GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47

Shan, Wenying; Chen, Lvqi; Xu, Hao; Zhong, Qinghao; Xu, Yinqiu; Yao, Hequan; Lin, Kejiang; Li, Xuanyi

doi:10.3389/fchem.2023.1292869

Cited by 3 publications

(2 citation statements)

References 43 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the establishment of some libraries containing structurally diverse compounds and the extraordinary advances of machine learning and deep learning, artificial intelligence (AI) has begun to participate in the screening of small molecule drugs 115 , 116 , including protein structural prediction, molecular virtual screening, molecular design, and drug pharmacokinetic prediction 117 , 118 . At present, novel small molecule inhibitors of CD47 have been predicted and designed by AI technology 36 . The involvement of AI technology substantially reduces the cycle and cost of drug research and development, and raises drug discovery efficiency, which represents promising prospects for discovering small molecule inhibitors of immune checkpoints.…”

Section: Prospectmentioning

confidence: 99%

Development of small molecule drugs targeting immune checkpoints

Chen,

Zhao,

Liu

et al. 2024

Cancer Biol Med

View full text Add to dashboard Cite

Immune checkpoint inhibitors (ICIs) are used to relieve and refuel anti-tumor immunity by blocking the interaction, transcription, and translation of co-inhibitory immune checkpoints or degrading co-inhibitory immune checkpoints. Thousands of small molecule drugs or biological materials, especially antibody-based ICIs, are actively being studied and antibodies are currently widely used. Limitations, such as anti-tumor efficacy, poor membrane permeability, and unneglected tolerance issues of antibody-based ICIs, remain evident but are thought to be overcome by small molecule drugs. Recent structural studies have broadened the scope of candidate immune checkpoint molecules, as well as innovative chemical inhibitors. By way of comparison, small molecule drug-based ICIs represent superior oral bioavailability and favorable pharmacokinetic features. Several ongoing clinical trials are exploring the synergetic effect of ICIs and other therapeutic strategies based on multiple ICI functions, including immune regulation, anti-angiogenesis, and cell cycle regulation. In this review we summarized the current progression of small molecule ICIs and the mechanism underlying immune checkpoint proteins, which will lay the foundation for further exploration.

show abstract

Section: Prospectmentioning

confidence: 99%

Development of small molecule drugs targeting immune checkpoints

Chen,

Zhao,

Liu

et al. 2024

Cancer Biol Med

View full text Add to dashboard Cite

show abstract

“…In recent years, AI, especially deep learning, has been applied to all stages of drug development, significantly improving high drug development cost, long drug development cycle, and low success rate of drug marketing. − At present, deep learning simulates brain neurons to build the neural network and realizes the nonlinear transmission of data information through the activation function. However, currently common activation functions, such as Sigmoid, tanh, and ReLU, do not mimic the spike signal of brain neurons.…”

Section: Introductionmentioning

confidence: 99%

Discovery of Covalent Lead Compounds Targeting 3CL Protease with a Lateral Interactions Spiking Neural Network

Gu,

Yan,

Liu

et al. 2024

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Covalent drugs exhibit advantages in that noncovalent drugs cannot match, and covalent docking is an important method for screening covalent lead compounds. However, it is difficult for covalent docking to screen covalent compounds on a large scale because covalent docking requires determination of the covalent reaction type of the compound. Here, we propose to use deep learning of a lateral interactions spiking neural network to construct a covalent lead compound screening model to quickly screen covalent lead compounds. We used the 3CL protease (3CL Pro) of SARS-CoV-2 as the screen target and constructed two classification models based on LISNN to predict the covalent binding and inhibitory activity of compounds. The two classification models were trained on the covalent complex data set targeting cysteine (Cys) and the compound inhibitory activity data set targeting 3CL Pro, respected, with good prediction accuracy (ACC > 0.9). We then screened the screening compound library with 6 covalent binding screening models and 12 inhibitory activity screening models. We tested the inhibitory activity of the 32 compounds, and the best compound inhibited SARS-CoV-2 3CL Pro with an IC 50 value of 369.5 nM. Further assay implied that dithiothreitol can affect the inhibitory activity of the compound to 3CL Pro, indicating that the compound may covalently bind 3CL Pro. The selectivity test showed that the compound had good target selectivity to 3CL Pro over cathepsin L. These correlation assays can prove the rationality of the covalent lead compound screening model. Finally, covalent docking was performed to demonstrate the binding conformation of the compound with 3CL Pro. The source code can be obtained from the GitHub repository (https://github.com/guzh970630/Screen_Covalent_Compound_by_ LISNN).

show abstract

An end-to-end method for predicting compound-protein interactions based on simplified homogeneous graph convolutional network and pre-trained language model

Zhang,

Li,

Lin

et al. 2024

J Cheminform

View full text Add to dashboard Cite

Identification of interactions between chemical compounds and proteins is crucial for various applications, including drug discovery, target identification, network pharmacology, and elucidation of protein functions. Deep neural network-based approaches are becoming increasingly popular in efficiently identifying compound-protein interactions with high-throughput capabilities, narrowing down the scope of candidates for traditional labor-intensive, time-consuming and expensive experimental techniques. In this study, we proposed an end-to-end approach termed SPVec-SGCN-CPI, which utilized simplified graph convolutional network (SGCN) model with low-dimensional and continuous features generated from our previously developed model SPVec and graph topology information to predict compound-protein interactions. The SGCN technique, dividing the local neighborhood aggregation and nonlinearity layer-wise propagation steps, effectively aggregates K-order neighbor information while avoiding neighbor explosion and expediting training. The performance of the SPVec-SGCN-CPI method was assessed across three datasets and compared against four machine learning- and deep learning-based methods, as well as six state-of-the-art methods. Experimental results revealed that SPVec-SGCN-CPI outperformed all these competing methods, particularly excelling in unbalanced data scenarios. By propagating node features and topological information to the feature space, SPVec-SGCN-CPI effectively incorporates interactions between compounds and proteins, enabling the fusion of heterogeneity. Furthermore, our method scored all unlabeled data in ChEMBL, confirming the top five ranked compound-protein interactions through molecular docking and existing evidence. These findings suggest that our model can reliably uncover compound-protein interactions within unlabeled compound-protein pairs, carrying substantial implications for drug re-profiling and discovery. In summary, SPVec-SGCN demonstrates its efficacy in accurately predicting compound-protein interactions, showcasing potential to enhance target identification and streamline drug discovery processes.Scientific contributionsThe methodology presented in this work not only enables the comparatively accurate prediction of compound-protein interactions but also, for the first time, take sample imbalance which is very common in real world and computation efficiency into consideration simultaneously, accelerating the target identification and drug discovery process.

show abstract

GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47

Cited by 3 publications

References 43 publications

Development of small molecule drugs targeting immune checkpoints

Development of small molecule drugs targeting immune checkpoints

Discovery of Covalent Lead Compounds Targeting 3CL Protease with a Lateral Interactions Spiking Neural Network

An end-to-end method for predicting compound-protein interactions based on simplified homogeneous graph convolutional network and pre-trained language model

Contact Info

Product

Resources

About