UsIL-6: An unbalanced learning strategy for identifying IL-6 inducing peptides by undersampling technique.

BACKGROUND AND OBJECTIVE: Interleukin-6 (IL-6) is the critical factor of early warning, monitoring, and prognosis in the inflammatory storm of COVID-19 cases. IL-6 inducing peptides, which can induce cytokine IL-6 production, are very important for the development of diagnosis and immunotherapy. Although the existing methods have some success in predicting IL-6 inducing peptides, there is still room for improvement in the performance of these models in practical application. METHODS: In this study, we proposed UsIL-6, a high-performance bioinformatics tool for identifying IL-6 inducing peptides. First, we extracted five groups of physicochemical properties and sequence structural information from IL-6 inducing peptide sequences, and obtained a 636-dimensional feature vector, we also employed NearMiss3 undersampling method and normalization method StandardScaler to process the data. Then, a 40-dimensional optimal feature vector was obtained by Boruta feature selection method. Finally, we combined this feature vector with extreme randomization tree classifier to build the final model UsIL-6. RESULTS: The AUC value of UsIL-6 on the independent test dataset was 0.87, and the BACC value was 0.808, which indicated that UsIL-6 had better performance than the existing methods in IL-6 inducing peptide recognition. CONCLUSIONS: The performance comparison on independent test dataset confirmed that UsIL-6 could achieve the highest performance, best robustness, and most excellent generalization ability. We hope that UsIL-6 will become a valuable method to identify, annotate and characterize new IL-6 inducing peptides.

PACVP: Prediction of Anti-Coronavirus Peptides Using a Stacking Learning Strategy With Effective Feature Representation.

Due to the global outbreak of COVID-19 and its variants, antiviral peptides with anti-coronavirus activity (ACVPs) represent a promising new drug candidate for the treatment of coronavirus infection. At present, several computational tools have been developed to identify ACVPs, but the overall prediction performance is still not enough to meet the actual therapeutic application. In this study, we constructed an efficient and reliable prediction model PACVP (Prediction of Anti-CoronaVirus Peptides) for identifying ACVPs based on effective feature representation and a two-layer stacking learning framework. In the first layer, we use nine feature encoding methods with different feature representation angles to characterize the rich sequence information and fuse them into a feature matrix. Secondly, data normalization and unbalanced data processing are carried out. Next, 12 baseline models are constructed by combining three feature selection methods and four machine learning classification algorithms. In the second layer, we input the optimal probability features into the logistic regression algorithm (LR) to train the final model PACVP. The experiments show that PACVP achieves favorable prediction performance on independent test dataset, with ACC of 0.9208 and AUC of 0.9465. We hope that PACVP will become a useful method for identifying, annotating and characterizing novel ACVPs.

Global warming is increasing the discrepancy between green (actual) and thermal (potential) seasons of temperate trees.

Over the past decades, global warming has led to a lengthening of the time window during which temperatures remain favorable for carbon assimilation and tree growth, resulting in a lengthening of the green season. The extent to which forest green seasons have tracked the lengthening of this favorable period under climate warming, however, has not been quantified to date. Here, we used remote sensing data and long-term ground observations of leaf-out and coloration for six dominant species of European trees at 1773 sites, for a total of 6060 species-site combinations, during 1980-2016 and found that actual green season extensions (GS: 3.1 ± 0.1 day decade-1 ) lag four times behind extensions of the potential thermal season (TS: 12.6 ± 0.1 day decade-1 ). Similar but less pronounced differences were obtained using satellite-derived vegetation phenology observations, that is, a lengthening of 4.4 ± 0.13 and 7.5 ± 0.13 day decade-1 for GS and TS, respectively. This difference was mainly driven by the larger advance in the onset of the thermal season compared to the actual advance of leaf-out dates (spring mismatch: 7.2 ± 0.1 day decade-1 ), but to a less extent caused by a phenological mismatch between GS and TS in autumn (2.4 ± 0.1 day decade-1 ). Our results showed that forest trees do not linearly track the new thermal window extension, indicating more complex interactions between winter and spring temperatures and photoperiod and a justification of demonstrating that using more sophisticated models that include the influence of chilling and photoperiod is needed to accurately predict spring phenological changes under warmer climate. They urge caution if such mechanisms are omitted to predict, for example, how vegetative health and growth, species distribution and crop yields will change in the future.

NeuroPred-CLQ: incorporating deep temporal convolutional networks and multi-head attention mechanism to predict neuropeptides.

Neuropeptides (NPs) are a particular class of informative substances in the immune system and physiological regulation. They play a crucial role in regulating physiological functions in various biological growth and developmental stages. In addition, NPs are crucial for developing new drugs for the treatment of neurological diseases. With the development of molecular biology techniques, some data-driven tools have emerged to predict NPs. However, it is necessary to improve the predictive performance of these tools for NPs. In this study, we developed a deep learning model (NeuroPred-CLQ) based on the temporal convolutional network (TCN) and multi-head attention mechanism to identify NPs effectively and translate the internal relationships of peptide sequences into numerical features by the Word2vec algorithm. The experimental results show that NeuroPred-CLQ learns data information effectively, achieving 93.6% accuracy and 98.8% AUC on the independent test set. The model has better performance in identifying NPs than the state-of-the-art predictors. Visualization of features using t-distribution random neighbor embedding shows that the NeuroPred-CLQ can clearly distinguish the positive NPs from the negative ones. We believe the NeuroPred-CLQ can facilitate drug development and clinical trial studies to treat neurological disorders.

Soil moisture regulates warming responses of autumn photosynthetic transition dates in subtropical forests.

Autumn phenology plays a key role in regulating the terrestrial carbon and water balance and their feedbacks to the climate. However, the mechanisms underlying autumn phenology are still poorly understood, especially in subtropical forests. In this study, we extracted the autumn photosynthetic transition dates (APTD) in subtropical China over the period 2003-2017 based on a global, fine-resolution solar-induced chlorophyll fluorescence (SIF) dataset (GOSIF) using four fitting methods, and then explored the temporal-spatial variations of APTD and its underlying mechanisms using partial correlation analysis and machine learning methods. We further predicted the APTD shifts under future climate warming conditions by applying process-based and machine learning-based models. We found that the APTD was significantly delayed, with an average rate of 7.7 days per decade, in subtropical China during 2003-2017. Both partial correlation analysis and machine learning methods revealed that soil moisture was the primary driver responsible for the APTD changes in southern subtropical monsoon evergreen forest (SEF) and middle subtropical evergreen forest (MEF), whereas solar radiation controlled the APTD variations in the northern evergreen-broadleaf deciduous mixed forest (NMF). Combining the effects of temperature, soil moisture and radiation, we found a significantly delayed trend in APTD during the 2030-2100 period, but the trend amplitude (0.8 days per decade) was much weaker than that over 2003-2017. In addition, we found that machine learning methods outperformed process-based models in projecting APTD. Our findings generate from different methods highlight that soil moisture is one of the key players in determining autumn photosynthetic phenological processes in subtropical forests. To comprehensively understand autumn phenological processes, in-situ manipulative experiments are urgently needed to quantify the contributions of different environmental and physiological factors in regulating plants' response to ongoing climate change.

Influences of Shifted Vegetation Phenology on Runoff Across a Hydroclimatic Gradient.

Climate warming has changed vegetation phenology, and the phenology-associated impacts on terrestrial water fluxes remain largely unquantified. The impacts are linked to plant adjustments and responses to climate change and can be different in different hydroclimatic regions. Based on remote sensing data and observed river runoff of hydrological station from six river basins across a hydroclimatic gradient from northeast to southwest in China, the relative contributions of the vegetation (including spring and autumn phenology, growing season length (GSL), and gross primary productivity) and climatic factors affecting the river runoffs over 1982-2015 were investigated by applying gray relational analysis (GRA). We found that the average GSLs in humid regions (190-241 days) were longer than that in semi-humid regions (186-192 days), and the average GSLs were consistently extended by 4.8-13.9 days in 1982-2015 period in six river basins. The extensions were mainly linked to the delayed autumn phenology in the humid regions and to advanced spring phenology in the semi-humid regions. Across all river basins, the GRA results showed that precipitation (r = 0.74) and soil moisture (r = 0.73) determine the river runoffs, and the vegetation factors (VFs) especially the vegetation phenology also affected the river runoffs (spring phenology: r = 0.66; GSL: r = 0.61; autumn phenology: r = 0.59), even larger than the contribution from temperature (r = 0.57), but its relative importance is climatic region-dependent. Interestingly, the spring phenology is the main VF in the humid region for runoffs reduction, while both spring and autumn growth phenology are the main VFs in the semi-humid region, because large autumn phenology delay and less water supply capacity in spring amplify the effect of advanced spring phenology. This article reveals diverse linkages between climatic and VFs, and runoff in different hydroclimatic regions, and provides insights that vegetation phenology influences the ecohydrology process largely depending on the local hydroclimatic conditions, which improve our understanding of terrestrial hydrological responses to climate change.

Scaling Effects on Chlorophyll Content Estimations with RGB Camera Mounted on a UAV Platform Using Machine-Learning Methods.

Timely monitoring and precise estimation of the leaf chlorophyll contents of maize are crucial for agricultural practices. The scale effects are very important as the calculated vegetation index (VI) were crucial for the quantitative remote sensing. In this study, the scale effects were investigated by analyzing the linear relationships between VI calculated from red-green-blue (RGB) images from unmanned aerial vehicles (UAV) and ground leaf chlorophyll contents of maize measured using SPAD-502. The scale impacts were assessed by applying different flight altitudes and the highest coefficient of determination (R2) can reach 0.85. We found that the VI from images acquired from flight altitude of 50 m was better to estimate the leaf chlorophyll contents using the DJI UAV platform with this specific camera (5472 × 3648 pixels). Moreover, three machine-learning (ML) methods including backpropagation neural network (BP), support vector machine (SVM), and random forest (RF) were applied for the grid-based chlorophyll content estimation based on the common VI. The average values of the root mean square error (RMSE) of chlorophyll content estimations using ML methods were 3.85, 3.11, and 2.90 for BP, SVM, and RF, respectively. Similarly, the mean absolute error (MAE) were 2.947, 2.460, and 2.389, for BP, SVM, and RF, respectively. Thus, the ML methods had relative high precision in chlorophyll content estimations using VI; in particular, the RF performed better than BP and SVM. Our findings suggest that the integrated ML methods with RGB images of this camera acquired at a flight altitude of 50 m (spatial resolution 0.018 m) can be perfectly applied for estimations of leaf chlorophyll content in agriculture.