Unlock instant, AI-driven research and patent intelligence for your innovation.

Prediction method of amniotic fluid protein based on recurrent neural network

A technology of cyclic neural network and prediction method, which is applied in the field of artificial intelligence and big data, to achieve the effect of improving accuracy

Inactive Publication Date: 2021-04-16
JILIN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But at present, there is still a gap in the known computational methods for predicting amniotic fluid protein

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Prediction method of amniotic fluid protein based on recurrent neural network
  • Prediction method of amniotic fluid protein based on recurrent neural network
  • Prediction method of amniotic fluid protein based on recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The prediction method of the amniotic fluid protein based on the recurrent neural network comprises the following steps:

[0052] 1. The establishment of the data set

[0053] (1) Positive sample data set collection

[0054]The protein information in amniotic fluid that has been verified by biological experiments is obtained by searching biologically relevant literature and existing databases as positive samples for model training and entered into the computer.

[0055] (2) Negative sample data set collection

[0056] Delete the protein family information corresponding to the positive sample in step 1 in the Pfam protein family information database, search for protein families with more than 5 proteins in the family in the remaining protein family information database, and randomly select 5 protein information from these protein families Enter the computer as negative samples for model training.

[0057] (3) Model training data set segmentation

[0058] The sample d...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method for predicting amniotic fluid proteins based on a circulating neural network belongs to the technical field of big data and artificial intelligence. In the present invention, the list of proteins in the amniotic fluid of existing literature and databases that have been verified by biological experiments is used as a positive sample for model training; the protein family information corresponding to the positive sample is deleted in the Pfam protein family information database, and the remaining protein family information database Find protein families with more than 5 proteins in the family, and randomly select 5 protein information from these protein families as negative samples for model training. Divide the positive and negative sample data into training set, validation set and test set. Perform feature selection on protein features, build a model, train the model with the training set, adjust the parameters on the validation set, and evaluate the performance on the test set. The input is the protein feature, and the output is the prediction result. The accuracy of amniotic fluid prediction is improved, and the prediction of amniotic fluid protein is finally realized.

Description

technical field [0001] The invention belongs to the technical fields of big data and artificial intelligence, and in particular relates to a method for predicting amniotic fluid protein based on a recurrent neural network. Background technique [0002] Amniotic fluid is a colorless and transparent alkaline liquid, more than 90% of which is water, and it also contains minerals, urea, uric acid, creatinine, vernix, and fetal epithelial cells. The amount of AFP in amniotic fluid can be used as an index to monitor whether the fetus has abnormalities. Through the detection of fetal cell chromosomes in amniotic fluid, the fetus can be screened for genetic diseases. [0003] Some specifically expressed protein markers were found in amniotic fluid, so that early diagnosis of pregnancy-related diseases such as amniotic fluid embolism can be performed. It can be said that the expression of certain proteins in amniotic fluid is very meaningful, and they reflect the physiological and p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G16B40/00G16B50/00G06N3/04G06K9/62
CPCG16B40/00G16B50/00G06N3/045G06N3/044G06F18/241
Inventor 王岩何凯邵丹黄岚王尧张睿
Owner JILIN UNIV