Machine learning and molecular modeling based design of nanobodies targeting human serotonin transporter and receptor DOI
Binbin Xu, Jin Liu, Weiwei Xue

et al.

Advances in protein chemistry and structural biology, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Language: Английский

Structural Models of Human Norepinephrine Transporter Ensemble Reveal the Allosteric Sites and Ligand-Binding Mechanism DOI
Ding Luo, Yang Zhang, Yinghong Li

et al.

The Journal of Physical Chemistry B, Journal Year: 2024, Volume and Issue: 128(36), P. 8651 - 8661

Published: Aug. 29, 2024

The norepinephrine transporter (NET) plays a pivotal role in recycling (NE) from the synaptic cleft. However, structures referring to conformational heterogeneity of NET during transport cycle remain poorly understood. Here, three structural models NE bound orthosteric site outward-open (OOholo), outward-occluded (OCholo), and inward-open (IOholo) conformations were first obtained using multistate serotonin as templates further characterized through Gaussian-accelerated molecular dynamics free energy reweighting. Analysis revealed eight potential allosteric sites on functional-specific states NET. One pharmacologically relevant pockets located at extracellular vestibule was verified by simulating binding behaviors clinical trial drug χ-MrIA that is allosterically regulating These energetic insights into advanced our understanding reuptake paved way for discovering novel molecules targeting sites.

Language: Английский

Citations

7
CNSMolGen: A Bidirectional Recurrent Neural Network-Based Generative Model for De Novo Central Nervous System Drug Design DOI

Rongpei Gou,

Jingyi Yang, Menghan Guo

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(10), P. 4059 - 4070

Published: May 13, 2024

Central nervous system (CNS) drugs have had a significant impact on treating wide range of neurodegenerative and psychiatric disorders. In recent years, deep learning-based generative models shown great potential for accelerating drug discovery improving efficacy. However, specific applications these techniques in CNS not been widely reported. this study, we developed the CNSMolGen model, which uses framework bidirectional recurrent neural networks (Bi-RNNs) de novo molecular design drugs. Results showed that pretrained model was able to generate more than 90% completely new structures, possessed properties molecules were synthesizable. addition, transfer learning performed small data sets with biological activities evaluate application optimization. Here, used against classical disease target serotonin transporter (SERT) as fine-tuned set generated focused database protein. The verified by using physics-based induced-fit docking study. success demonstrates its optimization, provides impetus future development.

Language: Английский

Citations

6
SYNBIP 2.0: epitopes mapping, sequence expansion and scaffolds discovery for synthetic binding protein innovation DOI Creative Commons
Yanlin Li, Fengcheng Li,

Zixin Duan

et al.

Nucleic Acids Research, Journal Year: 2024, Volume and Issue: 53(D1), P. D595 - D603

Published: Oct. 16, 2024

Abstract Synthetic binding proteins (SBPs) represent a pivotal class of artificially engineered proteins, meticulously crafted to exhibit targeted properties and specific functions. Here, the SYNBIP database, comprehensive resource for SBPs, has been significantly updated. These enhancements include (i) featuring 3D structures 899 SBP–target complexes illustrate epitopes (ii) using SBPs in monomer or complex forms with target their sequence space expanded five times 12 025 by integrating structure-based protein generation framework property prediction tool, (iii) offering detailed information on 78 473 newly identified SBP-like scaffolds from RCSB Protein Data Bank, an additional 16 401 555 ones AlphaFold Structure Database, (iv) database is regularly updated, incorporating 153 new SBPs. Furthermore, structural models all have enhanced through application AlphaFold2, clinical statuses concurrently refreshed. Additionally, design methods employed each SBP are now prominently featured database. In sum, 2.0 designed provide researchers essential data, facilitating innovation research, diagnosis therapy. freely accessible at https://idrblab.org/synbip/.

Language: Английский

Citations

4
Identification of acrylamide-based covalent inhibitors of SARS-CoV-2 (SCoV-2) Nsp15 using high-throughput screening and machine learning DOI Creative Commons
Teena Bajaj, Babak Mosavati, Lydia H. Zhang

et al.

RSC Advances, Journal Year: 2025, Volume and Issue: 15(13), P. 10243 - 10256

Published: Jan. 1, 2025

This study presented a novel screening of acrylamides discovering them as inhibitors against Nsp15 from SARS-CoV-2 and utilizing the data to develop an AI model screen more virtually.

Language: Английский

Citations

0
DTNPD: A comprehensive database of drugs and targets for neurological and psychiatric disorders DOI
Ding Luo, Zhuohao Tong,

Lu Wen

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 175, P. 108536 - 108536

Published: April 30, 2024

Language: Английский

Citations

1
Investigating the optoelectronic behavior of graphene—mordant red conjugate through DFT calculations and MD simulations DOI

Naina,

Madhur Babu Singh,

Kumar Rakesh Ranjan

et al.

Structural Chemistry, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 28, 2024

Language: Английский

Citations

1
CNSMolGen: a bidirectional recurrent neural networks based generative model for de novo central nervous system drug design DOI Creative Commons

Rongpei Gou,

Jingyi Yang, Menghan Guo

et al.

Published: Feb. 22, 2024

Central nervous system (CNS) drugs have had a significant impact on human health, e.g., treating wide range of neurodegenerative and psychiatric disorders. In recent years, deep learning-based generative models, particularly those for designing from scratch, shown great potential accelerating drug discovery, reducing costs improving efficacy. However, specific applications these techniques in CNS discovery not been widely reported. this study, we developed the CNSMolGen model, which uses bidirectional recurrent neural networks (Bi-RNNs) de novo molecular design by learning compounds with properties. Result that pre-trained model was able to generate more than 90% completely new structures, molecules possessed properties synthesizable. addition, transfer performed small datasets biological activities evaluate application optimization. Here, used against classical disease target serotonin transporter (SERT) as fine-tuned dataset generated Focused database protein. The were verified using physics-based induced fit docking study. success demonstrates its optimization, provides impetus future development.

Language: Английский

Citations

0
Machine learning and molecular modeling based design of nanobodies targeting human serotonin transporter and receptor DOI
Binbin Xu, Jin Liu, Weiwei Xue

et al.

Advances in protein chemistry and structural biology, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Language: Английский

Citations

0