Bird Object Detection: Dataset Construction, Model Performance Evaluation, and Model Lightweighting.

The application of object detection technology has a positive auxiliary role in advancing the intelligence of bird recognition and enhancing the convenience of bird field surveys. However, challenges arise due to the absence of dedicated bird datasets and evaluation benchmarks. To address this, we have not only constructed the largest known bird object detection dataset, but also compared the performances of eight mainstream detection models on bird object detection tasks and proposed feasible approaches for model lightweighting in bird object detection. Our constructed bird detection dataset of GBDD1433-2023, includes 1433 globally common bird species and 148,000 manually annotated bird images. Based on this dataset, two-stage detection models like Faster R-CNN and Cascade R-CNN demonstrated superior performances, achieving a Mean Average Precision (mAP) of 73.7% compared to one-stage models. In addition, compared to one-stage object detection models, two-stage object detection models have a stronger robustness to variations in foreground image scaling and background interference in bird images. On bird counting tasks, the accuracy ranged between 60.8% to 77.2% for up to five birds in an image, but this decreased sharply beyond that count, suggesting limitations of object detection models in multi-bird counting tasks. Finally, we proposed an adaptive localization distillation method for one-stage lightweight object detection models that are suitable for offline deployment, which improved the performance of the relevant models. Overall, our work furnishes an enriched dataset and practice guidelines for selecting suitable bird detection models.

Increasing areas of aquaculture ponds and reservoirs reshape runoff coefficients: evidence from a subtropical catchment, China.

Detention pond is a key storm water management measure employed both to attenuate surface runoff and to regulate depression storage, yet the effects of aquaculture ponds and reservoirs on runoff coefficient are not well quantified in a subtropical humid monsoon climate zone, China. Here, a set of six subcatchments ranging in size from 0.7 hm2 to 10,000 hm2 were evaluated over the 2011-2015 period. (i) The annual average runoff coefficient differed with different subcatchments due to the spatial heterogeneity of landscape patterns, while the event-based runoff coefficient under the same catchment showed a decreasing trend with increasing rainfall intensity. (ii) The annual average and event-based runoff coefficients initially increased and then decreased with an increase in the area ratio of aquaculture ponds and reservoirs. The critical area ratio of aquaculture ponds and reservoirs for the maximum runoff coefficient in annual, light, and moderate rainfall intensity was about 4%; but this value would be transferred forward to the position of < 4% under the intensity of heavy rain, rainstorms, and heavy rainstorms. (iii) All runoff coefficients decreased with increasing forestland but increased with increasing paddy fields, and the decreasing rate was greater than the increasing rate. The trends of runoff coefficient for the annual and event-based rainfall are opposite between river development coefficient and watershed shape coefficient. The results provide underlying insights for decision-makers in aquaculture land-use planning and the sustainable utilization of water resources in the upstream and downstream systems of a catchment.

Eyebirds: Enabling the Public to Recognize Water Birds at Hand.

Enabling the public to easily recognize water birds has a positive effect on wetland bird conservation. However, classifying water birds requires advanced ornithological knowledge, which makes it very difficult for the public to recognize water bird species in daily life. To break the knowledge barrier of water bird recognition for the public, we construct a water bird recognition system (Eyebirds) by using deep learning, which is implemented as a smartphone app. Eyebirds consists of three main modules: (1) a water bird image dataset; (2) an attention mechanism-based deep convolution neural network for water bird recognition (AM-CNN); (3) an app for smartphone users. The waterbird image dataset currently covers 48 families, 203 genera and 548 species of water birds worldwide, which is used to train our water bird recognition model. The AM-CNN model employs attention mechanism to enhance the shallow features of bird images for boosting image classification performance. Experimental results on the North American bird dataset (CUB200-2011) show that the AM-CNN model achieves an average classification accuracy of 85%. On our self-built water bird image dataset, the AM-CNN model also works well with classification accuracies of 94.0%, 93.6% and 86.4% at three levels: family, genus and species, respectively. The user-side app is a WeChat applet deployed in smartphones. With the app, users can easily recognize water birds in expeditions, camping, sightseeing, or even daily life. In summary, our system can bring not only fun, but also water bird knowledge to the public, thus inspiring their interests and further promoting their participation in bird ecological conservation.

Protein Function Prediction Based on PPI Networks: Network Reconstruction vs Edge Enrichment.

Over the past decades, massive amounts of protein-protein interaction (PPI) data have been accumulated due to the advancement of high-throughput technologies, and but data quality issues (noise or incompleteness) of PPI have been still affecting protein function prediction accuracy based on PPI networks. Although two main strategies of network reconstruction and edge enrichment have been reported on the effectiveness of boosting the prediction performance in numerous literature studies, there still lack comparative studies of the performance differences between network reconstruction and edge enrichment. Inspired by the question, this study first uses three protein similarity metrics (local, global and sequence) for network reconstruction and edge enrichment in PPI networks, and then evaluates the performance differences of network reconstruction, edge enrichment and the original networks on two real PPI datasets. The experimental results demonstrate that edge enrichment work better than both network reconstruction and original networks. Moreover, for the edge enrichment of PPI networks, the sequence similarity outperformes both local and global similarity. In summary, our study can help biologists select suitable pre-processing schemes and achieve better protein function prediction for PPI networks.

[Effect of Rainfall Intensity on the Content of Nitrogen and Phosphorus Components in Plateau Areas: A Case Study of the Fengyu River Watershed].

The runoff formed by rainfall carrying various land surface materials into rivers and lakes is an important factor leading to a change in water quality, and the characteristics of nitrogen and phosphorus output of rivers under different rainfall intensities are different. This study explores the impact of rainfall intensity on the water quality of the Fengyu River Watershed in the plateau agricultural region, based on the water quality monitoring data of the export section of the Fengyu River Watershed from 2011 to 2013, combined with local rainfall monitoring. The effects of four rainfall intensities (light rain, moderate rain, heavy rain, and torrential rain) on the content of different nitrogen and phosphorus components in water were analyzed. The results show that the rainfall intensity has a significant effect on the nitrogen and phosphorus emissions of the Fengyu River Watershed. The average nitrogen and phosphorus concentrations of all components are lower in light rain (<10 mm) and moderate rain (10-25 mm), and higher in heavy rain (25-50 mm) and torrential rain (50-100 mm). The percentage of NH4+-N (57.14%-76.85%) to TN is larger than that of PN (23.15%-42.86%), and the percentage of TDP (22.73%-28.00%) to TP is smaller than that of PP (72.00%-77.27%). The nitrogen concentration of different forms is:TN > NH4+-N > PN; the phosphorus concentration of different forms is:TP > PP > TDP.

Response of regional agricultural soil phosphorus status to net anthropogenic phosphorus input (NAPI) determined by soil pH value and organic matter content in subtropical China.

Exploring the relationship between net anthropogenic phosphorus input (NAPI) and soil available P (SAP) content could inform applied issues related to environmental quality and agronomic productivity and increase our knowledge of element biogeochemical cycles. Here, the NAPI was estimated and the SAP content determined in eight counties in subtropical China from 1980 to 2010. It is suggested that the NAPI ranging 318-924 km-2 yr-1 in 1980 had increased substantially to 865-3601 km-2 yr-1 in 2010 across the eight counties, in which the P fertilizer application was estimated to represent the largest individual source of NAPI, accounting for an average of 36.1-74.6% of the NAPI. The NAPI in agricultural land (NAPIa) was the largest component of the NAPI, and 60.7-77.1% of the NAPIa accumulated in the upper 20 cm layer of agricultural soils, which significantly increased soil total-P (TP) and SAP contents. The increases in SAP, resulting from 10,000 kg P km-2 of the NAPIa (IOPNAPI), were estimated to be 1.61-4.36 mg P kg-1 in the counties. Both the correlation and variation partitioning analyses (VPAs) suggested that the soil pH and organic matter content (SOM) were the most important factors influencing the variations of IOPNAPI (determination coefficient: 72.5%). Therefore, the contribution of soil pH and SOM should be considered in enriching soil SAP levels and implementing optimal P management strategies to improving the agronomic effectiveness of P fertilization and further reduce the environmental risk of P loss in subtropical region.

An effective approach to detecting both small and large complexes from protein-protein interaction networks.

BACKGROUND: Predicting protein complexes from protein-protein interaction (PPI) networks has been studied for decade. Various methods have been proposed to address some challenging issues of this problem, including overlapping clusters, high false positive/negative rates of PPI data and diverse complex structures. It is well known that most current methods can detect effectively only complexes of size ≥3, which account for only about half of the total existing complexes. Recently, a method was proposed specifically for finding small complexes (size = 2 and 3) from PPI networks. However, up to now there is no effective approach that can predict both small (size ≤ 3) and large (size >3) complexes from PPI networks. RESULTS: In this paper, we propose a novel method, called CPredictor2.0, that can detect both small and large complexes under a unified framework. Concretely, we first group proteins of similar functions. Then, the Markov clustering algorithm is employed to discover clusters in each group. Finally, we merge all discovered clusters that overlap with each other to a certain degree, and the merged clusters as well as the remaining clusters constitute the set of detected complexes. Extensive experiments have shown that the new method can more effectively predict both small and large complexes, in comparison with the state-of-the-art methods. CONCLUSIONS: The proposed method, CPredictor2.0, can be applied to accurately predict both small and large protein complexes.

Fusing multiple protein-protein similarity networks to effectively predict lncRNA-protein interactions.

BACKGROUND: Long non-coding RNA (lncRNA) plays important roles in many biological and pathological processes, including transcriptional regulation and gene regulation. As lncRNA interacts with multiple proteins, predicting lncRNA-protein interactions (lncRPIs) is an important way to study the functions of lncRNA. Up to now, there have been a few works that exploit protein-protein interactions (PPIs) to help the prediction of new lncRPIs. RESULTS: In this paper, we propose to boost the prediction of lncRPIs by fusing multiple protein-protein similarity networks (PPSNs). Concretely, we first construct four PPSNs based on protein sequences, protein domains, protein GO terms and the STRING database respectively, then build a more informative PPSN by fusing these four constructed PPSNs. Finally, we predict new lncRPIs by a random walk method with the fused PPSN and known lncRPIs. Our experimental results show that the new approach outperforms the existing methods. CONCLUSION: Fusing multiple protein-protein similarity networks can effectively boost the performance of predicting lncRPIs.

CPredictor3.0: detecting protein complexes from PPI networks with expression data and functional annotations.

BACKGROUND: Effectively predicting protein complexes not only helps to understand the structures and functions of proteins and their complexes, but also is useful for diagnosing disease and developing new drugs. Up to now, many methods have been developed to detect complexes by mining dense subgraphs from static protein-protein interaction (PPI) networks, while ignoring the value of other biological information and the dynamic properties of cellular systems. RESULTS: In this paper, based on our previous works CPredictor and CPredictor2.0, we present a new method for predicting complexes from PPI networks with both gene expression data and protein functional annotations, which is called CPredictor3.0. This new method follows the viewpoint that proteins in the same complex should roughly have similar functions and are active at the same time and place in cellular systems. We first detect active proteins by using gene express data of different time points and cluster proteins by using gene ontology (GO) functional annotations, respectively. Then, for each time point, we do set intersections with one set corresponding to active proteins generated from expression data and the other set corresponding to a protein cluster generated from functional annotations. Each resulting unique set indicates a cluster of proteins that have similar function(s) and are active at that time point. Following that, we map each cluster of active proteins of similar function onto a static PPI network, and get a series of induced connected subgraphs. We treat these subgraphs as candidate complexes. Finally, by expanding and merging these candidate complexes, the predicted complexes are obtained. We evaluate CPredictor3.0 and compare it with a number of existing methods on several PPI networks and benchmarking complex datasets. The experimental results show that CPredictor3.0 achieves the highest F1-measure, which indicates that CPredictor3.0 outperforms these existing method in overall. CONCLUSION: CPredictor3.0 can serve as a promising tool of protein complex prediction.

Side-chain dynamics analysis of KE07 series.

The significant improvement of KE07 series in catalytic activities shows the great success of computational design approaches combined with directed evolution in protein design. Understanding the protein dynamics in the evolutionary optimization process of computationally designed enzyme will provide profound implication to study enzyme function and guide protein design. Here, side chain squared generalized order parameters and entropy of each protein are calculated using 50ns molecular dynamics simulation data in both apo and bound states. Our results show a correlation between the increase of side chain motion amplitude and catalytic efficiency. By analyzing the relationship between these two values, we find side chain squared generalized order parameter is linearly related to side chain entropy, which indicates the computationally designed KE07 series have similar dynamics property with natural enzymes.

[Regional differences of inputs of organic matter and chemical fertilizer in South Central China].

This article analyzed the inputs of organic matter and chemical fertilizer in the cropland of South Central China, i.e., Hunan, Hubei, Guangdong and Guangxi, and then calculated the budgets of nitrogen (N), phosphorus (P) and potassium (K), based on the data from field investigations and peasant household surveys in the four provinces. The results showed that total amounts of organic matter inputs in the four provinces was ranked as follow: 8993 kg · hm(-2) in Guangxi, 6390 kg · hm(-2) in Hunan, 5012 kg · hm(-2) in Hubei, 4630 kg · hm(-2) in Guangdong, and average NPK inputs in the four provinces were ranked as follow: 777.5 kg · hm(-2) in Guangxi, 501.6 kg · hm(-2) in Hunan, 486.4 kg · hm(-2) in Hubei, 340.4 kg · hm(-2) in Guangdong. The N and P input surpluses were greatest in Guangxi (67.2% and 99.0% as for N and P, respectively) , followed by Hunan (33.2% and 50.8%), Hubei (11.8% and 11.0%), and Guangdong (7.8% and 30.0%). However, K input was deficient in Hunan, Hubei, and Guangdong (6.6%, 18.7% and 12.4%), but surplus in Guangxi (19.5%).