Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer’s representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue–residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/.
Image and Spectrum based Deep Feature Analysis for Particle Matter Estimation with Weather Information
Air pollution is a major global risk to human health and environment. Particle matter (PM) with diameters less than 2.5 micrometers (PM2.5) is more harmful to human health
than other air pollutants because it can penetrate deeply into lungs and damage human respiratory system. A new image-based deep feature analysis method is presented in this
paper for PM2.5 concentration estimation. Firstly, low level and high level features are extracted from images and their spectrums by a deep learning neural network, and then
regression models are created using the extracted deep features to estimate the PM2.5 concentrations, which are future refined by the collected weather information. The proposed method was evaluated using a PM2.5 dataset with 1460 photos and the experimental results demonstrated that our method outperformed other state-of-the-art methods.
more »
« less
- Award ID(s):
- 1726500
- NSF-PAR ID:
- 10114065
- Date Published:
- Journal Name:
- Proceedings of IEEE International Conference on Image Processing 2019
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
null (Ed.)X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.more » « less
-
We present a novel source attribution approach that incorporates satellite data into GEOS-Chem adjoint simulations to characterize the species-specific, regional, and sectoral contributions of daily emissions for 3 air pollutants: fine particulate matter (PM2.5), ozone (O3), and nitrogen dioxide (NO2). This approach is implemented for Washington, DC, first for 2011, to identify urban pollution sources, and again for 2016, to examine the pollution response to changes in anthropogenic emissions. In 2011, anthropogenic emissions contributed an estimated 263 (uncertainty: 130–444) PM2.5- and O3-attributable premature deaths and 1,120 (391–1795) NO2 attributable new pediatric asthma cases in DC. PM2.5 exposure was responsible for 90% of these premature deaths. On-road vehicle emissions contributed 51% of NO2-attributable new asthma cases and 23% of pollution-attributable premature deaths, making it the largest contributing individual sector to DC’s air pollution–related health burden. Regional emissions, originating from Maryland, Virginia, and Pennsylvania, were the most responsible for pollution-related health impacts in DC, contributing 57% of premature deaths impacts and 89% of asthma cases. Emissions from distant states contributed 34% more to PM2.5 exposure in the wintertime than in the summertime, occurring in parallel with strong wintertime westerlies and a reduced photochemical sink. Emission reductions between 2011 and 2016 resulted in health benefits of 76 (28–149) fewer pollution-attributable premature deaths and 227 (2–617) fewer NO2-attributable pediatric asthma cases. The largest sectors contributing to decreases in pollution-related premature deaths were energy generation units (26%) and on-road vehicles (20%). Decreases in NO2-attributable pediatric asthma cases were mostly due to emission reductions from on-road vehicles (63%). Emission reductions from energy generation units were found to impact PM2.5 more than O3, while on-road vehicle emission reductions impacted O3 proportionally more than PM2.5. This novel method is capable of capturing the sources of urban pollution at fine spatial and temporal scales and is applicable to many urban environments, globally.more » « less
-
In recent years, air pollution has caused more than 1 million deaths per year in China, making it a major focus of public health efforts. However, future climate change may exacerbate such human health impacts by increasing the frequency and duration of weather conditions that enhance air pollution exposure. Here, we use a combination of climate, air quality, and epidemiological models to assess future air pollution deaths in a changing climate under Representative Concentration Pathway 4.5 (RCP4.5). We find that, assuming pollution emissions and population are held constant at current levels, climate change would adversely affect future air quality for >85% of China’s population (∼55% of land area) by the middle of the century, and would increase by 3% and 4% the population-weighted average concentrations of fine particulate matter (PM2.5) and ozone, respectively. As a result, we estimate an additional 12,100 and 8,900 Chinese (95% confidence interval: 10,300 to 13,800 and 2,300 to 14,700, respectively) will die per year from PM2.5 and ozone exposure, respectively. The important underlying climate mechanisms are changes in extreme conditions such as atmospheric stagnation and heat waves (contributing 39% and 6%, respectively, to the increase in mortality). Additionally, greater vulnerability of China’s aging population will further increase the estimated deaths from PM2.5 and ozone in 2050 by factors of 1 and 3, respectively. Our results indicate that climate change and more intense extremes are likely to increase the risk of severe pollution events in China. Managing air quality in China in a changing climate will thus become more challenging.more » « less
-
Antibiotic resistance genes (ARGs) are commonly detected in the atmosphere, but questions remain regarding their sources and relative contributions, bacterial hosts, and corresponding human health risks. Here, we conducted a qPCR- and metagenomics-based investigation of inhalable fine particulate matter (PM2.5) at a large wastewater treatment plant (WWTP) and in the ambient air of Hong Kong, together with an in-depth analysis of published data of other potential sources in the area. PM2.5 was observed with increasing enrichment of total ARGs along the coastal–urban–WWTP gradient and clinically relevant ARGs commonly identified in urban and WWTP sites, illustrating anthropogenic impacts on the atmospheric accumulation of ARGs. With certain kinds of putative antibiotic-resistant pathogens detected in urban and WWTP PM2.5, a comparable proportion of ARGs that co-occurred with MGEs was found between the atmosphere and WWTP matrices. Despite similar emission rates of bacteria and ARGs within each WWTP matrix, about 11–13% of the bacteria and >57% of the relevant ARGs in urban and WWTP PM2.5 were attributable to WWTPs. Our study highlights the importance of WWTPs in disseminating bacteria and ARGs to the ambient air from a quantitative perspective and, thus, the need to control potential sources of inhalation exposure to protect the health of urban populations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
