16 results about "Toxicity data" patented technology

The invention relates to the technical field of environment informatization, in particular to a new pollutant environment fate simulation and risk assessment system, which comprises a data prediction module used for receiving molecular structures of target new pollutants, space-time emission source item data and basin environment medium parameters, and complementing missing physicochemical property parameters by using a model; the effect analysis module is used for acquiring new pollutant toxicity data and deducing and predicting non-effect concentration and sensitive point risk weight in combination with a mixed toxicity model; the sample generation module is used for simulating various discrete emission scenes based on a mechanism driving model and generating a space-time environment concentration response data set; and the agent model module is used for training a machine learning agent model according to the emission scene and the space-time environment concentration response data set. According to the method, the input and output relation of a deep neural network learning mechanism driving model is utilized through the agent model module, and the problem that a traditional mechanism model cannot support rapid iterative optimization of mass emission scenes due to slow operation is solved.

The invention relates to the technical field of toxicity detection, and discloses a micro-plastic toxicity prediction method integrating machine learning and meta analysis. The method comprises the following steps: performing multi-dimensional detection on a micro-plastic sample to obtain physicochemical characteristic parameters; carrying out meta analysis on the physicochemical characteristic parameters and the toxicity data to obtain quality correction toxicity data; judging whether the toxicity correlation meets constraint conditions or not, and if yes, performing collaborative learning to obtain a prediction algorithm; inputting characteristic parameters to carry out prediction calculation, and outputting a toxicity prediction value after determining uncertainty; and carrying out risk calculation and mechanism analysis, judging a risk level and generating an evaluation result. According to the invention, the accuracy of micro-plastic toxicity prediction is improved.

The application discloses a soil cadmium environmental ecological toxicity data screening processing method and application, and comprises the following steps: S1, obtaining ecological toxicity data, S2, screening data, S3, processing data, the screening processing method can obtain high-quality data, and the data is processed to a uniform level, which is more convenient for analysis and calculation; through the simulation of the species sensitivity distribution model by using the screened data, fitting parameters can be obtained, and the sensitivity distribution of ecological species to pollutants can be mastered to a large extent according to limited ecological toxicity data.

The invention relates to a method and a device for acquiring key components of a mixture, a storage medium and electronic equipment, and the method comprises the following steps: acquiring each component in a multi-component mixture system of a target area, and determining factor level numbers of factors corresponding to the components; constructing a track starting point based on the factor level number, and determining that the currently constructed track starting point is not repeated based on the constructed track starting point group; determining a preferred trajectory starting point group for the uniformity deviation of each constructed trajectory starting point group; for each preferable trajectory starting point in the preferable trajectory starting point group, performing conversion according to the factor sequence corresponding to the preferable trajectory starting point, and obtaining a mixture sample for the factor level of one factor in each conversion; and performing a mixture toxicity test based on the mixture sample to obtain mixture toxicity data, and performing global sensitivity analysis on the mixture toxicity data to determine the key component based on a global sensitivity analysis result. And the reliability of a mixture toxicity evaluation result can be improved.

This invention relates to a method, apparatus, storage medium, and electronic device for obtaining key components of a mixture. The method includes: obtaining each component in a multi-component mixture system in a target region; determining the number of factor levels corresponding to each component; constructing trajectory starting points based on the number of factor levels; determining that the currently constructed trajectory starting points are not repeated based on a previously constructed set of trajectory starting points; determining a preferred set of trajectory starting points based on the uniformity deviation of each constructed set of trajectory starting points; for each preferred trajectory starting point in the preferred set of trajectory starting points, performing a transformation according to the factor order corresponding to that preferred trajectory starting point, with each transformation targeting the factor level of one factor, to obtain a mixture sample; conducting a mixture toxicity test based on the mixture sample to obtain mixture toxicity data; performing a global sensitivity analysis on the mixture toxicity data; and determining key components based on the results of the global sensitivity analysis. This can improve the reliability of mixture toxicity assessment results.

The invention discloses a detection method for recessive toxicity multi-modal data and terminal equipment, belongs to the technical field of toxicity data detection, and can solve the problems that an existing model cannot effectively detect recessive toxicity content and is difficult to provide clear explanation and quantify the hiding degree of the recessive toxicity content. The method comprises the following steps: S1, acquiring a plurality of visual nodes from an input image of an input image-text pair, and constructing a visual association tree of the input image; s2, acquiring a plurality of text nodes from an input text of the input image-text pair, and constructing a text association tree of the input text; s3, constructing a cross-modal bipartite graph of the input image-text pair according to the visual association tree and the text association tree; and S4, matching each node pair in the cross-modal bipartite graph with all concept pairs in the toxic concept pair set, and determining a toxic label of the input image-text pair according to a matching result. The method is used for detecting the multi-modal data of the recessive toxicity.

The present application relates to the field of environmental science and computational toxicology, and specifically provides a method for constructing species sensitivity distribution and performing soil ecological risk probability assessment based on multi-species quantitative structure-activity relationship model, which constructs QSAR model for each receptor and combines Monte Carlo simulation technology, models three key uncertainty sources of model application domain confidence, model reliability factor and ecological weight as Beta distribution, Logit- Normal distribution and truncated normal distribution respectively, randomly samples and calculates comprehensive weight in each iteration, constructs SSD curve based on weighted toxicity data, and then obtains probability distribution of hazard concentration, and finally, outputs risk probability distribution of pollutants according to comparison between pollutant concentration and HC5 distribution in the environment, which quantitatively the uncertainty of QSAR model and ecological parameters, realizes the transformation from point estimation to probability distribution, and provides a scientific basis with statistical significance for soil ecological risk classification management and remediation decision.

This patent relates to an acute intraperitoneal toxicity prediction method based on MACCS bonds and a machine learning framework. This method collects and processes toxicity data of chemical compounds, calculates molecular descriptors using MACCS bonds, and constructs a gradient boosting decision tree model for toxicity prediction through feature selection and removal of highly correlated features. The model's hyperparameters are optimized using a grid search method, and the interpretability of the model is improved using SHAP value analysis. This achieves high-precision and highly interpretable toxicity prediction. The method achieves a coefficient of determination of 0.914, a mean squared error of 0.047, a root mean square error of 0.218, and a mean absolute error of 0.148 on the test set. This invention significantly improves the accuracy of toxicity prediction and has strong generalization ability, making it widely applicable to toxicity screening in new drug development, reducing reliance on traditional animal experiments, and lowering R&D costs and time.

The invention relates to a compound toxicity comprehensive evaluation method and system based on entropy weight method coupling multi-dimensional data. The invention provides an objective, quantitative and comprehensive toxicity assessment method, which comprises the following steps of: objectively weighting multi-dimensional toxicity data from different software and different end points by introducing an information entropy theory and constructing a mathematical model, and finally integrating the multi-dimensional toxicity data into a single and quantificationally comparable'comprehensive toxicity index '. Therefore, reliable assessment of AOPs degradation paths and intermediate product risks is realized.

The invention relates to the field of environmental science, and provides a sensitive species screening method and system for soil Cd environmental quality benchmark derivation. The method comprises the following steps: establishing a multi-dimensional evaluation index system, carrying out weighted scoring processing on candidate species, and screening to obtain a preliminary acceptor species directory; for species in the preliminary receptor species directory, acquiring soil Cd toxicity data, and performing soil property normalization processing on the soil Cd toxicity data to obtain a standardized toxicity data set; inputting the standardized toxicity data set into a species sensitivity distribution model for fitting calculation, and generating a species sensitivity distribution curve; according to the species sensitivity distribution curve, sorting the species according to the sensitivity, selecting sensitive species from a sorting result, and forming a sensitive ecological receptor directory. According to the method, scientificity, accuracy and regional applicability of soil Cd environment reference derivation are improved.

The invention discloses a water environment pollutant ecological risk sorting system and method in the technical field of water environment pollutant monitoring, and the system comprises a water environment pollutant exposure module which is used for obtaining the pollutant exposure data of each pollutant in the water environment of a monitoring region; the water environment pollutant ecological effect module is used for acquiring water ecological toxicity effect data of corresponding pollutants; the data analysis module is used for obtaining an exposure characteristic value and obtaining an effect characteristic value; and the risk sorting module is used for obtaining risk values of the corresponding pollutants according to the exposure characteristic values and the effect characteristic values, and carrying out risk sorting display on the pollutants. According to the invention, the pollutant exposure data and the water ecological toxicity effect data of the corresponding pollutants are obtained and then are processed through the data analysis module and the risk sorting module, so that the monitoring data and the toxicity data are effectively combined to improve the accuracy of the risk sorting result, and an environment manager can conveniently carry out rapid identification and targeted management and control on various pollutants.

The application relates to the technical field of toxicity detection, and discloses a microplastic toxicity prediction method combining machine learning and meta-analysis. The method comprises the following steps: performing multidimensional detection on a microplastic sample to obtain physicochemical characteristic parameters; performing meta-analysis on the physicochemical characteristic parameters and toxicity data to obtain quality-corrected toxicity data; judging whether the toxicity correlation meets a constraint condition, and if yes, performing collaborative learning to obtain a prediction algorithm; inputting the characteristic parameters to perform prediction calculation, outputting a toxicity prediction value after judging uncertainty; performing risk calculation and mechanism analysis, judging a risk grade, and generating an evaluation result. The application improves the accuracy of microplastic toxicity prediction.

The invention provides a method and device for evaluating the influence of new pollutants on health based on individualized early warning. The method comprises the following steps: collecting pollutant toxicity data; analyzing the reference value of the pollutant, and deducing to obtain a safety threshold value; for the pollutants without the threshold value, calculating a preset quantile of the internal exposure level of the target population pollutants and a corresponding confidence interval to obtain an internal exposure reference value; for the pollutants with the threshold value, deriving a reference value by adopting a reference dose method, and determining an internal exposure threshold value of the early effect marker change caused by the pollutants by setting a reference response value and calculating a reference dose under the corresponding reference response value and an upper limit and a lower limit of a corresponding confidence interval; determining a safety threshold value corresponding to the pollutant, and constructing a corresponding relationship between the personal characteristics of the user and the safety threshold value corresponding to the pollutant; a customized safety threshold is provided, real-time monitoring is carried out, and when it is obtained that the individual exposure concentration input by the user exceeds the safety threshold, warning information and health influence suggestions are sent to the user.

The invention discloses a phage receptor binding protein host prediction method based on cross-modal multi-source transfer learning, which is characterized in that the host prediction precision is enhanced by utilizing chemical toxicity data, and the challenge of scarcity of phage sequence data is overcome. First, a shared bidirectional long short-term memory network encoder is used to process features from chemical and biological modalities, and structure and sequence information is captured. Next, domain adaptation is performed through a maximum mean difference loss function, effectively aligning chemical and biological feature representations. According to the method, knowledge migration of cross-modal data is realized, the accuracy of host prediction is remarkably improved, and particularly, the precision is improved by about 30% compared with that of a traditional model in the early stage of training. Experimental results show that the method provided by the invention can realize rapid convergence and is excellent in performance when being used for processing the problem of data scarcity, a novel efficient method is provided for host prediction in the field of biological medicines, especially in phage therapy, and the method has a wide application prospect.

The invention discloses a small molecule drug metabolism and toxicity prediction method based on quantum chemistry, and belongs to the field of drug research and development. The method comprises the following steps: constructing a data set containing molecular structure, metabolism and toxicity data of the small-molecular drug; optimizing a molecular structure based on quantum chemistry, and calculating parameters such as front track energy and charge distribution; constructing a metabolic pathway prediction model through Monte Carlo simulation in combination with the parameters and a biotransformation rule, and outputting potential metabolites and pathway probabilities; integrating quantum chemical parameters, molecular fingerprints and physicochemical properties, training a toxicity prediction sub-model by using a gradient boosting tree algorithm, and outputting a toxicity probability value and type; and integrating results to generate a correlation prediction report, and verifying the model through an external test set. The method improves the prediction precision, reduces the experiment cost, shortens the research and development period, and provides a tool for the safety evaluation of candidate drugs.

This invention relates to a machine learning-based method and system for predicting interspecific toxicity. The method acquires toxicity data of the same chemical to both alternative and predicted species, calculates its molecular descriptors, and preprocesses them to select descriptors suitable for modeling. Combining the toxicity data of the alternative species with the selected descriptors as independent variables and the toxicity data of the predicted species as the dependent variable, a machine learning algorithm is used to construct an interspecific toxicity relationship prediction model. The model's performance is then evaluated and validated through cross-validation. For a chemical to be predicted, only its toxicity data to an alternative species and related molecular descriptors need to be acquired. The validated final interspecific relationship prediction model is then used to predict the toxicity of the chemical to the predicted species. Compared to existing technologies, this invention utilizes a reliable model to efficiently and accurately predict the potential toxicity of a chemical to a target predicted species, effectively reducing the cost and time of traditional cross-species toxicity testing.