RNAs have important biological functions and the functions of RNAs are generally coupled to their structures, especiallytheir secondary structures. In this work, we have made a comprehensive evaluation of the performa...RNAs have important biological functions and the functions of RNAs are generally coupled to their structures, especiallytheir secondary structures. In this work, we have made a comprehensive evaluation of the performances of existingtop RNA secondary structure prediction methods, including five deep-learning (DL) based methods and five minimum freeenergy (MFE) based methods. First, we made a brief overview of these RNA secondary structure prediction methods.Afterwards, we built two rigorous test datasets consisting of RNAs with non-redundant sequences and comprehensivelyexamined the performances of the RNA secondary structure prediction methods through classifying the RNAs into differentlength ranges and different types. Our examination shows that the DL-based methods generally perform better thanthe MFE-based methods for RNAs with long lengths and complex structures, while the MFE-based methods can achievegood performance for small RNAs and some specialized MFE-based methods can achieve good prediction accuracy forpseudoknots. Finally, we provided some insights and perspectives in modeling RNA secondary structures.展开更多
High-entropy alloys(HEA)are novel materials obtained by introducing chemical disorder through mixing multiple-principal components,performing rather attractive features together with charming and exceptional propertie...High-entropy alloys(HEA)are novel materials obtained by introducing chemical disorder through mixing multiple-principal components,performing rather attractive features together with charming and exceptional properties in comparison with traditional alloys.However,the trade-off relationship is still present between strength and ductility in HEAs,significantly limiting the practical and wide application of HEAs.Moreover,the preparation of HEAs by trial-and-error method is time-consuming and resource-wasting,hindering the high-speed and high-quality development of HEAs.Herein,the primary objective of this work is to summarize the latest advancements in HEAs,focusing on methods for predicting phase structures and the factors influencing mechanical properties.Additionally,strengthening and toughening strategies for HEAs are highlighted,thus maximizing their application potential.Besides,challenges and future investigation direction of HEAs are also identified and proposed.展开更多
The structural,relative stability,and electronic properties of two-dimensional AsP_(2)X_(6)(X=S,Se)were predicted and studied using the particle-swarm optimization method and first principles calculations.We proposed ...The structural,relative stability,and electronic properties of two-dimensional AsP_(2)X_(6)(X=S,Se)were predicted and studied using the particle-swarm optimization method and first principles calculations.We proposed two low energy structures with P312 and P-31m phases,both of which the structures are hexagonal in shape and show non-centrosymmetry for the P312 phase and centrosymmetry for the P-31m phase.According to our results,two structural phases are found to be stable thermally and dynamically.The P312 phase of AsP_(2)X_(6)(X=S,Se)are indirect semiconductors with band gaps of 2.44 eV(AsP2S6)and 2.18 eV(AsP2Se6)at the HSE06 level,and their absorption coefficients are predicted to reach the order of 10^(5)cm^(-1)from visible light to ultraviolet region,but the main absorption is manly in the ultraviolet region.The P-31m phase of AsP_(2)X_(6)(X=S,Se)exhibits metal character with the Fermi surface mainly occupied by the p orbital of S/Se.Remarkably,estimated by first principles calculations,the P-31m AsP2S6 is found to be an intrinsic phonon-mediated superconductor with a relatively high critical superconducting temperature of about 13.4 K,and the P-31m AsP2Se6 only has a superconducting temperature of 1.4 K,which suggest that the P-31m AsP2S6 may be a good candidate for a nanoscale superconductor.展开更多
Structure-based virtual screening（molecular docking）is now one of the most pragmatic techniques to leverage target structure for ligand discovery.Accurate binding pose prediction is critical to molecular docking.Her...Structure-based virtual screening（molecular docking）is now one of the most pragmatic techniques to leverage target structure for ligand discovery.Accurate binding pose prediction is critical to molecular docking.Here,we describe a general strategy to improve the accuracy of docking pose prediction by implementing the structural descriptor-based fltering and KGS-penalty function-based conformational clustering in an unbiased manner.We assessed our method against 150 high-quality protein–ligand complex structures.Surprisingly,such simple components are suffcient to improve the accuracy of docking pose prediction.The success rate of predicting near-native docking pose increased from 53%of the targets to 78%.We expect that our strategy may have general usage in improving currently available molecular docking programs.展开更多
Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distribu...Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.展开更多
Atomization energy(AE)is an important indicator for measuring material stability and reactivity,which refers to the energy change when a polyatomic molecule decomposes into its constituent atoms.Predicting AE based on...Atomization energy(AE)is an important indicator for measuring material stability and reactivity,which refers to the energy change when a polyatomic molecule decomposes into its constituent atoms.Predicting AE based on the structural information of molecules has been a focus of researchers,but existing methods have limitations such as being time-consuming or requiring complex preprocessing and large amounts of training data.Deep learning(DL),a new branch of machine learning(ML),has shown promise in learning internal rules and hierarchical representations of sample data,making it a potential solution for AE prediction.To address this problem,we propose a natural-parameter network(NPN)approach for AE prediction.This method establishes a clearer statistical interpretation of the relationship between the network’s output and the given data.We use the Coulomb matrix(CM)method to represent each compound as a structural information matrix.Furthermore,we also designed an end-to-end predictive model.Experimental results demonstrate that our method achieves excellent performance on the QM7 and BC2P datasets,and the mean absolute error(MAE)obtained on the QM7 test set ranges from 0.2 kcal/mol to 3 kcal/mol.The optimal result of our method is approximately an order of magnitude higher than the accuracy of 3 kcal/mol in published works.Additionally,our approach significantly accelerates the prediction time.Overall,this study presents a promising approach to accelerate the process of predicting structures using DL,and provides a valuable contribution to the field of chemical energy prediction.展开更多
Density functional theory method has been employed to investigate the structures of the prototypical technetium-labeled diphosphonate complex 99mTc-MDP, where MDP represents methylenediphosphonic acid. A total of 14 t...Density functional theory method has been employed to investigate the structures of the prototypical technetium-labeled diphosphonate complex 99mTc-MDP, where MDP represents methylenediphosphonic acid. A total of 14 trial structures were generated by allowing for the geometric, conformational, charge, and spin isomerism. Based on the optimized structures and calculated energies at the B3LYP/LANL2DZ level, two stable isomers were determined for the title complex. And they were further studied systematically in comparison with the experimental structure. The basis sets 6-31G＊（LANL2DZ for Tc）, 6-31G＊（cc-pVDZ-pp for Tc）, and DGDZVP have also been employed in combination with the B3LYP functional to study the basis set effect on the geometries of isomers. The optimized structures agree well with the available experimental data, and the bond lengths are more sensitive to the basis set than the bond angles. The charge distributions were studied by the Mulliken population analysis and natural bond orbital analysis. The results reflect a significant ligand-to-metal electron donation.展开更多
[Objective] To examine the grammar model based on lexical substring exac- tion for RNA secondary structure prediction. [Method] By introducing cloud model into stochastic grammar model, a machine learning algorithm su...[Objective] To examine the grammar model based on lexical substring exac- tion for RNA secondary structure prediction. [Method] By introducing cloud model into stochastic grammar model, a machine learning algorithm suitable for the lexicalized stochastic grammar model was proposed. The word grid mode was used to extract and divide RNA sequence to acquire lexical substring, and the cloud classifier was used to search the maximum probability of each lemma which was marked as a certain sec- ondary structure type. Then, the lemma information was introduced into the training stochastic grammar process as prior information, realizing the prediction on the sec- ondary structure of RNA, and the method was tested by experiment. [Result] The experimental results showed that the prediction accuracy and searching speed of stochastic grammar cloud model were significantly improved from the prediction with simple stochastic grammar. [Conclusion] This study laid the foundation for the wide application of stochastic grammar model for RNA secondary structure prediction.展开更多
Crystal structure prediction(CSP)is a foundational computational technique for determining the atomic arrangements of crystalline materials,especially under high-pressure conditions.While CSP plays a critical role in ...Crystal structure prediction(CSP)is a foundational computational technique for determining the atomic arrangements of crystalline materials,especially under high-pressure conditions.While CSP plays a critical role in materials science,traditional approaches often encounter significant challenges related to computational efficiency and scalability,particularly when applied to complex systems.Recent advances in machine learning(ML)have shown tremendous promise in addressing these limitations,enabling the rapid and accurate prediction of crystal structures across a wide range of chemical compositions and external conditions.This review provides a concise overview of recent progress in ML-assisted CSP methodologies,with a particular focus on machine learning potentials and generative models.By critically analyzing these advances,we highlight the transformative impact of ML in accelerating materials discovery,enhancing computational efficiency,and broadening the applicability of CSP.Additionally,we discuss emerging opportunities and challenges in this rapidly evolving field.展开更多
On 9 October 2024,in a high-profile vote of confidence for the promise of using artificial intelligence(AI)in scientific discovery,the Royal Swedish Academy of Sciences awarded Demis Hassabis(co-founder and chief exec...On 9 October 2024,in a high-profile vote of confidence for the promise of using artificial intelligence(AI)in scientific discovery,the Royal Swedish Academy of Sciences awarded Demis Hassabis(co-founder and chief executive officer)and John M.Jumper(direc-tor)of Google DeepMind(London,UK)the 2024 Nobel Prize in Chemistry for their pioneering work in developing the AI-powered protein structure prediction model AlphaFold2(AF2)[1].Also shar-ing the prize was David Baker(half to Hassabis and Jumper;half to Baker),professor of biochemistry at the University of Washington(Seattle,WA,USA),for his work on computational protein design that started with the mid-1990s development of Rosetta,a since-evolving suite of software tools that model protein structures using physical principles[2]-and now also AI[3].展开更多
TiO_(2)is a well-known photocatalyst with a band gap of 3.2 eV,yet its ability to absorb light is limited to the short wavelengths of ultraviolet light.To achieve a more effective photocatalytic material,we have desig...TiO_(2)is a well-known photocatalyst with a band gap of 3.2 eV,yet its ability to absorb light is limited to the short wavelengths of ultraviolet light.To achieve a more effective photocatalytic material,we have designed two-dimensional semiconductor TiOS materials using swarm intelligence algorithms combined with first-principles calculations.Three stable low-energy structures with space groups of P2_(1)/m,P3m1 and P2_(1)/c are identified.Among these structures,the Janus P3m1 phase is a direct bandgap semiconductor,while the P2_(1)/m and P2_(1)/c phases are indirect bandgap semiconductors.Utilizing the accurate hybrid density functional HSE06 method,the band gaps of the three structures are calculated to be 2.34 eV(P2_(1)/m),2.24 eV(P3m1)and 3.22 eV(P2_(1)/c).Optical calculations reveal that TiOS materials exhibit a good light-harvesting capability in both visible and ultraviolet spectral ranges.Moreover,the photocatalytic calculations also indicate that both P2_(1)/m and P3m1 TiOS can provide a strong driving force for converting H_(2)O to H_(2)and O_(2)in an acidic environment with pH=0.The structural stabilities,mechanical properties,electronic structures and hydrogen evolution reaction activities are also discussed in detail.Our research suggests that two-dimensional TiOS materials have potential applications in both semiconductor devices and photocatalysis.展开更多
As an extreme physical condition,high pressure serves as a potent means to substantially modify the interatomic distances and bonding patterns within condensed matter,thereby enabling the macroscopic manipulation of m...As an extreme physical condition,high pressure serves as a potent means to substantially modify the interatomic distances and bonding patterns within condensed matter,thereby enabling the macroscopic manipulation of material properties.We employed the CALYPSO method to predict the stable structures of RbB_(2)C_(4)across the pressure range from 0 GPa to 100 GPa and investigated its physical properties through first-principles calculations.Specially,we found four novel structures,namely,P6_(3)/mcm-,Amm2-,P1-,and I4/mmm-RbB_(2)C_(4).Under pressure conditions,electronic structure calculations reveal that all of them exhibit metallic characteristics.The calculation results of formation enthalpy show that the P6_(3)/mcm structure can be synthesized within the pressure range of 0–40 GPa.Specially,the Amm2,P1,and I4/mmm structures can be synthesized above 4 GPa,6 GPa,10 GPa,respectively.Moreover,the estimated Vickers hardness value of I4/mmm-RbB_(2)C_(4)compound is 47 GPa,suggesting that it is a superhard material.Interestingly,this study uncovers the continuous transformation of the crystal structure of RbB_(2)C_(4)from a layered configuration to folded and tubular forms,ultimately attaining a stabilized cage-like structure under the pressure span of 0–100 GPa.The application of pressure offers a formidable impetus for the advancement and innovation in condensed matter physics,facilitating the exploration of novel states and functions of matter.展开更多
Novel ordered intermetallic compounds have stimulated much interest.Ru–Al alloys are a prominent class of hightemperature structural materials,but the experimentally reported crystal structure of the intermetallic Ru...Novel ordered intermetallic compounds have stimulated much interest.Ru–Al alloys are a prominent class of hightemperature structural materials,but the experimentally reported crystal structure of the intermetallic Ru_(2)Al_(5) phase remains elusive and debatable.To resolve this controversy,we extensively explored the crystal structures of Ru_(2)Al_(5) using first-principles calculations combined with crystal structure prediction technique.Among the calculated x-ray diffraction patterns and lattice parameters of five candidate Ru2Al5structures,those of the orthorhombic Pmmn structure best aligned with recent experimental results.The structural stabilities of the five Ru_(2)Al_(5)structures were confirmed through formation energy,elastic constants,and phonon spectrum calculations.We also comprehensively analyzed the mechanical and electronic properties of the five candidates.This work can guide the exploration of novel ordered intermetallic compounds in Ru–Al alloys.展开更多
Structure-stratigraphy analysis" is a new method used in the study and prediction of and small-scaled structures in coal mines. The object of this method is coalbed structure that includes the folds and fracture ...Structure-stratigraphy analysis" is a new method used in the study and prediction of and small-scaled structures in coal mines. The object of this method is coalbed structure that includes the folds and fracture occurred in the vicinity of coal-seams. It emphases the analysis on the relationship between structural deformation and stratal lithologic combination.Based on the statistics of a series of related parameters in stratigraphy and structure,comprehensive analysis and drawing, this method may provide a good means for the quantitative evaluation and prediction of small scale structure in coal mines.展开更多
Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate t...Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate the membrane protein's structure by wet-lab experiments,accurate and fast amino acid sequence-based computational methods are highly desired. In this paper, we report an online prediction tool called Mem Brain, whose input is the amino acid sequence. Mem Brain consists of specialized modules for predicting transmembrane helices, residue–residue contacts and relative accessible surface area of a-helical membrane proteins. Mem Brain achieves aprediction accuracy of 97.9% of ATMH, 87.1% of AP,3.2 ± 3.0 of N-score, 3.1 ± 2.8 of C-score. Mem BrainContact obtains 62%/64.1% prediction accuracy on training and independent dataset on top L/5 contact prediction,respectively. And Mem Brain-Rasa achieves Pearson correlation coefficient of 0.733 and its mean absolute error of13.593. These prediction results provide valuable hints for revealing the structure and function of membrane proteins.Mem Brain web server is free for academic use and available at www.csbio.sjtu.edu.cn/bioinf/Mem Brain/.展开更多
Tannases produced by filamentous fungi are in a family of important hydrolases of gallotannins and have broad industry applications.But until now,the 3-D structures of fungi tannases have not been reported.The protein...Tannases produced by filamentous fungi are in a family of important hydrolases of gallotannins and have broad industry applications.But until now,the 3-D structures of fungi tannases have not been reported.The protein sequence deduced from the cDNA sequence obtained using RT-PCR amplification was identified as tannase through sequence alignment and phylogenetic analysis.Structure models based on the tannase sequence were collected using I-TASSER,and the model with the best match to the surface charge density-pH titration profile was selected as the final structure for tannase from Aspergillusniger N5-5.This work provides an effective method for protein structure research.The structure constructed in this work should be very important to understand the enzyme bioactivities and further developments of fungi tannases.展开更多
RNAs play crucial and versatile roles in biological processes.Computational prediction approaches can help to understand RNA structures and their stabilizing factors,thus providing information on their functions,and f...RNAs play crucial and versatile roles in biological processes.Computational prediction approaches can help to understand RNA structures and their stabilizing factors,thus providing information on their functions,and facilitating the design of new RNAs.Machine learning(ML)techniques have made tremendous progress in many fields in the past few years.Although their usage in protein-related fields has a long history,the use of ML methods in predicting RNA tertiary structures is new and rare.Here,we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation,the difficulties and potentials of these approaches when applied in the field.展开更多
Many recent exciting discoveries have revealed the versatility of RNAs and their importance in a variety of cellular functions which are strongly coupled to RNA structures. To understand the functions of RNAs, some st...Many recent exciting discoveries have revealed the versatility of RNAs and their importance in a variety of cellular functions which are strongly coupled to RNA structures. To understand the functions of RNAs, some structure prediction models have been developed in recent years. In this review, the progress in computational models for RNA structure prediction is introduced and the distinguishing features of many outstanding algorithms are discussed, emphasizing three- dimensional （3D） structure prediction. A promising coarse-grained model for predicting RNA 3D structure, stability and salt effect is also introduced briefly. Finally, we discuss the major challenges in the RNA 3D structure modeling.展开更多
Airframe maintenance is traditionally performed at scheduled maintenance stops.The decision to repair a fuselage panel is based on a fixed crack size threshold,which allows to ensure the aircraft safety until the next...Airframe maintenance is traditionally performed at scheduled maintenance stops.The decision to repair a fuselage panel is based on a fixed crack size threshold,which allows to ensure the aircraft safety until the next scheduled maintenance stop.With progress in sensor technology and data processing techniques,structural health monitoring（SHM） systems are increasingly being considered in the aviation industry.SHM systems track the aircraft health state continuously,leading to the possibility of planning maintenance based on an actual state of aircraft rather than on a fixed schedule.This paper builds upon a model-based prognostics framework that the authors developed in their previous work,which couples the Extended Kalman filter（EKF） with a firstorder perturbation（FOP） method.By using the information given by this prognostics method,a novel cost driven predictive maintenance（CDPM） policy is proposed,which ensures the aircraft safety while minimizing the maintenance cost.The proposed policy is formally derived based on the trade-off between probabilities of occurrence of scheduled and unscheduled maintenance.A numerical case study simulating the maintenance process of an entire fleet of aircrafts is implemented.Under the condition of assuring the same safety level,the CDPM is compared in terms of cost with two other maintenance policies：scheduled maintenance and threshold based SHM maintenance.The comparison results show CDPM could lead to significant cost savings.展开更多
The algorithm based on combination learning usually is superior to a singleclassification algorithm on the task of protein secondary structure prediction. However,the assignment of the weight of the base classifier us...The algorithm based on combination learning usually is superior to a singleclassification algorithm on the task of protein secondary structure prediction. However,the assignment of the weight of the base classifier usually lacks decision-makingevidence. In this paper, we propose a protein secondary structure prediction method withdynamic self-adaptation combination strategy based on entropy, where the weights areassigned according to the entropy of posterior probabilities outputted by base classifiers.The higher entropy value means a lower weight for the base classifier. The final structureprediction is decided by the weighted combination of posterior probabilities. Extensiveexperiments on CB513 dataset demonstrates that the proposed method outperforms theexisting methods, which can effectively improve the prediction performance.展开更多
基金supported by grants from the National Science Foundation of China(Grant Nos.12375038 and 12075171 to ZJT,and 12205223 to YLT).
文摘RNAs have important biological functions and the functions of RNAs are generally coupled to their structures, especiallytheir secondary structures. In this work, we have made a comprehensive evaluation of the performances of existingtop RNA secondary structure prediction methods, including five deep-learning (DL) based methods and five minimum freeenergy (MFE) based methods. First, we made a brief overview of these RNA secondary structure prediction methods.Afterwards, we built two rigorous test datasets consisting of RNAs with non-redundant sequences and comprehensivelyexamined the performances of the RNA secondary structure prediction methods through classifying the RNAs into differentlength ranges and different types. Our examination shows that the DL-based methods generally perform better thanthe MFE-based methods for RNAs with long lengths and complex structures, while the MFE-based methods can achievegood performance for small RNAs and some specialized MFE-based methods can achieve good prediction accuracy forpseudoknots. Finally, we provided some insights and perspectives in modeling RNA secondary structures.
基金supported by the National Natural Science Foundation of China(Nos.52375451,52005396)Shandong Provincial Natural Science Foundation,China(Nos.ZR2023YQ052,ZR2023ME087)+6 种基金Shandong Provincial Technological SME Innovation Capability Promotion Project,China(No.2023TSGC0375)Young Taishan Scholars Program of Shandong Province,China(No.tsqn202306041)Guangdong Basic and Applied Basic Research Foundation,China(No.2023 A1515010044)Shandong Provincial Youth Innovation Team,China(No.2022KJ038)Open Project of State Key Laboratory of Solid Lubrication,China(No.LSL-22-11)Young Talent Fund of University Association for Science and Technology in Shaanxi,China(No.20210414)Qilu Youth Scholar Project Funding of Shandong University,China。
文摘High-entropy alloys(HEA)are novel materials obtained by introducing chemical disorder through mixing multiple-principal components,performing rather attractive features together with charming and exceptional properties in comparison with traditional alloys.However,the trade-off relationship is still present between strength and ductility in HEAs,significantly limiting the practical and wide application of HEAs.Moreover,the preparation of HEAs by trial-and-error method is time-consuming and resource-wasting,hindering the high-speed and high-quality development of HEAs.Herein,the primary objective of this work is to summarize the latest advancements in HEAs,focusing on methods for predicting phase structures and the factors influencing mechanical properties.Additionally,strengthening and toughening strategies for HEAs are highlighted,thus maximizing their application potential.Besides,challenges and future investigation direction of HEAs are also identified and proposed.
基金Funded by the National Natural Science Foundation of China(No.U1904612)the Natural Science Foundation of Henan Province(No.222300420506)。
文摘The structural,relative stability,and electronic properties of two-dimensional AsP_(2)X_(6)(X=S,Se)were predicted and studied using the particle-swarm optimization method and first principles calculations.We proposed two low energy structures with P312 and P-31m phases,both of which the structures are hexagonal in shape and show non-centrosymmetry for the P312 phase and centrosymmetry for the P-31m phase.According to our results,two structural phases are found to be stable thermally and dynamically.The P312 phase of AsP_(2)X_(6)(X=S,Se)are indirect semiconductors with band gaps of 2.44 eV(AsP2S6)and 2.18 eV(AsP2Se6)at the HSE06 level,and their absorption coefficients are predicted to reach the order of 10^(5)cm^(-1)from visible light to ultraviolet region,but the main absorption is manly in the ultraviolet region.The P-31m phase of AsP_(2)X_(6)(X=S,Se)exhibits metal character with the Fermi surface mainly occupied by the p orbital of S/Se.Remarkably,estimated by first principles calculations,the P-31m AsP2S6 is found to be an intrinsic phonon-mediated superconductor with a relatively high critical superconducting temperature of about 13.4 K,and the P-31m AsP2Se6 only has a superconducting temperature of 1.4 K,which suggest that the P-31m AsP2S6 may be a good candidate for a nanoscale superconductor.
文摘Structure-based virtual screening（molecular docking）is now one of the most pragmatic techniques to leverage target structure for ligand discovery.Accurate binding pose prediction is critical to molecular docking.Here,we describe a general strategy to improve the accuracy of docking pose prediction by implementing the structural descriptor-based fltering and KGS-penalty function-based conformational clustering in an unbiased manner.We assessed our method against 150 high-quality protein–ligand complex structures.Surprisingly,such simple components are suffcient to improve the accuracy of docking pose prediction.The success rate of predicting near-native docking pose increased from 53%of the targets to 78%.We expect that our strategy may have general usage in improving currently available molecular docking programs.
文摘Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.
基金the Nature Science Foundation of China(Nos.61671362 and 62071366).
文摘Atomization energy(AE)is an important indicator for measuring material stability and reactivity,which refers to the energy change when a polyatomic molecule decomposes into its constituent atoms.Predicting AE based on the structural information of molecules has been a focus of researchers,but existing methods have limitations such as being time-consuming or requiring complex preprocessing and large amounts of training data.Deep learning(DL),a new branch of machine learning(ML),has shown promise in learning internal rules and hierarchical representations of sample data,making it a potential solution for AE prediction.To address this problem,we propose a natural-parameter network(NPN)approach for AE prediction.This method establishes a clearer statistical interpretation of the relationship between the network’s output and the given data.We use the Coulomb matrix(CM)method to represent each compound as a structural information matrix.Furthermore,we also designed an end-to-end predictive model.Experimental results demonstrate that our method achieves excellent performance on the QM7 and BC2P datasets,and the mean absolute error(MAE)obtained on the QM7 test set ranges from 0.2 kcal/mol to 3 kcal/mol.The optimal result of our method is approximately an order of magnitude higher than the accuracy of 3 kcal/mol in published works.Additionally,our approach significantly accelerates the prediction time.Overall,this study presents a promising approach to accelerate the process of predicting structures using DL,and provides a valuable contribution to the field of chemical energy prediction.
基金This work was supported by the National Natural Science Foundation of China （No.20801024 and No.21001055）, the Natural Science Foundation of Jiangsu Province （No.BK2009077）, and the Science Foundation of Health Department of Jiangsu Province （No.H200963）.
文摘Density functional theory method has been employed to investigate the structures of the prototypical technetium-labeled diphosphonate complex 99mTc-MDP, where MDP represents methylenediphosphonic acid. A total of 14 trial structures were generated by allowing for the geometric, conformational, charge, and spin isomerism. Based on the optimized structures and calculated energies at the B3LYP/LANL2DZ level, two stable isomers were determined for the title complex. And they were further studied systematically in comparison with the experimental structure. The basis sets 6-31G＊（LANL2DZ for Tc）, 6-31G＊（cc-pVDZ-pp for Tc）, and DGDZVP have also been employed in combination with the B3LYP functional to study the basis set effect on the geometries of isomers. The optimized structures agree well with the available experimental data, and the bond lengths are more sensitive to the basis set than the bond angles. The charge distributions were studied by the Mulliken population analysis and natural bond orbital analysis. The results reflect a significant ligand-to-metal electron donation.
基金Supported by the Science Foundation of Hengyang Normal University of China(09A36)~~
文摘[Objective] To examine the grammar model based on lexical substring exac- tion for RNA secondary structure prediction. [Method] By introducing cloud model into stochastic grammar model, a machine learning algorithm suitable for the lexicalized stochastic grammar model was proposed. The word grid mode was used to extract and divide RNA sequence to acquire lexical substring, and the cloud classifier was used to search the maximum probability of each lemma which was marked as a certain sec- ondary structure type. Then, the lemma information was introduced into the training stochastic grammar process as prior information, realizing the prediction on the sec- ondary structure of RNA, and the method was tested by experiment. [Result] The experimental results showed that the prediction accuracy and searching speed of stochastic grammar cloud model were significantly improved from the prediction with simple stochastic grammar. [Conclusion] This study laid the foundation for the wide application of stochastic grammar model for RNA secondary structure prediction.
基金supported by the National Key Research and Development Program of China(Grant No.2022YFA1402304)the National Natural Science Foundation of China(Grant Nos.12034009,12374005,52288102,52090024,and T2225013)+1 种基金the Fundamental Research Funds for the Central Universitiesthe Program for JLU Science and Technology Innovative Research Team.
文摘Crystal structure prediction(CSP)is a foundational computational technique for determining the atomic arrangements of crystalline materials,especially under high-pressure conditions.While CSP plays a critical role in materials science,traditional approaches often encounter significant challenges related to computational efficiency and scalability,particularly when applied to complex systems.Recent advances in machine learning(ML)have shown tremendous promise in addressing these limitations,enabling the rapid and accurate prediction of crystal structures across a wide range of chemical compositions and external conditions.This review provides a concise overview of recent progress in ML-assisted CSP methodologies,with a particular focus on machine learning potentials and generative models.By critically analyzing these advances,we highlight the transformative impact of ML in accelerating materials discovery,enhancing computational efficiency,and broadening the applicability of CSP.Additionally,we discuss emerging opportunities and challenges in this rapidly evolving field.
文摘On 9 October 2024,in a high-profile vote of confidence for the promise of using artificial intelligence(AI)in scientific discovery,the Royal Swedish Academy of Sciences awarded Demis Hassabis(co-founder and chief executive officer)and John M.Jumper(direc-tor)of Google DeepMind(London,UK)the 2024 Nobel Prize in Chemistry for their pioneering work in developing the AI-powered protein structure prediction model AlphaFold2(AF2)[1].Also shar-ing the prize was David Baker(half to Hassabis and Jumper;half to Baker),professor of biochemistry at the University of Washington(Seattle,WA,USA),for his work on computational protein design that started with the mid-1990s development of Rosetta,a since-evolving suite of software tools that model protein structures using physical principles[2]-and now also AI[3].
基金supported by the National Natural Science Foundation of China(Grant Nos.52272219 and U1904612)the Natural Science Foundation of Henan Province(Grant No.242300421191).
文摘TiO_(2)is a well-known photocatalyst with a band gap of 3.2 eV,yet its ability to absorb light is limited to the short wavelengths of ultraviolet light.To achieve a more effective photocatalytic material,we have designed two-dimensional semiconductor TiOS materials using swarm intelligence algorithms combined with first-principles calculations.Three stable low-energy structures with space groups of P2_(1)/m,P3m1 and P2_(1)/c are identified.Among these structures,the Janus P3m1 phase is a direct bandgap semiconductor,while the P2_(1)/m and P2_(1)/c phases are indirect bandgap semiconductors.Utilizing the accurate hybrid density functional HSE06 method,the band gaps of the three structures are calculated to be 2.34 eV(P2_(1)/m),2.24 eV(P3m1)and 3.22 eV(P2_(1)/c).Optical calculations reveal that TiOS materials exhibit a good light-harvesting capability in both visible and ultraviolet spectral ranges.Moreover,the photocatalytic calculations also indicate that both P2_(1)/m and P3m1 TiOS can provide a strong driving force for converting H_(2)O to H_(2)and O_(2)in an acidic environment with pH=0.The structural stabilities,mechanical properties,electronic structures and hydrogen evolution reaction activities are also discussed in detail.Our research suggests that two-dimensional TiOS materials have potential applications in both semiconductor devices and photocatalysis.
基金Project supported by the Jilin Provincial Science and Technology Development Joint Fund Project(Grant No.YDZJ202201ZYTS581)supported by the Scientific and Technological Research Project of Jilin Provincial Education Department(Grant No.JJKH20240077KJ).
文摘As an extreme physical condition,high pressure serves as a potent means to substantially modify the interatomic distances and bonding patterns within condensed matter,thereby enabling the macroscopic manipulation of material properties.We employed the CALYPSO method to predict the stable structures of RbB_(2)C_(4)across the pressure range from 0 GPa to 100 GPa and investigated its physical properties through first-principles calculations.Specially,we found four novel structures,namely,P6_(3)/mcm-,Amm2-,P1-,and I4/mmm-RbB_(2)C_(4).Under pressure conditions,electronic structure calculations reveal that all of them exhibit metallic characteristics.The calculation results of formation enthalpy show that the P6_(3)/mcm structure can be synthesized within the pressure range of 0–40 GPa.Specially,the Amm2,P1,and I4/mmm structures can be synthesized above 4 GPa,6 GPa,10 GPa,respectively.Moreover,the estimated Vickers hardness value of I4/mmm-RbB_(2)C_(4)compound is 47 GPa,suggesting that it is a superhard material.Interestingly,this study uncovers the continuous transformation of the crystal structure of RbB_(2)C_(4)from a layered configuration to folded and tubular forms,ultimately attaining a stabilized cage-like structure under the pressure span of 0–100 GPa.The application of pressure offers a formidable impetus for the advancement and innovation in condensed matter physics,facilitating the exploration of novel states and functions of matter.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11965005 and 11964026)the Natural Science Basic Research Plan in Shaanxi Province,China(Grant Nos.2023-JC-YB-021 and 2022JM-035)+1 种基金the Fundamental Research Funds for the Central Universitiesthe 111 Project(Grant No.B17035)。
文摘Novel ordered intermetallic compounds have stimulated much interest.Ru–Al alloys are a prominent class of hightemperature structural materials,but the experimentally reported crystal structure of the intermetallic Ru_(2)Al_(5) phase remains elusive and debatable.To resolve this controversy,we extensively explored the crystal structures of Ru_(2)Al_(5) using first-principles calculations combined with crystal structure prediction technique.Among the calculated x-ray diffraction patterns and lattice parameters of five candidate Ru2Al5structures,those of the orthorhombic Pmmn structure best aligned with recent experimental results.The structural stabilities of the five Ru_(2)Al_(5)structures were confirmed through formation energy,elastic constants,and phonon spectrum calculations.We also comprehensively analyzed the mechanical and electronic properties of the five candidates.This work can guide the exploration of novel ordered intermetallic compounds in Ru–Al alloys.
文摘Structure-stratigraphy analysis" is a new method used in the study and prediction of and small-scaled structures in coal mines. The object of this method is coalbed structure that includes the folds and fracture occurred in the vicinity of coal-seams. It emphases the analysis on the relationship between structural deformation and stratal lithologic combination.Based on the statistics of a series of related parameters in stratigraphy and structure,comprehensive analysis and drawing, this method may provide a good means for the quantitative evaluation and prediction of small scale structure in coal mines.
基金supported by the National Natural Science Foundation of China(Nos.61671288,91530321,61603161)Science and Technology Commission of Shanghai Municipality(Nos.16JC1404300,17JC1403500,16ZR1448700)
文摘Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate the membrane protein's structure by wet-lab experiments,accurate and fast amino acid sequence-based computational methods are highly desired. In this paper, we report an online prediction tool called Mem Brain, whose input is the amino acid sequence. Mem Brain consists of specialized modules for predicting transmembrane helices, residue–residue contacts and relative accessible surface area of a-helical membrane proteins. Mem Brain achieves aprediction accuracy of 97.9% of ATMH, 87.1% of AP,3.2 ± 3.0 of N-score, 3.1 ± 2.8 of C-score. Mem BrainContact obtains 62%/64.1% prediction accuracy on training and independent dataset on top L/5 contact prediction,respectively. And Mem Brain-Rasa achieves Pearson correlation coefficient of 0.733 and its mean absolute error of13.593. These prediction results provide valuable hints for revealing the structure and function of membrane proteins.Mem Brain web server is free for academic use and available at www.csbio.sjtu.edu.cn/bioinf/Mem Brain/.
基金the National Natural Science Foundation of China (No. 21374117)the 100 Talents Program of Chinese Academy of Sciences for financial support
文摘Tannases produced by filamentous fungi are in a family of important hydrolases of gallotannins and have broad industry applications.But until now,the 3-D structures of fungi tannases have not been reported.The protein sequence deduced from the cDNA sequence obtained using RT-PCR amplification was identified as tannase through sequence alignment and phylogenetic analysis.Structure models based on the tannase sequence were collected using I-TASSER,and the model with the best match to the surface charge density-pH titration profile was selected as the final structure for tannase from Aspergillusniger N5-5.This work provides an effective method for protein structure research.The structure constructed in this work should be very important to understand the enzyme bioactivities and further developments of fungi tannases.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11774158,11974173,11774157,and 11934008)。
文摘RNAs play crucial and versatile roles in biological processes.Computational prediction approaches can help to understand RNA structures and their stabilizing factors,thus providing information on their functions,and facilitating the design of new RNAs.Machine learning(ML)techniques have made tremendous progress in many fields in the past few years.Although their usage in protein-related fields has a long history,the use of ML methods in predicting RNA tertiary structures is new and rare.Here,we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation,the difficulties and potentials of these approaches when applied in the field.
基金supported by the National Natural Science Foundation of China(Grant Nos.11074191,11175132,and 11374234)the National Basic Research Programof China(Grant No.2011CB933600)the Program for New Century Excellent Talents of China(Grant No.NCET 08-0408)
文摘Many recent exciting discoveries have revealed the versatility of RNAs and their importance in a variety of cellular functions which are strongly coupled to RNA structures. To understand the functions of RNAs, some structure prediction models have been developed in recent years. In this review, the progress in computational models for RNA structure prediction is introduced and the distinguishing features of many outstanding algorithms are discussed, emphasizing three- dimensional （3D） structure prediction. A promising coarse-grained model for predicting RNA 3D structure, stability and salt effect is also introduced briefly. Finally, we discuss the major challenges in the RNA 3D structure modeling.
基金supported by UT-INSA Program(2013)the support of the China Scholarship Council(CSC)
文摘Airframe maintenance is traditionally performed at scheduled maintenance stops.The decision to repair a fuselage panel is based on a fixed crack size threshold,which allows to ensure the aircraft safety until the next scheduled maintenance stop.With progress in sensor technology and data processing techniques,structural health monitoring（SHM） systems are increasingly being considered in the aviation industry.SHM systems track the aircraft health state continuously,leading to the possibility of planning maintenance based on an actual state of aircraft rather than on a fixed schedule.This paper builds upon a model-based prognostics framework that the authors developed in their previous work,which couples the Extended Kalman filter（EKF） with a firstorder perturbation（FOP） method.By using the information given by this prognostics method,a novel cost driven predictive maintenance（CDPM） policy is proposed,which ensures the aircraft safety while minimizing the maintenance cost.The proposed policy is formally derived based on the trade-off between probabilities of occurrence of scheduled and unscheduled maintenance.A numerical case study simulating the maintenance process of an entire fleet of aircrafts is implemented.Under the condition of assuring the same safety level,the CDPM is compared in terms of cost with two other maintenance policies：scheduled maintenance and threshold based SHM maintenance.The comparison results show CDPM could lead to significant cost savings.
文摘The algorithm based on combination learning usually is superior to a singleclassification algorithm on the task of protein secondary structure prediction. However,the assignment of the weight of the base classifier usually lacks decision-makingevidence. In this paper, we propose a protein secondary structure prediction method withdynamic self-adaptation combination strategy based on entropy, where the weights areassigned according to the entropy of posterior probabilities outputted by base classifiers.The higher entropy value means a lower weight for the base classifier. The final structureprediction is decided by the weighted combination of posterior probabilities. Extensiveexperiments on CB513 dataset demonstrates that the proposed method outperforms theexisting methods, which can effectively improve the prediction performance.
