Xudong Huang

Prof. Dr. Xudong Huang

Massachusetts General Hospital - Harvard Medical School, Boston, USA
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2012 in Current Alzheimer Research
Verified
Journal Article
Closed access
PDF file
DODavid Olivares
David Olivares
VDVarun K. Deshpande
Varun K. Deshpande
YSYing Shi
Ying Shi
DLDebomoy K. Lahiri
Debomoy K. Lahiri
NGNigel H. Greig
Nigel H. Greig
Xudong HuangXudong Huang
Xudong Huang
Memantine, a partial antagonist of N-methyl-D-aspartate receptor (NMDAR), approved for moderate to severe Alzheimer’s disease (AD) treatment within the US and Europe under brand name Namenda (Forest), Axura and Akatinol (Merz), and Ebixa and Abixa (Lundbeck), may have potential in alleviating additional neurological conditions, such as vascular dementia (VD) and Parkinson’s disease (PD). In various animal models, memantine has been reported to be a neuroprotective agent that positively impacts both neurodegenerative and vascular processes. While excessive levels of glutamate result in neurotoxicity, in part through the over-activation of NMDARs, memantine—as a partial NMDAR antagonist, blocks the NMDA glutamate receptors to normalize the glutamatergic system and ameliorate cognitive and memory deficits. The key to memantine’s therapeutic action lies in its uncompetitive binding to the NMDAR through which low affinity and rapid off-rate kinetics of memantine at the level of the NMDAR-channel preserves the physiological function of the receptor, underpinning memantine’s tolerability and low adverse event profile. As the biochemical pathways evoked by NMDAR antagonism also play a role in PD and since no other drug is sufficiently effective to substitute for the first-line treatment of L-dopa despite its side effects, memantine may be useful in PD treatment with possibly fewer side effects. In spite of the relative modest nature of its adverse effects, memantine has been shown to provide only a moderate decrease in clinical deterioration in AD and VD, and hence efforts are being undertaken in the design of new and more potent memantine-based drugs to hopefully provide greater efficacy.

Verified
Journal Article
Open access
PDF file
APAlexander Pilozzi
Alexander Pilozzi
Caitlin CarroCaitlin Carro
Caitlin Carro
Xudong HuangXudong Huang
Xudong Huang
β-Endorphins are peptides that exert a wide variety of effects throughout the body. Produced through the cleavage pro-opiomelanocortin (POMC), β-endorphins are the primarily agonist of mu opioid receptors, which can be found throughout the body, brain, and cells of the immune system that regulate a diverse set of systems. As an agonist of the body’s opioid receptors, β-endorphins are most noted for their potent analgesic effects, but they also have their involvement in reward-centric and homeostasis-restoring behaviors, among other effects. These effects have implicated the peptide in psychiatric and neurodegenerative disorders, making it a research target of interest. This review briefly summarizes the basics of endorphin function, goes over the behaviors and regulatory pathways it governs, and examines the variability of β-endorphin levels observed between normal and disease/disorder affected individuals.

7 December 2018 in Current Pharmaceutical Design
Verified
Journal Article
Open access
PDF file
KCKristy A. Carpenter
Kristy A. Carpenter
Xudong HuangXudong Huang
Xudong Huang
Background: Virtual Screening (VS) has emerged as an important tool in the drug development process, as it conducts efficient in silico searches over millions of compounds, ultimately increasing yields of potential drug leads. As a subset of Artificial Intelligence (AI), Machine Learning (ML) is a powerful way of conducting VS for drug leads. ML for VS generally involves assembling a filtered training set of compounds, comprised of known actives and inactives. After training the model, it is validated and, if sufficiently accurate, used on previously unseen databases to screen for novel compounds with desired drug target binding activity. Objective: The study aims to review ML-based methods used for VS and applications to Alzheimer’s Disease (AD) drug discovery. Methods: To update the current knowledge on ML for VS, we review thorough backgrounds, explanations, and VS applications of the following ML techniques: Naïve Bayes (NB), k-Nearest Neighbors (kNN), Support Vector Machines (SVM), Random Forests (RF), and Artificial Neural Networks (ANN). Results: All techniques have found success in VS, but the future of VS is likely to lean more largely toward the use of neural networks – and more specifically, Convolutional Neural Networks (CNN), which are a subset of ANN that utilize convolution. We additionally conceptualize a work flow for conducting ML-based VS for potential therapeutics for AD, a complex neurodegenerative disease with no known cure and prevention. This both serves as an example of how to apply the concepts introduced earlier in the review and as a potential workflow for future implementation. Conclusion: Different ML techniques are powerful tools for VS, and they have advantages and disadvantages albeit. ML-based VS can be applied to AD drug development.

5 October 2018 in Future Medicinal Chemistry
Verified
Journal Article
Open access
KCKristy A Carpenter
Kristy A Carpenter
DCDavid S Cohen
David S Cohen
JJJuliet T Jarrell
Juliet T Jarrell
Xudong HuangXudong Huang
Xudong Huang
Current drug development is still costly and slow given tremendous technological advancements in drug discovery and medicinal chemistry. Using machine learning (ML) to virtually screen compound libraries promises to fix this for generating drug leads more efficiently and accurately. Herein, we explain the broad basics and integration of both virtual screening (VS) and ML. We then discuss artificial neural networks (ANNs) and their usage for VS. The ANN is emerging as the dominant classifier for ML in general, and has proven its utility for both structure-based and ligand-based VS. Techniques such as dropout, multitask learning and convolution improve the performance of ANNs and enable them to take on chemical meaning when learning about the drug-target-binding activity of compounds. Graphic abstract

1 November 2008 in BioTechniques
Verified
Journal Article
Open access
WKWei Kong
Wei Kong
CVCharles R. Vanderburg
Charles R. Vanderburg
HGHiromi Gunshin
Hiromi Gunshin
JRJack Rogers
Jack Rogers
Xudong HuangXudong Huang
Xudong Huang
Independent component analysis (ICA) methods have received growing attention as effective data-mining tools for microarray gene expression data. As a technique of higher-order statistical analysis,...

23 December 2011 in BMC Genomics
Verified
Journal Article
Open access
PDF file
Qingzhong LiuQingzhong Liu
Qingzhong Liu
ASAndrew H Sung
Andrew H Sung
ZCZhongxue Chen
Zhongxue Chen
JLJianzhong Liu
Jianzhong Liu
LCLei Chen
Lei Chen
YDYouping Deng
Youping Deng
Background: Microarray data have a high dimension of variables and a small sample size. In microarray data analyses, two important issues are how to choose genes, which provide reliable and good prediction for disease status, and how to determine the final gene set that is best for classification. Associations among genetic markers mean one can exploit information redundancy to potentially reduce classification cost in terms of time and money.Results: To deal with redundant information and improve classification, we propose a gene selection method, Recursive Feature Addition, which combines supervised learning and statistical similarity measures. To determine the final optimal gene set for prediction and classification, we propose an algorithm, Lagging Prediction Peephole Optimization. By using six benchmark microarray gene expression data sets, we compared Recursive Feature Addition with recently developed gene selection methods: Support Vector Machine Recursive Feature Elimination, Leave-One-Out Calculation Sequential Forward Selection and several others.Conclusions: On average, with the use of popular learning machines including Nearest Mean Scaled Classifier, Support Vector Machine, Naive Bayes Classifier and Random Forest, Recursive Feature Addition outperformed other methods. Our studies also showed that Lagging Prediction Peephole Optimization is superior to random strategy; Recursive Feature Addition with Lagging Prediction Peephole Optimization obtained better testing accuracies than the gene selection method varSelRF.