends Pharmacol Sci. 2023; 44(11): 832-848.

[15] His M, Gunter MJ, Keski-Rahkonen P, Rinaldi S. Application of metabolomics to epidemiologic studies of breast cancer: new perspectives for etiology and prevention. J Clin Oncol. 2024; 42(1): 103-115.

[16] Guo Y, Wang R, Shi J, et al. Machine learning-based integration develops a metabolism-derived consensus model for improving immunotherapy in pancreatic cancer. J Immunother Cancer. 2023; 11(9): e007466.

[17] Shi J-Y, Wang X, Ding G-Y, et al. Exploring prognostic indicators in the pathological images of hepatocellular carcinoma based on deep learning. Gut. 2020; 70(5): 951-961.

[18] Wagner SJ, Reisenbüchler D, West NP, et al. Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study. Cancer Cell. 2023; 41(9): 1650-1661.e4.

[19] Zeng Q, Klein C, Caruso S, et al. Artificial intelligence-based pathology as a biomarker of sensitivity to atezolizumab–bevacizumab in patients with hepatocellular carcinoma: a multicentre retrospective study. Lancet Oncol. 2023; 24(12): 1411-1422.

[20] Lipkova J, Chen RJ, Chen B, et al. Artificial intelligence for multimodal data integration in oncology. Cancer Cell. 2022; 40(10): 1095-1110.

[21] Yu Y, He Z, Ouyang J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study. eBioMedicine. 2021; 69: 103460.

[22] Zhang Q, Xu Y, Kang S, et al. A novel computational framework for integrating multidimensional data to enhance accuracy in predicting the prognosis of colorectal cancer. MedComm—Future Medicine. 2022; 1(2): e27.

[23] ElKarami B, Alkhateeb A, Qattous H, Alshomali L, Shahrrava B. Multi-omics data integration model based on UMAP embedding and convolutional neural network. Cancer Inform. 2022; 21: 11769351221124205.

[24] Zhou L, Rueda M, Alkhateeb A. Classification of breast cancer nottingham prognostic index using high-dimensional embedding and residual neural network. Cancers (Basel). 2022; 14(4): 934.

[25] Loe AKH, Zhu L, Kim T-H. Chromatin and noncoding RNA-mediated mechanisms of gastric tumorigenesis. Experimental (Molecular Medicine). 2023; 55(1): 22-31.

[26] Hashemi M, Hajimazdarany S, Mohan CD, et al. Long non-coding RNA/epithelial-mesenchymal transition axis in human cancers: tumorigenesis, chemoresistance, and radioresistance. Pharmacol Res. 2022; 186: 106535.

[27] Ahmad M, Weiswald L-B, Poulain L, Denoyelle C. Meryet-Figuiere M. Involvement of lncRNAs in cancer cells migration, invasion and metastasis: cytoskeleton and ECM crosstalk. Journal of Experimental (Clinical Cancer Research). 2023; 42(1): 173.

[28] Wang T, Gao Y. Metabolic insights into tumor pathogenesis: unveiling pan-cancer metabolism and the potential of untargeted metabolomics. MedComm—Future Medicine. 2023; 2(3): e59.

[29] Johnson MO, Wolf MM, Madden MZ, et al. Distinct regulation of Th17 and Th1 cell differentiation by glutaminase-dependent metabolism. Cell. 2018; 175(7): 1780-1795.e19.

[30] Vander Heiden MG, DeBerardinis RJ. Understanding the intersections between metabolism and cancer biology. Cell. 2017; 168(4): 657-669.

[31] Koppenol WH, Bounds PL, Dang CV. Otto Warburg’s contributions to current concepts of cancer metabolism. Nat Rev Cancer. 2011; 11(5): 325-337.

[32] Mak TW, Grusdat M, Duncan GS, et al. Glutathione primes T cell metabolism for inflammation. Immunity. 2017; 46(4): 675-689.

[33] Ma EH, Bantug G, Griss T, et al. Serine is an essential metabolite for effector T cell expansion. Cell Metab. 2017; 25(2): 345-357.

[34] Zhao J, Sun Z, Yu Y, et al. Radiomic and clinical data integration using machine learning predict the efficacy of anti-PD-1 antibodies-based combinational treatment in advanced breast cancer: a multicentered study. J Immunother Cancer. 2023; 11(5): e006514.

[35] Yu Y, Ren W, He Z, et al. Machine learning radiomics of magnetic resonance imaging predicts recurrence-free survival after surgery and correlation of LncRNAs in patients with breast cancer: a multicenter cohort study. Breast Cancer Res. 2023; 25(1): 132.

[36] Dacic S, Travis WD, Giltnane JM, et al. Artificial intelligence-powered assessment of pathologic response to neoadjuvant atezolizumab in patients with NSCLC: results from the LCMC3 study. J Thorac Oncol. 2024; 19(5): 719-731.

[37] Koido M, Hon C-C, Koyama S, et al. Prediction of the cell-type-specific transcription of non-coding RNAs from genome sequences via machine learning. Nature Biomedical Engineering. 2022; 7(6): 830-844.

[38] Jha A, Quesnel-Vallières M, Wang D, Thomas-Tikhonenko A, Lynch KW, Barash Y. Identifying common transcriptome signatures of cancer by interpreting deep learning models. Genome Biol. 2022; 23(1): 117.

[39] Addala V, Newell F, Pearson JV, et al. Computational immunogenomic approaches to predict response to cancer immunotherapies. Nat Rev Clin Oncol. 2023; 21(1): 28-46.

[40] Yang J, Chen Y, Jing Y, Green MR, Han L. Advancing CAR T cell therapy through the use of multidimensional omics data. Nat Rev Clin Oncol. 2023; 20(4): 211-228.

[41] He X, Liu X, Zuo F, Shi H, Jing J. Artificial intelligence-based multi-omics analysis fuels cancer precision medicine. Semin Cancer Biol. 2023; 88: 187-200.

[42] Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015; 350: g7594.

[43] Grossman RL, Heath AP, Ferretti V, et al. Toward a shared vision for cancer genomic data. N Engl J Med. 2016; 375(12): 1109-1112.

[44] Gradishar WJ, Moran MS, Abraham J, et al. NCCN Guidelines® insights: breast cancer, version 4.2023. J Natl Compr Canc Netw. 2023; 21(6): 594-608.

[45] Lu MY, Williamson DFK, Chen TY, Chen RJ, Barbieri M, Mahmood F. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomed Eng. 2021; 5(6): 555-570.

[46] Ritchie ME, Phipson B, Wu D, et al. limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 2015; 43(7): e47-e47.

[47] Love MI, Huber W, Anders S. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 2014; 15(12): 550.

[48] Robinson MD, McCarthy DJ, Smyth GK. edgeR: a Bioconductor package for differential expression analysis of digital gene expression data. Bioinformatics. 2009; 26(1): 139-140.

[49] Wilkerson MD, Hayes DN. ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking. Bioinformatics. 2010; 26(12): 1572-1573.

[50] Wu T, Hu E, Xu S, et al. clusterProfiler 4.0: a universal enrichment tool for interpreting omics data. The Innovation. 2021; 2(3): 100141.

[51] Barbie DA, Tamayo P, Boehm JS, et al. Systematic RNA interference reveals that oncogenic KRAS-driven cancers require TBK1. Nature. 2009; 462(7269): 108-112.

[52] Liu Q, Nie R, Li M, et al. Identification of subtypes correlated with tumor immunity and immunotherapy in cutaneous melanoma. Comput Struct Biotechnol J. 2021; 19: 4472-4485.

[53] Tamborero D, Gonzalez-Perez A, Lopez-Bigas N. OncodriveCLUST: exploiting the positional clustering of somatic mutations to identify cancer genes. Bioinformatics. 2013; 29(18): 2238-2244.

[54] He K, Zhang X, Ren S, Sun J, Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition 2016: 770-778.

[55] Lu MY, Chen TY, Williamson DFK, et al. AI-based pathology predicts origins for cancers of unknown primary. Nature. 2021; 594(7861): 106-110.

[56] Ilse M, Tomczak JM, Welling M, Attention-based Deep Multiple Instance Learning. 2018:

[57] Dauphin YN, Fan A, Auli M, Grangier D, Language modeling with gated convolutional networks. presented at: Proceedings of the 34th International Conference on Machine Learning—Volume 70; 2017; Sydney, NSW, Australia.

[58] Clevert D-A, Unterthiner T, Hochreiter S, Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv: Learning. 2015;

[59] Jang E, Gu SS, Poole B, Categorical Reparameterization with Gumbel-Softmax. ArXiv. 2016;abs/1611.01144.

RIGHTS & PERMISSIONS

2024 The Author(s). MedComm published by Sichuan International Medical Exchange & Promotion Association (SCIMEA) and John Wiley & Sons Australia, Ltd.