CN110970098A - Functional polypeptide bitter taste prediction method - Google Patents
Functional polypeptide bitter taste prediction method Download PDFInfo
- Publication number
- CN110970098A CN110970098A CN201911174720.9A CN201911174720A CN110970098A CN 110970098 A CN110970098 A CN 110970098A CN 201911174720 A CN201911174720 A CN 201911174720A CN 110970098 A CN110970098 A CN 110970098A
- Authority
- CN
- China
- Prior art keywords
- bitter taste
- functional polypeptide
- polypeptide
- model
- functional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 108090000765 processed proteins & peptides Proteins 0.000 title claims abstract description 55
- 102000004196 processed proteins & peptides Human genes 0.000 title claims abstract description 53
- 229920001184 polypeptide Polymers 0.000 title claims abstract description 52
- 235000019658 bitter taste Nutrition 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000013210 evaluation model Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims abstract description 6
- 230000003993 interaction Effects 0.000 claims abstract description 5
- 230000007613 environmental effect Effects 0.000 claims abstract description 4
- 229920000858 Cyclodextrin Polymers 0.000 claims description 7
- HFHDHCJBZVLPGP-UHFFFAOYSA-N schardinger α-dextrin Chemical compound O1C(C(C2O)O)C(CO)OC2OC(C(C2O)O)C(CO)OC2OC(C(C2O)O)C(CO)OC2OC(C(O)C2O)C(CO)OC2OC(C(C2O)O)C(CO)OC2OC2C(O)C(O)C1OC2CO HFHDHCJBZVLPGP-UHFFFAOYSA-N 0.000 claims description 7
- 150000001413 amino acids Chemical class 0.000 claims description 3
- -1 aromatic amino acid Chemical class 0.000 claims description 3
- 230000002209 hydrophobic effect Effects 0.000 claims description 3
- 239000002904 solvent Substances 0.000 claims description 3
- 235000019640 taste Nutrition 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 102000015636 Oligopeptides Human genes 0.000 description 2
- 108010038807 Oligopeptides Proteins 0.000 description 2
- 238000004617 QSAR study Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 235000019596 Masking bitterness Nutrition 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting bitterness of functional polypeptide, which comprises the following steps: local and overall combination strategies are adopted to represent sequence-structure-kinetic characteristics related to functional polypeptides and bitter taste, the sequence-structure-kinetic characteristics comprise two-dimensional information, three-dimensional structure information, kinetic characteristics and environmental parameters, 20 parameters are used as input variables of a model, a long-time memory neural network is used for establishing a functional polypeptide bitter taste prediction model, the internal prediction capability of the evaluation model is checked in a five-fold interaction mode, and the external prediction capability of the evaluation model is checked in a test set. The method can be used for predicting the bitter taste of the functional polypeptide, analyzing the structure-bitter taste relation of the functional polypeptide and assisting in optimizing and selecting proper experimental conditions and parameters for covering or eliminating the bitter taste of the functional polypeptide.
Description
Technical Field
The invention relates to a method for predicting physicochemical properties of functional polypeptides, in particular to a method for predicting bitterness of functional polypeptides.
Background
However, many functional polypeptides have bitter taste, which greatly limits the wide application of the functional polypeptides, so that timely or accurate detection of the bitter taste of the polypeptides has important practical significance for expanding the application of the functional polypeptides, but because the number of the functional polypeptides is large, the detection of the bitter taste one by using an experimental method is time-consuming, labor-consuming and expensive. With the rapid development and fusion of the artificial intelligence technology and the mathematics and other subjects, the method for predicting the bitter taste of the functional polypeptide by adopting the artificial intelligence technology is an effective method. The quantitative structure-activity relationship model provides an important tool for predicting the bitterness of the peptide, and the quantitative relation is established among the sequence, the structure and the bitterness of the peptide, so that the quantitative change rule between the structural characteristics and the bitterness is found, the bitterness is predicted, and the quantitative structure-activity relationship model has very important significance for selecting and optimizing experimental conditions and quickly knowing the bitterness characteristics of functional peptides. The invention discloses a functional polypeptide bitter taste prediction method based on a quantitative sequence-structure-dynamics-bitter taste relation model.
Disclosure of Invention
In view of the above, in order to solve the above problems, the present invention provides a method for predicting bitterness of a functional polypeptide, which can be used for predicting bitterness of a functional polypeptide, analyzing a structure-bitterness relationship of a functional polypeptide, and evaluating a bitterness masking effect of cyclodextrin on a functional polypeptide.
The purpose of the invention is realized as follows: a bitter taste prediction method of functional polypeptide comprises the following steps:
a) local and overall combination strategies are adopted to characterize sequence-structure-kinetic characteristics of functional polypeptides related to bitter taste, including a1) two-dimensional information including sequence length, aromatic amino acid proportion, hydrophobic amino acid proportion, isoelectric point, polarizability and hydrophobicity of the polypeptides; a2) three-dimensional structural information including spatial features, geometric features, local flexibility; a3) the dynamic characteristics comprise polypeptide main chain torsion angle, polypeptide disorder degree, accessible surface area, solvent free energy, side chain volume and side chain gyration radius; a4) environmental parameters including pH, temperature, polypeptide concentration, cyclodextrin concentration and cyclodextrin type of the reaction system, wherein the 20 parameters are used as input variables of the model;
b) establishing a functional polypeptide bitter taste prediction model by using a long-time memory neural network, testing the internal prediction capability of the evaluation model by five-fold interaction, testing the external prediction capability of the evaluation model by a test set, bringing the input variable of each functional polypeptide sample into the model, and calculating the bitter taste value of the functional polypeptide.
The invention discloses a bitter prediction method of functional polypeptide, which is provided based on a novel quantitative sequence-structure-dynamics-bitter relation model. The selected local and integral combination strategies represent sequence-structure-kinetic characteristics of functional polypeptides, and the selected local and integral combination strategies have the advantages of large information content, strong representation capability, good expansion performance and simple and convenient operation; the long-time memory neural network can well correlate the relationship between the structure variable and the bitter value of the bitter oligopeptide, overfitting of the model can be effectively prevented, meanwhile, the prediction capability of the established model can be greatly guaranteed by the adoption of the five-fold interaction inspection and external inspection verification method, and the established method has good generalization performance.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof.
Detailed Description
The following is a detailed description of an example of bitterness prediction for functional polypeptides using the method of the invention, comprising the steps of:
a) local and overall combination strategies are adopted to characterize sequence-structure-kinetic characteristics of functional polypeptides related to bitter taste, including a1) two-dimensional information including sequence length, aromatic amino acid proportion, hydrophobic amino acid proportion, isoelectric point, polarizability and hydrophobicity of the polypeptides; a2) three-dimensional structural information including spatial features, geometric features, local flexibility; a3) the dynamic characteristics comprise polypeptide main chain torsion angle, polypeptide disorder degree, accessible surface area, solvent free energy, side chain volume and side chain gyration radius; a4) environmental parameters including pH, temperature, polypeptide concentration, cyclodextrin concentration, and cyclodextrin type of the reaction system, and the above 20 parameters were used as input variables of the model.
b) Establishing a functional polypeptide bitter taste prediction model by using a long-time memory neural network, testing the internal prediction capability of the evaluation model by five-fold interaction, testing the external prediction capability of the evaluation model by a test set, bringing the input variable of each functional polypeptide sample into the model, and calculating the bitter taste value of the functional polypeptide.
Dividing 60 experimentally determined functional polypeptide samples into a training set and a testing set according to a ratio of 2:1, taking 20 variables as input, taking experimentally determined bitterness values as output values, and establishing a bitterness prediction model of the functional polypeptide by using a long-time memory neural network. And then, the internal prediction capability of the verification model is interactively checked by a five-fold method, and the external prediction capability of the model is evaluated by using an external prediction result of the test set.
Model prediction capability is evaluated by the statistical quantity of the fitted complex correlation coefficient (R)2) Complex correlation coefficient (Q) of five-fold cross validation2 cv) Externally verified complex correlation coefficient (Q)2 ext) And an error (MSE).
The prediction results are shown in Table 1, and it can be seen that the correlation coefficients of the fitting, the five-fold cross test and the external test are R respectively2＝0.973，Q2 cv＝0.921，Q2 ext0.886, the errors (MSEs) are 0.18, 0.26 and 0.33, respectively. The result shows that the established method has stronger bitter prediction capability.
TABLE 1 bitter taste prediction of bitter oligopeptides
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and it is apparent that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (1)
1. A method for predicting bitterness of a functional polypeptide, which is characterized by comprising the following steps:
a) local and overall combination strategies are adopted to characterize sequence-structure-kinetic characteristics of functional polypeptides related to bitter taste, including a1) two-dimensional information including sequence length, aromatic amino acid proportion, hydrophobic amino acid proportion, isoelectric point, polarizability and hydrophobicity of the polypeptides; a2) three-dimensional structural information including spatial features, geometric features, local flexibility; a3) the dynamic characteristics comprise polypeptide main chain torsion angle, polypeptide disorder degree, accessible surface area, solvent free energy, side chain volume and side chain gyration radius; a4) environmental parameters including pH, temperature, polypeptide concentration, cyclodextrin concentration and cyclodextrin type of the reaction system, wherein the 20 parameters are used as input variables of the model;
b) establishing a functional polypeptide bitter taste prediction model by using a long-time memory neural network, testing the internal prediction capability of the evaluation model by five-fold interaction, testing the external prediction capability of the evaluation model by a test set, bringing the input variable of each functional polypeptide sample into the model, and calculating the bitter taste value of the functional polypeptide.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911174720.9A CN110970098A (en) | 2019-11-26 | 2019-11-26 | Functional polypeptide bitter taste prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911174720.9A CN110970098A (en) | 2019-11-26 | 2019-11-26 | Functional polypeptide bitter taste prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110970098A true CN110970098A (en) | 2020-04-07 |
Family
ID=70031727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911174720.9A Pending CN110970098A (en) | 2019-11-26 | 2019-11-26 | Functional polypeptide bitter taste prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110970098A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050084907A1 (en) * | 2002-03-01 | 2005-04-21 | Maxygen, Inc. | Methods, systems, and software for identifying functional biomolecules |
| CN108491680A (en) * | 2018-03-07 | 2018-09-04 | 安庆师范大学 | Drug relationship abstracting method based on residual error network and attention mechanism |
| CN109033738A (en) * | 2018-07-09 | 2018-12-18 | 湖南大学 | A kind of pharmaceutical activity prediction technique based on deep learning |
| CN109671469A (en) * | 2018-12-11 | 2019-04-23 | 浙江大学 | The method for predicting marriage relation and binding affinity between polypeptide and HLA I type molecule based on Recognition with Recurrent Neural Network |
| US20190304568A1 (en) * | 2018-03-30 | 2019-10-03 | Board Of Trustees Of Michigan State University | System and methods for machine learning for drug design and discovery |
| CN110308254A (en) * | 2019-04-22 | 2019-10-08 | 江南大学 | The accurate monitoring method of low dissolved oxygen |
| CN110413319A (en) * | 2019-08-01 | 2019-11-05 | 北京理工大学 | A kind of code function taste detection method based on deep semantic |
-
2019
- 2019-11-26 CN CN201911174720.9A patent/CN110970098A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050084907A1 (en) * | 2002-03-01 | 2005-04-21 | Maxygen, Inc. | Methods, systems, and software for identifying functional biomolecules |
| CN108491680A (en) * | 2018-03-07 | 2018-09-04 | 安庆师范大学 | Drug relationship abstracting method based on residual error network and attention mechanism |
| US20190304568A1 (en) * | 2018-03-30 | 2019-10-03 | Board Of Trustees Of Michigan State University | System and methods for machine learning for drug design and discovery |
| CN109033738A (en) * | 2018-07-09 | 2018-12-18 | 湖南大学 | A kind of pharmaceutical activity prediction technique based on deep learning |
| CN109671469A (en) * | 2018-12-11 | 2019-04-23 | 浙江大学 | The method for predicting marriage relation and binding affinity between polypeptide and HLA I type molecule based on Recognition with Recurrent Neural Network |
| CN110308254A (en) * | 2019-04-22 | 2019-10-08 | 江南大学 | The accurate monitoring method of low dissolved oxygen |
| CN110413319A (en) * | 2019-08-01 | 2019-11-05 | 北京理工大学 | A kind of code function taste detection method based on deep semantic |
Non-Patent Citations (6)
| Title |
|---|
| HYUN OCK KIM ET AL.: ""Quantitative Structure-Activity Relationship Study of Bitter Peptides"", 《J. AGRIC. FOOD CHEM.》, pages 10102 - 10111 * |
| 云永欢;邓百川;梁逸曾;: "化学建模与模型集群分析", 分析化学, no. 11, pages 37 - 46 * |
| 仝建波;李康楠;吴英纪;占培;李玲霄;: "一种新的氨基酸描述符及其在肽QSAR中的应用", 分析测试学报, no. 02, pages 87 - 92 * |
| 秦琦枫等: ""深度神经网络在化学中的应用研究"", 《江西化工》, pages 1 - 5 * |
| 郭延哺;李维华;王兵益;金宸;: "基于卷积长短时记忆神经网络的蛋白质二级结构预测", 模式识别与人工智能, no. 06, pages 80 - 86 * |
| 马铁铮等: ""蛋白短肽苦味成因与脱苦技术研究进展"", 《中国粮油学报》, pages 220 - 226 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230207068A1 (en) | Methods of Profiling Mass Spectral Data Using Neural Networks | |
| Vlasov et al. | Nonspecific sensor arrays (" electronic tongue") for chemical analysis of liquids (IUPAC Technical Report) | |
| Ciosek et al. | The analysis of sensor array data with various pattern recognition techniques | |
| Daikuzono et al. | Information visualization and feature selection methods applied to detect gliadin in gluten-containing foodstuff with a microfluidic electronic tongue | |
| Gustafson et al. | Optimizing information content in MOF sensor arrays for analyzing methane-air mixtures | |
| CN110018294B (en) | Soil heavy metal detection value correction method and device and computer storage medium | |
| Kalinichenko et al. | Electronic nose combined with chemometric approaches to assess authenticity and adulteration of sausages by soy protein | |
| CN114445407B (en) | Method and device for detecting wear resistance of material | |
| CN112418212A (en) | Improved YOLOv3 algorithm based on EIoU | |
| CN106779217A (en) | Detection of Air Quality method and air quality detection system | |
| KR20210116278A (en) | Gas sensing device and method for operating a gas sensing device | |
| CN114936528A (en) | Extreme learning machine semi-supervised soft measurement modeling method based on variable weighting self-adaptive local composition | |
| CN115809427A (en) | Mixed gas identification method based on mixed strategy optimization BP neural network | |
| CN110970098A (en) | Functional polypeptide bitter taste prediction method | |
| CN115496724A (en) | Line width detection method and device and storage medium | |
| CN115641316A (en) | Weak supervision change detection method and device based on background mixed data expansion technology | |
| Marengo et al. | Investigation of the applicability of Zernike moments to the classification of SDS 2D-PAGE maps | |
| Natale et al. | Data analysis for chemical sensor arrays | |
| Vidaurre et al. | A quick assessment of topology preservation for SOM structures | |
| CN114022724A (en) | Pipeline disease image data enhancement method for generating countermeasure network based on style migration | |
| CN110879530A (en) | Method for the secure training of dynamic models | |
| Ling et al. | Usage Space Sampling for Fringe Customer Identification. | |
| Da Wang et al. | In situ characterization of heterogeneous surface wetting in porous materials | |
| Xie et al. | Gas quantitative analysis with support vector machine | |
| CN110310706A (en) | A kind of protein is without mark absolute quantification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |