Research Progress of Artificial Intelligence and Molecular Simulation in Drug Design / 医药导报

With the deepening of modern drug research,traditional computer simulation can not meet the needs of future drug design experiments.As a classic technology of standard computer simulation,molecular simulation can construct and analyze complex molecular models to study the dynamic processes of molecular motion.However,the simulation results are easy to be affected by human factors.In recent years,the integration of artificial intelligence and molecular simulation has become a new method of drug design research.Artificial intelligence technology uses big data to screen out the corresponding compounds for molecular simulation and feedback on the simulation results to the artificial intelligence system to optimize the artificial neural network.The combination of artificial intelligence and molecular simulation technology improves the efficiency of drug design research,reduces the influence of human factors on simulation results,and increases the credibility of simulation results.In this review,we summarized the progress of artificial intelligence and molecular simulation technology in drug design to provide a reference for the change from computer assisted drug design(CADD)to artificial intelligence-aided drug design(AIDD)in future pharmaceutical development.

Reflections on improving drug success rates with AIDD and CADD / 中国药科大学学报

@#Abstract: The rapid advancements in artificial intelligence (AI) and computational sciences, particularly through the introduction of artificial intelligence drug design (AIDD) and computer-aided drug design (CADD) technologies, have revolutionized pathways in drug development. These include techniques such as natural language processing, image recognition, deep learning, and machine learning. By employing advanced algorithms and data processing techniques, these technologies have significantly enhanced the efficiency and success rate of R&D processes. In drug discovery, AI technologies have accelerated the identification of drug targets, screening of candidate drugs, pharmacological assessments, and quality control, effectively reducing R&D risks and costs. This article delves into the application of AIDD and CADD in drug development, analyzing their roles in enhancing the success rates and efficiencies of drug design, exploring their future trends, and addressing the potential challenges.

Advances in the application of artificial intelligence in nucleic acid drug development / 中国药科大学学报

@#Abstract: In recent years, the field of nucleic acid therapeutics has been flourishing, progressively establishing itself as the third generation of drug modalities following small molecules and antibody-based drugs. Artificial intelligence technology based on machine learning is advancing rapidly, which can significantly accelerate the development process of nucleic acid therapeutics. This review provides an overview of the foundational aspects of artificial intelligence algorithms, databases, and characterizations in the field of nucleic acid drug development. It elucidates the advances in the application of artificial intelligence in nucleic acid structural prediction, small nucleic acid drug design, and other research and development phases of nucleic acid therapeutics, aiming to offer some reference for the interdisciplinary development of artificial intelligence and nucleic acid drugs.

Aplicação de ferramentas de quimioinformática na comparação da estrutura tridimensional da dihidrofolato redutase expressa em diferentes organismos / Application of cheminformatics tools for comparing dihydrofolate reductase's tridimensional structure expressed by different organisms

A quimioinformática, definida como o emprego de técnicas informáticas na solução de problemas da química, evolui em conjunto com o desenvolvimento de ferramentas computacionais e é de grande relevância para o planejamento racional de fármacos ao otimizar etapas do desenvolvimento de novas moléculas e economizar recursos e tempo. Dentre as técnicas disponíveis destacam-se o planejamento de fármacos baseado na estrutura e no ligante, que quando combinadas auxiliam na identificação e otimização de moléculas ativas frente a alvos farmacológicos. A Dihidrofolato Redutase (DHFR) é uma importante enzima da via dos folatos que catalisa a redução do dihidrofolato em tetrahidrofolato, utilizando NADPH como cofator, reação essencial para a replicação celular, visto que este ciclo resulta na síntese de precursores das bases nitrogenadas que compõem o DNA, consequentemente, inibidores de DHFR são utilizados no tratamento de infecções bacterianas e alguns tipos de câncer. Trypanosoma cruzi, protozoário causador da doença de chagas, é um dos organismos que expressam a DHFR, além do próprio Homo sapiens. Analisaram-se ligantes conhecidos e as estruturas da proteína expressa pelos dois organismos, visando identificar pontos de divergência que possam ser explorados no planejamento de moléculas seletivas para o tratamento da doença de Chagas. Os 6 modelos cristalográficos de T. cruzi e 2 de H. sapiens foram obtidos do banco de dados de proteínas (PDB) após aplicação de filtros de qualidade. Foram analisadas as sequências de aminoácidos dos modelos, com o uso do Cluster Ômega, sua estrutura tridimensional com os programas Pymol e Chimera X, além da análise das cavidades proteicas com o CavityPlus, que também gerou os farmacóforos de ambos alvos. A análise de estrutura primária identificou mutações em três aminoácidos nos cristais do parasita, que podem ser explicados por diferentes caminhos evolutivos de grupos segregados, embora nenhuma mutação observada esteja em regiões de sítio ativo. A análise dos modelos permitiu que fossem identificados os 25 aminoácidos que estão a menos de 5 Å de distância dos ligantes de T. cruzi, sendo 5 aminoácidos responsáveis por interações de hidrogênio com pelo menos um dos ligantes analisados. Destes, 18 se repetem na proteína humana ou são substituídos por outro aminoácido que mantém a mesma interação. Quanto às diferenças observadas, destacam-se a asparagina 44 substituída por uma prolina na proteína humana e a prolina 92, substituída por uma lisina. A análise de cavidades identificou três cavidades em cada proteína, embora somente as cavidades correspondentes ao sítio ativo sejam druggables. A cavidade da proteína humana é maior e mais alongada, além de apresentar o aspecto de um túnel, enquanto a cavidade da proteína parasita é mais aberta, tal abertura permite que ligantes com o anel benzeno meta substituídos explorem uma região existente na cavidade de T. cruzi que é fechada na humana. O farmacóforo de ambas proteínas foi identificado, apresentando diferenças no tamanho e angulação que também podem ser explorados no planejamento de fármacos seletivos

Chemoinformatic, defined as the use of informatic techniques to solve chemical problems, has evolved together with new computational tools and it is quite important for rational drug designing, by optimizing different steps on the development pipeline of new molecules, saving resources and time. From all the available tools, structure and ligand based drug design shall be highlighted, when combined, they support the identification and optimization of active molecules from pharmaceutical targets. Dihydrofolate reductase (DHFR) is an important enzyme of the folate pathway that catalyzes the reduction of dihydrofolate to tetrahydrofolate, by using NADPH as cofactor. This reaction is essential for cell replication, as this pathway results in the synthesis of nucleobases that build the DNA. That's the reason why DHFR inhibitors are used for treating bacterial infections and some types of cancer. Trypanosoma cruzi, a protozoa that causes Chagas disease, is one of the organisms that express DHFR, besides Homo sapiens itself. This work analyzed known ligands and the structure of the protein expressed by both organisms, aiming to identify divergence points that could be explored for designing selective drugs for Chagas disease treatment. The 6 proteins crystallographic models from T. cruzi and 2 from H. sapiens were obtained from protein data bank (PDB) after the application of quality filters. The amino acid sequence of each model was analyzed by Clustal Omega, its tridimensional structure by Pymol and Chimera X and the cavity analysis by CavityPlus, that also generated the pharmacophore from both targets. The primary structure analysis identified mutations on three amino acids on the parasite christal, which may be explained by different evolutive paths from segregated groups, although none of the observed mutations are on the active site region. The model's analysis allowed the identification of 24 amino acids that are closer than 5 Å from the T. cruzi ligands, 5 of them responsible for hydrogen interactions on at least one of the ligands analyzed. 18 of them are repeated on the human protein or are replaced by another amino acid that preserves the same interaction. As by the differences observed that shall be highlighted, asparagine 44 is replaced by a proline on the human protein, and proline 92 by a lysin. The cavity analysis identified three cavities on each protein, although only the cavities of the active site are druggables. The human protein cavity is bigger and longer, besides it looks like its a tunnel, when the parasite protein is open, that opening allows ligands with benzene ring meta substituted to explore the existing regions of the T. cruzi protein that is closed on the human protein. Lastly, the pharmacophore from both proteins was identified, it shows differences on size and angulation that also could be explored in the designing of selective drugs

Estudo estrutural e comparativo entre Sirtuínas 2 de diferentes espécies de Leishmania / Structural and comparative study between Sirtuins 2 of different species of Leishmania by means of Comparative Modeling and Molecular Dynamic

As leishmanioses são doenças negligenciadas que afetam mais de um bilhão e meio de pessoas ao redor do mundo, principalmente nos países em desenvolvimento, provocando grandes impactos socioeconômicos. Os fármacos disponíveis para o tratamento dessas doenças são ineficazes e apresentam graves efeitos adversos. O processo de pesquisa de novos fármacos envolve, entre outras coisas, a seleção de alvos bioquímicos essenciais para a sobrevivência e desenvolvimento do agente causador. Neste sentido, a Sirtuína 2, uma enzima epigenética com atividade hidrolase essencial para a sobrevivência dos parasitas do gênero Leishmania se apresenta como um alvo validado na busca de novos fármacos contra essas parasitoses. O planejamento de fármacos baseado na estrutura do receptor requer o conhecimento da estrutura tridimensional da proteína alvo. Desta forma, a elucidação estrutural e um estudo minucioso das Sirtuínas das várias espécies do gênero Leishmania apresenta-se como uma importante abordagem na aplicação desta estratégia na busca por agentes quimioterápicos. Até o momento, na família Trypanosomatidae, a única estrutura tridimensional resolvida experimentalmente de uma enzima Sirtuína 2 é a da espécie L. infantum. Assim, este trabalho aplicou a abordagem de Modelagem Comparativa utilizando o software Modeller na construção de modelos da Sir2rp1 das espécies L. infantum, L. major e L. braziliensis, cujas sequências de aminoácidos foram extraídas do banco de dados UNIProt. Os modelos construídos foram validados por meio da função de escore DOPE do Modeller e dos servidores PROCHECK, MolProbity e QMEAN, avaliando sua qualidade estereoquímica e seu enovelamento. Os ligantes naturais da enzima foram sobrepostos nos modelos construídos por alinhamento estrutural utilizando o software PyMol e os complexos validados foram submetidos a simulações de Dinâmica Molecular através do pacote GROMACS. Os complexos refinados foram então analisados por meio dos softwares PyMol e LigPlotPlus e dos pacotes GROMACS e gmx_MMPBSA, e foram estudados os sítios de ligação dos substratos e os resíduos de aminoácidos relevantes envolvidos em sua ligação e reconhecimento. A Modelagem Comparativa da Sirtuína 2 humana e seus homólogos das espécies L. infantum, L. major e L. braziliensis, as simulações de Dinâmica Molecular realizadas com os modelos enzimáticos construídos e validados complexados com seus ligantes naturais, os cálculos de energia de interação entre os modelos e seus substratos e o estudo estrutural comparativo realizado entre eles nos fornecem uma base teórica para a busca de novos inibidores da Sirtuína 2 que sejam mais seletivos e potentes contra as enzimas parasitárias, abrindo caminho para o desenvolvimento de candidatos a fármacos leishmanicidas mais seguros e eficazes

Leishmaniasis are neglected diseases that affect more than one and a half billion people around the world, mainly in developing countries, causing major socioeconomic impacts. The drugs available for the treatment of these diseases are ineffective and have serious adverse effects. The process of researching new drugs involves, among other things, the selection of biochemical targets essential for the survival and development of the causative agent. In this sense, Sirtuin 2, an epigenetic enzyme with hydrolase activity essential for the survival of parasites of the Leishmania genus, presents itself as a validated target in the search for new drugs against these parasites. Structure-Based Drug Design requires knowledge of the three-dimensional structure of the target protein. In this way, structural elucidation and a detailed study of Sirtuins from various species of the genus Leishmania presents itself as an important approach in the application of this strategy in the search for chemotherapeutic agents. To date, in the Trypanosomatidae family, the only experimentally resolved three-dimensional structure of a Sirtuin 2 enzyme is that of the species L. infantum. Thus, this work applied the Comparative Modeling approach using the Modeller software in the construction of Sir2rp1 models of the species L. infantum, L. major and L. braziliensis, whose amino acid sequences were retrieved from the UNIProt database. The constructed models were validated using Modeller's DOPE score function and the PROCHECK, MolProbity and QMEAN servers, evaluating their stereochemical quality and folding. The enzyme's natural ligands were superimposed on the built models by structural alignment using the PyMol software and the validated complexes were subjected to Molecular Dynamics simulations using the GROMACS package. The refined complexes were then analyzed using the PyMol and LigPlotPlus softwares and the GROMACS and gmx_MMPBSA packages, and the substrate binding sites and relevant amino acid residues involved in their binding and recognition were studied. The Comparative Modeling of human Sirtuin 2 and its homologues from the species L. infantum, L. major and L. braziliensis, the Molecular Dynamics simulations carried out with the constructed and validated enzymatic models complexed with their natural ligands, the interaction energy calculations between the models and their substrates and the comparative structural study carried out between them provide us with a theoretical basis for the search for new Sirtuin 2 inhibitors that are more selective and potent against the parasitic enzymes, paving the way for the development of safer and more effective leishmanicidal drug candidates

Potencial inibitório do ácido elágico sobre a formação do complexo Keap1-Nrf2: implicações terapêuticas em doenças crônico-degenerativas / Inhibitory potential of ellagic acid on the formation of the keap1-Nrf2 complex: Therapeutical implications in chronic-degenerative diseases

Objetivos ­ Avaliar o potencial inibitório do ácido elágico sobre as interações do complexo Keap1-Nrf2, com o intuito de esclarecer um dos eventuais mecanismos associado à atividade antioxidante do ácido elágico. Métodos ­ Foram empregadas simulações de docagem molecular para prever o modo de ligação do ácido elágico no sítio ligante da proteína Keap1, o qual foi comparado com o modo de ligação obtido experimentalmente e descrito na literatura para o ligante natural, a proteína Nrf2, e um potente inibidor monoácido do complexo Keap1-Nrf2. Resultados ­ As simulações de docagem revelaram que o ácido elágico apresenta potencial para realizar uma rede de ligações de hidrogênio com resíduos de aminoácidos da proteína Keap1 considerados importantes para o reconhecimento do Nrf2, se assemelhando ao perfil observado para inibidores do complexo Keap1-Nrf2 descritos na literatura. Conclusão ­ O ácido elágico apresenta características químicas e espaciais favoráveis para a inibição do complexo Keap1-Nrf2 e a elucidação do seu modo de ligação pode auxiliar na identificação de novos produtos naturais com propriedades antioxidantes e potencializar o desenvolvimento de fármacos contra doenças crônico-degenerativas.

Blind docking of 4-Amino-7-Chloroquinoline analogs as potential dengue virus protease inhibitor using CB Dock a web server-Supplemenntary data

Currently, there is no approved drug to combat dengue. Various quinoline derivatives are known for potential antimalarial, antiviral activities, etc. In the present work docking between 4-Amino-7-Chloroquinoline analogs was performed with dengue virus NS2B/NS3 protease using CB dock, a web server. Lys74, Ile165, Val147, Asn152, Asn167, Trp83 and Leu149 amino acid residues were found to be in contact with designed 4-Amino-7-Chloroquinoline analogs. Different modes of binding like hydrogen bonding, hydrophobic interactions, etc with designed compounds improve potential anti-dengue characteristics in silico. ADME results are in acceptable range.

Blind docking of 4-Amino-7-Chloroquinoline analogs as potential dengue virus protease inhibitor using CB Dock a web server

Currently, there is no approved drug to combat dengue. Various quinoline derivatives are known for potential antimalarial, antiviral activities, etc. In the present work docking between 4-Amino-7-Chloroquinoline analogs was performed with dengue virus NS2B/NS3 protease using CB dock, a web server. Lys74, Ile165, Val147, Asn152, Asn167, Trp83 and Leu149 amino acid residues were found to be in contact with designed 4-Amino-7-Chloroquinoline analogs. Different modes of binding like hydrogen bonding, hydrophobic interactions, etc with designed compounds improve potential anti-dengue characteristics in silico. ADME results are in acceptable range.

3D-QSARpy: Combining variable selection strategies and machine learning techniques to build QSAR models

Abstract Quantitative Structure-Activity Relationship (QSAR) is a computer-aided technology in the field of medicinal chemistry that seeks to clarify the relationships between molecular structures and their biological activities. Such technologies allow for the acceleration of the development of new compounds by reducing the costs of drug design. This work presents 3D-QSARpy, a flexible, user-friendly and robust tool, freely available without registration, to support the generation of QSAR 3D models in an automated way. The user only needs to provide aligned molecular structures and the respective dependent variable. The current version was developed using Python with packages such as scikit-learn and includes various techniques of machine learning for regression. The diverse techniques employed by the tool is a differential compared to known methodologies, such as CoMFA and CoMSIA, because it expands the search space of possible solutions, and in this way increases the chances of obtaining relevant models. Additionally, approaches for select variables (dimension reduction) were implemented in the tool. To evaluate its potentials, experiments were carried out to compare results obtained from the proposed 3D-QSARpy tool with the results from already published works. The results demonstrated that 3D-QSARpy is extremely useful in the field due to its expressive results.

Discovery of novel phosphodiesterase-1 inhibitors for curing vascular dementia: Suppression of neuroinflammation by blocking NF-κB transcription regulation and activating cAMP/CREB axis

Vascular dementia (VaD) is the second commonest type of dementia which lacks of efficient treatments currently. Neuroinflammation as a prominent pathological feature of VaD, is highly involved in the development of VaD. In order to verify the therapeutic potential of PDE1 inhibitors against VaD, the anti-neuroinflammation, memory and cognitive improvement were evaluated in vitro and in vivo by a potent and selective PDE1 inhibitor 4a. Also, the mechanism of 4a in ameliorating neuroinflammation and VaD was systematically explored. Furthermore, to optimize the drug-like properties of 4a, especially for metabolic stability, 15 derivatives were designed and synthesized. As a result, candidate 5f, with a potent IC50 value of 4.5 nmol/L against PDE1C, high selectivity over PDEs, and remarkable metabolic stability, efficiently ameliorated neuron degeneration, cognition and memory impairment in VaD mice model by suppressing NF-κB transcription regulation and activating cAMP/CREB axis. These results further identified PDE1 inhibition could serve as a new therapeutic strategy for treatment of VaD.

Discovery of novel exceptionally potent and orally active c-MET PROTACs for the treatment of tumors with MET alterations

Various c-mesenchymal-to-epithelial transition (c-MET) inhibitors are effective in the treatment of non-small cell lung cancer; however, the inevitable drug resistance remains a challenge, limiting their clinical efficacy. Therefore, novel strategies targeting c-MET are urgently required. Herein, through rational structure optimization, we obtained novel exceptionally potent and orally active c-MET proteolysis targeting chimeras (PROTACs) namely D10 and D15 based on thalidomide and tepotinib. D10 and D15 inhibited cell growth with low nanomolar IC50 values and achieved picomolar DC50 values and >99% of maximum degradation (Dmax) in EBC-1 and Hs746T cells. Mechanistically, D10 and D15 dramatically induced cell apoptosis, G1 cell cycle arrest and inhibited cell migration and invasion. Notably, intraperitoneal administration of D10 and D15 significantly inhibited tumor growth in the EBC-1 xenograft model and oral administration of D15 induced approximately complete tumor suppression in the Hs746T xenograft model with well-tolerated dose-schedules. Furthermore, D10 and D15 exerted significant anti-tumor effect in cells with c-METY1230H and c-METD1228N mutations, which are resistant to tepotinib in clinic. These findings demonstrated that D10 and D15 could serve as candidates for the treatment of tumors with MET alterations.

Application and development of systems biology in computer-aided drug design / 中国中药杂志

With the advances in medicine, people have deeply understood the complex pathogenesis of diseases. Revealing the mechanism of action and therapeutic effect of drugs from an overall perspective has become the top priority of drug design. However, the traditional drug design methods cannot meet the current needs. In recent years, with the rapid development of systems biology, a variety of new technologies including metabolomics, genomics, and proteomics have been used in drug research and development. As a bridge between traditional pharmaceutical theory and modern science, computer-aided drug design(CADD) can shorten the drug development cycle and improve the success rate of drug design. The application of systems biology and CADD provides a methodological basis and direction for revealing the mechanism and action of drugs from an overall perspective. This paper introduces the research and application of systems biology in CADD from different perspectives and proposes the development direction, providing reference for promoting the application.

Application of self-assembly in polypeptide drugs: a review / 生物工程学报

Self-assembly refers to the spontaneous process where basic units such as molecules and nanostructured materials form a stable and compact structure. Peptides can self-assemble by non-covalent driving forces to form various morphologies such as nanofibers, nano layered structures, and micelles. Peptide self-assembly technology has become a hot research topic in recent years due to the advantages of definite amino acid sequences, easy synthesis and design of peptides. It has been shown that the self-assembly design of certain peptide drugs or the use of self-assembled peptide materials as carriers for drug delivery can solve the problems such as short half-life, poor water solubility and poor penetration due to physiological barrier. This review summarizes the formation mechanism of self-assembled peptides, self-assembly morphology, influencing factors, self-assembly design methods and major applications in biomedical field, providing a reference for the efficient use of peptides.

Research of the mechanism of Huganning tablet in the treatment of nonalcoholic fatty liver disease based on network pharmacology and computer-aided drug design / 药学学报

In this study, we explored the mechanism of Huganning tablet (HGNP) in the treatment of nonalcoholic fatty liver disease (NAFLD) based on network pharmacology and computer-aided drug design. Firstly, the potential ingredients and targets of HGNP were identified from TCMSP database, Swiss Target Prediction database, Chinese pharmacopoeia (2015) and literatures, and then the targets of HGNP intersected with NAFLD disease targets that obtained in GeneCards database to acquired potential targets. The bioconductor bioinformatics package of R software was used for gene ontology (GO) enrichment and Kyoto encyclopedia of genes and genomes (KEGG) enrichment analysis. The network of “potential ingredient-key target-pathway” was formed in Cytoscape software to study the interactions between potential ingredients of HGNP, key targets, pathways and NAFLD. Based on the results of network pharmacology, the molecular docking analysis of the key targets and potential active ingredients in HGNP tablets with top degree in the network was conducted using Discovery Studio 2020 software, followed by molecular dynamics simulations, binding free energy calculation, drug-likeness properties analysis and ADMET (absorption, distribution, metabolism, excretion and toxicity) properties prediction. In vitro, HepG2 cells were used to establish steatosis model, and the effects of five key compounds on hepatocyte steatosis were analyzed by oil red O staining and triglyceride (TG) content determination. The results showed that 141 ingredients and 151 potential targets were obtained. A total of 2 526 items and 151 pathways were identified by GO and KEGG enrichment analysis. The molecular docking suggested that five components, isorhamnetin, salvianolic acid B, emodin, resveratrol and rhein, exhibited strong binding ability with key targets [retinoic acid receptor RXR-alpha (RXRA), tumor necrosis factor (TNF), glycogen synthase kinase-3 beta (GSK3B), serine/threonine-protein kinase 1 (AKT1)]. It was further verified that isorhamnetin and salvianolic acid B bind to key targets with good structural stability and binding affinity based on molecular dynamics simulations and binding free energy calculations. The drug-likeness properties, pharmacokinetic properties and toxicity of five key compounds were more comprehensively analyzed through drug-likeness properties analysis and ADMET properties prediction. In vitro, all five compounds, isorhamnetin, salvianolic acid B, emodin, resveratrol, and rhein, improved hepatocyte steatosis of HepG2 cells, confirming the reliability of the present study. In conclusion, based on network pharmacology, computer-aided drug design and in vitro validation, this study investigated the mechanism of HGNP for the treatment of NAFLD at multiple levels and provided a basis for its clinical application.

FBDD and drugs originated from FBDD / 药学学报

The binding of small molecule drugs to targets is mostly through non-covalent bonds, and hydrogen bond, electrostatic, hydrophobic and van der Waals interactions function to maintain the binding force. The more these binding factors lead to strong bindings and high activities. However, it is often accompanied by the increase of molecular size, resulting in pharmacokinetic problems such as membrane penetration and absorption, as well as metabolism, which ultimately affects the drug success. Fragment-based drug discovery (FBDD) is to screen high-quality fragment library to find hits. Combine with structural biology, FBDD generates lead compounds by means of fragment growth, linking and fusion, and finally drug candidates by the optimization operation. During the value chain FBDD is closely related to structure-based drug discovery (SBDD). In this paper, the principle of FBDD is briefly described by several launched drugs.

Application and advance of artificial intelligence in biomedical field / 中国药科大学学报

@#Artificial intelligence (AI) has developed rapidly in the twentieth century, and has substantialy changed the modern way of life.At the same time, AI has greatly contributed to the development of the pharmaceutical industry, playing a key role in precision medicine, intelligent diagnosis, computer-aided drug design, and clinical trial decision-making, and has also greatly developed itself through its integration with the pharmaceutical industry.This paper outlines the key issues in research, describes the key applications of AI in the health and pharmaceutical industries, and finally analyzes the opportunities and challenges of AI in the health pharmaceutical industry to provide reference for the development of AI in the health and pharmaceutical fields.

Artificial intelligence-based drug development: current progress and future challenges / 中国药科大学学报

@#In recent years, artificial intelligence (AI) has been widely applied in the field of drug discovery and development.In particular, natural language processing technology has been significantly improved after the emergence of the pre-training model.On this basis, the introduction of graph neural network has also made drug development more accurate and efficient.In order to help drug developers more systematically and comprehensively understand the application of artificial intelligence in drug discovery, this article introduces cutting-edge algorithms in AI, and elaborates on the various applications of AI in drug development, including drug small molecule design, virtual screening, drug repurposing, and drug property prediction, finally discusses the opportunities and challenges of AI in future drug development.

Deep learning-based de novo drug design: principles, tools and practice / 药学学报

Design of structurally-novel drug molecules with deep learning can overcome the technical bottleneck of classical computer-aided drug design. It has become the frontier of new technique research on drug design, and has shown great potential in drug research and development practice. This review starts from the basic principles of deep learning-driven de novo drug design, goes on with the brief introduction to deep molecular generation techniques as well as computational tools and the analysis on representative successful cases, and eventually provides our perspective for future direction and application prospect about this technique. This review will provide ideas on new technique research and references for new drug research and development practice to which this technique is applied.

Molecular mechanism of Cigu Xiaozhi formula interfering with HSC-T6 cell activation by regulating HIF-1α signaling pathway based on computer aided drug design / 药学学报

In this study, we investigated the effect of Cigu Xiaozhi formula on HSC-T6 activity in hypoxic microenvironment based on network pharmacology and computer-aided drug design, and predicted and verified its possible targets and related signaling pathways. The potential active components and targets of Cigu Xiaozhi formula were screened by searching Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP), Encyclopaedia of Traditional Chinese Medicine (ETCM) and Bioinformatics Analysis Tool for Molecular Mechanism of Traditional Chinese Medicine (BATMAN-TCM) databases, and the liver fibrosis related targets retrieved from Gene Cards and Pharm GK database were integrated to obtain the potential targets of Cigu Xiaozhi formula in the treatment of liver fibrosis. GO enrichment analysis and KEGG signaling pathway enrichment analysis were performed on Omic Share platform, and Cytoscape software was used to construct the "potential active ingredient-key target-pathway" network. The active components and target proteins were subjected to molecular docking analysis by Auto Dock software. According to the results of molecular dynamics simulation and binding free energy calculation, the top 5 active components with degree were scored. The active components stigmasterol and β-sitosterol were subjected to molecular docking. CoCl2 was used to induce HSC-T6 cells to construct hypoxia model in vitro. The cell viability was detected by CCK-8 assay, and the optimal time and concentration of hypoxia model of HSC-T6 cells was determined to be 100 µmol·L-1 CoCl2 for 24 h. Under hypoxia condition, HSC-T6 cells were activated, the wound healing rate was significantly increased, and the fluorescence signal of activation marker protein α-smooth muscle actin (α-SMA) was significantly enhanced. However, 6% drug-containing serum could inhibit the activation of HSC-T6 cells, and the wound healing rate was significantly decreased, and the fluorescence signal of α-SMA was significantly weakened. Further studies showed that the expressions of hypoxia-inducible factor-1α (HIF-1α), α-SMA and key proteins of Hedgehog (Hh) signaling pathway in HSC-T6 cells were up-regulated under hypoxia, while the expressions of HIF-1α, α-SMA, Patched-1 (Ptch-1) and glioma related oncogene homology-1 (Gli-1) were down-regulated in 6% drug-containing serum group, the YC-1 group and the cyclopamine group. These results indicated that HIF-1α and Hh signaling pathways were involved in the activation of HSC-T6 cells, and the traditional Chinese medicine Cigu Xiaozhi formula could inhibit the activation of HSC-T6 cells, and the mechanism may be related to the inhibition of HIF-1α expression and the blocking of Hh signaling pathway. In conclusion, Cigu Xiaozhi formula can inhibit the activation of HSC-T6 cells by directly acting on HIF-1α and Hh signaling pathway, and exert an anti-hepatic fibrosis effect. The animal experimental protocol has been reviewed and approved by Laboratory Animal Ethics Committee of Gansu University of Chinese Medicine, in compliance with the Institutional Animal Care Guidelines.

Structure-based drug discovery of novel fused-pyrazolone carboxamide derivatives as potent and selective AXL inhibitors

As a novel and promising antitumor target, AXL plays an important role in tumor growth, metastasis, immunosuppression and drug resistance of various malignancies, which has attracted extensive research interest in recent years. In this study, by employing the structure-based drug design and bioisosterism strategies, we designed and synthesized in total 54 novel AXL inhibitors featuring a fused-pyrazolone carboxamide scaffold, of which up to 20 compounds exhibited excellent AXL kinase and BaF3/TEL-AXL cell viability inhibitions. Notably, compound 59 showed a desirable AXL kinase inhibitory activity (IC50: 3.5 nmol/L) as well as good kinase selectivity, and it effectively blocked the cellular AXL signaling. In turn, compound 59 could potently inhibit BaF3/TEL-AXL cell viability (IC50: 1.5 nmol/L) and significantly suppress GAS6/AXL-mediated cancer cell invasion, migration and wound healing at the nanomolar level. More importantly, compound 59 oral administration showed good pharmacokinetic profile and in vivo antitumor efficiency, in which we observed significant AXL phosphorylation suppression, and its antitumor efficacy at 20 mg/kg (qd) was comparable to that of BGB324 at 50 mg/kg (bid), the most advanced AXL inhibitor. Taken together, this work provided a valuable lead compound as a potential AXL inhibitor for the further antitumor drug development.