Model For Prediction Of Solubility Research Articles

Machine learning analysis of rivaroxaban solubility in mixed solvents for application in pharmaceutical crystallization

This study investigates the use of machine learning models to predict solubility of rivaroxaban in binary solvents based on temperature (T), mass fraction (w), and solvent type. Using a dataset with over 250 data points and including solvents encoded with one-hot encoding, four models were compared: Gradient Boosting (GB), Light Gradient Boosting (LGB), Extra Trees (ET), and Random Forest (RF). The Jellyfish Optimizer (JO) algorithm was applied to tune hyperparameters, enhancing model performance. The LGB model achieved the best results, with an R2 of 0.988 on the test set and low error rates (RMSE of 9.1284E-05 and MAE of 5.85322E-05), surpassing other models in predictive accuracy and generalizability. Parity plots confirmed the LGB model’s close alignment between predicted and actual solubility values, highlighting its robust performance. Furthermore, 3D surface plots and partial effect plots demonstrated LGB’s capacity to model solubility across different solvent systems, capturing complex interactions between T, w, and solvent effects. Finally, the LGB model predicted maximum solubility at a temperature of 305.76 K and a mass fraction of 0.753 in a dichloromethane + methanol mixture, providing valuable insights for solubility optimization in solvent selection. This work underscores the effectiveness of the LGB model for solubility prediction, with potential applications in formulation and experimental planning.

Solubility prediction and interaction mechanism of FOX-7 in ten solvents by molecular and thermodynamic modeling

Solubility is a fundamental physicochemical property of materials. Current solubility prediction models are often highly parameterized by existing data, leading to a serious issue of transferability; thus, it is still challenging to enhancing their accuracy and generalization-ability. In this study, we employ molecular dynamics (MD) simulations and some thermodynamic modeling methods (SMD, COSMO-RS, and COSMO-SAC) to predict the relative solubility of 1,1-diamino-2,2-dinitroethylene (FOX-7) in ten solvents. A meticulous comparison with experimental data reveals that the alchemical free energy approach based on MD simulations outperforms SMD, COSMO-RS and COSMO-SAC models in solubility prediction. Furthermore, we identify that the more negative solvation free energy corresponds to the higher solubility, and the stronger solute–solvent hydrogen bonding corresponds to the higher solubility for low polar solvents too. Finally, it is confirmed that the electrostatic attraction dominates the binding energy between solute and solvent molecules. This work transcends traditional solubility prediction by offering a robust theoretical framework and computational strategy, proving both economical and environmentally benign. It paves the way for the rational selection of solvents for FOX-7 crystallization and provides a versatile tool for predicting the solubility of organic compounds.

GGAS2SN: Gated Graph and SmilesToSeq Network for Solubility Prediction.

Aqueous solubility is a critical physicochemical property of drug discovery. Solubility is a key issue in pharmaceutical development because it can limit a drug's absorption capacity. Accurate solubility prediction is crucial for pharmacological, environmental, and drug development studies. This research introduces a novel method for solubility prediction by combining gated graph neural networks (GGNNs) and graph attention neural networks (GATs) with Smiles2Seq encoding. Our methodology involves converting chemical compounds into graph structures with nodes representing atoms and edges indicating chemical bonds. These graphs are then processed by using a specialized graph neural network (GNN) architecture. Incorporating attention mechanisms into GNN allows for capturing subtle structural dependencies, fostering improved solubility predictions. Furthermore, we utilized the Smiles2Seq encoding technique to bridge the semantic gap between molecular structures and their textual representations. Smiles2Seq seamlessly converts chemical notations into numeric sequences, facilitating the efficient transfer of information into our model. We demonstrate the efficacy of our approach through comprehensive experiments on benchmark solubility data sets, showcasing superior predictive performance compared to traditional methods. Our model outperforms existing solubility prediction models and provides interpretable insights into the molecular features driving solubility behavior. This research signifies an important advancement in solubility prediction, offering potent tools for drug discovery, formulation development, and environmental assessments. The fusion of GGNN and Smiles2Seq encoding establishes a robust framework for accurately forecasting solubility across various chemical compounds, fostering innovation in various domains reliant on solubility data.

Enhanced ResNet50 Model for Aqueous Solubility Prediction of Drug Compounds Using Deep Learning Techniques

Background: Aqueous Solubility (AS) is a critical factor in drug discovery (DD), directly influencing a drug’s bioavailability and overall efficacy. Accurate prediction of AS remains a challenge despite the advancement in machine learning techniques, which are essential for improving the pharmacokinetics and formulation of new compounds. Methods: This study determines an enhanced ResNet50 deep learning architecture for predicting AS in drug compounds. Deep-net models with 8, 16, and 20-layer ResNet50 Convolutional Neural Network (CNN) architectures were developed. A dataset of 9,532 drug compounds, represented by molecular footprints, was used to train the models. The training process utilized a ten-fold cross-validation technique to optimize the model's predictive performance. Results: The 20-layer ResNet50 model outperformed human experts and shallower models, achieving an R² value of 0.423 and an RMSE of 0.678. The model also demonstrated an impressive ASP accuracy rate of 90.6%, significantly surpassing the predictions made by human experts and simpler neural network models. Conclusion: This study demonstrates that deeper-net architectures, particularly the 20-layer ResNet50 model, offer superior performance in predicting AS. These deep learning models provide a reliable and efficient solution for improving solubility predictions, crucial for advancing drug discovery efforts.

AlphaFold 2-based stacking model for protein solubility prediction and its transferability on seed storage proteins

Accurate protein solubility prediction is crucial in screening suitable candidates for food application. Existing models often rely only on sequences, overlooking important structural details. In this study, a regression model for protein solubility was developed using both the sequences and predicted structures of 2983 E. coli proteins. The sequence and structural level properties of the proteins were bioinformatically extracted and subjected to multilayer perceptron (MLP). Moreover, residue level features and contact maps were utilized to construct a graph convolutional network (GCN). The out-of-fold predictions of the two models were combined and fed into multiple meta-regressors to create a stacking model. The stacking model with support vector regressor (SVR) achieved R2 of 0.502 and 0.468 on test and external validation datasets, respectively, displaying higher performance compared to existing regression models. Based on the improved performance compared to its based models, the stacking model effectively captured the strength of its base models as well as the significance of the different features used. Furthermore, the model's transferability was indirectly validated on a dataset of seed storage proteins using Osborne definition as well as on a case study using molecular dynamic simulation, showing potential for application beyond microbial proteins to food and agriculture-related ones.

PLM_Sol: predicting protein solubility by benchmarking multiple protein language models with the updated Escherichia coli protein solubility dataset.

Protein solubility plays a crucial role in various biotechnological, industrial, and biomedical applications. With the reduction in sequencing and gene synthesis costs, the adoption of high-throughput experimental screening coupled with tailored bioinformatic prediction has witnessed a rapidly growing trend for the development of novel functional enzymes of interest (EOI). High protein solubility rates are essential in this process and accurate prediction of solubility is a challenging task. As deep learning technology continues to evolve, attention-based protein language models (PLMs) can extract intrinsic information from protein sequences to a greater extent. Leveraging these models along with the increasing availability of protein solubility data inferred from structural database like the Protein Data Bank holds great potential to enhance the prediction of protein solubility. In this study, we curated an Updated Escherichia coli protein Solubility DataSet (UESolDS) and employed a combination of multiple PLMs and classification layers to predict protein solubility. The resulting best-performing model, named Protein Language Model-based protein Solubility prediction model (PLM_Sol), demonstrated significant improvements over previous reported models, achieving a notable 6.4% increase in accuracy, 9.0% increase in F1_score, and 11.1% increase in Matthews correlation coefficient score on the independent test set. Moreover, additional evaluation utilizing our in-house synthesized protein resource as test data, encompassing diverse types of enzymes, also showcased the good performance of PLM_Sol. Overall, PLM_Sol exhibited consistent and promising performance across both independent test set and experimental set, thereby making it well suited for facilitating large-scale EOI studies. PLM_Sol is available as a standalone program and as an easy-to-use model at https://zenodo.org/doi/10.5281/zenodo.10675340.

Prediction of CO2 solubility in Ionic liquids for CO2 capture using deep learning models

Ionic liquids (ILs) are highly effective for capturing carbon dioxide (CO2). The prediction of CO2 solubility in ILs is crucial for optimizing CO2 capture processes. This study investigates the use of deep learning models for CO2 solubility prediction in ILs with a comprehensive dataset of 10,116 CO2 solubility data in 164 kinds of ILs under different temperature and pressure conditions. Deep neural network models, including Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM), were developed to predict CO2 solubility in ILs. The ANN and LSTM models demonstrated robust test accuracy in predicting CO2 solubility, with coefficient of determination (R2) values of 0.986 and 0.985, respectively. Both model's computational efficiency and cost were investigated, and the ANN model achieved reliable accuracy with a significantly lower computational time (approximately 30 times faster) than the LSTM model. A global sensitivity analysis (GSA) was performed to assess the influence of process parameters and associated functional groups on CO2 solubility. The sensitivity analysis results provided insights into the relative importance of input attributes on output variables (CO2 solubility) in ILs. The findings highlight the significant potential of deep learning models for streamlining the screening process of ILs for CO2 capture applications.

GATSol, an enhanced predictor of protein solubility through the synergy of 3D structure graph and large language modeling

BackgroundProtein solubility is a critically important physicochemical property closely related to protein expression. For example, it is one of the main factors to be considered in the design and production of antibody drugs and a prerequisite for realizing various protein functions. Although several solubility prediction models have emerged in recent years, many of these models are limited to capturing information embedded in one-dimensional amino acid sequences, resulting in unsatisfactory predictive performance.ResultsIn this study, we introduce a novel Graph Attention network-based protein Solubility model, GATSol, which represents the 3D structure of proteins as a protein graph. In addition to the node features of amino acids extracted by the state-of-the-art protein large language model, GATSol utilizes amino acid distance maps generated using the latest AlphaFold technology. Rigorous testing on independent eSOL and the Saccharomyces cerevisiae test datasets has shown that GATSol outperforms most recently introduced models, especially with respect to the coefficient of determination R2, which reaches 0.517 and 0.424, respectively. It outperforms the current state-of-the-art GraphSol by 18.4% on the S. cerevisiae_test set.ConclusionsGATSol captures 3D dimensional features of proteins by building protein graphs, which significantly improves the accuracy of protein solubility prediction. Recent advances in protein structure modeling allow our method to incorporate spatial structure features extracted from predicted structures into the model by relying only on the input of protein sequences, which simplifies the entire graph neural network prediction process, making it more user-friendly and efficient. As a result, GATSol may help prioritize highly soluble proteins, ultimately reducing the cost and effort of experimental work. The source code and data of the GATSol model are freely available at https://github.com/binbinbinv/GATSol.

A comprehensive model analysis of activity coefficients and thermodynamic properties of EAE-1DMA2P blended solvent

Solubility has an important influence on industrial applications of amine solvents. The CO2 equilibrium solubilities of EAE-1DMA2P solvents were obtained in 1:2, 1.5:1.5, and 2:1 ratios at 298–333 K and CO2 partial pressures of 8–100 kPa. Using these data, the accurate prediction of CO2 equilibrium solubility of EAE-1DMA2P solvent was achieved by constructing an activity coefficient model with an AARD of only 0.79%. In addition, by constructing the solubility prediction model of EAE-1DMA2P system based on an empirical model, KE model, Austgen model, Li-Shen model, Hu-Chakma model, Helei Liu model, and Liu et al. model the results were compared to confirm introduction of the activity coefficient has effectively improved the accuracy of the model prediction. Based on thermodynamic parameters of solubility, ΔrGm and ΔrHm, EAE-1DMA2P solvent was screened against other solvents. The results showed that EAE-1DMA2P solvent had excellent absorption, reaction rate and low desorption energy consumption, confirming its potential in CO2 capture.

Artificial Intelligence aided pharmaceutical engineering: Development of hybrid machine learning models for prediction of nanomedicine solubility in supercritical solvent

This study aims to model the relationship between pressure (P) and temperature (T) inputs and the corresponding outputs of supercritical carbon dioxide (SC-CO2) density and mole fraction of rivaroxaban as the solute. Three models employed in this work included Support Vector Regression (SVR), Multilayer Perceptron (MLP), and LASSO. The hyper-parameter tuning was performed using Tabu Search approach. The results revealed that MLP is the best model for predicting SC-CO2 density, achieving an R2 score of 0.9994 and demonstrating high accuracy and precision for correlating the density dataset. However, for the mole fraction of rivaroxaban (solubility), SVR outperformed the other models. It revealed an R2 value of 0.98037, confirming a strong correlation between the inputs and outputs. SVR also exhibits a lower mean squared error and maximum error compared to MLP and LASSO for the mole fraction prediction. Although MLP excels in predicting SC-CO2 density, SVR proves to be the superior model for accurately estimating the mole fraction of rivaroxaban based on the given inputs. These findings contribute to the understanding and modeling of SC-CO2 properties, particularly the mole fraction of rivaroxaban, which can be valuable in various research and practical applications.

Solubility of dapsone in deep eutectic solvents: Experimental analysis, molecular insights and machine learning predictions.

Dapsone (DAP) is an anti-inflammatory and antimicrobial active pharmaceutical ingredient used to treat, e.g., AIDS-related diseases. However, low solubility is a feature hampering its efficient use. First, deep eutectic solvents (DES) were used as solubilizing agents for DAP as an alternative to traditional solvents. Second, intermolecular interactions in the systems were described and quantified. Finally, the solubility prediction model, previously created using the machine learning protocol, was extended and improved using new data obtained for eutectic systems. New DES were created by blending choline chloride (ChCl) with 6 selected polyols. The solubility of DAP in these solvents was measured spectrophotometrically. The impact of water dilution on the solubility curve was investigated. Experimental research was enriched with theoretical interpretations of intermolecular interactions, identifying the most probable pairs in the systems. Dapsone self-association and its ability to interact with components of the analyzed systems were considered. Thermodynamic characteristics of pairs were utilized as molecular descriptors in the machine learning process, predicting solubility in both traditional organic solvents and the newly designed DES. The newly formulated solvents demonstrated significantly higher efficiency compared to traditional organic solvents, and a small addition of water increased solubility, indicating its role as a co-solvent. The interpretation of the mechanism of DAP solubility highlighted the competitive nature of self-association and pair formation. Thermodynamic parameters characterizing affinity were instrumental in developing an efficient model for theoretical screening across diverse solvent classes. The study emphasized the necessity of retraining models when introducing new experimental data, as exemplified by enriching the model with data from DES. The research showcased the efficacy of developing new DES for enhancing solubility and creating environmentally and pharmaceutically viable systems, using DAP as an example. Molecular interactions proved valuable in understanding solubility mechanisms and formulating predictive models through machine learning processes.

SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network.

Computational methods play a pivotal role in the pursuit of efficient drug discovery, enabling the rapid assessment of compound properties before costly and time-consuming laboratory experiments. With the advent of technology and large data availability, machine and deep learning methods have proven efficient in predicting molecular solubility. High-precision in silico solubility prediction has revolutionized drug development by enhancing formulation design, guiding lead optimization, and predicting pharmacokinetic parameters. These benefits result in considerable cost and time savings, resulting in a more efficient and shortened drug development process. The proposed SolPredictor is designed with the aim of developing a computational model for solubility prediction. The model is based on residual graph neural network convolution (RGNN). The RGNNs were designed to capture long-range dependencies in graph-structured data. Residual connections enable information to be utilized over various layers, allowing the model to capture and preserve essential features and patterns scattered throughout the network. The two largest datasets available to date are compiled, and the model uses a simplified molecular-input line-entry system (SMILES) representation. SolPredictor uses the ten-fold split cross-validation Pearson correlation coefficient R2 0.79±0.02 and root mean square error (RMSE) 1.03±0.04. The proposed model was evaluated using five independent datasets. Error analysis, hyperparameter optimization analysis, and model explainability were used to determine the molecular features that were most valuable for prediction.

Enhancing Predictions of Drug Solubility through Multidimensional Structural Characterization Exploitation.

Solubility is not only a significant physical property of molecules but also a vital factor in smallmolecule drug development. Determining drug solubility demands stringent equipment, controlled environments, and substantial human and material resources. The accurate prediction of drug solubility using computational methods has long been a goal for researchers. In this study, we introduce MSCSol, a solubility prediction model that integrates multidimensional molecular structure information. We incorporate a graph neural network with geometric vector perceptrons (GVP-GNN) to encode 3D molecular structures, representing spatial arrangement and orientation of atoms, as well as atomic sequences and interactions. We also employ Selective Kernel Convolution combined with Global and Local attention mechanisms to capture molecular features context at different scales. Additionally, various descriptors are calculated to enrich the molecular representation. For the 2D and 3D structural data of molecules, we design different data augmentation strategies to enhance generalization ability and prevent the model from learning irrelevant information. Extensive experiments on benchmark and independent datasets demonstrate MSCSol's superior performance. Ablation studies further confirm the effectiveness of different modules. Interpretability analysis highlights the importance of various atomic groups and substructures for solubility and verifies that our model effectively captures functional molecular structures and higher-order knowledge. The source code and datasets are freely available at https://github.com/ZiyuFanCSU/MSCSol.

Thermodynamic Properties of a Gas–Liquid–Solid System during the CO2 Geological Storage and Utilization Process: A Review

Emission reduction in the main greenhouse gas, CO2, can be achieved efficiently via CO2 geological storage and utilization (CCUS) methods such as the CO2 enhanced oil/water/gas recovery technique, which is considered to be an important strategic technology for the low-carbon development of China’s coal-based energy system. During the CCUS, the thermodynamic properties of the CO2–water–rock system, such as the interfacial tension (IFT) and wettability of the caprock, determine the injectability, sealing capacity, and safety of this scheme. Thus, researchers have been conducting laboratory experiments and modeling work on the interfacial tension between CO2 and the water/brine, wettability of caprocks, the solubility of gas–liquid binary systems, and the pH of CO2-saturated brine under reservoir temperature and pressure conditions. In this study, the literature related to the thermodynamic properties of the CO2–water–rock system is reviewed, and the main findings of previous studies are listed and discussed thoroughly. It is concluded that limited research is available on the pH of gas-saturated aqueous solutions under CO2 saline aquifer storage conditions, and less emphasis has been given to the wettability of the CO2–water/brine–rock system. Thus, further laboratory and modeling research on the wettability alternations of caprock in terms of molecular dynamics is required to simulate this phenomenon at the molecular level. Moreover, simplified IFT and solubility prediction models with thermodynamic significance and high integrity need to be developed. Furthermore, interaction mechanisms coupling with multi-factors associated with the gas–liquid–solid interface properties and the dissolution and acidification process need to be explored in future work.

Creation and interpretation of machine learning models for aqueous solubility prediction

Aim: Solubility prediction is an essential factor in rational drug design and many models have been developed with machine learning (ML) methods to enhance the predictive ability. However, most of the ML models are hard to interpret which limits the insights they can give in the lead optimization process. Here, an approach to construct and interpret solubility models with a combination of physicochemical properties and ML algorithms is presented. Methods: The models were trained, optimized, and tested in a dataset containing 12,983 compounds from two public datasets and further evaluated in two external test sets. More importantly, the SHapley Additive exPlanations (SHAP) and heat map coloring approaches were used to explain the predictive models and assess their suitability to guide compound optimization. Results: Among the different ML methods, random forest (RF) models obtain the best performance in the different test sets. From the interpretability perspective, fragment-based coloring offers a more robust interpretation than atom-based coloring and that normalizing the values further improves it. Conclusions: Overall, for certain applications simple ML algorithms such as RF work well and can outperform more complex methods and that combining them with fragment-coloring can offer guidance for chemists to modify the structure with a desired property. This interpretation strategy is publicly available at https://github.com/Pharmacelera/predictive-model-coloring and could be further applied in other property predictions to improve the interpretability of ML models.

Development of computational intelligence models for assessment of drug nanonization using green chemistry technique: Improvement of drug solubility

Determination of solubility via theoretical approaches was carried out in this study. Because of its importance to the expansion of the pharmaceutical industry, this study models Lenalidomide solubility in supercritical carbon dioxide using multiple tree-based techniques which are of machine learning nature. These parameters are molded based on temperature and pressure input features due to the significant variability of drug solubility with the temperature and pressure. The experimental data have been collected and inputted the models to train them and used the data for testing the machine learning models. The results are useful for production of nanomedicine with enhanced solubility in solvents. Decision Tree (DT), Extra Trees (ET), and Gradient Boosting (GB) models are used and optimized using SCA algorithm to obtain more robust models for prediction of the drug solubility in the solvent. So, the developed models are called SCA-DT, SCA-ET, and SCA-GB in this study and have R2-scores of 0.932, 0.951, and 0.997, respectively. The SCA-DT model has an RMSE error rate of 0.0948, this rate is 0.0822 for SCA-ET, and 0.0203 for SCA-GB. So, the SCA-GB is introduced as the best model of this research for prediction of Lenalidomide solubility in the solvent.

An advanced computational method for studying drug nanonization using green supercritical-based processing for improvement of pharmaceutical bioavailability in aqueous media

In this study, we implemented and compared various non-mechanistic based models for prediction of drug solubility in supercritical solvent. The data were collected from references and the models were built considering various operational circumstances. Small data sets, like the solubility data used in this study, have always been one of the challenges for modeling in machine learning method. In this study, in order to solve the regression problem related to the solubility of drugs, which includes 32 laboratory data, we implemented and studied models that are naturally compatible with very small data like solubility data of drugs in solvents. These models included Random Forest (RF), KNN and Extra Tree (ET). After obtaining the best settings for each model, their final results were compared in terms of accuracy for predicting drug solubility. The ET model had the best result with a score of 0.9999 on the R2 criterion. Random forests with 0.978 and KNN with 0.972 also had acceptable regression results. Finally, the trained model was used to display and evaluate the effect of input parameters like pressure and temperature on drug solubility to understand the process.

Integrated a Fused Silica Capillary Cell and In Situ Raman Spectroscopy for Determining the Solubility of CO2 in n-Decane and n-Decane + n-Hexane System

Understanding the solubility of CO2 is critical for implementing CO2-enhanced oil recovery (CO2-EOR). In this work, the solubility of CO2 in n-decane in a temperature range between 303.15 K and 353.15 K and pressures up to 15 MPa was measured using a fused silica capillary cell with in situ Raman spectroscopy. A semi-empirical CO2 solubility prediction model was obtained according to the experimental results. In order to improve the solubility of CO2 in n-decane, the solubility of CO2 in n-decane and co-solvent n-hexane (3% wt) mixture was also comparatively investigated. The results indicated that the solubility of CO2 in n-decane was 1.6355~64.0084 mol/kg. The data from the prediction model were in good agreement with the experimental data, and the mean relative deviation was 3.65%, indicating that the prediction model could be used to predict the solubility of CO2 in n-decane under different conditions. The solubility of CO2 in n-decane + n-hexane system ranged from 1.0127 mol/kg to 65.7286 mol/kg. It was found that, under low-pressure conditions, the addition of co-solvent n-hexane did not enhance the solubility of CO2, while it had a certain enhancement effect on the dissolution of CO2 under high-pressure conditions. As the temperature increased from 303.15 K to 353.15 K, the enhancement efficiency of the solubility of CO2 also increased from 1.34~2.05% to 8.17~9.82%, and the average enhancement efficiency increased from 1.74% to 9.00%. This study provides more CO2 solubility data for CO2-EOR.

A Study on Elemental Sulfur Equilibrium Content in Mixtures of Methane, Carbon Dioxide, and Hydrogen Sulfide under Conditions of Natural Gas Pipeline Transmission

The effect of gathering pipeline pressure, temperature, and key components on the solubility of monomeric sulfur in high-sulfur-content natural gas is directly related to the prediction and prevention of sulfur deposition in surface gathering pipelines. Based on our previous study on a prediction model of sulfur solubility in gas with a new formula for the binary interaction coefficient between sulfur and H2S, a new gas–solid thermodynamic phase equilibrium solubility prediction model for monomeric sulfur in high-sulfur-content natural gas was improved based on the gas–solid phase equilibrium principle considering both physical and chemical solution mechanisms. Two new expressions for binary interaction coefficients between sulfur and CO2 and CH4, considering both temperature and solvent density, are proposed in this new solubility prediction model. In this paper, the main factors, such as the gathering pipeline pressure, gathering pipeline temperature, H2S, and CO2, affecting the solubility law of elemental sulfur in high-sulfur-content natural gas are investigated. The results show that the total solubility of elemental sulfur in high-sulfur-bearing natural gas tends to decrease with an increase in the gathering temperature, in which the increase in temperature promotes physical solution, and the physical solution mechanism prevails. Conversely, chemical solution is promoted, and the chemical solution mechanism prevails. With an increase in the gathering pressure, the total solubility of elemental sulfur in high-sulfur-content gas tends to increase, where the physical solubility decreases slightly at first and then increases continuously, with a pressure inflection point of about 2.0 MPa, and the pressure increase has a significant promoting effect on the chemical solubility of elemental sulfur. The increase in the H2S concentration promotes the solution of elemental sulfur in the gas phase in general and significantly promotes the chemical solution of elemental sulfur. The effect on elemental sulfur solubility can be neglected when the molar concentration of CO2 in the gas phase does not exceed 10%.

Prediction of protein solubility based on sequence physicochemical patterns and distributed representation information with DeepSoluE

BackgroundProtein solubility is a precondition for efficient heterologous protein expression at the basis of most industrial applications and for functional interpretation in basic research. However, recurrent formation of inclusion bodies is still an inevitable roadblock in protein science and industry, where only nearly a quarter of proteins can be successfully expressed in soluble form. Despite numerous solubility prediction models having been developed over time, their performance remains unsatisfactory in the context of the current strong increase in available protein sequences. Hence, it is imperative to develop novel and highly accurate predictors that enable the prioritization of highly soluble proteins to reduce the cost of actual experimental work.ResultsIn this study, we developed a novel tool, DeepSoluE, which predicts protein solubility using a long-short-term memory (LSTM) network with hybrid features composed of physicochemical patterns and distributed representation of amino acids. Comparison results showed that the proposed model achieved more accurate and balanced performance than existing tools. Furthermore, we explored specific features that have a dominant impact on the model performance as well as their interaction effects.ConclusionsDeepSoluE is suitable for the prediction of protein solubility in E. coli; it serves as a bioinformatics tool for prescreening of potentially soluble targets to reduce the cost of wet-experimental studies. The publicly available webserver is freely accessible at http://lab.malab.cn/~wangchao/softs/DeepSoluE/.