iCEMIGE: Integration of CEll-morphometrics, MIcrobiome, and GEne biomarker signatures for risk stratification in breast cancers

Abstract

BACKGROUND The development of precision medicine is essential for personalized treatment and improved clinical outcome, whereas biomarkers are critical for the success of precision therapies. AIM To investigate whether iCEMIGE (integration of CEll-morphometrics, MIcro biome, and GEne biomarker signatures) improves risk stratification of breast cancer (BC) patients. METHODS We used our recently developed machine learning technique to identify cellular morphometric biomarkers (CMBs) from the whole histological slide images in The Cancer Genome Atlas (TCGA) breast cancer (TCGA-BRCA) cohort. Multivariate Cox regression was used to assess whether cell-morphometrics prognosis score (CMPS) and our previously reported 12-gene expression prognosis score (GEPS) and 15-microbe abundance prognosis score (MAPS) were independent prognostic factors. iCEMIGE was built upon the sparse representation learning technique. The iCEMIGE scoring model performance was measured by the area under the receiver operating characteristic curve compared to CMPS, GEPS, or MAPS alone. Nomogram models were created to predict overall survival (OS) and progress-free survival (PFS) rates at 5- and 10-year in the TCGA-BRCA cohort. RESULTS We identified 39 CMBs that were used to create a CMPS system in BCs. CMPS, GEPS, and MAPS were found to be significantly independently associated with OS. We then established an iCEMIGE scoring system for risk stratification of BC patients. The iGEMIGE score has a significant prognostic value for OS and PFS independent of clinical factors (age, stage, and estrogen and progesterone receptor status) and PAM50-based molecular subtype. Importantly, the iCEMIGE score significantly increased the power to predict OS and PFS compared to CMPS, GEPS, or MAPS alone. CONCLUSION Our study demonstrates a novel and generic artificial intelligence framework for multimodal data integration toward improving prognosis risk stratification of BC patients, which can be extended to other types of cancer.

Recent Advancements in Deep Learning Using Whole Slide Imaging for Cancer Prognosis

“…The integration of multimodal data, such as combining WSIs with genomic, transcriptomic, or clinical data, has been shown to enhance predictive power [ 41 , 65 ]. However, such integration poses its own challenges, including data harmonization, dealing with missing data, and developing models that can effectively learn from different data types.…”

“…In addition to the challenges mentioned above, the computational resources required to train deep learning models on WSIs constitute another hurdle [ 38 , 41 ]. Due to the high-resolution nature of WSIs, the size of these images can be enormous, leading to increased memory requirements and extended processing times.…”

“…For instance, Liu et al [ 65 ] developed cellular morphometric subtypes (CMS) using artificial intelligence for lower-grade gliomas (LGG), which independently predicted overall survival. Mao et al [ 41 ] developed iCEMIGE, an integrative model combining cell morphometrics, microbiome, and gene biomarker signatures.…”

Pan-cancer evaluation of clinical value of mitotic network activity index (MNAI) and its predictive value for immunotherapy

“…CMSs in these two cohorts have independent clinical values and underlying molecular associations ( 18 , 19 ). Given these pre-established CMSs, the multimodal integration and evaluation were based on multivariate CoxPH model ( 20 ). Specifically, concordance index (C-index) was used to evaluate the performance of the CMS, MNAI, and integrated models with 1000 bootstrapping iterations and 80% sampling rate per iteration.…”

A review of machine learning methods for cancer characterization from microbiome data

“…Until recently, most of the applications of ML in the field of microbiome and cancer have focused on colorectal cancer and the gut microbiome [27][28][29] . However, recent studies using ML approaches have suggested biomarkers for cancer detection, disease prognosis, and response to treatment in different cancer types based on the tumor, gut, and oral microbiomes 18,[30][31][32][33][34][35] . Despite their promising results, these approaches require further improvement in the accuracy of models before widespread use and translation of the findings into the clinic.…”