Aqueous Developable and CO2-Sourced Chemical Amplification Photoresist with High Performance.

Seeking high-performance photoresists is an important item for semiconductor industry due to the continuous miniaturization and intelligentization of integrated circuits. Polymer resin containing carbonate group has many desirable properties, such as high transmittance, acid sensitivity and chemical formulation, thus serving as promising photoresist material. In this work, a series of aqueous developable CO2-sourced polycarbonates (CO2-PCs) were produced via alternating copolymerization of CO2 and epoxides bearing acid-cleavable cyclic acetal groups in the presence of tetranuclear organoborane catalyst. The produced CO2-PCs were investigated as chemical amplification resists in deep ultraviolet (DUV) lithography. Under the catalysis of photogenerated acid, the acetal (ketal) groups in CO2-PC were hydrolysed into two equivalents of hydroxyl groups, which change the exposed area from hydrophobicity to hydrophilicity, thus enabling the exposed area to be developed with water. Through normalized remaining thickness analysis, the optimal CO2-derived resist achieved a remarkable sensitivity of 1.9 mJ/cm2, a contrast of 7.9, a favorable resolution (750 nm, half pitch), and a good etch resistance (38 % higher than poly(tert-butyl acrylate)). Such performances outperform commercial KrF and ArF chemical amplification resists (i.e., polyhydroxystyrene-derived and polymethacrylate-based resists), which endows broad application prospects in the field of DUV (KrF and ArF) and extreme ultraviolet (EUV) lithography for nanomanufacturing.

Novel Structural Design and Adsorption/Insertion Coordinating Quasi-Metallic Na Storage Mechanism toward High-performance Hard Carbon Anode Derived from Carboxymethyl Cellulose.

Hard Carbon have become the most promising anode candidates for sodium-ion batteries, but the poor rate performance and cycle life remain key issues. In this work, N-doped hard carbon with abundant defects and expanded interlayer spacing is constructed by using carboxymethyl cellulose sodium as precursor with the assistance of graphitic carbon nitride. The formation of N-doped nanosheet structure is realized by the CN• or CC• radicals generated through the conversion of nitrile intermediates in the pyrolysis process. This greatly enhances the rate capability (192.8 mAh g-1 at 5.0 A g-1 ) and ultra-long cycle stability (233.3 mAh g-1 after 2000 cycles at 0.5 A g-1 ). In situ Raman spectroscopy, ex situ X-ray diffraction and X-ray photoelectron spectroscopy analysis in combination with comprehensive electrochemical characterizations, reveal that the interlayer insertion coordinated quasi-metallic sodium storage in the low potential plateau region and adsorption storage in the high potential sloping region. The first-principles density functional theory calculations further demonstrate strong coordination effect on nitrogen defect sites to capture sodium, especially with pyrrolic N, uncovering the formation mechanism of quasi-metallic bond in the sodium storage. This work provides new insights into the sodium storage mechanism of high-performance carbonaceous materials, and offers new opportunities for better design of hard carbon anode.

MultiGran-SMILES: multi-granularity SMILES learning for molecular property prediction.

MOTIVATION: Extracting useful molecular features is essential for molecular property prediction. Atom-level representation is a common representation of molecules, ignoring the sub-structure or branch information of molecules to some extent; however, it is vice versa for the substring-level representation. Both atom-level and substring-level representations may lose the neighborhood or spatial information of molecules. While molecular graph representation aggregating the neighborhood information of a molecule has a weak ability in expressing the chiral molecules or symmetrical structure. In this article, we aim to make use of the advantages of representations in different granularities simultaneously for molecular property prediction. To this end, we propose a fusion model named MultiGran-SMILES, which integrates the molecular features of atoms, sub-structures and graphs from the input. Compared with the single granularity representation of molecules, our method leverages the advantages of various granularity representations simultaneously and adjusts the contribution of each type of representation adaptively for molecular property prediction. RESULTS: The experimental results show that our MultiGran-SMILES method achieves state-of-the-art performance on BBBP, LogP, HIV and ClinTox datasets. For the BACE, FDA and Tox21 datasets, the results are comparable with the state-of-the-art models. Moreover, the experimental results show that the gains of our proposed method are bigger for the molecules with obvious functional groups or branches. AVAILABILITY AND IMPLEMENTATION: The code and data underlying this work are available on GitHub at https://github. com/Jiangjing0122/MultiGran. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Noninvasive assessment of myocardial work during left ventricular isovolumic relaxation in patients with diastolic dysfunction.

BACKGROUND: This study aims to investigate the value of myocardial work (MW) parameters during the isovolumic relaxation (IVR) period in patients with left ventricular diastolic dysfunction (LVDD). METHODS: This study prospectively recruited 448 patients with risks for LVDD and 95 healthy subjects. An additional 42 patients with invasive measurements of left ventricular (LV) diastolic function were prospectively included. The MW parameters during IVR were noninvasively measured using EchoPAC. RESULTS: The total myocardial work during IVR (MWIVR), myocardial constructive work during IVR (MCWIVR), myocardial wasted work during IVR (MWWIVR), and myocardial work efficiency during IVR (MWEIVR) of these patients were 122.5 ± 60.1 mmHg%, 85.7 ± 47.8 mmHg%, 36.7 ± 30.6 mmHg%, and 69.4 ± 17.8%, respectively. The MW during IVR was significantly different between patients and healthy subjects. For patients, MWEIVR and MCWIVR were significantly correlated with the LV E/e' ratio and left atrial volume index, MWEIVR exhibited a significant correlation with the maximal rate of decrease in LV pressure (dp/dt per min) and tau, and the MWEIVR corrected by IVRT also exhibited a significant correlation with tau. CONCLUSIONS: MW during IVR significantly changes in patients with risks for LVDD, and is correlated to LV conventional diastolic indices, including dp/dt min and tau. Noninvasive MW during IVR may be a promising tool to evaluate the LV diastolic function.

Clinical Outcomes of Cardiac Shockwave Therapy in Severe Coronary Artery Disease Patients after Coronary Artery Bypass Grafting.

Cardiac shockwave therapy (CSWT) is a noninvasive treatment for patients with refractory angina or myocardial ischemia. This study aims to evaluate the potential beneficial effect and safety of CSWT in patients with severe coronary artery disease (CAD) who have undergone coronary artery bypass grafting (CABG).This was a single-arm prospective cohort study. A total of 30 patients with severe CAD who were not suitable for coronary revascularization and who had undergone CABG were enrolled. All patients received CSWT for nine sessions. Evaluation was performed before and after CSWT, including the Canadian Cardiovascular Society (CCS) classification, New York Heart Association (NYHA) classification, 6-minute walk test (6MWT), Seattle Angina Questionnaire (SAQ) score, nitroglycerin dosage, echocardiography, myocardial perfusion imaging (MPI), and safety parameters. All patients were followed up at both 1 month and 9 months after CSWT.After treatment, CSWT significantly improved CCS classification (P < 0.05), NYHA classification (P < 0.05), nitroglycerin dosage (P < 0.001), and 6MWT (P < 0.05) at 1 month and 9 months after CSWT. SAQ score (P < 0.05) and left ventricular ejection fraction (LVEF; P = 0.037) by echocardiography significantly improved at 1 month after CSWT. Significant decreases in summed stress score (SSS), summed difference score (SDS), ischemic area stress, and ischemic area difference by MPI were observed at 1 month and 9 months after CSWT (P < 0.01). There were no changes in safety parameters before and after CSWT.CSWT may have a beneficial effect on improving myocardial perfusion, clinical symptoms, exertional capacity, and quality of life and is a safe alternative treatment for patients with severe CAD who have undergone CABG.

TranGRU: focusing on both the local and global information of molecules for molecular property prediction.

Molecular property prediction is an essential but challenging task in drug discovery. The recurrent neural network (RNN) and Transformer are the mainstream methods for sequence modeling, and both have been successfully applied independently for molecular property prediction. As the local information and global information of molecules are very important for molecular properties, we aim to integrate the bi-directional gated recurrent unit (BiGRU) into the original Transformer encoder, together with self-attention to better capture local and global molecular information simultaneously. To this end, we propose the TranGRU approach, which encodes the local and global information of molecules by using the BiGRU and self-attention, respectively. Then, we use a gate mechanism to reasonably fuse the two molecular representations. In this way, we enhance the ability of the proposed model to encode both local and global molecular information. Compared to the baselines and state-of-the-art methods when treating each task as a single-task classification on Tox21, the proposed approach outperforms the baselines on 9 out of 12 tasks and state-of-the-art methods on 5 out of 12 tasks. TranGRU also obtains the best ROC-AUC scores on BBBP, FDA, LogP, and Tox21 (multitask classification) and has a comparable performance on ToxCast, BACE, and ecoli. On the whole, TranGRU achieves better performance for molecular property prediction. The source code is available in GitHub: https://github.com/Jiangjing0122/TranGRU.

Efficacy and safety of cardiac shock wave therapy for patients with severe coronary artery disease: A randomized, double-blind control study.

BACKGROUND: Previous studies proved the efficacy of cardiac shock wave therapy (CSWT) for coronary artery disease (CAD) patients who are not candidate for reperfusion therapy. Randomized control trials are limited. We try to explore the efficacy and safety of CSWT for patients with severe CAD. METHODS: Thirty patients with severe CAD who had obvious ischemia on myocardial perfusion imaging (MPI) were enrolled and randomly assigned to the CSWT group or the control group. They had received optimal medication treatment for at least three months. Nine sessions of shock wave therapy were conducted over 3 months. CSWT group received the real treatment, while the control group received the pseudo-treatment. Clinical symptom, imaging outcomes and safety parameters were compared between two groups. RESULTS: After treatment, regional stress score (P = .023), improvement rate (IR) of ischemic area (IA) stress (P < .001) and IR of IA difference (P < .001) were significantly favor CSWT group. The interaction of summed rest score (P < .001), summed stress score (P = .004), summed difference score (P = .036) were significantly improved in the CSWT group compared to the control group. Seattle angina questionnaire, quality of life (QOL) and the distance of six-minute walking test (6MWT) were improved in both groups without significant difference between them. Hemodynamic parameters were stable during procedure. Myocardial injury markers showed no changes in two groups. CONCLUSIONS: Our study demonstrated CSWT could effectively and safely improve myocardial perfusion in patients with severe CAD. Clinical symptom, QOL and 6MWT were all improved after treatment, but no significant difference between two groups.

Quantum Chemical Calculations with Machine Learning for Multipolar Electrostatics Prediction in RNA: An Application to Pentose.

To develop a realistic electrostatic model that allows for the anisotropy of the atomic electron density, high-rank atomic multipole moments computed by quantum chemical calculations have been studied extensively. However, it is hard to process huge RNA systems only relying on quantum chemical calculations due to its highly computational cost. In this study, we employ five machine learning methods of Gaussian process regression with automatic relevance determination (ARDGPR), Kriging, radial basis function neural networks, Bagging, and generalized regression neural network to predict atomic multipole moments. Atom-atom electrostatic interaction energies are subsequently computed using the predicted atomic multipole moments in the pilot system pentose of RNA. Here, the performance of the five methods is compared in terms of both the multipole moment prediction errors and the electrostatic energy prediction errors. For the predicted high-rank multipole moments of the four elements (O, C, N, and H) in capped pentose, ARDGPR and Kriging consistently outperform the other three methods. Therefore, the multipole moments predicted by the two best methods of ARDGPR and Kriging are then used to predict electrostatic interaction energy of each pentose. Finally, the absolute average energy errors of ARDGPR and Kriging are 1.83 and 4.33 kJ mol-1, respectively. Compared to Kriging, the ARDGPR method achieves a 58% decrease in the absolute average energy error. These satisfactory results demonstrated that the ARDGPR method with the strong feature extraction ability can predict the electrostatic interaction energy of pentose in RNA correctly and reliably.

The value of myocardial work in assessment of ventricular function in patients with non-obstructive hypertrophic cardiomyopathy.

BACKGROUND: To evaluate myocardial work using speckle tracking echocardiography in patients with non-obstructive hypertrophic cardiomyopathy (HCM). METHODS: Fifty patients with HCM and 50 normal controls were included. Left ventricular ejection fraction (LVEF) was quantified using the bi-plane Simpson's method. Myocardial work parameters, which included global work index (GWI), global constructive work (GCW), global waste work (GWW), and global work efficiency (GWE), were derived from the 2D strain-pressure loop. RESULTS: The patient group was older (49.19 ± 14.69 vs. 37.16 ± 7.49 years old) and had a higher body mass index (24.93 ± 3.67 vs. 23.26 ± 3.32 kg/m2) and systolic blood pressure (121.81 ± 16.50 vs. 115.30 ± 11.01 mmHg) (P < 0.05). The mean LVEF in patients was 51%, with 54% of patients had LVEF ≤ 50%. Compared to controls, GWI (946.42 ± 360.64 vs. 1639.72 ± 204.56 mmHg%), GCW (1176.94 ± 373.23 vs. 1960.16 ± 255.72 mmHg%), and GWE (83.96 ± 7.68 vs. 95.26 ± 1.98%) were significantly decreased, while GWW (158.17 ± 82.47 vs. 79.12 ± 40.26 mmHg%) was significantly increased (P < 0.05) in the patient group. In patients, GWE showed a trend of positive correlation with LVEF (r = 0.276, P = 0.06), while GWW had a trend of negative correlation with LVEF (r = - 0.241, P = 0.09). No correlation between myocardial work and LV diastolic function or QRS duration was observed. Maximal wall thickness significantly correlated with all the myocardial work parameters. CONCLUSIONS: Assessing myocardial work adds useful information of LV function in patients with non-obstructive HCM.

Multipolar electrostatics for hairpin and pseudoknots in RNA: Improving the accuracy of force field potential energy function.

Molecular dynamics (MD) simulations that rely on force field methods has been widely used to explore the structure and function of RNAs. However, the current commonly used force fields are limited by the electrostatic description offered by atomic charge, dipole and at most quadrupole moments, failing to capture the anisotropic picture of electronic features. Actually, the distribution of electrons around atomic nuclei is not spherically symmetric but is geometry dependent. A multipolar electrostatic model based on high rank multipole moments is described in this work, which allows us to combine polarizability and anisotropy of electron density. RNA secondary structure was taken as a research system, and its substructures including stem, loops (hairpin loop, bulge loop, internal loop, and multi-branch loop), and pseudoknots (H-type and K-type) were investigated, respectively, as well as the hairpin. First, the atom-atom electrostatic properties derived from one chain of a duplex RNA 2MVY in our previous work (Ref. 58) were measured by the pilot RNA systems of hairpin, hairpin loop, stem, and H-type pseudoknot, respectively. The prediction results were not satisfactory. Consequently, to obtain a general set of electrostatic parameters for RNA force fields, the convergence behavior of the atom-atom electrostatic interactions in the pilot RNA systems was explored using high rank atomic multipole moments. The pilot RNA systems were cut into four types of different-sized molecular fragments, and the single nucleotide fragment and nucleotide-paired fragment proved to be the most reasonable systems for base-unpairing regions and base-pairing regions to investigate the convergence behavior of all types of atom-atom electrostatic interactions, respectively. Transferability of the electrostatic properties drawn from the pilot RNA systems to the corresponding test systems was also investigated. Furthermore, the convergence behavior of atomic electrostatic interactions in other substructures including bulge loop, internal loop, multi-branch loop, and K-type pseudoknot was expected to be modeled via the hairpin.

Two-Dimensional Speckle Tracking Echocardiography Identifies Coronary Artery Disease in 690 Patients: A Retrospective Study from a Single Center.

BACKGROUND Two-dimensional speckle tracking echocardiography (2D-STE) is a novel and non-invasive technique for the diagnosis of coronary artery disease (CAD). This retrospective study from a single center aimed to identify myocardial ischemia using 2D-STE in CAD patients identified by angiography. MATERIAL AND METHODS From March 1 to November 30, 2019, 690 patients in Beijing Hospital were enrolled. After angiography, 346 patients were diagnosed with CAD. Reduction in vessel diameter of ≥50% by stenosis in at least 1 major coronary artery or its main branch was considered CAD. Analysis of 2D-STE was performed using EchoPAC version 201. RESULTS The global strain was significantly impaired in CAD patients (P<0.01). Global longitudinal peak strain (GLPS) was analyzed in layers. For GLPS of the epicardium, the odds ratio (OR) was 1.297 (1.217-1.382; P=0.002), the area under the curve (AUC) was 0.727, and the cut-off value was -16.95; sensitivity and specificity were 73.7% and 63.0%, respectively. For GLPS of the middle layer, the OR was 1.260 (1.192-1.333; P<0.001), the AUC was 0.732, and the cut-off value was -20.95; sensitivity and specificity were 82.4% and 56.2%, respectively. For GLPS of the endocardium, the OR was 1.193 (1.137-1.251; P<0.001), the AUC was 0.708, and the cut-off value was -22.95; sensitivity and specificity were 82.9% and 52.9%, respectively. CONCLUSIONS The findings from this study support the clinical application of 2D-STE in patient populations with suspected myocardial ischemia due to CAD. Therefore, 2D-STE combined with ECG monitoring may have a future role for early screening of CAD patients.

LPA-MNI: An Improved Label Propagation Algorithm Based on Modularity and Node Importance for Community Detection.

Community detection is of great significance in understanding the structure of the network. Label propagation algorithm (LPA) is a classical and effective method, but it has the problems of randomness and instability. An improved label propagation algorithm named LPA-MNI is proposed in this study by combining the modularity function and node importance with the original LPA. LPA-MNI first identify the initial communities according to the value of modularity. Subsequently, the label propagation is used to cluster the remaining nodes that have not been assigned to initial communities. Meanwhile, node importance is used to improve the node order of label updating and the mechanism of label selecting when multiple labels are contained by the maximum number of nodes. Extensive experiments are performed on twelve real-world networks and eight groups of synthetic networks, and the results show that LPA-MNI has better accuracy, higher modularity, and more reasonable community numbers when compared with other six algorithms. In addition, LPA-MNI is shown to be more robust than the traditional LPA algorithm.

Tumor-associated macrophage interleukin-ß promotes glycerol-3-phosphate dehydrogenase activation, glycolysis and tumorigenesis in glioma cells.

Tumor-immune crosstalk within the tumor microenvironment (TME) occurs at all stages of tumorigenesis. Tumor-associated M2 macrophages play a central role in tumor development, but the molecular underpinnings have not been fully elucidated. We demonstrated that M2 macrophages produce interleukin 1ß (IL-1ß), which activates phosphorylation of the glycolytic enzyme glycerol-3-phosphate dehydrogenase (GPD2) at threonine 10 (GPD2 pT10) through phosphatidylinositol-3-kinase-mediated activation of protein kinase-delta (PKCδ) in glioma cells. GPD2 pT10 enhanced its substrate affinity and increased the catalytic rate of glycolysis in glioma cells. Inhibiting PKCδ or GPD2 pT10 in glioma cells or blocking IL-1ß generated by macrophages attenuated the glycolytic rate and proliferation of glioma cells. Furthermore, human glioblastoma tumor GPD2 pT10 levels were positively correlated with tumor p-PKCδ and IL-1ß levels as well as intratumoral macrophage recruitment, tumor grade and human glioblastoma patient survival. These results reveal a novel tumorigenic role for M2 macrophages in the TME. In addition, these findings suggest possible treatment strategies for glioma patients through blockade of cytokine crosstalk between M2 macrophages and glioma cells.

Robust MST-Based Clustering Algorithm.

Minimax similarity stresses the connectedness of points via mediating elements rather than favoring high mutual similarity. The grouping principle yields superior clustering results when mining arbitrarily-shaped clusters in data. However, it is not robust against noises and outliers in the data. There are two main problems with the grouping principle: first, a single object that is far away from all other objects defines a separate cluster, and second, two connected clusters would be regarded as two parts of one cluster. In order to solve such problems, we propose robust minimum spanning tree (MST)-based clustering algorithm in this letter. First, we separate the connected objects by applying a density-based coarsening phase, resulting in a low-rank matrix in which the element denotes the supernode by combining a set of nodes. Then a greedy method is presented to partition those supernodes through working on the low-rank matrix. Instead of removing the longest edges from MST, our algorithm groups the data set based on the minimax similarity. Finally, the assignment of all data points can be achieved through their corresponding supernodes. Experimental results on many synthetic and real-world data sets show that our algorithm consistently outperforms compared clustering algorithms.

Assessing Force Field Potential Energy Function Accuracy via a Multipolar Description of Atomic Electrostatic Interactions in RNA.

Computational investigations of RNA properties often rely on a molecular mechanical approach to define molecular potential energy. Force fields for RNA typically employ a point charge model of electrostatics, which does not provide a realistic quantum-mechanical picture. In reality, electron distributions around nuclei are not spherically symmetric and are geometry dependent. A multipole expansion method which allows for incorporation of polarizability and anisotropy in a force field is described, and its applicability to modeling the behavior of RNA molecules is investigated. Transferability of the model, critical for force field development, is also investigated.

Molecular modeling study of the induced-fit effect on kinase inhibition: the case of fibroblast growth factor receptor 3 (FGFR3).

Tyrosine kinases are a wide family of targets with strong pharmacological relevance. These proteins undergo large-scale conformational motions able to inactivate them. By the end of one of these structural processes, a new cavity is opened allowing the access to a specific type of inhibitors, called type II. The kinase domain of fibroblast growth factor receptor 3 (FGFR3) falls into this family of kinases. We describe here, for the first time, its inactivation process through target molecular dynamics. The transient cavity, at the crossroad between the DFGout and Cα helix out inactivation is herein explored. Molecular docking calculations of known ligands demonstrated that type II inhibitors are able to interact with this metastable transient conformation of FGFR3 kinase. Besides, supplemental computations were conducted and clearly show that type II inhibitors drive the kinase inactivation process through specific stabilization with the DFG triad. This induced-fit effect of type II ligands toward FGFR3 might be extrapolated to other kinase systems and provides meaningful structural information for future drug developments.

Wfold: A new method for predicting RNA secondary structure with deep learning.

Precise estimations of RNA secondary structures have the potential to reveal the various roles that non-coding RNAs play in regulating cellular activity. However, the mainstay of traditional RNA secondary structure prediction methods relies on thermos-dynamic models via free energy minimization, a laborious process that requires a lot of prior knowledge. Here, RNA secondary structure prediction using Wfold, an end-to-end deep learning-based approach, is suggested. Wfold is trained directly on annotated data and base-pairing criteria. It makes use of an image-like representation of RNA sequences, which an enhanced U-net incorporated with a transformer encoder can process effectively. Wfold eventually increases the accuracy of RNA secondary structure prediction by combining the benefits of self-attention mechanism's mining of long-range information with U-net's ability to gather local information. We compare Wfold's performance using RNA datasets that are within and across families. When trained and evaluated on different RNA families, it achieves a similar performance as the traditional methods, but dramatically outperforms the state-of-the-art methods on within-family datasets. Moreover, Wfold can also reliably forecast pseudoknots. The findings imply that Wfold may be useful for improving sequence alignment, functional annotations, and RNA structure modeling.

INTransformer: Data augmentation-based contrastive learning by injecting noise into transformer for molecular property prediction.

Molecular property prediction plays an essential role in drug discovery for identifying the candidate molecules with target properties. Deep learning models usually require sufficient labeled data to train good prediction models. However, the size of labeled data is usually small for molecular property prediction, which brings great challenges to deep learning-based molecular property prediction methods. Furthermore, the global information of molecules is critical for predicting molecular properties. Therefore, we propose INTransformer for molecular property prediction, which is a data augmentation method via contrastive learning to alleviate the limitations of the labeled molecular data while enhancing the ability to capture global information. Specifically, INTransformer consists of two identical Transformer sub-encoders to extract the molecular representation from the original SMILES and noisy SMILES respectively, while achieving the goal of data augmentation. To reduce the influence of noise, we use contrastive learning to ensure the molecular encoding of noisy SMILES is consistent with that of the original input so that the molecular representation information can be better extracted by INTransformer. Experiments on various benchmark datasets show that INTransformer achieved competitive performance for molecular property prediction tasks compared with the baselines and state-of-the-art methods.

Kinetic Ensemble of Tau Protein through the Markov State Model and Deep Learning Analysis.

The ordered assembly of Tau protein into filaments characterizes Alzheimer's and other neurodegenerative diseases, and thus, stabilization of Tau protein is a promising avenue for tauopathies therapy. To dissect the underlying aggregation mechanisms on Tau, we employ a set of molecular simulations and the Markov state model to determine the kinetics of ensemble of K18. K18 is the microtubule-binding domain of Tau protein and plays a vital role in the microtubule assembly, recycling processes, and amyloid fibril formation. Here, we efficiently explore the conformation of K18 with about 150 µs lifetimes in silico. Our results observe that all four repeat regions (R1-R4) are very dynamic, featuring frequent conformational conversion and lacking stable conformations, and the R2 region is more flexible than the R1, R3, and R4 regions. Additionally, it is worth noting that residues 300-310 in R2-R3 and residues 319-336 in R3 tend to form sheet structures, indicating that K18 has a broader functional role than individual repeat monomers. Finally, the simulations combined with Markov state models and deep learning reveal 5 key conformational states along the transition pathway and provide the information on the microsecond time scale interstate transition rates. Overall, this study offers significant insights into the molecular mechanism of Tau pathological aggregation and develops novel strategies for both securing tauopathies and advancing drug discovery.

GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction.

Accurately predicting compound-protein interactions (CPI) is a critical task in computer-aided drug design. In recent years, the exponential growth of compound activity and biomedical data has highlighted the need for efficient and interpretable prediction approaches. In this study, we propose GraphsformerCPI, an end-to-end deep learning framework that improves prediction performance and interpretability. GraphsformerCPI treats compounds and proteins as sequences of nodes with spatial structures, and leverages novel structure-enhanced self-attention mechanisms to integrate semantic and graph structural features within molecules for deep molecule representations. To capture the vital association between compound atoms and protein residues, we devise a dual-attention mechanism to effectively extract relational features through .cross-mapping. By extending the powerful learning capabilities of Transformers to spatial structures and extensively utilizing attention mechanisms, our model offers strong interpretability, a significant advantage over most black-box deep learning methods. To evaluate GraphsformerCPI, extensive experiments were conducted on benchmark datasets including human, C. elegans, Davis and KIBA datasets. We explored the impact of model depth and dropout rate on performance and compared our model against state-of-the-art baseline models. Our results demonstrate that GraphsformerCPI outperforms baseline models in classification datasets and achieves competitive performance in regression datasets. Specifically, on the human dataset, GraphsformerCPI achieves an average improvement of 1.6% in AUC, 0.5% in precision, and 5.3% in recall. On the KIBA dataset, the average improvement in Concordance index (CI) and mean squared error (MSE) is 3.3% and 7.2%, respectively. Molecular docking shows that our model provides novel insights into the intrinsic interactions and binding mechanisms. Our research holds practical significance in effectively predicting CPIs and binding affinities, identifying key atoms and residues, enhancing model interpretability.