Location: Cleveland Clinic Main Campus
The primary goal of Cheng lab (Alzheimer’s Network Medicine Laboratory) is to create and combine research tools to answer the challenging questions surrounding Alzheimer’s diseases (AD) and Alzheimer’s disease-related dementia (ADRD). We develop experimental and computational methods and tools to be applicable to human disease as a whole to maximize the impact they have in identifying features that can be used to better diagnose or treat patients in a personalized manner (1,2,3,4,5). We are a multi-disciplinary team that integrates tools from:
In summary, the long-term goal of the Cheng’s lab is to develop and apply AI/machine-learning, systems biology technologies, and genome/network medicine methodologies for prediction of drug targets and identification of disease mechanisms. Our methods advance progress towards achieving the goal of coordinated, patient-centered strategies to innovative diagnostics and therapeutics development, in particular for Alzheimer’s disease and Alzheimer’s disease-related dementia (AD/ADRD).
Our lab has several major focus areas, described in greater detail below:
Over 16 million people in the United States, more than 150% the 2023 population of Ohio, are predicted to live with Alzheimer’s disease (AD) by 2050. Current AD patients face lack of effective disease-modifying treatments. High-throughput “omics” analyses (including genomics, transcriptomics (single-cell), proteomics, and metabolomics) offer power tools to study complex human disease, including AD. However, it is still a great challenge in the AD field to translate genetics and multi-omics findings to disease pathobiology. These difficulties make developing new therapeutics difficult.
Supported by NIH/NIA awards (R01s and U01), The Cheng lab has developed multiple Artificial Intelligence and genome medicine technologies to identify the pathobiology of AD and enable and therapeutic discovery. The group developed Interpretable deep learning (1), in silico network medicine (11), EHRs (3), and multimodal single-cell/nucleus genomics/epigenomics analytic approaches (8,15) to uncover molecular networks between disease-associated microglia and astrocytes with implications for AD drug repurposing. We have also created The Alzheimer’s Cell Atlas and AlzGPS, two genome-wide drug target identification platforms to catalyze multi-omics for Alzheimer's therapeutic discovery (16,4). In addition, The Cheng lab has established high-throughput drug screening approaches using patient iPSC-derived models, along with drug mechanistic studies using brain organoids and transgenic mouse models.
Traditional drug discovery pipelines involve complex, expensive, and time-consuming processes. Many drug candidates with ideal in vitro activities are failed because of low efficacy in vivo or safety problems. We believe that this high clinical attrition rate is due to shortcomings in the traditional drug discovery paradigm of ‘one drug, one gene, one disease’. Since the COVID-19 pandemic, Cheng group has developed several multi-omics and systems pharmacology approaches for drug discovery/repurposing (10,17,18,19,20). These network systems pharmacology methodologies offer powerful tools for identifying active therapeutics for COVID-19 and other complex diseases such as Alzheimer's disease and related dementia-like sequelae of SARS-CoV-2.
The growing awareness of cardiac dysfunction by cancer treatment has led to the emerging field of Cardio-Oncology. However, due to limited experimental assays there are no guidelines to prevent and treat the new cardiotoxicity in cancer survivors. Network medicine – a discipline that seeks to redefine disease and therapeutics from an integrated perspective using systems biology and network science – offers a non-invasive way to identify actionable biomarkers for cardio-oncology.
The Cheng lab has established integrated, network-based, systems pharmacology approaches that incorporate genomics, drug-target networks, and the human protein-protein interactome, along with large-scale patient longitudinal data as a means for efficient screening of potentially new indications for old drugs or previously unidentified adverse events. Supported by NHLBI, our team has developed several state-of-the-art systems pharmacology and network medicine approaches in cardio-oncology that focuses on screening, monitoring, and treating cancer survivors with cardiac dysfunction resulting from cancer treatments (21,22,23).
The central, unifying hypothesis is that using sequencing data, drug-target networks, drug-induced transcriptome, the human interactome and EHR data will identify novel and effective ways to evaluate the risk of cardiac dysfunction for different therapeutics.
Although often described as a disease of the genome, it is perhaps more appropriate to describe cancer as a “disease of the interactome”. Understanding cancer from the point-of-view of how cellular systems and interactome network perturbations underlie tumorigenesis is the essence of the field of cancer systems biology.
Our lab hypothesized that cellular networks gradually rewire throughout cancer initiation, progression and maintenance, leading to progressive shifts of local and global network properties and systems states, all of which in turn underlie tumorigenesis. It follows that most steps of cancer initiation, progression, maintenance and metastasis should be understood by considering network models in which every perturbed biophysical, biochemical or functional interaction is taken into account. Systematic identification and characterization of perturbed “driver protein-protein interactions (oncoPPIs)”, starting from cancer genomes, exomes and transcriptomes will serve as a foundation for generating predictive, and eventually dynamic, cancer network rewiring models.
We have developed network systems biology tools for identification of edgetic (e.g., oncoPPIs) drivers and pharmacogenomics biomarkers for precision oncology (6,7,12,13,24,25,26).
Alzheimer’s Target and Drug Discovery
1) Fang J, Zhang P, Zhou Y, Chiang WC, Tan J, Hou Y, Stauffer S, Li L, Pieper AA, Cummings J, Cheng F (2021) Endophenotype-based in-silico network medicine discovery combined with insurance records data mining identifies sildenafil as a candidate drug for Alzheimer’s disease. Nature Aging, 1, 1175–1188. (highlighted by NIH/NIA and 50+ major news outlets such as Newsweek, US News, BBC News, Fox News, UK Daily Mail)
2) Xu J, Mao C, Hou Y, Luo Y, Binder JL, Zhou Y, Bekris L, Shin J, Hu M, Wang F, Eng C, Oprea IT, Pieper AA, Cummings J, Leverenz JB, Cheng F (2022) Interpretable deep learning translation of GWAS and multi-omics findings to understanding pathobiology and drug repurposing in Alzheimer’s disease. Cell Reports, 41(9):111717.
3) Zhang P, Hou Y, Tu W, Campbell N, Pieper AA, Leverenz JB, Gao S, Cummings J, Cheng F (2022) Population-based discovery and Mendelian randomization analysis identify telmisartan as a candidate medicine for Alzheimer's disease in African Americans. Alzheimer's & Dementia: The Journal of the Alzheimer's Association. 2022 Nov 4. doi: 10.1002/alz.12819. Online ahead of print.
4) Fang J, Zhang P, Wang Q, Chiang C, Zhou Y, Hou Y, Xu J, Chen R, Zhang B, Lewis JS, Leverenz B.J., Pieper A.A., Li B, Li L, Cummings J, Cheng F (2022) Artificial intelligence framework identifies candidate targets for drug repurposing in Alzheimer’s disease, Alzheimer's Research & Therapy, 14(1):7.
5) Xu J, Zhang P, Huang Y, Bekris L, Lathia JD, Chiang WC, Li L, Pieper AA, Leverenz BJ, Cummings J, Cheng F (2021) Multimodal single-cell/nucleus RNA-sequencing data analysis uncovers molecular networks between disease-associated microglia and astrocytes with implications for drug repurposing in Alzheimer’s disease. Genome Research, 31(10):1900-1912.
6) Zhou Y, Xu J, Hou Y, Bekris L, Leverenz JB, Pieper AA, Cummings J, Cheng F (2022) The Alzheimer's Cell Atlas (TACA): A single-cell molecular map for translational therapeutics accelerator in Alzheimer's disease. Alzheimer and Dementia, 8(1): e12350.
7) Shin KM, Vázquez-Rosa E, Koh YG, Dhar M, Chaubey K, Cintrón-Pérez JC, Barker S, M. E., Franke K, Noterman M, Seth D, Allen SR, Motz TC, Rao R, Skelton AL, Pardue TM, Fliesler JS, Wang C, Tracy ET, Gan L, Liebl JD, Savarraj J, Torres LG, Ahnstedt H, McCullough DL, Zhang P, Hou Y, Chiang WC, Li L, Ortiz F, Kilgore AJ, Williams SN, Whitehair CV, Gefen T, Flanagan EM, Stamler SJ, Jain KM, Kraus A, Cheng F, Reynolds DJ, Pieper AA (2021) Reducing tau acetylation is neuroprotective in brain injury. Cell, 184(10):2715-2732.e23.
8) Zhou Y, Xu J, Hou Y, Leverenz B.J., Kallianpur A, Mehra MR, Liu Y, Yu H, Pieper AA, Jehi, L., Cheng F (2021) Network medicine links SARS-CoV-2/COVID-19 infection to brain microvascular injury and neuroinflammation in dementia-like cognitive impairment. Alzheimer's Research & Therapy, 13:110.
9) Zhou Y, Fang J, Bekris L, Young H.K., Pieper AA, Leverenz J, Cummings J, Cheng F (2021) AlzGPS: A Genome-wide Positioning Systems platform to catalyze multi-omics findings for Alzheimer's drug discovery. Alzheimer's Research & Therapy, 13: 24.
10) Martin W, Sheynkman G, Lightstone FC, Nussinov R, Cheng F (2022) Interpretable artificial intelligence and exascale molecular dynamics simulations to reveal kinetics: Applications to Alzheimer's disease. Current Opinion of Structural Biology. 2022, 72:103-113. 11) Fang J, Pieper AA, Lee G, Bekris L, Nussinov R, Leverenz BJ, Cummings J, Cheng F (2020) Harnessing endophenotypes and using network medicine in Alzheimer’s drug repurposing, Medicinal Research Reviews, 40(6):2386-2426.
Network Systems Biology, Artificial Intelligence, and Multi-Omics Tools
1) Zhou Y, Liu Y, Gupta S, Paramo M, Hou Y, Mao C, Luo Y, Judd J, Wierbowski S, Bertolotti M, Nerkar M, Jehi L, Drayman N, Nicolaescu V, Gula H, Tay S, Randall G, Lis TJ, Feschotte C, Erzurum CS, Cheng F# (Co-corresponding author), Yu H#. A comprehensive SARS-CoV-2-human protein-protein interactome network identifies pathobiology and host-targeting therapies for COVID-19. Nature Biotechnology. 2023, 41(1):128-139. (Journal Cover)
2) Zeng X, Xiang H, Yu L, Wang J, Li K, Nussinov R, Cheng F (2022) Accurate prediction of molecular targets using a self-supervised image representation learning framework. Nature Machine Intelligence, 4, 1004–1016.
3) Cheng F, Zhao J, Wang Y, Lu W, Liu Z, Zhou Y, Martin W, Wang R, Hao T, Yue H, Ma J, Fang J, Hou Y, Lathia JD, Keri R, Lightstone C.F., Antmam ME, Rabadan R, David H, Eng C, Vidal M, Loscalzo J (2021) Comprehensive characterization of protein-protein interactions perturbed by disease mutations. Nature Genetics, 53(3):342-353.
4) Xu J, Xu J, Meng Y, Lu C, Cai L, Zeng X, Nussinov R, Cheng F (2023) Graph embedding and Gaussian mixture variational autoencoder network for end-to-end analysis of single-cell RNA sequencing data. Cell Reports Methods, 3, 100382
5) Zeng X, Wang F, Luo Y, Kang S, Tang J, Lightstone F.C., Fang E.F., Cornell W, Nussinov R, Cheng F (2022) Deep generative molecular design reshapes drug discovery, Cell Reports Medicine, 3(12): 100794.
6) Hou Y, Zhou Y, Gack MU, Luo Y, Jehi L, Chan T, Yu H, Eng C, Pieper A, Cheng F (2022) Aging-related cell type-specific pathophysiologic immune responses that exacerbate disease severity in aged COVID-19 patients. Aging Cell, 21(2):e13544.
7) Hou Y, Zhou Y, Hussain M, Budd GT, Tang WHW, Abraham J, Xu B, Shah C, Moudgil R, Popovic Z, Watson C, Cho L, Chung M, Kanj M, Kapadia S, Griffin B, Svensson L, Collier P, Cheng F (2021) Cardiac risk stratification in cancer patients: A longitudinal patient-patient network analysis. PLOS Medicine, 18(8): e1003736.
8) Zhou Y, Zhao J, Fang J, Martin W, Li L, Nussinov R, Eng C, Chan TA, Cheng F (2021) My Personal Mutanome: A personalized cancer medicine platform for searching network perturbing alleles linking somatic genotype to phenotype. Genome Biology, 22: 53.
9) Zhou Y, Hou Y, Shen J, Kallianpur A, Zein J, Culver AD, Farha S, Comhair S, Fiocchi C, Gack UM, Mehra R, Stappenbeck T, Chan T, Eng C, Jung UJ, Jehi L, Erzurum S, Cheng F (2020) A Network Medicine Approach to Prediction and Patient-based Validation of Disease Manifestations and Drug Repurposing for COVID-19, PLoS Biology 18(11): e3000970.
10) Zhou Y, Hou Y, Shen J, Huang Y, Martin W, Cheng F (2020) Network-based drug repurposing for novel coronavirus 2019-nCoV/SARS-CoV-2. Cell Discovery, 6, 14. (cited by over 1300 times and highlighted by >10 national media releases)
11) Zhou Y, Wang F, Tang J, Nussinov R, Cheng F (2020) Artificial Intelligence in COVID-19 Drug Repurposing. Lancet Digital Health, 2(12): e667–e676. (Journal Cover)
12) Huang Y, Fang J, Wang Z, Lu W, Wang Q, Hou Y, Jiang X, Reizes O, Lathia J, Nussinov R, Eng C, Cheng F (2019) A systems pharmacology approach uncovers wogonoside as a novel angiogenesis inhibitor of triple-negative breast cancer by targeting Hedgehog signaling, Cell Chemical Biology, 26: 1143-1158.
13) Cheng F, Liu C, Lu W, Fang J, Hou Y, Handy ED, Wang R, Zhao Y, Yang Y, Huang J, Hill ED, Vidal M, Eng C, Loscalzo J (2019) A genome-wide positioning systems network algorithm for in silico drug repurposing. Nature Communications. 10, 3476.
14) Cheng F, Kovacs I, Barabasi AL (2019) Network-based prediction of drug combinations. Nature Communications. 10: 1197.
15) Cheng F, Desai JR, Handy ED, Wang R, Schneeweiss S, Barabasi AL, Loscalzo J (2018) Network-based approach to prediction and population-based validation of in silico drug repurposing. Nature Communications. 9: 2691.
Dr. Cheng has mentored or is currently mentoring MD-PhD students, PhD students (including HHMI Gilliam fellowship), and 10+ postdoctoral fellowships. We have multiple postdoc and graduate student positions available for NIH-funded Network Medicine and Artificial Intelligence projects (U01 and R01s). If you have PhD or MD in the field of systems biology, bioinformatics, computational biology, machine learning, natural language processing, mathematics, network science, and/or experimental skills (Alzheimer’s mouse models and patient-derived iPSC and brain organoids), please send your:
The open-source artificial intelligence (AI) technology uses human genetic data to identify candidate drugs.
Analyzing data from more than 5 million patients revealed telmisartan is associated with lower Alzheimer’s disease incidence in Black patients, providing clues for potential treatment and prevention.
How drugs and atrial fibrillation affect functions and genes in the body is the subject of a recent study into metformin and other candidate drugs.
Cleveland Clinic researchers utilize artificial intelligence to create a discovery tool by outlining interactions between viral and host proteins.
Dr. Cheng’s team identified several differences in immune and inflammatory responses that may help explain the elevated risk for severe illness and death observed in older COVID-19 patients.
Dr. Cheng’s team developed an endophenotype-based drug repurposing methodology that identified the FDA-approved drug sildenafil as a candidate for the prevention and treatment of Alzheimer’s disease.
With this award, Dr. Cheng’s team will develop artificial intelligence and machine learning tools capable of identifying novel endophenotypes and actionable targets for drug repurposing in Alzheimer’s disease.
With a new $4 million grant, Drs. Cheng, Bekris and Leverenz will develop and utilize artificial intelligence tools to identify novel drug targets and repurposable drugs for Alzheimer’s disease.
A research team led by Drs. Cheng and Collier developed an artificial intelligence methodology to help identify cancer patients at risk for cancer therapy-related cardiac dysfunction.
Utilizing large-scale patient data and samples from the Cleveland Clinic COVID-19 registry, Dr. Cheng’s team identified clinical characteristics and immune-related mechanisms associated with sex differences in COVID-19 outcomes.