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 ...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.展开更多
BACKGROUND Colorectal cancer(CRC)is the second leading cause of cancer-related death,lar-gely due to limited treatment options in advanced stages.Genomic alterations in advanced CRC(aCRC)are complex and not fully char...BACKGROUND Colorectal cancer(CRC)is the second leading cause of cancer-related death,lar-gely due to limited treatment options in advanced stages.Genomic alterations in advanced CRC(aCRC)are complex and not fully characterized,with only 30%of patients benefiting from targeted therapies.AIM To investigate the molecular heterogeneity of primary aCRC in order to identify clinically relevant genomic alterations.METHODS We conducted a retrospective molecular analysis of 73 consecutive patients with histologically confirmed primary aCRC(stage pT4a-b).All molecular findings were correlated with available clinicopathological data.In addition,we performed RESULTS Genetic abnormalities identified in primary tumors were most frequently mutations in tumor protein p53(58%of cases),Kirsten rat sarcoma viral oncogene homolog(52%),phosphatidylinositol-4,5-bisphosphate 3-kinase catalytic subunit alpha(25%),B-Raf kinase(11%)and fibroblast growth factor receptor 3(8%),as well as R-spondin 3(RSPO3)fusions(8%).Alterations in the tumor protein p53 and neuroblastoma RAS viral oncogene homolog genes were predominantly observed in tumors from the left colon,whereas B-Raf kinase mutations and RSPO3 fusions were more frequently detected in the right or transverse colon.We also show a strong association between the presence of RSPO3 rearrangements and patients with small tumors,normal carcinoembryonic antigen levels,and microsatellite stable tumors.Furthermore,aCRC patients with protein tyrosine phosphatase receptor type k::RSPO3 fusions exhibited a higher mortality rate.Elevated RSPO3 gene expression levels were also significantly correlated with poorer OS across two large,independent CRC cohorts.CONCLUSION This study identifies a relatively high incidence of RSPO3 rearrangements in aCRC and a strong association with clinical features.Furthermore,we find that RSPO3 fusions are associated with poorer OS.展开更多
基金Supported by This work was supported by the Department of Defense(DoD)BCRP,No.BC190820the National Cancer Institute(NCI)at the National Institutes of Health(NIH),No.R01CA184476+1 种基金MCIN/AEI/10.13039/501100011039,No.PID2020-118527RB-I00,and No.PDC2021-121735-I00the“European Union Next Generation EU/PRTR.”the Regional Government of Castile and León,No.CSI144P20.Lawrence Berkeley National Laboratory(LBNL)is a multi-program national laboratory operated by the University of California for the DOE under contract DE AC02-05CH11231.
文摘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.
文摘BACKGROUND Colorectal cancer(CRC)is the second leading cause of cancer-related death,lar-gely due to limited treatment options in advanced stages.Genomic alterations in advanced CRC(aCRC)are complex and not fully characterized,with only 30%of patients benefiting from targeted therapies.AIM To investigate the molecular heterogeneity of primary aCRC in order to identify clinically relevant genomic alterations.METHODS We conducted a retrospective molecular analysis of 73 consecutive patients with histologically confirmed primary aCRC(stage pT4a-b).All molecular findings were correlated with available clinicopathological data.In addition,we performed RESULTS Genetic abnormalities identified in primary tumors were most frequently mutations in tumor protein p53(58%of cases),Kirsten rat sarcoma viral oncogene homolog(52%),phosphatidylinositol-4,5-bisphosphate 3-kinase catalytic subunit alpha(25%),B-Raf kinase(11%)and fibroblast growth factor receptor 3(8%),as well as R-spondin 3(RSPO3)fusions(8%).Alterations in the tumor protein p53 and neuroblastoma RAS viral oncogene homolog genes were predominantly observed in tumors from the left colon,whereas B-Raf kinase mutations and RSPO3 fusions were more frequently detected in the right or transverse colon.We also show a strong association between the presence of RSPO3 rearrangements and patients with small tumors,normal carcinoembryonic antigen levels,and microsatellite stable tumors.Furthermore,aCRC patients with protein tyrosine phosphatase receptor type k::RSPO3 fusions exhibited a higher mortality rate.Elevated RSPO3 gene expression levels were also significantly correlated with poorer OS across two large,independent CRC cohorts.CONCLUSION This study identifies a relatively high incidence of RSPO3 rearrangements in aCRC and a strong association with clinical features.Furthermore,we find that RSPO3 fusions are associated with poorer OS.
