The pursuit of optimal neural network architectures is foundational to the progression of Neural Architecture Search (NAS). However, the existing NAS methods suffer from the following problem using traditional search ...The pursuit of optimal neural network architectures is foundational to the progression of Neural Architecture Search (NAS). However, the existing NAS methods suffer from the following problem using traditional search strategies, i.e., when facing a large and complex search space, it is difficult to mine more effective architectures within a reasonable time, resulting in inferior search results. This research introduces the Generative Pre-trained Transformer NAS (GPT-NAS), an innovative approach designed to overcome the limitations which are inherent in traditional NAS strategies. This approach improves search efficiency and obtains better architectures by integrating GPT model into the search process. Specifically, we design a reconstruction strategy that utilizes the trained GPT to reorganize the architectures obtained from the search. In addition, to equip the GPT model with the design capabilities of neural architecture, we propose the use of the GPT model for training on a neural architecture dataset. For each architecture, the structural information of its previous layers is utilized to predict the next layer of structure, iteratively traversing the entire architecture. In this way, the GPT model can efficiently learn the key features required for neural architectures. Extensive experimental validation shows that our GPT-NAS approach beats both manually constructed neural architectures and automatically generated architectures by NAS. In addition, we validate the superiority of introducing the GPT model in several ways, and find that the accuracy of the neural architecture on the image dataset obtained from the search after introducing the GPT model is improved by up to about 9%.展开更多
Antibody leads must fulfill multiple desirable properties to be clinical candidates.Primarily due to the low throughput in the experimental procedure,the need for such multiproperty optimization causes the bottleneck ...Antibody leads must fulfill multiple desirable properties to be clinical candidates.Primarily due to the low throughput in the experimental procedure,the need for such multiproperty optimization causes the bottleneck in preclinical antibody discovery and development,because addressing one issue usually causes another.We developed a reinforcement learning(RL)method,named AB-Gen,for antibody library design using a generative pre-trained transformer(GPT)as the policy network of the RL agent.We showed that this model can learn the antibody space of heavy chain complementarity determining region 3(CDRH3)and generate sequences with similar property distributions.Besides,when using human epidermal growth factor receptor-2(HER2)as the target,the agent model of AB-Gen was able to generate novel CDRH3 sequences that fulfill multi-property constraints.Totally,509 generated sequences were able to pass all property filters,and three highly conserved residues were identified.The importance of these residues was further demonstrated by molecular dynamics simulations,consolidating that the agent model was capable of grasping important information in this complex optimization task.Overall,the ABGen method is able to design novel antibody sequences with an improved success rate than the traditional propose-then-filter approach.It has the potential to be used in practical antibody design,thus empowering the antibody discovery and development process.The source code of AB-Gen is freely available at Zenodo(https://doi.org/10.5281/zenodo.7657016)and BioCode(https://ngdc.cncb.ac.cn/biocode/tools/BT007341).展开更多
BACKGROUND With the rising use of endoscopic submucosal dissection(ESD)and endoscopic mucosal resection(EMR),patients are increasingly questioning various aspects of these endoscopic procedures.At the same time,conver...BACKGROUND With the rising use of endoscopic submucosal dissection(ESD)and endoscopic mucosal resection(EMR),patients are increasingly questioning various aspects of these endoscopic procedures.At the same time,conversational artificial intelligence(AI)tools like chat generative pretrained transformer(ChatGPT)are rapidly emerging as sources of medical information.AIM To evaluate ChatGPT’s reliability and usefulness regarding ESD and EMR for patients and healthcare professionals.METHODS In this study,30 specific questions related to ESD and EMR were identified.Then,these questions were repeatedly entered into ChatGPT,with two independent answers generated for each question.A Likert scale was used to rate the accuracy,completeness,and comprehensibility of the responses.Meanwhile,a binary category(high/Low)was used to evaluate each aspect of the two responses generated by ChatGPT and the response retrieved from Google.RESULTS By analyzing the average scores of the three raters,our findings indicated that the responses generated by ChatGPT received high ratings for accuracy(mean score of 5.14 out of 6),completeness(mean score of 2.34 out of 3),and comprehensibility(mean score of 2.96 out of 3).Kendall’s coefficients of concordance indicated good agreement among raters(all P<0.05).For the responses generated by Google,more than half were classified by experts as having low accuracy and low completeness.CONCLUSION ChatGPT provided accurate and reliable answers in response to questions about ESD and EMR.Future studies should address ChatGPT’s current limitations by incorporating more detailed and up-to-date medical information.This could establish AI chatbots as significant resource for both patients and health care professionals.展开更多
We have designed,assembled,and tested a 4-MA,60-ns fast linear transformer driver(LTD),which is the first operating generator featuring multiple LTD modules connected in parallel.The LTD-based accelerator comprises si...We have designed,assembled,and tested a 4-MA,60-ns fast linear transformer driver(LTD),which is the first operating generator featuring multiple LTD modules connected in parallel.The LTD-based accelerator comprises six modules in parallel,each of which has ten-stage cavities stacked in series.The six LTD modules are connected to a water tank of diameter 6 m via a 3-m-long impedance-matched deionized waterinsulated coaxial transmission line.In the water tank,the electrical pulses are transmitted down by six horizontal tri-plate transmission lines.A 2.1-m-diameter two-level vacuum insulator stack is utilized to separate the deionized water region from the vacuum region.In the vacuum,the currents are further transported downstream by a two-level magnetically insulated transmission-line and then converged through four post-hole convolutes.Plasma radiation loads or bremsstrahlung electron beam diodes serve as loads that are expected to generate intense soft X rays or warm X rays.The machine is 3.2 m in height and 22 m in outer diameter,including support systems such as a high-voltage charge supply,magnetic core reset system,trigger system,and support platform for inner stalk installation and maintenance.A total of 1440 individual±100-kV multi-gap spark switches and 2880 individual 100-kV capacitors are employed in the accelerator.A total of 12 fiberoptic laser-controlled trigger generators combining photoconductive and traditional gas spark switch technologies are used to realize the synchronous discharge of the more than 1000 gas switches.At an LTD charge voltage of±85 kV,the accelerator stores an initial energy of about 300 kJ and is expected to deliver a current of 3–5 MA into various loads.To date,the LTD facility has shot into a thick-walled aluminum liner load and a reflex triode load.With a thick-walled aluminum liner of inductance 1.81 nH,a current with peak up to 4.1 MA and rise time(10%–90%)of about 60 ns has been achieved.The current transport efficiency from the insulator stack to the liner load approaches 100%during peak times.The LTD accelerator has been used to drive reflex triode loads generating warm X rays with high energy fluence and large radiation area.It has been demonstrated that this LTD is a promising and high-efficiency prime pulsed power source suitable for use in constructing the next generation of large-scale accelerators with currents of tens of megaamperes.展开更多
Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,th...Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,the existing generative image steganography methods generally have good steganography performance,but there is still potential room for enhancing both the quality of stego images and the accuracy of secret information extraction.Therefore,this paper proposes a generative image steganography algorithm based on attribute feature transformation and invertible mapping rule.Firstly,the reference image is disentangled by a content and an attribute encoder to obtain content features and attribute features,respectively.Then,a mean mapping rule is introduced to map the binary secret information into a noise vector,conforming to the distribution of attribute features.This noise vector is input into the generator to produce the attribute transformed stego image with the content feature of the reference image.Additionally,we design an adversarial loss,a reconstruction loss,and an image diversity loss to train the proposed model.Experimental results demonstrate that the stego images generated by the proposed method are of high quality,with an average extraction accuracy of 99.4%for the hidden information.Furthermore,since the stego image has a uniform distribution similar to the attribute-transformed image without secret information,it effectively resists both subjective and objective steganalysis.展开更多
This essay is showing an opinion that despite the many disadvantages of T.G grammar,its main theories about human language learning can give valuable guide to language teaching,which will be illustrated in the followi...This essay is showing an opinion that despite the many disadvantages of T.G grammar,its main theories about human language learning can give valuable guide to language teaching,which will be illustrated in the following from three main aspects.展开更多
Recently,diffusion models have emerged as a promising paradigm for molecular design and optimization.However,most diffusion-based molecular generative models focus on modeling 2D graphs or 3D geom-etries,with limited ...Recently,diffusion models have emerged as a promising paradigm for molecular design and optimization.However,most diffusion-based molecular generative models focus on modeling 2D graphs or 3D geom-etries,with limited research on molecular sequence diffusion models.The International Union of Pure and Applied Chemistry(IUPAC)names are more akin to chemical natural language than the simplified molecular input line entry system(SMILES)for organic compounds.In this work,we apply an IUPAC-guided conditional diffusion model to facilitate molecular editing from chemical natural language to chemical language(SMILES)and explore whether the pre-trained generative performance of diffusion models can be transferred to chemical natural language.We propose DiffIUPAC,a controllable molecular editing diffusion model that converts IUPAC names to SMILES strings.Evaluation results demonstrate that our model out-performs existing methods and successfully captures the semantic rules of both chemical languages.Chemical space and scaffold analysis show that the model can generate similar compounds with diverse scaffolds within the specified constraints.Additionally,to illustrate the model’s applicability in drug design,we conducted case studies in functional group editing,analogue design and linker design.展开更多
现有图像修复技术通常很难为缺失区域生成视觉上连贯的内容,其原因是高频内容质量下降导致频谱结构的偏差,以及有限的感受野无法有效建模输入特征之间的非局部关系。为解决上述问题,提出一种融合双向感知Transformer与频率分析策略的图...现有图像修复技术通常很难为缺失区域生成视觉上连贯的内容,其原因是高频内容质量下降导致频谱结构的偏差,以及有限的感受野无法有效建模输入特征之间的非局部关系。为解决上述问题,提出一种融合双向感知Transformer与频率分析策略的图像修复网络(bidirect-aware Transformer and frequency analysis,BAT-Freq)。具体内容包括,设计了双向感知Transformer,用自注意力和n-gram的组合从更大的窗口捕获上下文信息,以全局视角聚合高级图像上下文;同时,提出了频率分析指导网络,利用频率分量来提高图像修复质量,并设计了混合域特征自适应对齐模块,有效地对齐并融合破损区域的混合域特征,提高了模型的细节重建能力。该网络实现空间域与频率域相结合的图像修复。在CelebA-HQ、Place2、Paris StreetView三个数据集上进行了大量的实验,结果表明,PSNR和SSIM分别平均提高了2.804 dB和8.13%,MAE和LPIPS分别平均降低了0.0158和0.0962。实验证明,该方法能够同时考虑语义结构的完善和纹理细节的增强,生成具有逼真感的修复结果。展开更多
基金supported by the National Nature Science Foundation of China(No.62106161)the Fundamental Research Funds for the Central Universities(No.1082204112364)+4 种基金the Sichuan University Luzhou Municipal Government Strategic Cooperation Project(No.2022CDLZ-8)the Key R&D Program of Sichuan Province(Nos.2022YFN0017 and 2023YFG0019)the Natural Science Foundation of Sichuan(No.2023NSFSC0474)the Tianfiu Yongxing Laboratory Organized Research Project Funding(No.2023CXXM14)the Digital Media Art,Key Laboratory of Sichuan Province,Sichuan Conservatory of Music(No.22DMAKL04).
文摘The pursuit of optimal neural network architectures is foundational to the progression of Neural Architecture Search (NAS). However, the existing NAS methods suffer from the following problem using traditional search strategies, i.e., when facing a large and complex search space, it is difficult to mine more effective architectures within a reasonable time, resulting in inferior search results. This research introduces the Generative Pre-trained Transformer NAS (GPT-NAS), an innovative approach designed to overcome the limitations which are inherent in traditional NAS strategies. This approach improves search efficiency and obtains better architectures by integrating GPT model into the search process. Specifically, we design a reconstruction strategy that utilizes the trained GPT to reorganize the architectures obtained from the search. In addition, to equip the GPT model with the design capabilities of neural architecture, we propose the use of the GPT model for training on a neural architecture dataset. For each architecture, the structural information of its previous layers is utilized to predict the next layer of structure, iteratively traversing the entire architecture. In this way, the GPT model can efficiently learn the key features required for neural architectures. Extensive experimental validation shows that our GPT-NAS approach beats both manually constructed neural architectures and automatically generated architectures by NAS. In addition, we validate the superiority of introducing the GPT model in several ways, and find that the accuracy of the neural architecture on the image dataset obtained from the search after introducing the GPT model is improved by up to about 9%.
基金supported in part by the Office of Research Administration(ORA),King Abdullah University of Science and Technology(KAUST),Saudi Arabia(Grant Nos.FCC/1/1976-44-01,FCC/1/1976-45-01,REI/1/5234-01-01,and URF/1/4352-01-01)the National Natural Science Foundation of China(Grant No.22273107).
文摘Antibody leads must fulfill multiple desirable properties to be clinical candidates.Primarily due to the low throughput in the experimental procedure,the need for such multiproperty optimization causes the bottleneck in preclinical antibody discovery and development,because addressing one issue usually causes another.We developed a reinforcement learning(RL)method,named AB-Gen,for antibody library design using a generative pre-trained transformer(GPT)as the policy network of the RL agent.We showed that this model can learn the antibody space of heavy chain complementarity determining region 3(CDRH3)and generate sequences with similar property distributions.Besides,when using human epidermal growth factor receptor-2(HER2)as the target,the agent model of AB-Gen was able to generate novel CDRH3 sequences that fulfill multi-property constraints.Totally,509 generated sequences were able to pass all property filters,and three highly conserved residues were identified.The importance of these residues was further demonstrated by molecular dynamics simulations,consolidating that the agent model was capable of grasping important information in this complex optimization task.Overall,the ABGen method is able to design novel antibody sequences with an improved success rate than the traditional propose-then-filter approach.It has the potential to be used in practical antibody design,thus empowering the antibody discovery and development process.The source code of AB-Gen is freely available at Zenodo(https://doi.org/10.5281/zenodo.7657016)and BioCode(https://ngdc.cncb.ac.cn/biocode/tools/BT007341).
基金Supported by Ningbo Top Medical and Health Research Program,No.2023020612the Ningbo Leading Medical&Healthy Discipline Project,No.2022-S04+1 种基金the Medical Health Science and Technology Project of Zhejiang Provincial Health Commission,No.2022KY315Ningbo Science and Technology Public Welfare Project,No.2023S133.
文摘BACKGROUND With the rising use of endoscopic submucosal dissection(ESD)and endoscopic mucosal resection(EMR),patients are increasingly questioning various aspects of these endoscopic procedures.At the same time,conversational artificial intelligence(AI)tools like chat generative pretrained transformer(ChatGPT)are rapidly emerging as sources of medical information.AIM To evaluate ChatGPT’s reliability and usefulness regarding ESD and EMR for patients and healthcare professionals.METHODS In this study,30 specific questions related to ESD and EMR were identified.Then,these questions were repeatedly entered into ChatGPT,with two independent answers generated for each question.A Likert scale was used to rate the accuracy,completeness,and comprehensibility of the responses.Meanwhile,a binary category(high/Low)was used to evaluate each aspect of the two responses generated by ChatGPT and the response retrieved from Google.RESULTS By analyzing the average scores of the three raters,our findings indicated that the responses generated by ChatGPT received high ratings for accuracy(mean score of 5.14 out of 6),completeness(mean score of 2.34 out of 3),and comprehensibility(mean score of 2.96 out of 3).Kendall’s coefficients of concordance indicated good agreement among raters(all P<0.05).For the responses generated by Google,more than half were classified by experts as having low accuracy and low completeness.CONCLUSION ChatGPT provided accurate and reliable answers in response to questions about ESD and EMR.Future studies should address ChatGPT’s current limitations by incorporating more detailed and up-to-date medical information.This could establish AI chatbots as significant resource for both patients and health care professionals.
基金supported by the National Natural Science Foundation of China(Grant Nos.12027811 and 51790524).
文摘We have designed,assembled,and tested a 4-MA,60-ns fast linear transformer driver(LTD),which is the first operating generator featuring multiple LTD modules connected in parallel.The LTD-based accelerator comprises six modules in parallel,each of which has ten-stage cavities stacked in series.The six LTD modules are connected to a water tank of diameter 6 m via a 3-m-long impedance-matched deionized waterinsulated coaxial transmission line.In the water tank,the electrical pulses are transmitted down by six horizontal tri-plate transmission lines.A 2.1-m-diameter two-level vacuum insulator stack is utilized to separate the deionized water region from the vacuum region.In the vacuum,the currents are further transported downstream by a two-level magnetically insulated transmission-line and then converged through four post-hole convolutes.Plasma radiation loads or bremsstrahlung electron beam diodes serve as loads that are expected to generate intense soft X rays or warm X rays.The machine is 3.2 m in height and 22 m in outer diameter,including support systems such as a high-voltage charge supply,magnetic core reset system,trigger system,and support platform for inner stalk installation and maintenance.A total of 1440 individual±100-kV multi-gap spark switches and 2880 individual 100-kV capacitors are employed in the accelerator.A total of 12 fiberoptic laser-controlled trigger generators combining photoconductive and traditional gas spark switch technologies are used to realize the synchronous discharge of the more than 1000 gas switches.At an LTD charge voltage of±85 kV,the accelerator stores an initial energy of about 300 kJ and is expected to deliver a current of 3–5 MA into various loads.To date,the LTD facility has shot into a thick-walled aluminum liner load and a reflex triode load.With a thick-walled aluminum liner of inductance 1.81 nH,a current with peak up to 4.1 MA and rise time(10%–90%)of about 60 ns has been achieved.The current transport efficiency from the insulator stack to the liner load approaches 100%during peak times.The LTD accelerator has been used to drive reflex triode loads generating warm X rays with high energy fluence and large radiation area.It has been demonstrated that this LTD is a promising and high-efficiency prime pulsed power source suitable for use in constructing the next generation of large-scale accelerators with currents of tens of megaamperes.
基金supported in part by the National Natural Science Foundation of China(Nos.62202234,62401270)the China Postdoctoral Science Foundation(No.2023M741778)the Natural Science Foundation of Jiangsu Province(Nos.BK20240706,BK20240694).
文摘Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,the existing generative image steganography methods generally have good steganography performance,but there is still potential room for enhancing both the quality of stego images and the accuracy of secret information extraction.Therefore,this paper proposes a generative image steganography algorithm based on attribute feature transformation and invertible mapping rule.Firstly,the reference image is disentangled by a content and an attribute encoder to obtain content features and attribute features,respectively.Then,a mean mapping rule is introduced to map the binary secret information into a noise vector,conforming to the distribution of attribute features.This noise vector is input into the generator to produce the attribute transformed stego image with the content feature of the reference image.Additionally,we design an adversarial loss,a reconstruction loss,and an image diversity loss to train the proposed model.Experimental results demonstrate that the stego images generated by the proposed method are of high quality,with an average extraction accuracy of 99.4%for the hidden information.Furthermore,since the stego image has a uniform distribution similar to the attribute-transformed image without secret information,it effectively resists both subjective and objective steganalysis.
文摘This essay is showing an opinion that despite the many disadvantages of T.G grammar,its main theories about human language learning can give valuable guide to language teaching,which will be illustrated in the following from three main aspects.
基金supported by the Yonsei University graduate school Department of Integrative Biotechnology.
文摘Recently,diffusion models have emerged as a promising paradigm for molecular design and optimization.However,most diffusion-based molecular generative models focus on modeling 2D graphs or 3D geom-etries,with limited research on molecular sequence diffusion models.The International Union of Pure and Applied Chemistry(IUPAC)names are more akin to chemical natural language than the simplified molecular input line entry system(SMILES)for organic compounds.In this work,we apply an IUPAC-guided conditional diffusion model to facilitate molecular editing from chemical natural language to chemical language(SMILES)and explore whether the pre-trained generative performance of diffusion models can be transferred to chemical natural language.We propose DiffIUPAC,a controllable molecular editing diffusion model that converts IUPAC names to SMILES strings.Evaluation results demonstrate that our model out-performs existing methods and successfully captures the semantic rules of both chemical languages.Chemical space and scaffold analysis show that the model can generate similar compounds with diverse scaffolds within the specified constraints.Additionally,to illustrate the model’s applicability in drug design,we conducted case studies in functional group editing,analogue design and linker design.
文摘现有图像修复技术通常很难为缺失区域生成视觉上连贯的内容,其原因是高频内容质量下降导致频谱结构的偏差,以及有限的感受野无法有效建模输入特征之间的非局部关系。为解决上述问题,提出一种融合双向感知Transformer与频率分析策略的图像修复网络(bidirect-aware Transformer and frequency analysis,BAT-Freq)。具体内容包括,设计了双向感知Transformer,用自注意力和n-gram的组合从更大的窗口捕获上下文信息,以全局视角聚合高级图像上下文;同时,提出了频率分析指导网络,利用频率分量来提高图像修复质量,并设计了混合域特征自适应对齐模块,有效地对齐并融合破损区域的混合域特征,提高了模型的细节重建能力。该网络实现空间域与频率域相结合的图像修复。在CelebA-HQ、Place2、Paris StreetView三个数据集上进行了大量的实验,结果表明,PSNR和SSIM分别平均提高了2.804 dB和8.13%,MAE和LPIPS分别平均降低了0.0158和0.0962。实验证明,该方法能够同时考虑语义结构的完善和纹理细节的增强,生成具有逼真感的修复结果。
