MIRS: An AI scoring system for predicting the prognosis and therapy of breast cancer

Chen Huang; Min Deng; Dongliang Leng; Baoqing Sun; Peiyan Zheng; Xiaohua Douglas Zhang

doi:10.1016/j.isci.2023.108322

MIRS: An AI scoring system for predicting the prognosis and therapy of breast cancer

Chen Huang, Min Deng, Dongliang Leng, Baoqing Sun, Peiyan Zheng, Xiaohua Douglas Zhang

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Tumor-infiltrating immune cells (TIICs) and metastasis are crucial characteristics for tumorigenesis. However, the potential role of their combination in breast cancer (BRCA) remains elusive. Herein, on the basis of quantifying TIICs and tumor metastasis together, we established a precise prognostic scoring system named metastatic and immunogenomic risk score (MIRS) using a neural network model. MIRS showed better performance when compared with other published signatures. MIRS stratifies patients into a high risk subtype (MIRS^high) and a low risk subtype (MIRS^low). The MIRS^high patients exhibit significantly lower survival rate compared with MIRS^low patients (P<0.0001), higher response to chemotherapy, but lower response to immunotherapy. Conversely, higher infiltration level of TIICs and significantly prolonged survival (P=0.029) are observed in MIRS^low patients, indicating sensitive response in immunotherapy. This work presents a promising indicator to guide treatment options of the BRCA population and provides a predicted webtool that is almost universally applicable to BRCA patients.

Original language	English
Article number	108322
Journal	iScience
Volume	26
Issue number	11
DOIs	https://doi.org/10.1016/j.isci.2023.108322
State	Published - Nov 17 2023

Bibliographical note

Publisher Copyright:
© 2023 The Author(s)

Funding

This work was supported by The Science and Technology Development Fund, Macau SAR 462 and Dr. Neher's Biophysics Laboratory for Innovative Drug Discovery, State Key Laboratory of Quality Research in Chinese Medicine in Macau University of Science and Technology, Macau, China (File no. 0020/2021/A, 002/2023/ALC, SKL-QRCM (MUST)-2020-2022), and General Research Grants of Macau University of Science and Technology, Macau, China (grant no. FRG-21-032-SKL), Zhongnanshan Medical Foundation of Guangdong Province (grant no. ZNSA-2021016), China, by US National Institutes of Health (grant no's UL1TR001998, 1U01DK135111, and OT2HL161847) and by the DRC at Washington University (grant no. P30 DK020579). The authors thank the University of Kentucky's College of Public Health Office of Scientific Writing for editorial assistance and Steve Claas for his professional English editing work in preparing this manuscript. Conceptualization: C.H. and X.D.Z.; methodology: C.H. and M.D.; investigation: M.D. D.L.L. and P.Y.Z.; data curation: M.D. and D.L.L.; writing – original draft: C.H. and M.D.; writing – review and editing: X.D.Z. C.H. and M.D.; supervision: X.D.Z. C.H. and B.Q.S.; funding acquisition: X.D.Z. and C.H.; All authors read and approved the final manuscript. The authors declare no competing interests. This work was supported by The Science and Technology Development Fund , Macau SAR 462 and Dr. Neher’s Biophysics Laboratory for Innovative Drug Discovery , State Key Laboratory of Quality Research in Chinese Medicine in Macau University of Science and Technology , Macau, China (File no. 0020/2021/A , 002/2023/ALC , SKL-QRCM (MUST)-2020-2022 ), and General Research Grants of Macau University of Science and Technology , Macau, China (grant no. FRG-21-032-SKL ), Zhongnanshan Medical Foundation of Guangdong Province (grant no. ZNSA-2021016 ), China, by US National Institutes of Health (grant no’s UL1TR001998 , 1U01DK135111 , and OT2HL161847 ) and by the DRC at Washington University (grant no. P30 DK020579 ).

Funders	Funder number
General Research Grants of Macau University of Science and Technology , Macau, China	FRG-21-032-SKL
General Research Grants of Macau University of Science and Technology , Macau, China
SKL-QRCM
Zhongnanshan Medical Foundation of Guangdong Province	ZNSA-2021016
National Institutes of Health (NIH)	UL1TR001998, OT2HL161847, 1U01DK135111
National Institutes of Health (NIH)
University of Kentucky
The George Washington University	P30 DK020579
The George Washington University
Diabetes Research Connection
Fundo para o Desenvolvimento das Ciências e da Tecnologia	SAR 462
Fundo para o Desenvolvimento das Ciências e da Tecnologia
State Key Laboratory of Quality Research in Chinese Medicine, Macau University of Science and Technology	0020/2021/A
State Key Laboratory of Quality Research in Chinese Medicine, Macau University of Science and Technology
Malawi University of Science and Technology	-2020-2022
Malawi University of Science and Technology

Keywords

Biological sciences
Cancer

ASJC Scopus subject areas

General

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.isci.2023.108322

Cite this

@article{3bcb9040dc4b4415b7148311dff6796d,

title = "MIRS: An AI scoring system for predicting the prognosis and therapy of breast cancer",

abstract = "Tumor-infiltrating immune cells (TIICs) and metastasis are crucial characteristics for tumorigenesis. However, the potential role of their combination in breast cancer (BRCA) remains elusive. Herein, on the basis of quantifying TIICs and tumor metastasis together, we established a precise prognostic scoring system named metastatic and immunogenomic risk score (MIRS) using a neural network model. MIRS showed better performance when compared with other published signatures. MIRS stratifies patients into a high risk subtype (MIRShigh) and a low risk subtype (MIRSlow). The MIRShigh patients exhibit significantly lower survival rate compared with MIRSlow patients (P<0.0001), higher response to chemotherapy, but lower response to immunotherapy. Conversely, higher infiltration level of TIICs and significantly prolonged survival (P=0.029) are observed in MIRSlow patients, indicating sensitive response in immunotherapy. This work presents a promising indicator to guide treatment options of the BRCA population and provides a predicted webtool that is almost universally applicable to BRCA patients.",

keywords = "Biological sciences, Cancer",

author = "Chen Huang and Min Deng and Dongliang Leng and Baoqing Sun and Peiyan Zheng and Zhang, \{Xiaohua Douglas\}",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2023",

month = nov,

day = "17",

doi = "10.1016/j.isci.2023.108322",

language = "English",

volume = "26",

number = "11",

}

TY - JOUR

T1 - MIRS

T2 - An AI scoring system for predicting the prognosis and therapy of breast cancer

AU - Huang, Chen

AU - Deng, Min

AU - Leng, Dongliang

AU - Sun, Baoqing

AU - Zheng, Peiyan

AU - Zhang, Xiaohua Douglas

PY - 2023/11/17

Y1 - 2023/11/17

N2 - Tumor-infiltrating immune cells (TIICs) and metastasis are crucial characteristics for tumorigenesis. However, the potential role of their combination in breast cancer (BRCA) remains elusive. Herein, on the basis of quantifying TIICs and tumor metastasis together, we established a precise prognostic scoring system named metastatic and immunogenomic risk score (MIRS) using a neural network model. MIRS showed better performance when compared with other published signatures. MIRS stratifies patients into a high risk subtype (MIRShigh) and a low risk subtype (MIRSlow). The MIRShigh patients exhibit significantly lower survival rate compared with MIRSlow patients (P<0.0001), higher response to chemotherapy, but lower response to immunotherapy. Conversely, higher infiltration level of TIICs and significantly prolonged survival (P=0.029) are observed in MIRSlow patients, indicating sensitive response in immunotherapy. This work presents a promising indicator to guide treatment options of the BRCA population and provides a predicted webtool that is almost universally applicable to BRCA patients.

AB - Tumor-infiltrating immune cells (TIICs) and metastasis are crucial characteristics for tumorigenesis. However, the potential role of their combination in breast cancer (BRCA) remains elusive. Herein, on the basis of quantifying TIICs and tumor metastasis together, we established a precise prognostic scoring system named metastatic and immunogenomic risk score (MIRS) using a neural network model. MIRS showed better performance when compared with other published signatures. MIRS stratifies patients into a high risk subtype (MIRShigh) and a low risk subtype (MIRSlow). The MIRShigh patients exhibit significantly lower survival rate compared with MIRSlow patients (P<0.0001), higher response to chemotherapy, but lower response to immunotherapy. Conversely, higher infiltration level of TIICs and significantly prolonged survival (P=0.029) are observed in MIRSlow patients, indicating sensitive response in immunotherapy. This work presents a promising indicator to guide treatment options of the BRCA population and provides a predicted webtool that is almost universally applicable to BRCA patients.

KW - Biological sciences

KW - Cancer

UR - https://www.scopus.com/pages/publications/85175652447

UR - https://www.scopus.com/inward/citedby.url?scp=85175652447&partnerID=8YFLogxK

U2 - 10.1016/j.isci.2023.108322

DO - 10.1016/j.isci.2023.108322

M3 - Article

AN - SCOPUS:85175652447

SN - 2589-0042

VL - 26

JO - iScience

JF - iScience

IS - 11

M1 - 108322

ER -

MIRS: An AI scoring system for predicting the prognosis and therapy of breast cancer

Abstract

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this