Large-scale Prediction Research Articles

Computational Methods and Deep Learning for Elucidating Protein Interaction Networks.

Protein interactions play a critical role in all biological processes, but experimental identification of protein interactions is a time- and resource-intensive process. The advances in next-generation sequencing and multi-omics technologies have greatly benefited large-scale predictions of protein interactions using machine learning methods. A wide range of tools have been developed to predict protein-protein, protein-nucleic acid, and protein-drug interactions. Here, we discuss the applications, methods, and challenges faced when employing the various prediction methods. We also briefly describe ways to overcome the challenges and prospective future developments in the field of protein interaction biology.

Predicting methane emission in Canadian Holstein dairy cattle using milk mid-infrared reflectance spectroscopy and other commonly available predictors via artificial neural networks.

Interest in reducing eructed CH4 is growing, but measuring CH4 emissions is expensive and difficult in large populations. In this study, we investigated the effectiveness of milk mid-infrared spectroscopy (MIRS) data to predict CH4 emission in lactating Canadian Holstein cows. A total of 181 weekly average CH4 records from 158 Canadian cows and 217 records from 44 Danish cows were used. For each milk spectra record, the corresponding weekly average CH4 emission (g/d), test-day milk yield (MY, kg/d), fat yield (FY, g/d), and protein yield (PY, g/d) were available. The weekly average CH4 emission was predicted using various artificial neural networks (ANN), partial least squares regression, and different sets of predictors. The ANN architectures consisted of 3 training algorithms, 1 to 10 neurons with hyperbolic tangent activation function in the hidden layer, and 1 neuron with linear (purine) activation function in the hidden layer. Random cross-validation was used to compared the predictor sets: MY (set 1); FY (set 2); PY (set 3); MY and FY (set 4); MY and PY (set 5); MY, FY, and PY (set 6); MIRS (set 7); and MY, FY, PY, and MIRS (set 8). All predictor sets also included age at calving and days in milk, in addition to country, season of calving, and lactation number as categorical effects. Using only MY (set 1), the predictive accuracy (r) ranged from 0.245 to 0.457 and the root mean square error (RMSE) ranged from 87.28 to 99.39 across all prediction models and validation sets. Replacing MY with FY (set 2; r = 0.288-0.491; RMSE = 85.94-98.04) improved the predictive accuracy, but using PY (set 3; r = 0.260-0.468; RMSE = 86.95-98.47) did not. Adding FY to MY (set 4; r = 0.272-0.469; RMSE = 87.21-100.76) led to a negligible improvement compared with sets 1 and 3, but it slightly decreased accuracy compared with set 2. Adding PY to MY (set 5; r = 0.250-0.451; RMSE = 87.66-100.94) did not improve prediction ability. Combining MY, FY, and PY (set 6; r = 0.252-0.455; RMSE = 87.74-101.93) yielded accuracy slightly lower than sets 2 and 3. Using only MIRS data (set 7; r = 0.586-0.717; RMSE = 69.09-96.20) resulted in superior accuracy compared with all previous sets. Finally, the combination of MIRS data with MY, FY, and PY (set 8; r = 0.590-0.727; RMSE = 68.02-87.78) yielded similar accuracy to set 7. Overall, sets including the MIRS data yielded significantly better predictions than the other sets. To assess the predictive ability in a new unseen herd, a limited block cross-validation was performed using 20 cows in the same Canadian herd, which yielded r = 0.229 and RMSE = 154.44, which were clearly much worse than the average r = 0.704 and RMSE = 70.83 when predictions were made by random cross-validation. These results warrant further investigation when more data become available to allow for a more comprehensive block cross-validation before applying the calibrated models for large-scale prediction of CH4 emissions.

Streamflow data availability in Europe: a detailed dataset of interpolated flow-duration curves

Abstract. For about 24 000 river basins across Europe, we provide a continuous representation of the streamflow regime in terms of empirical flow-duration curves (FDCs), which are key signatures of the hydrological behaviour of a catchment and are widely used for supporting decisions on water resource management as well as for assessing hydrologic change. In this study, FDCs are estimated by means of the geostatistical procedure termed total negative deviation top-kriging (TNDTK), starting from the empirical FDCs made available by the Joint Research Centre of the European Commission (DG-JRC) for about 3000 discharge measurement stations across Europe. Consistent with previous studies, TNDTK is shown to provide high accuracy for the entire study area, even with different degrees of reliability, which varies significantly over the study area. In order to provide this kind of information site by site, together with the estimated FDCs, for each catchment we provide indicators of the accuracy and reliability of the performed large-scale geostatistical prediction. The dataset is freely available at the PANGAEA open-access library (Data Publisher for Earth & Environmental Science) at https://doi.org/10.1594/PANGAEA.938975 (Persiano et al., 2021b).

A Novel System for the Measurement of an Evaporation Duct Using the Magnetic Coupling Principle for Power Feeding and Data Transmission.

Since the evaporation duct height (EDH) only covers the antenna height of most shipborne microwave radars, mastering the EDH in advance has great significance in achieving long-range target detection. In this paper, a set of hydrological and meteorological sensors based on the gradient meteorological instrument (GMI) were built to monitor the evaporation duct of the South China Sea (SCS). However, the monitoring needed to be interrupted during the battery replacement of the sensor, which could result in the loss of some important data collection. On the basis of the inductively coupled power transfer (ICPT) technology, the resonance principle was used to compensate the inductive reactance on the closed steel ring (CSR), and the energy stored in the super capacitor was introduced for data collection and return. A novel measuring system for the detection of an evaporation duct was proposed. To avoid iterative calculation by setting the initial value of the current evaporation duct models in large-scale and multi time evaporation duct prediction and diagnosis, on the basis of the non-iterative air–sea flux (NAF) model, the EDH was obtained by introducing the K theoretical flux observation method into the atmospheric refractive index equation. Finally, preliminary experimental results are presented for the detection of evaporation duct to demonstrate the feasibility and effectiveness of the proposed system. The communication accuracy rate of the proposed system was 99.7%. The system transmission power reached 22.8 W. The research results of the NAF model adaptability showed that the mean value of the EDH was 8.7 m, which was lower than the mean EDH of the SCS. The EDH calculated by the NAF model in the unstable air–sea stratification state was slightly lower than that calculated by the NPS model. The diagnosis of the EDH by the NAF model was similar to that of the NPS model, but the calculation stability of the NAF model was better.

A chronotherapeutics-applicable multi-target therapeutics based on AI: Example of therapeutic hypothermia.

Nowadays, the complexity of disease mechanisms and the inadequacy of single-target therapies in restoring the biological system have inevitably instigated the strategy of multi-target therapeutics with the analysis of each target individually. However, it is not suitable for dealing with the conflicts between targets or between drugs. With the release of high-precision protein structure prediction artificial intelligence, large-scale high-precision protein structure prediction and docking have become possible. In this article, we propose a multi-target drug discovery method by the example of therapeutic hypothermia (TH). First, we performed protein structure prediction for all protein targets of each group by AlphaFold2 and RoseTTAFold. Then, QuickVina 2 is used for molecular docking between the proteins and drugs. After docking, we use PageRank to rank single drugs and drug combinations of each group. The ePharmaLib was used for predicting the side effect targets. Given the differences in the weights of different targets, the method can effectively avoid inhibiting beneficial proteins while inhibiting harmful proteins. So it could minimize the conflicts between different doses and be friendly to chronotherapeutics. Besides, this method also has potential in precision medicine for its high compatibility with bioinformatics and promotes the development of pharmacogenomics and bioinfo-pharmacology.

Mapping Soil Organic Matter Content Based on Feature Band Selection with ZY1-02D Hyperspectral Satellite Data in the Agricultural Region

Soil organic matter (SOM) is an essential nutrient for crop growth and development. Hyperspectral satellite images with comprehensive spectral band coverage and high spectral resolution can be used to estimate and draw a spatial distribution map of SOM content in the region, which can provide a scientific management basis for precision agriculture. This study takes Xinzheng City, Henan Province’s agricultural area, as the research object. Based on ZY1-02D hyperspectral satellite image data, the first derivative of reflectance (FDR) was processed on the original reflectance (OR). The SOM characteristic spectral bands were extracted using the correlation coefficient (CC) and least absolute shrinkage and selection operator (Lasso) methods. The prediction model of SOM content was established by multiple linear regression (MLR), partial least squares regression (PLSR), and random forest (RF) algorithms. The results showed that: (1) FDR processing can enhance SOM spectral features and reduce noise; (2) the Lasso feature band extraction method can reduce the model’s input variables and raise the estimation precision; (3) the SOM content prediction ability of the RF model was significantly better than that of the MLR and PLSR models. The FDR-Lasso-RF model was the best SOM content prediction model, and the validation set R2 = 0.921, MAEV = 0.512 g/kg, RMSEV = 0.645 g/kg; (4) compared with laboratory hyperspectral data-SOM prediction methods, hyperspectral satellite data can achieve accurate, rapid, and large-scale SOM content prediction and mapping. This study provides an efficient, accurate, and feasible method for predicting and mapping SOM content in an agricultural region.

Serverless High-Performance Computing over Cloud

Abstract HPC clouds may provide fast access to fully configurable and dynamically scalable virtualized HPC clusters to address the complex and challenging computation and storage-intensive requirements. The complex environmental, software, and hardware requirements and dependencies on such systems make it challenging to carry out our large-scale simulations, prediction systems, and other data and compute-intensive workloads over the cloud. The article aims to present an architecture that enables HPC workloads to be serverless over the cloud (Shoc), one of the most critical cloud capabilities for HPC workloads. On one hand, Shoc utilizes the abstraction power of container technologies like Singularity and Docker, combined with the scheduling and resource management capabilities of Kubernetes. On the other hand, Shoc allows running any CPU-intensive and data-intensive workloads in the cloud without needing to manage HPC infrastructure, complex software, and hardware environment deployments.

Defining a nitrogen efficiency index in Holstein cows and assessing its potential effect on the breeding program of bulls.

The purposes of this study were (1) to explore the relationship between 3 milk mid-infrared predicted features including nitrogen intake (NINT), milk true protein N (MTPN), and milk urea-N yield (MUNY); (2) to integrate these 3 features into an N efficiency index (NEI) and analyses approximate genetic correlations between the NEI and 37 traits (indices) of interest; and (3) to assess the potential effect of including the NEI into breeding programs of bulls. The edited data were 1,043,171 test-day records on 342,847 cows in 1,931 herds and 143,595 test-day records on 53,660 cows in 766 herds used for estimating breeding values (EBV) and variance components, respectively. The used records were within 5 to 50 d in milk. The records were grouped into primiparous and multiparous. The genetic parameters for the included mid-infrared features and EBV of the animals included in the pedigree were estimated using a multiple-trait repeatability animal model. Then, the EBV of the NINT, MTPN, MUNY were integrated into the NEI using a selection index assuming weights based on the N partitioning. The approximate genetic correlations between the NEI and 37 traits of interest were estimated using the EBV of the selected bulls. The bulls born from 2011 to 2014 with NEI were selected and the NEI distribution of these bulls having EBV for the 8 selected traits (indices) was checked. The heritability and repeatability estimates for NINT, MTPN, and MUNY ranged from 0.09 to 0.13, and 0.37 to 0.65, respectively. The genetic and phenotypic correlations between NINT, MTPN, and MUNY ranged from -0.31 to 0.87, and -0.02 to 0.42, respectively. The NEI ranged from -13.13 to 12.55 kg/d. In total, 736 bulls with reliability ≥0.50 for all included traits (NEI and 37 traits) and at least 10 daughters distributed in at least 10 herds were selected to investigate genetic aspects of the NEI. The NEI had positive genetic correlations with production yield traits (0.08-0.46), and negative genetic correlations with the investigated functional traits and indices (-0.71 to -0.07), except for the production economic index and functional type economic index. The daughters of bulls with higher NEI had lower NINT and MUNY, and higher MTPN. Furthermore, 26% of the bulls (n = 50) with NEI born between 2011 to 2014 had higher NEI and global economic index than the average in the selected bulls. Finally, the developed NEI has the advantage of large-scale prediction and therefore has the potential for routine application in dairy cattle breeding in the future.

LeMeDISCO is a computational method for large-scale prediction & molecular interpretation of disease comorbidity

To understand the origin of disease comorbidity and to identify the essential proteins and pathways underlying comorbid diseases, we developed LeMeDISCO (Large-Scale Molecular Interpretation of Disease Comorbidity), an algorithm that predicts disease comorbidities from shared mode of action proteins predicted by the artificial intelligence-based MEDICASCY algorithm. LeMeDISCO was applied to predict the occurrence of comorbid diseases for 3608 distinct diseases. Benchmarking shows that LeMeDISCO has much better comorbidity recall than the two molecular methods XD-score (44.5% vs. 6.4%) and the SAB score (68.6% vs. 8.0%). Its performance is somewhat comparable to the phenotype method-based Symptom Similarity Score, 63.7% vs. 100%, but LeMeDISCO works for far more cases and its large comorbidity recall is attributed to shared proteins that can help provide an understanding of the molecular mechanism(s) underlying disease comorbidity. The LeMeDISCO web server is available for academic users at: http://sites.gatech.edu/cssb/LeMeDISCO.

Large-scale prediction of key dynamic interacting proteins in multiple cancers

Tracking cancer dynamic protein-protein interactions (PPIs) and deciphering their pathogenesis remain a challenge. We presented a dynamic PPIs' hypothesis: permanent and transient interactions might achieve dynamic switchings from normal cells to malignancy, which could cause maintenance functions to be interrupted and transient functions to be sustained. Based on the hypothesis, we first predicted >1400 key cancer genes (KCG) by applying PPI-express we proposed to 18 cancer gene expression datasets. We then further screened out key dynamic interactions (KDI) of cancer based on KCG and transient and permanent interactions under both conditions. Two prominent functional characteristics, “Cell cycle-related” and “Immune-related”, were presented for KCG, suggesting that these might be their general characteristics. We found that, compared to permanent to transient KDI pairs (P2T) in the network, transient to permanent (T2P) have significantly higher edge betweenness (EB), and P2T pairs tending to locate intra-functional modules may play roles in maintaining normal biological functions, while T2P KDI pairs tending to locate inter-modules may play roles in biological signal transduction. It was consistent with our hypothesis. Also, we analyzed network characteristics of KDI pairs and their functions. Our findings of KDI may serve to understand and explain a few hallmarks of cancer.

Intelligent Case-based Hybrid Model for Process and Endpoint Prediction of Converter via Data Mining Technique

An intelligent case-based hybrid converter model has been established to predict the converter endpoint and process operations. The case-based reasoning (CBR) technique combined with the similarity calculation system was used in the intelligent converter model. The actual production data during the converter process in a time span from 2018 to 2020 was collected in the model database. The influencing factors during converter stage were divided into five categories, including steel composition, steel temperature, total processing time, steel cleanliness and total steelmaking cost of converter process in the model. All these factors were used in the similarity degree calculation, and then the historical cases in the model database were retrieved to guide the actual operation by analyzing its similarity degree to new case. The prediction accuracy was improved through self-learning with constant supplement of massive data. The prediction results based on 120-ton industrial converter showed a reasonable operation selection, the mean deviation of endpoint [C] content and [P] was 9.66% and 6.24%, respectively. Moreover, the difference between the predicted endpoint temperature and the measured endpoint temperature is within 10°C. Accordingly, the intelligent converter model was stable and suitable for large-scale prediction in converter endpoint and process operations.

The Compressional Beta Effect and Convective System Propagation

Abstract The compressional beta effect (CBE) arises in a compressible atmosphere with the nontraditional Coriolis terms (NCTs), the Coriolis force from the locally horizontal part of the planetary rotation. Previous studies proposed that the CBE speeds up the eastward propagation and slows down the westward propagation of zonal vertical circulations in a dry atmosphere. Here, we examine how the CBE affects the propagation of convectively coupled tropical waves. We perform 2D (x, z), large-domain cloud-resolving simulations with and without NCTs. This model setup mimics the atmosphere along Earth’s equator, and differences between the simulations highlight the role of the CBE. We analyze precipitation, precipitable water, and surface and upper-level winds from our simulations. Gravity wave signals emerge in all fields. In the no-NCT simulation, eastward and westward gravity waves propagate at the same speed. With NCTs, eastward gravity waves propagate faster than westward gravity waves. To quantify the strength of the CBE, we then measure the difference in gravity wave speed and find that it linearly increases with the system rotation rate. This result is consistent with our theoretical prediction and suggests that the CBE can induce zonal asymmetry in propagation behaviors of convectively coupled waves. Significance Statement The rotation of Earth turns eastward motion upward and upward motion westward, and vice versa. This effect is called the nontraditional Coriolis effect and is omitted in most of the current atmospheric models for predicting weather and climate. Using an idealized model with cloud physics, this study suggests that the inclusion of the nontraditional Coriolis effect speeds up eastward-moving rainy systems and slows down westward-moving ones. The speed change agrees with a theory without cloud physics. This study encourages restoring the nontraditional Coriolis effect to the atmospheric models since it increases the accuracy of tropical large-scale weather prediction while the cost is low.

More Complex is Not Necessarily Better in Large-Scale Hydrological Modeling: A Model Complexity Experiment across the Contiguous United States

Abstract Conceptual hydrological models are irreplaceable tools for large-scale (i.e., from ­regional to global) hydrological predictions. Large-scale modeling studies typically strive to employ one single model structure regardless of the diversity of catchments under study. However, little is known on the optimal model complexity for large-scale applications. In a modeling experiment across 700 catchments in the contiguous United States, we analyze the performance of a ­conceptual (bucket style) distributed hydrological model with varying complexity (5 model versions with 11–45 parameters) but with exactly the same inputs and spatial and temporal resolution and implementing the same regional parameterization approach. The performance of all model versions compares well with those of contemporary large-scale models tested in the United States, suggesting that the applied model structures reasonably account for the dominant hydrological processes. Remarkably, our results favor a simpler model structure where the main hydrological processes of runoff generation and routing through soil, groundwater, and the river network are conceptualized in distinct but parsimonious ways. As long as only observed runoff is used for model validation, including additional soil layers in the model structure to better represent ­vertical soil heterogeneity seems not to improve model performance. More complex models tend to have lower model performance and may result in rather large uncertainties in simulating states and fluxes (soil moisture and groundwater recharge) in model ensemble applications. Overall, our results indicate that simpler model structures tend to be a more reliable choice, given the limited validation data available at large scale.

Hybrid Deep Learning Applied on Saudi Smart Grids for Short-Term Load Forecasting

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load’s consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy.

Assessing the accuracy of large-scale rainfall erosivity estimation based on climate zones and rainfall patterns

Rainfall erosivity is affected by the amount and intensity of rainfall in a certain period, which is an essential factor for soil erosion prediction. However, it is generally calculated by field measurements on a local scale. With a focus on global soil erosion assessment, some researchers have improved the estimation of global rainfall erosivity by using statistical models in some climate zones. However, the climate zones cannot represent actual erosive rainfall events. Therefore, such usage of models would lead to more uncertainties when estimating rainfall erosivity across the globe. Here, our study compared six common-used models of rainfall erosivity and then improved the accuracy of rainfall erosivity estimations based on global rainfall patterns, which are defined by the amount and distribution of rainfall in a year. Results showed that: (1) Compared with the climate zone classification, the model fitting under the rainfall pattern classification can improve the model accuracy and result in higher variation among the rainfall patterns. The average accuracy of all models was improved by 8%, and the accuracy of annual models was increased by 33%. (2) Models based on annual rainfall are more suitable for the drought and seasonal rainfall patterns, while most models based on monthly rainfall are suitable for the moderate rainfall pattern. However, most models based on monthly or annual rainfall have high uncertainties and low accuracies in regions with annual precipitation < 200 mm or > 850 mm. This study can provide helpful implications for model selection and parameter calibration associated with large-scale water erosion prediction.

A Discovery Strategy for Active Compounds of Chinese Medicine Based on the Prediction Model of Compound-Disease Relationship.

An accurate characterization of diseases and compounds is the key to predicting the compound-disease relationship (CDR). However, due to the difficulty of a comprehensive description of CDR, the accuracy of traditional drug development models for large-scale CDR prediction is usually unsatisfactory. In order to solve this problem, we propose a new method that integrates the molecular descriptors of compounds and the symptom descriptors of diseases to build a CDR two-dimensional matrix to predict candidate active compounds. The Matlab software draws grayscale images of CDRs, which are used as a benchmark dataset for training convolutional neural network (CNN) models. The trained model is used to predict candidate antitumor active compounds. Among the AlexNet and GoogLeNet models, we selected the GoogLeNet model for the prediction of active compounds in Chinese medicine, and its Acc, Sen, Pre, F-measure, MCC, and AUC are 0.960, 0.956, 0.965, 0.960, 0.920, and 0.964, respectively. In the prediction results of compounds, 1624 candidate CDRs were found in 124 Chinese medicines. Among them, we obtained 31 features of candidate antitumor active compounds. This method provides new insights for the discovery of candidate active compounds in Chinese medicine.

BayesR3 enables fast MCMC blocked processing for largescale multi-trait genomic prediction and QTN mapping analysis

Bayesian methods, such as BayesR, for predicting the genetic value or risk of individuals from their genotypes, such as Single Nucleotide Polymorphisms (SNP), are often implemented using a Markov Chain Monte Carlo (MCMC) process. However, the generation of Markov chains is computationally slow. We introduce a form of blocked Gibbs sampling for estimating SNP effects from Markov chains that greatly reduces computational time by sampling each SNP effect iteratively n-times from conditional block posteriors. Subsequent iteration over all blocks m-times produces chains of length m × n. We use this strategy to solve large-scale genomic prediction and fine-mapping problems using the Bayesian MCMC mixed-effects genetic model, BayesR3. We validate the method using simulated data, followed by analysis of empirical dairy cattle data using high dimension milk mid infra-red spectra data as an example of “omics” data and show its use to increase the precision of mapping variants affecting milk, fat, and protein yields relative to a univariate analysis of milk, fat, and protein.

Rice Yield Estimation Based on Continuous Wavelet Transform With Multiple Growth Periods.

Yield is an important indicator in evaluating rice planting, and it is the collective result of various factors over multiple growth stages. To achieve a large-scale accurate prediction of rice yield, based on yield estimation models using a single growth stage and conventional spectral transformation methods, this study introduced the continuous wavelet transform algorithm and constructed models under the premise of combined multiple growth stages. In this study, canopy reflectance spectra at four important stages of rice elongation, heading, flowering and milky were selected, and then, a rice yield estimation model was constructed by combining vegetation index, first derivative and wavelet transform based on random forest algorithm or multiple stepwise regression. This study found that the combination of multiple growth stages significantly improved the model accuracy. In addition, after two validations, the optimal model combination for rice yield estimation is first derivative-wavelet transform-vegetation index-random forest model based on four growth stages, with the coefficient of determination (R2) of 0.86, the root mean square error (RMSE) of 35.50 g·m−2 and the mean absolute percentage error (MAPE) of 4.6% for the training set, R2 of 0.85, RMSE of 33.40 g.m−2 and MAPE 4.30% for the validation set 1, and R2 of 0.80, RMSE of 37.40 g·m−2 and MAPE of 4.60% for the validation set 2. The research results demonstrated that the established model could accurately predict rice yield, providing technical support and a foundation for large-scale statistical estimating of rice yield.

An Online Service Performance Prediction Learning Method

In order to improve the quality of service operations, it is necessary to take the initiative to prevent service failures and service performance fluctuations, instead of triggering handlers when service errors occur. Effective prediction and analysis of the large-scale services performance is an effective and feasible proactive prevention tool. However, the traditional service performance prediction model mostly adopts the full batch training mode, it is difficult to meet the real-time requirements of large-scale service calculation. Based on the comprehensive trade-off between the method of full batch learning and the stochastic gradient descent method, a large-scale service performance prediction model is established based on online learning, and a service performance prediction method is proposed based on small batch online learning. Through properly setting the batch parameters, the proposed approach only need to train the sample data with small batches in one iteration, the time efficiency is improved for large-scale service performance prediction.

DeepTracer-ID: De novo protein identification from cryo-EM maps

The recent revolution in cryo-electron microscopy (cryo-EM) has made it possible to determine macromolecular structures directly from cell extracts. However, identifying the correct protein from the cryo-EM map is still challenging and often needs additional sequence information from other techniques, such as tandem mass spectrometry and/or bioinformatics. Here, we present DeepTracer-ID, a server-based approach to identify the candidate protein in a user-provided organism de novo from a cryo-EM map, without the need for additional information. Our method first uses DeepTracer to generate a protein backbone model that best represents the cryo-EM map, and this model is then searched against the library of AlphaFold2 predictions for all proteins in the given organism. This method is highly accurate and robust for high-resolution cryo-EM maps: in all 13 experimental maps tested blindly, DeepTracer-ID identified the correct proteins as the top candidates. Eight of the maps were of known structures, while the other five unpublished maps were validated by prior protein annotation and careful inspection of the model refined into the map. The program also showed promising results for both homomeric and heteromeric protein complexes. This platform is possible because of the recent breakthroughs in large-scale three-dimensional protein structure prediction.