اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدHierarchy and assortativity as new tools for affinity investigation: the case of the TBA aptamer-ligand complex
44
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Aptamers are single stranded DNA, RNA or peptide sequences having the ability to bind a variety of specific targets (proteins, molecules as well as ions). Therefore, aptamer production and selection for therapeutic and diagnostic applications is very challenging. Usually they are in vitro generated, but, recently, computational approaches have been developed for the in silico selection, with a higher affinity for the specific target. Anyway, the mechanism of aptamer-ligand formation is not completely clear, and not obvious to predict. This paper aims to develop a computational model able to describe aptamer-ligand affinity performance by using the topological structure of the corresponding graphs, assessed by means of numerical tools such as the conventional degree distribution, but also the rank-degree distribution (hierarchy) and the node assortativity. Calculations are applied to the thrombin binding aptamer (TBA), and the TBA-thrombin complex, produced in the presence of Na+ or K+. The topological analysis reveals different affinity performances between the macromolecules in the presence of the two cations, as expected by previous investigations in literature. These results nominate the graph topological analysis as a novel theoretical tool for testing affinity. Otherwise, starting from the graphs, an electrical network can be obtained by using the specific electrical properties of amino acids and nucleobases. Therefore, a further analysis concerns with the electrical response, which reveals that the resistance sensitively depends on the presence of sodium or potassium thus posing resistance as a crucial physical parameter for testing affinity.
قيم البحث
اقرأ أيضاً
The cornerstone of computational drug design is the calculation of binding affinity between two biological counterparts, especially a chemical compound, i.e., a ligand, and a protein. Predicting the strength of protein-ligand binding with reasonable
accuracy is critical for drug discovery. In this paper, we propose a data-driven framework named DeepAtom to accurately predict the protein-ligand binding affinity. With 3D Convolutional Neural Network (3D-CNN) architecture, DeepAtom could automatically extract binding related atomic interaction patterns from the voxelized complex structure. Compared with the other CNN based approaches, our light-weight model design effectively improves the model representational capacity, even with the limited available training data. With validation experiments on the PDBbind v.2016 benchmark and the independent Astex Diverse Set, we demonstrate that the less feature engineering dependent DeepAtom approach consistently outperforms the other state-of-the-art scoring methods. We also compile and propose a new benchmark dataset to further improve the model performances. With the new dataset as training input, DeepAtom achieves Pearsons R=0.83 and RMSE=1.23 pK units on the PDBbind v.2016 core set. The promising results demonstrate that DeepAtom models can be potentially adopted in computational drug development protocols such as molecular docking and virtual screening.
Motivation: Protein-ligand affinity prediction is an important part of structure-based drug design. It includes molecular docking and affinity prediction. Although molecular dynamics can predict affinity with high accuracy at present, it is not suita
ble for large-scale virtual screening. The existing affinity prediction and evaluation functions based on deep learning mostly rely on experimentally-determined conformations. Results: We build a predictive model of protein-ligand affinity through the ResNet neural network with added attention mechanism. The resulting ResAtom-Score model achieves Pearsons correlation coefficient R = 0.833 on the CASF-2016 benchmark test set. At the same time, we evaluated the performance of a variety of existing scoring functions in combination with ResAtom-Score in the absence of experimentally-determined conformations. The results show that the use of {Delta}VinaRF20 in combination with ResAtom-Score can achieve affinity prediction close to scoring functions in the presence of experimentally-determined conformations. These results suggest that ResAtom system may be used for in silico screening of small molecule ligands with target proteins in the future. Availability: https://github.com/wyji001/ResAtom
There is great interest to develop artificial intelligence-based protein-ligand affinity models due to their immense applications in drug discovery. In this paper, PointNet and PointTransformer, two pointwise multi-layer perceptrons have been applied
for protein-ligand affinity prediction for the first time. Three-dimensional point clouds could be rapidly generated from the data sets in PDBbind-2016, which contain 3 772 and 11 327 individual point clouds derived from the refined or/and general sets, respectively. These point clouds were used to train PointNet or PointTransformer, resulting in protein-ligand affinity prediction models with Pearson correlation coefficients R = 0.831 or 0.859 from the larger point clouds respectively, based on the CASF-2016 benchmark test. The analysis of the parameters suggests that the two deep learning models were capable to learn many interactions between proteins and their ligands, and these key atoms for the interaction could be visualized in point clouds. The protein-ligand interaction features learned by PointTransformer could be further adapted for the XGBoost-based machine learning algorithm, resulting in prediction models with an average Rp of 0.831, which is on par with the state-of-the-art machine learning models based on PDBbind database. These results suggest that point clouds derived from the PDBbind datasets are useful to evaluate the performance of 3D point clouds-centered deep learning algorithms, which could learn critical protein-ligand interactions from natural evolution or medicinal chemistry and have wide applications in studying protein-ligand interactions.
Based entirely upon actual experimental observations on electron-phonon coupling, we develop a theoretical framework to show that the lowest energy band of the Fenna- Matthews-Olson (FMO) complex exhibits observable features due to the quantum nature
of the vibrational manifolds present in its chromophores. The study of linear spectra provides us with the basis to understand the dynamical features arising from the vibronic structure in non-linear spectra in a progressive fashion, starting from a microscopic model to finally performing an inhomogenous average. We show that the discreteness of the vibronic structure can be witnessed by probing the diagonal peaks of the non-linear spectra by means of a relative phase shift in the waiting time resolved signal. Moreover, we demonstrate the photon-echo and non-rephasing paths are sensitive to different harmonics in the vibrational manifold when static disorder is taken into account. Supported by analytical and numerical calculations, we show that nondiagonal resonances in the 2D spectra in the waiting time, further capture the discreteness of vibrations through a modulation of the amplitude without any effect in the signal intrinsic frequency. This fact generates a signal that is highly sensitive to correlations in the static disorder of the excitonic energy albeit protected against dephasing due to inhomogeneities of the vibrational ensemble.
Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-l
igand complexes. However, existing solutions usually treat protein-ligand complexes as topological graph data, thus the biomolecular structural information is not fully utilized. The essential long-range interactions among atoms are also neglected in GNN models. To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool). Specifically, PGAL iteratively performs the node-edge aggregation process to update embeddings of nodes and edges while preserving the distance and angle information among atoms. Then, PiPool is adopted to gather interactive edges with a subsequent reconstruction loss to reflect the global interactions. Exhaustive experimental study on two benchmarks verifies the superiority of SIGN.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
