CN118098338A - Microorganism culture condition prediction method and system based on deep learning - Google Patents
Microorganism culture condition prediction method and system based on deep learning Download PDFInfo
- Publication number
- CN118098338A CN118098338A CN202410527736.8A CN202410527736A CN118098338A CN 118098338 A CN118098338 A CN 118098338A CN 202410527736 A CN202410527736 A CN 202410527736A CN 118098338 A CN118098338 A CN 118098338A
- Authority
- CN
- China
- Prior art keywords
- microorganism
- protein sequence
- deep learning
- culture condition
- layer
- 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
- 244000005700 microbiome Species 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013135 deep learning Methods 0.000 title claims abstract description 21
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 70
- 102000004169 proteins and genes Human genes 0.000 claims abstract description 65
- 239000013598 vector Substances 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013136 deep learning model Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 235000015097 nutrients Nutrition 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 230000001902 propagating effect Effects 0.000 claims description 3
- 238000009629 microbiological culture Methods 0.000 claims 4
- 230000000813 microbial effect Effects 0.000 claims 2
- 238000007781 pre-processing Methods 0.000 abstract 1
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012258 culturing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012136 culture method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000011081 inoculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Landscapes
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The application relates to a microorganism culture condition prediction method and a system based on deep learning, wherein the method comprises the following steps: obtaining the protein sequence of a known microorganism and the culture condition; taking the culture condition of the microorganism as a tag, and carrying out coding pretreatment on the tag and a protein sequence of the microorganism corresponding to the tag to obtain a two-dimensional vector; training a deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model; the prediction model predicts the culture condition of the target microorganism based on the protein sequence of the target microorganism. The system comprises: the device comprises an acquisition module, a coding preprocessing module, a training module and a prediction module. The method can accurately and effectively predict the culture conditions required by different microorganisms, and can effectively excavate and culture unknown low-abundance microorganisms.
Description
Technical Field
The application relates to the technical field of machine learning, in particular to a microorganism culture condition prediction method and system based on deep learning.
Background
The culture conditions of the microorganisms have a great influence on the growth and yield of the microorganisms.
Common microorganism culture methods include in-situ culture, wherein microorganisms are directly inoculated in natural environment or simulated environment for culture, so that ecological characteristics and genetic stability of the microorganisms can be maintained, and the method is suitable for culturing microorganisms in certain special environments, but cannot culture microorganisms with unknown or low abundance.
And the operations such as microorganism inoculation, pipetting and detection are automatically performed by using a robot technology, and the proper culture conditions are summarized through a large number of experiments, so that the culture efficiency is greatly improved, but the problems of long time consumption and low accuracy are solved.
In addition, there are methods for determining classification of microorganisms in a sample by gene sequencing and then culturing the target microorganism according to culture conditions of similar microorganisms in the classification tree; the disadvantage is that the number of different microorganisms determined by sequencing is limited and the similarity alignment error is large, failing to excavate deep a large number of unknown microorganisms.
Disclosure of Invention
Based on this, it is necessary to provide a microorganism culture condition prediction method and system based on deep learning.
In one aspect, a method for predicting a microorganism culture condition based on deep learning includes:
S1: obtaining the protein sequence of a known microorganism and the culture condition;
s2: taking the culture condition of the microorganism as a tag, and carrying out coding pretreatment on the tag and a protein sequence of the microorganism corresponding to the tag to obtain a two-dimensional vector;
s3: training a deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model;
s4: the prediction model predicts the culture condition of the target microorganism based on the protein sequence of the target microorganism.
Preferably, in S1, the obtaining a protein sequence of a known microorganism includes:
Step 1: performing metagenome sequencing on known microorganisms, and obtaining a genome sketch of a single microorganism after binning;
step 2: carrying out gene annotation and redundant sequence removal on the genome sketch to obtain the protein sequence of a single microorganism;
Step 3: repeating steps 1-2 until all known protein sequences of the microorganism are obtained.
Preferably, S2 comprises:
S2.1: screening the protein sequences of the single species by adopting a machine learning algorithm to obtain a first characteristic protein sequence;
S2.2: encoding the tag and a first characteristic protein sequence of the corresponding microorganism according to LIBSVM format to obtain the two-dimensional vector;
s2.3: repeating S2.1-S2.2 until all known microorganisms are traversed, and obtaining a plurality of two-dimensional vectors.
Preferably, S3 comprises:
s3.1: dividing a plurality of the two-dimensional vectors into a training set and a testing set;
S3.2: the deep learning model comprises a convolution layer, a pooling layer, a flat layer and a full connection layer; inputting the training set into the deep learning model, taking a two-class cross entropy as a loss function, iterating by adopting a random gradient descent method, and reversely propagating and updating model parameters to obtain a trained prediction model;
S3.3: and inputting the test set into a trained prediction model, wherein the test set is used for testing the accuracy of prediction of the trained prediction model.
Preferably, in the convolutional layer,
The calculation formula from the size of the convolution layer input to the size of the convolution layer output is:
;
Wherein, Representing the size of the convolutional layer output; /(I)Representing the size of the convolutional layer input; p represents the size of the padding; f represents the convolution kernel size; s represents the convolution step length;
The calculation formula of the parameter number for carrying out convolution operation is as follows:
;
Wherein weights denotes the number of parameters; c in represents the number of channels of the previous layer; c out denotes the number of channels of the current layer;
the activation function in the convolution layer is a ReLU function;
in the pooling layer, average pooling is adopted, and the calculation formula is as follows:
;
Wherein, An average value representing the neuron activation value; /(I)Representation area/>Upper ith neuron activation value;
The flat layer is used for converting a matrix formed by neuron activation values into nodes;
the full connection layer is used for converting the node into two kinds of output by adopting a Sigmoid function, wherein 0 in the two kinds of output indicates that the culture condition is not applicable, and 1 indicates that the culture condition is applicable.
Preferably, S4 comprises:
Screening the protein sequence of the target microorganism by adopting a machine learning algorithm to obtain a second characteristic protein sequence;
replacing the protein sequence of the target microorganism with the second characteristic protein sequence, and replacing the position, which does not belong to the second characteristic protein sequence, in the protein sequence of the target microorganism with 0 to obtain a vector;
removing 0 value items in the vector, expanding the vector into two dimensions, and normalizing and storing the two dimensions as a gray level map;
and inputting the gray level map into the prediction model to obtain the culture condition of the target microorganism.
Preferably, the machine learning algorithm includes decision trees, XGBoost, SVC, random deep forest, and neural networks.
Preferably, the coding mode comprises sequential coding, single-hot coding and language coding.
Preferably, the culture conditions include temperature, pH, oxygen concentration, and nutrients.
In another aspect, a deep learning-based microorganism culture condition prediction system includes:
An acquisition module for protein sequences and culture conditions of known microorganisms;
The encoding pretreatment module is used for taking the culture condition of the microorganism as a tag, and carrying out encoding pretreatment on the tag and a protein sequence of the microorganism corresponding to the tag to obtain a two-dimensional vector;
The training module is used for training the deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model;
and the prediction module is used for predicting the culture condition of the target microorganism based on the protein sequence of the target microorganism by the prediction model.
The beneficial effects are that: the method can accurately and effectively predict the culture conditions required by different microorganisms, and can effectively excavate and culture unknown low-abundance microorganisms.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for predicting a microorganism culture condition based on deep learning according to an embodiment of the present application.
FIG. 2 is a schematic diagram of a prediction model according to an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the application will be readily understood, a more particular description of the application will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit of the application, whereby the application is not limited to the specific embodiments disclosed below.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
As shown in fig. 1, the present embodiment provides a method for predicting a microorganism culture condition based on deep learning, the method comprising:
s1: obtaining the protein sequence of the known microorganism and the culture condition.
Specifically, the obtaining of the protein sequence of the known microorganism includes:
Step 1: performing metagenome sequencing on known microorganisms, and obtaining a genome sketch of a single microorganism after binning;
In this embodiment, further comprising: after obtaining the metagenome sequencing data of the known microorganism, protein sequences with different functions are marked through belief analysis.
Step 2: carrying out gene annotation and redundant sequence removal on the genome sketch to obtain protein sequences of single microorganism, wherein the number of the protein sequences is more than 1 and less than i and less than 14000, and the protein sequences are arranged according to the sequence of the gene position information;
Step 3: repeating steps 1-2 until all known protein sequences of the microorganism are obtained.
In this example, the culture conditions include temperature, pH, oxygen concentration, and nutrients.
S2: taking the culture condition of the microorganism as a label, and carrying out coding pretreatment on the label and a protein sequence of the microorganism corresponding to the label to obtain a two-dimensional vector.
Specifically, the method comprises the following steps:
s2.1: screening the protein sequences of single species by adopting a machine learning algorithm according to the importance to obtain a first characteristic protein sequence;
in this embodiment, the machine learning algorithm includes decision trees, XGBoost, SVC, random deep forests, and neural networks.
S2.2: encoding the tag and the first characteristic protein sequence of the corresponding microorganism according to LIBSVM format to obtain the two-dimensional vector, wherein the dimension is m multiplied by n=20 multiplied by 20;
In this embodiment, the encoding mode includes sequential encoding, single-hot encoding, and language encoding.
S2.3: repeating S2.1-S2.2 until all known microorganisms are traversed, and obtaining a plurality of two-dimensional vectors.
S3: and training a deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model.
Specifically, the process includes:
s3.1: dividing a plurality of the two-dimensional vectors into a training set (accounting for 80%) and a testing set;
S3.2: the deep learning model comprises a convolution layer, a pooling layer, a flat layer and a full connection layer; inputting the training set into the deep learning model, taking a two-class cross entropy as a loss function, iterating by adopting a random gradient descent method, and reversely propagating and updating model parameters to obtain a trained prediction model, as shown in figure 2;
in this embodiment, the input feature dimensions and parameter amounts of each layer of the model are shown in table 1;
table 1 is a table of comparison of input feature dimensions and parameter amounts of each layer of the model;
;
S3.3: and inputting the test set into a trained prediction model, wherein the test set is used for testing the accuracy of prediction of the trained prediction model.
Further, in the convolutional layer,
The calculation formula from the size of the convolution layer input to the size of the convolution layer output is:
;
Wherein, Representing the size of the convolutional layer output; /(I)Representing the size of the convolutional layer input; p represents the size of the padding; f represents the convolution kernel size, f=5×5; s represents the convolution step length;
The calculation formula of the parameter number for carrying out convolution operation is as follows:
;
Wherein weights denotes the number of parameters; c in represents the number of channels of the previous layer; c out denotes the number of channels of the current layer;
There are 1300 parameters in the convolution layer of the layer, 50 of which are bias term parameters;
the activation function in the convolution layer is a ReLU function;
in the pooling layer, average pooling is adopted, and the calculation formula is as follows:
;
Wherein, An average value representing the neuron activation value; /(I)Representation area/>Upper ith neuron activation value; the input of the layer is the output of the first layer, which is a node matrix of 16×16×50, the filter size adopted by the layer is 2×2, and the step sizes of the length and the width are both 2, so the output matrix size of the layer is 8×8×50.
The flat layer is used for converting a matrix formed by neuron activation values into nodes;
the full connection layer is used for converting the node into two kinds of output by adopting a Sigmoid function, wherein 0 in the two kinds of output indicates that the culture condition is not applicable, and 1 indicates that the culture condition is applicable.
S4: the prediction model predicts the culture condition of the target microorganism based on the protein sequence of the target microorganism.
Specifically, the method comprises the following steps:
Screening the protein sequence of the target microorganism by adopting a machine learning algorithm according to the importance to obtain a second characteristic protein sequence;
replacing the protein sequence of the target microorganism with the second characteristic protein sequence, and replacing the position, which does not belong to the second characteristic protein sequence, in the protein sequence of the target microorganism with 0 to obtain a vector;
removing 0 value items in the vector, expanding the vector into two dimensions, and normalizing and storing the two dimensions as a gray level map;
and inputting the gray level map into the prediction model to obtain the culture condition of the target microorganism.
The embodiment also provides a microorganism culture condition prediction system based on deep learning, which comprises:
An acquisition module for protein sequences and culture conditions of known microorganisms;
The encoding pretreatment module is used for taking the culture condition of the microorganism as a tag, and carrying out encoding pretreatment on the tag and a protein sequence of the microorganism corresponding to the tag to obtain a two-dimensional vector;
The training module is used for training the deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model;
and the prediction module is used for predicting the culture condition of the target microorganism based on the protein sequence of the target microorganism by the prediction model.
The microorganism culture condition prediction method and system based on deep learning provided by the embodiment have the following beneficial effects:
1. the protein sequence (functional protein sequence) is used as a whole to encode, so that the relation between the protein sequence (functional protein sequence) and the culture condition is conveniently mined, and the prediction result is more accurate and reliable.
2. Through deep learning and machine learning algorithm, key characteristics of protein sequences are screened according to importance in advance, the dimension is reduced, and the prediction efficiency and accuracy are improved.
3. The culture conditions required by different microorganisms can be accurately and effectively predicted, and unknown low-abundance microorganisms can be effectively excavated and cultured.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (9)
1. A method for predicting microbial culture conditions based on deep learning, comprising the steps of:
S1: obtaining the protein sequence of a known microorganism and the culture condition;
s2: taking the culture condition of the microorganism as a tag, and carrying out coding pretreatment on the tag and a protein sequence of the microorganism corresponding to the tag to obtain a two-dimensional vector;
S2.1: screening the protein sequences of the single species by adopting a machine learning algorithm to obtain a first characteristic protein sequence;
S2.2: encoding the tag and a first characteristic protein sequence of the corresponding microorganism according to LIBSVM format to obtain the two-dimensional vector;
s2.3: repeating S2.1-S2.2 until all known microorganisms are traversed, and obtaining a plurality of two-dimensional vectors;
s3: training a deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model;
s4: the prediction model predicts the culture condition of the target microorganism based on the protein sequence of the target microorganism.
2. The method for predicting microbial culture conditions based on deep learning according to claim 1, wherein in S1, the obtaining a protein sequence of a known microorganism comprises:
Step 1: performing metagenome sequencing on known microorganisms, and obtaining a genome sketch of a single microorganism after binning;
step 2: carrying out gene annotation and redundant sequence removal on the genome sketch to obtain the protein sequence of a single microorganism;
Step 3: repeating steps 1-2 until all known protein sequences of the microorganism are obtained.
3. The method for predicting the culture conditions of microorganisms based on deep learning according to claim 2, wherein S3 comprises:
s3.1: dividing a plurality of the two-dimensional vectors into a training set and a testing set;
S3.2: the deep learning model comprises a convolution layer, a pooling layer, a flat layer and a full connection layer; inputting the training set into the deep learning model, taking a two-class cross entropy as a loss function, iterating by adopting a random gradient descent method, and reversely propagating and updating model parameters to obtain a trained prediction model;
S3.3: and inputting the test set into a trained prediction model, wherein the test set is used for testing the accuracy of prediction of the trained prediction model.
4. The method for predicting microbial cultivation conditions based on deep learning according to claim 3, wherein, in the convolution layer,
The calculation formula from the size of the convolution layer input to the size of the convolution layer output is:
;
Wherein, Representing the size of the convolutional layer output; /(I)Representing the size of the convolutional layer input; p represents the size of the padding; f represents the convolution kernel size; s represents the convolution step length;
The calculation formula of the parameter number for carrying out convolution operation is as follows:
;
Wherein weights denotes the number of parameters; c in represents the number of channels of the previous layer; c out denotes the number of channels of the current layer;
the activation function in the convolution layer is a ReLU function;
in the pooling layer, average pooling is adopted, and the calculation formula is as follows:
;
Wherein, An average value representing the neuron activation value; /(I)Representation area/>Upper ith neuron activation value;
The flat layer is used for converting a matrix formed by neuron activation values into nodes;
the full connection layer is used for converting the node into two kinds of output by adopting a Sigmoid function, wherein 0 in the two kinds of output indicates that the culture condition is not applicable, and 1 indicates that the culture condition is applicable.
5. The method for predicting microbial culture conditions based on deep learning according to claim 1, wherein S4 comprises:
Screening the protein sequence of the target microorganism by adopting a machine learning algorithm to obtain a second characteristic protein sequence;
replacing the protein sequence of the target microorganism with the second characteristic protein sequence, and replacing the position, which does not belong to the second characteristic protein sequence, in the protein sequence of the target microorganism with 0 to obtain a vector;
removing 0 value items in the vector, expanding the vector into two dimensions, and normalizing and storing the two dimensions as a gray level map;
and inputting the gray level map into the prediction model to obtain the culture condition of the target microorganism.
6. The deep learning-based microbial cultivation condition prediction method according to claim 5, wherein the machine learning algorithm comprises decision trees, XGBoost, SVC, random deep forests, and neural networks.
7. The method for predicting the culture conditions of microorganisms based on deep learning according to claim 1, wherein the coding mode comprises sequential coding, single-hot coding and language coding.
8. The method for predicting the culture condition of microorganisms based on deep learning according to claim 1, wherein the culture condition comprises temperature, pH, oxygen concentration, and nutrient composition.
9. A deep learning-based microbial culture condition prediction system, comprising:
An acquisition module for protein sequences and culture conditions of known microorganisms;
The encoding pretreatment module is used for taking the culture condition of the microorganism as a tag, and carrying out encoding pretreatment on the tag and a protein sequence of the microorganism corresponding to the tag to obtain a two-dimensional vector;
The training module is used for training the deep learning model based on a plurality of the two-dimensional vectors to obtain a prediction model;
and the prediction module is used for predicting the culture condition of the target microorganism based on the protein sequence of the target microorganism by the prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410527736.8A CN118098338A (en) | 2024-04-29 | 2024-04-29 | Microorganism culture condition prediction method and system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410527736.8A CN118098338A (en) | 2024-04-29 | 2024-04-29 | Microorganism culture condition prediction method and system based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118098338A true CN118098338A (en) | 2024-05-28 |
Family
ID=91153581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410527736.8A Pending CN118098338A (en) | 2024-04-29 | 2024-04-29 | Microorganism culture condition prediction method and system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118098338A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113450882A (en) * | 2020-09-27 | 2021-09-28 | 东莞太力生物工程有限公司 | Artificial intelligence-based basic culture medium formula development method and system |
CN114121163A (en) * | 2021-11-30 | 2022-03-01 | 深圳太力生物技术有限责任公司 | Culture medium prediction system based on ensemble learning, training and culture medium prediction method |
CN114360652A (en) * | 2022-01-28 | 2022-04-15 | 深圳太力生物技术有限责任公司 | Cell strain similarity evaluation method and similar cell strain culture medium formula recommendation method |
JP2023544067A (en) * | 2020-11-26 | 2023-10-19 | シェンチェン タイリ バイオテクノロジー カンパニー リミテッド | Basal medium development method and system |
CN117235673A (en) * | 2023-11-15 | 2023-12-15 | 中南大学 | Cell culture prediction method and device, electronic equipment and storage medium |
-
2024
- 2024-04-29 CN CN202410527736.8A patent/CN118098338A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113450882A (en) * | 2020-09-27 | 2021-09-28 | 东莞太力生物工程有限公司 | Artificial intelligence-based basic culture medium formula development method and system |
JP2023544067A (en) * | 2020-11-26 | 2023-10-19 | シェンチェン タイリ バイオテクノロジー カンパニー リミテッド | Basal medium development method and system |
CN114121163A (en) * | 2021-11-30 | 2022-03-01 | 深圳太力生物技术有限责任公司 | Culture medium prediction system based on ensemble learning, training and culture medium prediction method |
CN114360652A (en) * | 2022-01-28 | 2022-04-15 | 深圳太力生物技术有限责任公司 | Cell strain similarity evaluation method and similar cell strain culture medium formula recommendation method |
CN117235673A (en) * | 2023-11-15 | 2023-12-15 | 中南大学 | Cell culture prediction method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
胡如云 等: "面向合成生物学的机器学习方法及应用", 《科学通报》, vol. 66, no. 03, 15 December 2021 (2021-12-15), pages 284 - 299 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Flagel et al. | The unreasonable effectiveness of convolutional neural networks in population genetic inference | |
EP2694669B1 (en) | Methods for making or creating a synthetic microbial consortium identified by computational analysis of amplicon sequences | |
Kaytoue et al. | Mining gene expression data with pattern structures in formal concept analysis | |
CN110502277B (en) | Code bad smell detection method based on BP neural network | |
Bhatt et al. | Bioinformatic tools to study the soil microorganisms: an in silico approach for sustainable agriculture | |
Papaxanthos et al. | Finding significant combinations of features in the presence of categorical covariates | |
CN111916148B (en) | Method for predicting protein interaction | |
CN110309867A (en) | A kind of Mixed gas identification method based on convolutional neural networks | |
CN111325264A (en) | Multi-label data classification method based on entropy | |
Yu et al. | iDNA-ABT: advanced deep learning model for detecting DNA methylation with adaptive features and transductive information maximization | |
CN116051479A (en) | Textile defect identification method integrating cross-domain migration and anomaly detection | |
CN115329908A (en) | Power transformer fault diagnosis method based on deep learning | |
CN114897085A (en) | Clustering method based on closed subgraph link prediction and computer equipment | |
Diana et al. | eDNAPlus: a unifying modelling framework for DNA-based biodiversity monitoring | |
CN116844646B (en) | Enzyme function prediction method based on deep contrast learning | |
CN118098338A (en) | Microorganism culture condition prediction method and system based on deep learning | |
CN110222793B (en) | Online semi-supervised classification method and system based on multi-view active learning | |
CN115064218B (en) | Method and device for constructing pathogenic microorganism data identification platform | |
Chang et al. | Reconstructing large networks with time-varying interactions | |
Schrider et al. | Machine Learning for Population Genetics: A New Paradigm | |
Qayyumi et al. | Active Learning for kNN Using Instance Impact | |
EP4124997A1 (en) | Computer-implemented method for determining at least one updated model parameter | |
CN118014155A (en) | Carbon emission prediction system, method and medium based on lifting stack learning | |
CN110827915A (en) | Method for carrying out geographical positioning on unknown sample through microorganism metagenome | |
Peter | Frame Work to Classify Data in Interactive System to Enhance Decision Making |
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 |