Recent advances in high-throughput genomic technologies coupled with exponential increases in computer processing and memory have allowed us to interrogate the complex aberrant molecular underpinnings of human disease from a genome-wide perspective. While the deluge of genomic information is expected to increase, a bottleneck in conventional high-performance computing is rapidly approaching. Inspired in part by recent advances in physical quantum processors, we evaluated several unconventional machine learning (ML) strategies on actual human tumor data. Here we show for the first time the efficacy of multiple annealing-based ML algorithms for classification of high-dimensional, multi-omics human cancer data from the Cancer Genome Atlas. To assess algorithm performance, we compared these classifiers to a variety of standard ML methods. Our results indicate the feasibility of using annealing-based ML to provide competitive classification of human cancer types and associated molecular subtypes and superior performance with smaller training datasets, thus providing compelling empirical evidence for the potential future application of unconventional computing architectures in the biomedical sciences.
Multi-Objective Optimization with Quantum-Annealing-Inspired Algorithms
Southern University of Science and Technology（南方科技大学）；International Quantum Academy（国际量子研究院）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Polytechnic University（香港理工大学）
Digital quantum simulation of squeezed states via enhanced bosonic encoding in a superconducting quantum processor
Arclight Quantum Computing Inc.（阿特莱特量子计算有限公司）；QuantumCTek (Shanghai) Co., Ltd.（国盾量子（上海）有限公司）；China Telecom Quantum Information Technology Group Co., Ltd.（中国电信量子信息技术集团有限公司）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physics
Russian Quantum Center（俄罗斯量子中心）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；University of Oxford（牛津大学）；P. N. Lebedev Physics Institute（P. N. 列别杰夫物理研究所）
Pretty Good Measurement for Radiomics: A Quantum-Inspired Multi-Class Classifier for Lung Cancer Subtyping and Prostate Cancer Risk Stratification
Università degli Studi di Cagliari（卡利亚里大学）；Institute of Bioimaging and Complex Biological Systems - National Research Council (IBSBC - CNR)（生物成像与复杂生物系统研究所 - 国家研究委员会）；National Laboratory of South, National Institute for Nuclear Physics(LNS-INFN)（南部国家实验室，核物理研究所）
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
National Taiwan University（台湾大学）；National Center for High-Performance Computing（国家高速计算机中心）；National Institutes of Applied Research（应用研究院）；Brookhaven National Laboratory（布鲁克海文国家实验室）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Harvard University（哈佛大学）；National Yang Ming Chiao Tung University（国立阳明交通大学）；National Center for Theoretical Sciences（国家理论科学中心）
