arXiv subjects

Hongsong Feng

Publications and source records attributed to Hongsong Feng.

23 records · Page 2Linked to original sources

arXiv2023

Machine-learning Repurposing of DrugBank Compounds for Opioid Use Disorder

Opioid use disorder (OUD) is a chronic and relapsing condition that involves the continued and compulsive use of opioids despite harmful consequences. The development of medications with improved efficacy and safety profiles for OUD treatment is urgently needed. Drug repurposing is a promising option for drug discovery due to its reduced cost and expedited approval procedures. Computational approaches based on machine learning enable the rapid screening of DrugBank compounds, identifying those with the potential to be repurposed for OUD treatment. We collected inhibitor data for four major opioid receptors and used advanced machine learning predictors of binding affinity that fuse the gradient boosting decision tree algorithm with two natural language processing (NLP)-based molecular fingerprints and one traditional 2D fingerprint. Using these predictors, we systematically analyzed the binding affinities of DrugBank compounds on four opioid receptors. Based on our machine learning predictions, we were able to discriminate DrugBank compounds with various binding affinity thresholds and selectivities for different receptors. The prediction results were further analyzed for ADMET (absorption, distribution, metabolism, excretion, and toxicity), which provided guidance on repurposing DrugBank compounds for the inhibition of selected opioid receptors. The pharmacological effects of these compounds for OUD treatment need to be tested in further experimental studies and clinical trials. Our machine learning studies provide a valuable platform for drug discovery in the context of OUD treatment.

q-bio.BM↗

arXiv2023

Machine-learning Analysis of Opioid Use Disorder Informed by MOR, DOR, KOR, NOR and ZOR-Based Interactome Networks

Opioid use disorder (OUD) continuously poses major public health challenges and social implications worldwide with dramatic rise of opioid dependence leading to potential abuse. Despite that a few pharmacological agents have been approved for OUD treatment, the efficacy of said agents for OUD requires further improvement in order to provide safer and more effective pharmacological and psychosocial treatments. Preferable therapeutic treatments of OUD rely on the advances in understanding the neurobiological mechanism of opioid dependence. Proteins including mu, delta, kappa, nociceptin, and zeta opioid receptors are the direct targets of opioids. Each receptor has a large protein-protein interaction (PPI) network, that behaves differently when subjected to various treatments, thus increasing the complexity in the drug development process for an effective opioid addiction treatment. The report below analyzes the work by presenting a PPI-network informed machine-learning study of OUD. We have examined more than 500 proteins in the five opioid receptor networks and subsequently collected 74 inhibitor datasets. Machine learning models were constructed by pairing gradient boosting decision tree (GBDT) algorithm with two advanced natural language processing (NLP)-based molecular fingerprints. With these models, we systematically carried out evaluations of screening and repurposing potential of drug candidates for four opioid receptors. In addition, absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties were also considered in the screening of potential drug candidates. Our study can be a valuable and promising tool of pharmacological development for OUD treatments.

q-bio.BM↗

arXiv2022

SVSBI: Sequence-based virtual screening of biomolecular interactions

Virtual screening (VS) is an essential technique for understanding biomolecular interactions, particularly, drug design and discovery. The best-performing VS models depend vitally on three-dimensional (3D) structures, which are not available in general but can be obtained from molecular docking. However, current docking accuracy is relatively low, rendering unreliable VS models. We introduce sequence-based virtual screening (SVS) as a new generation of VS models for modeling biomolecular interactions. The SVS model utilizes advanced natural language processing (NLP) algorithms and optimizes deep $K$-embedding strategies to encode biomolecular interactions without invoking 3D structure-based docking. We demonstrate the state-of-art performance of SVS for four regression datasets involving protein-ligand binding, protein-protein, protein-nucleic acid binding, and ligand inhibition of protein-protein interactions and five classification datasets for the protein-protein interactions in five biological species. SVS has the potential to dramatically change the current practice in drug discovery and protein engineering.

q-bio.BM↗

arXiv2022

Virtual screening of DrugBank database for hERG blockers using topological Laplacian-assisted AI models

The human {\it ether-a-go-go} (hERG) potassium channel (K$_\text{v}11.1$) plays a critical role in mediating cardiac action potential. The blockade of this ion channel can potentially lead fatal disorder and/or long QT syndrome. Many drugs have been withdrawn because of their serious hERG-cardiotoxicity. It is crucial to assess the hERG blockade activity in the early stage of drug discovery. We are particularly interested in the hERG-cardiotoxicity of compounds collected in the DrugBank database considering that many DrugBank compounds have been approved for therapeutic treatments or have high potential to become drugs. Machine learning-based in silico tools offer a rapid and economical platform to virtually screen DrugBank compounds. We design accurate and robust classifiers for blockers/non-blockers and then build regressors to quantitatively analyze the binding potency of the DrugBank compounds on the hERG channel. Molecular sequences are embedded with two natural language processing (NPL) methods, namely, autoencoder and transformer. Complementary three-dimensional (3D) molecular structures are embedded with two advanced mathematical approaches, i.e., topological Laplacians and algebraic graphs. With our state-of-the-art tools, we reveal that 227 out of the 8641 DrugBank compounds are potential hERG blockers, suggesting serious drug safety problems. Our predictions provide guidance for the further experimental interrogation of DrugBank compounds' hERG-cardiotoxicity .

q-bio.BM↗

arXiv2022

Machine learning analysis of cocaine addiction informed by DAT, SERT, and NET-based interactome networks

Cocaine addiction is a psychosocial disorder induced by the chronic use of cocaine and causes a large of number deaths around the world. Despite many decades' effort, no drugs have been approved by the Food and Drug Administration (FDA) for the treatment of cocaine dependence. Cocaine dependence is neurological and involves many interacting proteins in the interactome. Among them, dopamine transporter (DAT), serotonin transporter (SERT), and norepinephrine transporter (NET) are three major targets. Each of these targets has a large protein-protein interaction (PPI) network which must be considered in the anti-cocaine addiction drug discovery. This work presents DAT, SERT, and NET interactome network-informed machine learning/deep learning (ML/DL) studies of cocaine addiction. We collect and analyze 61 protein targets out 460 proteins in the DAT, SERT, and NET PPI networks that have sufficient existing inhibitor datasets. Utilizing autoencoder and other ML algorithms, we build ML/DL models for these targets with 115,407 inhibitors to predict drug repurposing potentials and possible side effects. We further screen their absorption, distribution, metabolism, and excretion, and toxicity (ADMET) properties to search for nearly optimal leads for anti-cocaine addiction. Our approach sets up a systematic protocol for artificial intelligence (AI)-based anti-cocaine addiction lead discovery.

q-bio.MN↗