Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Tingjun Hou
Facilitating structure-based drug discovery with an artificial intelligence-driven virtual screening platform
Abstract Structure-based virtual screening (VS) via molecular docking is a pivotal approach for hit identification. Many artificial intelligence (AI)-powered protein–ligand docking and scoring methods have demonstrated impressive speed and accuracy. Retrospective benchmarking studies using enrichment rate and computational efficiency on curated datasets have corroborated their potential for discovering bioactive compounds.
Overcoming Resistance in the Androgen Receptor: Rational and Strategic Design of Advanced Antagonists Click to copy article link Article link copied!
Abstract Click to copy section linkSection link copied! Conspectus Prostate cancer (PCa) is the most prevalent malignancy among men worldwide, with its pathogenesis and progression heavily reliant on the sustained activation of the androgen receptor (AR) signaling pathway. The AR, a transcription factor of nuclear receptor superfamily, serves as the most privileged therapeutic target in PCa, as evidenced by the clinical efficacy of first- and second-generation AR antagonists.
Targeting the intrinsically disordered AR-NTD through a machine learning-based enhanced sampling workflow
Abstract Targeting the intrinsically disordered N-terminal domain of the androgen receptor (AR-NTD) represents a promising strategy to overcome resistance in prostate cancer. However, its inherent lack of a stable tertiary structure and highly dynamic conformational ensemble pose formidable challenges for rational drug design.
LaMGen: LLM-based 3D molecular generation for multi-target drug design
Abstract Multi-target drugs hold great promise for treating complex diseases, yet existing methodologies predominantly rely on ligand-based approaches, which lack sufficient biological context and are often confined to specific target pairs, resulting in limited generalizability. Here, we introduce LaMGen, a general-purpose multi-target drug design framework powered by large language models (LLMs).
A scalable and quantum-accurate foundation model for biomolecular force fields via linearly tensorized quadrangle attention - Nature Communications
Abstract Accurate atomistic biomolecular simulations are vital for understanding disease mechanisms and drug discovery, yet existing methods struggle to balance quantum-mechanical accuracy with computational scalability. Classical force fields often lack precision, while quantum methods are computationally prohibitive for complex biological systems.
More than microglial depletion: PLX5622 activates the hepatic constitutive androstane receptor to alter anesthesia and addiction
Keywords microglia colony-stimulating factor 1 receptor PLX5622 constitutive androstane receptor metabolism anesthesia Get full text access Log in, subscribe or purchase for full access. References 1. Paolicelli, R.C. ∙ Sierra, A. ∙ Stevens, B. ... Microglia states and nomenclature: A field at its crossroads Neuron. 2022; 110:3458-3483 2. Badimon, A. ∙ Strasburger, H.J. ∙ Ayata, P. ... Negative feedback control of neuronal activity by microglia Nature. 2020; 586:417-423 3. Cserép, C. ∙ Pósfai, B. ∙ Lénárt, N.
AutoLoop is an autoregressive deep learning method for protein loop prediction with high accuracy
Keywords protein loop prediction deep learning Introduction Proteins are fundamental to life, participating in numerous biological functions.
SynGFN: learning across chemical space with generative flow-based molecular discovery - Nature Computational Science
Abstract In recent years, artificial intelligence has advanced the design–make–test–analyze cycle, transforming molecular discovery. Despite these advances, the compartmentalized approach to computer-aided molecular design and synthesis remains a critical bottleneck, limiting further optimization of the design–make–test–analyze cycle.
A fused deep learning approach to transform drug repositioning - Communications Chemistry
Abstract Drug repositioning holds promise for discovering new therapeutic applications for existing drugs, accelerating drug development and reducing associated costs. However, current methodologies encounter difficulties in managing diverse network representations, tackling cold start issues, and handling intrinsic attribute representations.
Biology-driven insights into the power of single-cell foundation models - Genome Biology
In this study, we standardized to select 2000 highly variable genes with a predefined batch key using the Scanpy [62] Python package. Crucially, HVG selection is also part of the data processing protocols of scVI, Harmony, and scGPT. scVI [18] is a variational autoencoder (VAE)-based generative model, which is widely used in single-cell transcriptomics data analysis.
Discovery of antimicrobial peptides with notable antibacterial potency by an LLM-based foundation model
The HHS Officials Being Paid Six Figures to Do Nothing The Trump administration hasn’t fired them but won’t let them do their jobs. When she succeeded Anthony Fauci as the director of the National Institute of Allergy and Infectious Diseases, Jeanne Marrazzo felt that she’d landed “probably the most important infectious-disease job in the world,” she …
Protein–peptide docking with a rational and accurate diffusion generative model - Nature Machine Intelligence
Abstract Therapeutic peptides represent the forefront of drug discovery, offering potent and safe alternatives to traditional small molecules. However, their weak and context-dependent nature complicates the efficient virtual screening and structural characterization of protein–peptide patterns. Here we introduce RAPiDock, a diffusion generative model designed for rational, accurate and rapid protein–peptide docking at an all-atomic level.
RSGPT: a generative transformer model for retrosynthesis planning pre-trained on ten billion datapoints - Nature Communications
Abstract Retrosynthesis planning is a crucial task in organic synthesis, and deep-learning methods have enhanced and accelerated this process. With the advancement of the emergence of large language models, the demand for data is rapidly increasing. However, available retrosynthesis data are limited to only millions. Therefore, we pioneer the utilization of the template-based algorithm to generate chemical reaction data, resulting in the production of over 10 billion reaction datapoints.
Linker-free PROTACs efficiently induce the degradation of oncoproteins - Nature Communications
Abstract Proteolysis-targeting chimeras (PROTACs) present a potentially effective strategy against various diseases via selective proteolysis. How to increase the efficacy of PROTACs remains challenging.
Deep lead optimization enveloped in protein pocket and its application in designing potent and selective ligands targeting LTK protein - Nature Machine Intelligence
Abstract Optimizing the chemical structure of promising drug candidates through systematic modifications to improve potency and physiochemical properties is a vital step in the drug discovery pipeline. In contrast to the well-established de novo generation schemes, computational methods specifically tailored for lead optimization remain largely underexplored.
Benchmarking AI-powered docking methods from the perspective of virtual screening - Nature Machine Intelligence
Abstract Recently, many artificial intelligence (AI)-powered protein–ligand docking and scoring methods have been developed, demonstrating impressive speed and accuracy. However, these methods often neglected the physical plausibility of the docked complexes and their efficacy in virtual screening (VS) projects. Therefore, we conducted a comprehensive benchmark analysis of four AI-powered and four physics-based docking tools and two AI-enhanced rescoring methods.
Correction: FragGen: towards 3D geometry reliable fragment-based molecular generation
Correction: FragGen: towards 3D geometry reliable fragment-based molecular generation Correction for ‘FragGen: towards 3D geometry reliable fragment-based molecular generation’ by Odin Zhang et al., Chem. Sci., 2024, 15, 19452–19465, https://doi.org/10.1039/D4SC04620J. This article is Open Access This article has not yet been cited.
Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction - Nature Communications
Abstract Structure-based machine learning algorithms have been utilized to predict the properties of protein-protein interaction (PPI) complexes, such as binding affinity, which is critical for understanding biological mechanisms and disease treatments.
Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites - Nature Communications
Abstract Annotating active sites in enzymes is crucial for advancing multiple fields including drug discovery, disease research, enzyme engineering, and synthetic biology. Despite the development of numerous automated annotation algorithms, a significant trade-off between speed and accuracy limits their large-scale practical applications.
Retrosynthesis prediction with an iterative string editing model - Nature Communications
Abstract Retrosynthesis is a crucial task in drug discovery and organic synthesis, where artificial intelligence (AI) is increasingly employed to expedite the process. However, existing approaches employ token-by-token decoding methods to translate target molecule strings into corresponding precursors, exhibiting unsatisfactory performance and limited diversity. As chemical reactions typically induce local molecular changes, reactants and products often overlap significantly.
Hsc70 promotes anti-tumor immunity by targeting PD-L1 for lysosomal degradation - Nature Communications
Abstract Immune checkpoint inhibition targeting the PD-1/PD-L1 pathway has become a powerful clinical strategy for treating cancer, but its efficacy is complicated by various resistance mechanisms. One of the reasons for the resistance is the internalization and recycling of PD-L1 itself upon antibody binding. The inhibition of lysosome-mediated degradation of PD-L1 is critical for preserving the amount of PD-L1 recycling back to the cell membrane.
Combining Transition Path Sampling with Data-Driven Collective Variables through a Reactivity-Biased Shooting Algorithm
Download Hi-Res ImageDownload to MS-PowerPointCite This:J. Chem. Theory Comput. 2024, XXXX, XXX Terms & Conditions Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses).
OptADMET: a web-based tool for substructure modifications to improve ADMET properties of lead compounds - Nature Protocols
Abstract Lead optimization is a crucial step in the drug discovery process, which aims to design potential drug candidates from biologically active hits. During lead optimization, active hits undergo modifications to improve their absorption, distribution, metabolism, excretion and toxicity (ADMET) profiles. Medicinal chemists face key questions regarding which compound(s) should be synthesized next and how to balance multiple ADMET properties.
CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training
CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training The expertise accumulated on deep neural networks-based structure prediction has been widely transferred to the field of protein-ligand binding pose prediction, thus leading to the emergence of a variety of deep learning-guided docking models for predicting protein-ligand binding poses without relying on heavy sampling.
A generalized protein-ligand scoring framework with balanced scoring, docking, ranking and screening powers
A generalized protein-ligand scoring framework with balanced scoring, docking, ranking and screening powers Tingjun Hou, Chao Shen, Xujun Zhang, Chang-Yu Hsieh, Yafeng Deng, Dong Wang, Lei Xu, Jian Wu, Dan Li, Yu Kang and Peichen Pan Abstract Applying machine learning algorithms to protein-ligand scoring functions has aroused widespread attention in recent years due to the high predictive accuracy and affordable computational cost.
Development and test of highly accurate endpoint free energy methods. 2: Prediction of logarithm of n‐octanol–water partition coefficient (logP) for druglike molecules using MM‐PBSA method
Abstract The logarithm of n-octanol–water partition coefficient (logP) is frequently used as an indicator of lipophilicity in drug discovery, which has substantial impacts on the absorption, distribution, metabolism, excretion, and toxicity of a drug candidate. Considering that the experimental measurement of the property is costly and time-consuming, it is of great importance to develop reliable prediction models for logP.
Development and test of highly accurate endpoint free energy methods. 1: Evaluation of ABCG2 charge model on solvation free energy prediction and optimization of atom radii suitable for more accurate solvation free energy prediction by the PBSA method - S
REVIEW ARTICLE Funding information: National Institutes of Health, Grant/Award Number: R01GM147673; National Science Foundation, Grant/Award Number: 1955260 Abstract Accurate estimation of solvation free energy (SFE) lays the foundation for accurate prediction of binding free energy.
Structure-guided and phage-assisted evolution of a therapeutic anti-EGFR antibody to reverse acquired resistance - Nature Communications
Abstract Acquired resistance to cetuximab in colorectal cancers is partially mediated by the acquisition of mutations located in the cetuximab epitope in the epidermal growth factor receptor (EGFR) ectodomain and hinders the clinical application of cetuximab. We develop a structure-guided and phage-assisted evolution approach for cetuximab evolution to reverse EGFRS492R- or EGFRG465R-driven resistance without altering the binding epitope or undermining antibody efficacy.
Monolayer Graphitic Germanium Carbide (g-GeC): The Promising Cathode Catalysts for Fuel Cell and Lithium-Oxygen Battery Applications
Designing and searching high-efficient metal-free oxygen reduction reaction (ORR) catalysts are demanding objective for academic and industrial researches. Herein, the ORR mechanism of monolayer graphitic germanium carbide (g-GeC) is studied by first-principles calculations. The monolayer g-GeC possesses excellent electro-catalytic properties that originate from the charge redistribution by electronegativity difference.
Controlling of the electronic properties of WS2 and graphene oxide heterostructures from first-principles calculations
Two-dimensional nanomaterials have attracted extensive interest and their heterostructures possess excellent electronic and optical properties suitable for various applications. Based on first-principles calculations, we investigated the structural stability and electronic properties of WS and graphene oxide (GO) heterostructures. We considered three types of GO, including epoxy only, hydroxyl only and both epoxy and hydroxyl on the GO surface.
Monolayer group IVA monochalcogenides as potential and efficient catalysts for oxygen reduction reaction from the first-principles calculations
Exploration of oxygen reduction reaction (ORR) catalysts based on non-precious metal is of great importance to the development of fuel cells. In this work, we theoretically investigate the practical feasibility and catalytic activity of two-dimensional (2D) group IVA monochalcogenides MXs (M=Ge/Sn, X=S/Se) as potential and efficient ORR catalysts.
Controlling of the Electronic Properties of WS2 and Graphene Oxide Heterostructures from First-principles calculations
Two-dimensional nanomaterials attracted extensive interests and their heterostructures provide excellent electronic and optical properties for various applications. Based on the first-principles calculations, we investigated the structural stability and electronic properties of WS2 and Graphene Oxide (GO) heterostructures. We considered three types of GO, including epoxy only, hydroxyl only and both epoxy and hydroxyl on the GO surface.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Tingjun
Contact Tingjun, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack