Terahertz （THz） radiation, whose frequency ranges from 0.1 THz to 10.0 THz, has rich science, but limited technology. It has long been considered the last remaining scientific gap in the electromagnetic spectrum. Fa...Terahertz （THz） radiation, whose frequency ranges from 0.1 THz to 10.0 THz, has rich science, but limited technology. It has long been considered the last remaining scientific gap in the electromagnetic spectrum. Far from being fully exploited, it offers great opportunities in science, innovation, new technology, and potential applications. THz science and technology enables fundamental research directly impact our lives, from industrial quality control,展开更多
The number of therapeutic monoclonal antibodies used in clinical trials has recently increased dramatically, leading to the development of optimized downstream purification processes[1]. Staphylococcal protein A （SPA...The number of therapeutic monoclonal antibodies used in clinical trials has recently increased dramatically, leading to the development of optimized downstream purification processes[1]. Staphylococcal protein A （SPA）, a cell-wall protein of Staphylococcus aureus, has been developed as a universal ligand for immunoglobulin G （IgG） purification because it binds specifically to the Fc portion of the IgG molecule of many mammals[2]. However, certain characteristics of SPA severely restrict the advancement of the antibody industry.展开更多
The relative toxicity of 48 anilines using the Tetrahymena pyriformis population growth characteristics IGC50 （concentration causing 50% growth inhibition）, available in the literature, was studied. At first, the en...The relative toxicity of 48 anilines using the Tetrahymena pyriformis population growth characteristics IGC50 （concentration causing 50% growth inhibition）, available in the literature, was studied. At first, the entire data set was randomly split into a training set （31 chemicals） used to establish the QSAR model, and a test set （17 chemicals） for statistical external validation. A biparametric model was developed using, as independent variables, 3D theoretical descriptors derived from DRAGON software. The GA-MLR （genetic algorithm variable subset selection） procedure was performed on the trainingset by the software mobydigs using the OLS （ordinary least squares） regression method, and GA（genetic algorithm）-VSS（variable subset selection） by maximising the cross-validated explained variance （Q^2Loo）＇ The obtained model was examined for robustness （Q^2LOOcross-validation, Y-scrambling） and predictive ability through both internal （Q^2LM0, bootstrap） and external validation （Q^2ext） methods. Descriptors included in the QSAR model indicated that log/GC^-150 value was related to molecular size and shape, and interaction of molecule with its surrounding medium or its target. Moreover, the applicability domain of the model was discussed.展开更多
This work was carried out on a series of twenty-two (22) benzimidazole derivatives with inhibitory activities against Mycobacterium tuberculosis H37Rv by applying the Quantitative Structure-Activity Relationship (QSAR...This work was carried out on a series of twenty-two (22) benzimidazole derivatives with inhibitory activities against Mycobacterium tuberculosis H37Rv by applying the Quantitative Structure-Activity Relationship (QSAR) method. The molecules were optimized at the level DFT/B3LYP/6-31 + G (d, p), to obtain the molecular descriptors. We used three statistical learning tools namely, the linear multiple regression (LMR) method, the nonlinear regression (NLMR) and the artificial neural network (ANN) method. These methods allowed us to obtain three (3) quantitative models from the quantum descriptors that are, chemical potential (μ), polarizability (α), bond length l (C = N), and lipophilicity. These models showed good statistical performance. Among these, the ANN has a significantly better predictive ability R<sup>2</sup> = 0.9995;RMSE = 0.0149;F = 31879.0548. The external validation tests verify all the criteria of Tropsha et al. and Roy et al. Also, the internal validation tests show that the model has a very satisfactory internal predictive character and can be considered as robust. Moreover, the applicability range of this model determined from the levers shows that a prediction of the pMIC of the new benzimidazole derivatives is acceptable when its lever value is lower than 1.展开更多
Elasticity imaging offers the possibility of detecting changes in elastic properties and assesses the biomechanical properties of soft tissue with increased sensitivity and spatial resolution compared with conventiona...Elasticity imaging offers the possibility of detecting changes in elastic properties and assesses the biomechanical properties of soft tissue with increased sensitivity and spatial resolution compared with conventional palpation. However, the range of applied strains is limited by the concomitant increase of echo signal decorrelation, The decorrelation is mainly introduced by diffuse scattering, while the regular scattering is highly correlated. Because the regular scattering and diffuse scattering localize with different patterns in different ranges of time-scale plane, a new method is put forward to detect the regular scattering with matched filters based on wavelet transform using Generalized Likelihood Aatio Test (GLRT). The simulation results illustrate that the change in estimated mean interscatterer spacing introduced by a SNR of -10 dB is 1.1±2.8%. Thus, by tracking the highly correlated regular scattering, the internal strain can be estimated based on the change in interscatterer spacing under the condition of large surface deformation. The experiment studies show that the internal strain can be estimated up to 10% applied deformation in phantom and 5% strain in porcine liver.展开更多
Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions.In this work,we develop a new and general approach of assessing model domain and de...Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions.In this work,we develop a new and general approach of assessing model domain and demonstrate that our approach provides accurate and meaningful domain designation across multiple model types and material property data sets.Our approach assesses the distance between data in feature space using kernel density estimation,where this distance provides an effective tool for domain determination.We show that chemical groups considered unrelated based on chemical knowledge exhibit significant dissimilarities by our measure.We also show that high measures of dissimilarity are associated with poor model performance(i.e.,high residual magnitudes)and poor estimates of model uncertainty(i.e.,unreliable uncertainty estimation).Automated tools are provided to enable researchers to establish acceptable dissimilarity thresholds to identify whether new predictions of their own machine learning models are in-domain versus out-of-domain.展开更多
Estrogen compounds may pose a serious threat to the health of humans and wildlife. The estrogen receptor （ER） exists as two subtypes, ERα and ERβ. Compounds might have different relative affinities and binding mod...Estrogen compounds may pose a serious threat to the health of humans and wildlife. The estrogen receptor （ER） exists as two subtypes, ERα and ERβ. Compounds might have different relative affinities and binding modes for ERα and ERβ. In this study, the heuristic method was performed on 31 compounds binding to ERβ to select 5 variances most related to the activity （LogRBA） from 1524 variances, which were then employed to develop the best model with the significant correlation and the best predictive power （γ^2 = 0.829, q^2LOO = 0.742, γ^2pred = 0.772, q^2ext = 0.724, RMSEE = 0.395） using multiple linear regression （MLR）. The model derived identified critical structural features related to the activity of binding to ERβ. The applicability domain （AD） of the model was assessed by Williams plot.展开更多
文摘Terahertz （THz） radiation, whose frequency ranges from 0.1 THz to 10.0 THz, has rich science, but limited technology. It has long been considered the last remaining scientific gap in the electromagnetic spectrum. Far from being fully exploited, it offers great opportunities in science, innovation, new technology, and potential applications. THz science and technology enables fundamental research directly impact our lives, from industrial quality control,
基金supported by grants from the National High Technology Research and Development Program of China(863 Program)(No.2012AA020304)the National Natural Science Foundation of China(Grant No.31300643)the Innovation Fund for Postgraduate Students from the Simcere Pharmaceutical Company(No.02704051)
文摘The number of therapeutic monoclonal antibodies used in clinical trials has recently increased dramatically, leading to the development of optimized downstream purification processes[1]. Staphylococcal protein A （SPA）, a cell-wall protein of Staphylococcus aureus, has been developed as a universal ligand for immunoglobulin G （IgG） purification because it binds specifically to the Fc portion of the IgG molecule of many mammals[2]. However, certain characteristics of SPA severely restrict the advancement of the antibody industry.
文摘The relative toxicity of 48 anilines using the Tetrahymena pyriformis population growth characteristics IGC50 （concentration causing 50% growth inhibition）, available in the literature, was studied. At first, the entire data set was randomly split into a training set （31 chemicals） used to establish the QSAR model, and a test set （17 chemicals） for statistical external validation. A biparametric model was developed using, as independent variables, 3D theoretical descriptors derived from DRAGON software. The GA-MLR （genetic algorithm variable subset selection） procedure was performed on the trainingset by the software mobydigs using the OLS （ordinary least squares） regression method, and GA（genetic algorithm）-VSS（variable subset selection） by maximising the cross-validated explained variance （Q^2Loo）＇ The obtained model was examined for robustness （Q^2LOOcross-validation, Y-scrambling） and predictive ability through both internal （Q^2LM0, bootstrap） and external validation （Q^2ext） methods. Descriptors included in the QSAR model indicated that log/GC^-150 value was related to molecular size and shape, and interaction of molecule with its surrounding medium or its target. Moreover, the applicability domain of the model was discussed.
文摘This work was carried out on a series of twenty-two (22) benzimidazole derivatives with inhibitory activities against Mycobacterium tuberculosis H37Rv by applying the Quantitative Structure-Activity Relationship (QSAR) method. The molecules were optimized at the level DFT/B3LYP/6-31 + G (d, p), to obtain the molecular descriptors. We used three statistical learning tools namely, the linear multiple regression (LMR) method, the nonlinear regression (NLMR) and the artificial neural network (ANN) method. These methods allowed us to obtain three (3) quantitative models from the quantum descriptors that are, chemical potential (μ), polarizability (α), bond length l (C = N), and lipophilicity. These models showed good statistical performance. Among these, the ANN has a significantly better predictive ability R<sup>2</sup> = 0.9995;RMSE = 0.0149;F = 31879.0548. The external validation tests verify all the criteria of Tropsha et al. and Roy et al. Also, the internal validation tests show that the model has a very satisfactory internal predictive character and can be considered as robust. Moreover, the applicability range of this model determined from the levers shows that a prediction of the pMIC of the new benzimidazole derivatives is acceptable when its lever value is lower than 1.
基金This work is supported by Nature Science foundation of China (No. 39470212) and Trans-centuryTraining Program for Talents from
文摘Elasticity imaging offers the possibility of detecting changes in elastic properties and assesses the biomechanical properties of soft tissue with increased sensitivity and spatial resolution compared with conventional palpation. However, the range of applied strains is limited by the concomitant increase of echo signal decorrelation, The decorrelation is mainly introduced by diffuse scattering, while the regular scattering is highly correlated. Because the regular scattering and diffuse scattering localize with different patterns in different ranges of time-scale plane, a new method is put forward to detect the regular scattering with matched filters based on wavelet transform using Generalized Likelihood Aatio Test (GLRT). The simulation results illustrate that the change in estimated mean interscatterer spacing introduced by a SNR of -10 dB is 1.1±2.8%. Thus, by tracking the highly correlated regular scattering, the internal strain can be estimated based on the change in interscatterer spacing under the condition of large surface deformation. The experiment studies show that the internal strain can be estimated up to 10% applied deformation in phantom and 5% strain in porcine liver.
基金the Bridge to the Doctorate:Wisconsin Louis Stokes Alliance for Minority Participation National Science Foundation(NSF)award number HRD-1612530the University of Wisconsin-Madison Graduate Engineering Research Scholars(GERS)fellowship program,and the PPG Coating Innovation Center for financial support for the initial part of this work.The other authors gratefully acknowledge support from the NSF Collaborative Research:Framework:Machine Learning Materials Innovation Infrastructure award number 1931306+1 种基金Lane E.Schultz also acknowledges this award for support for the latter part of this work.Machine learning was performed with the computational resources provided by XSEDE 2.0:Integrating,Enabling and Enhancing National Cyberinfrastructure with Expanding Community Involvement Grant ACI-1548562We thank former and current members of the Informatics Skunkworks at the University of Wisconsin-Madison for their contributions to early aspects of this work:Angelo Cortez,Evelin Yin,Jodie Felice Ritchie,Stanley Tzeng,Avi Sharma,Linxiu Zeng,and Vidit Agrawal.
文摘Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions.In this work,we develop a new and general approach of assessing model domain and demonstrate that our approach provides accurate and meaningful domain designation across multiple model types and material property data sets.Our approach assesses the distance between data in feature space using kernel density estimation,where this distance provides an effective tool for domain determination.We show that chemical groups considered unrelated based on chemical knowledge exhibit significant dissimilarities by our measure.We also show that high measures of dissimilarity are associated with poor model performance(i.e.,high residual magnitudes)and poor estimates of model uncertainty(i.e.,unreliable uncertainty estimation).Automated tools are provided to enable researchers to establish acceptable dissimilarity thresholds to identify whether new predictions of their own machine learning models are in-domain versus out-of-domain.
基金supported by the Science and Technology Development Foundation Key Project of Nanjing Medical University (09NJMUZ16)
文摘Estrogen compounds may pose a serious threat to the health of humans and wildlife. The estrogen receptor （ER） exists as two subtypes, ERα and ERβ. Compounds might have different relative affinities and binding modes for ERα and ERβ. In this study, the heuristic method was performed on 31 compounds binding to ERβ to select 5 variances most related to the activity （LogRBA） from 1524 variances, which were then employed to develop the best model with the significant correlation and the best predictive power （γ^2 = 0.829, q^2LOO = 0.742, γ^2pred = 0.772, q^2ext = 0.724, RMSEE = 0.395） using multiple linear regression （MLR）. The model derived identified critical structural features related to the activity of binding to ERβ. The applicability domain （AD） of the model was assessed by Williams plot.
