Model based on multiple characteristics of oligonucleotide probe sequence

Abstract

The invention provides a model based on multiple characteristics of oligonucleotide probe sequences, and belongs to the technical field of molecular biology. Comprising the following steps: S1, probe design: arranging oligonucleotide probes with the length of 25nt on a DNA microarray chip; s2, feature extraction: aiming at each oligonucleotide probe sequence, extracting a plurality of feature parameters, the feature parameters including five features, namely GC content, secondary structure tendency, thermodynamic stability, sequence complexity and base accumulation energy; s3, model construction: constructing a prediction model by using a machine learning algorithm based on the five extracted features; and S4, signal prediction: applying the model to a new oligonucleotide probe sequence, and predicting the intensity of a fluorescence signal generated in the hybridization process. According to the method, five characteristics of the oligonucleotide probe are jointly used for constructing the model, so that closed-loop optimization of DNA microarray chip probe design is realized, the probe design efficiency is improved, and the test production cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of molecular biology, and particularly relates to a model based on multiple features of oligonucleotide probe sequences. Background Art

[0002] DNA Microarray is a high-throughput gene detection technology used to study gene expression, gene mutation, and genomic function. It immobilizes designed oligonucleotide probes on a solid support (such as a glass slide, silicon wafer, or nylon membrane). Based on the principle of nucleic acid complementary base pairing (A pairs with T, and C pairs with G), it obtains the characteristic information of the target DNA fragment by detecting the fluorescence signal emitted after the target DNA fragment hybridizes with the oligonucleotide probes immobilized on the chip.

[0003] DNA Microarrays are widely used in fields such as gene expression analysis, genotyping, and genomic research. A large number of oligonucleotide (oligo) probes are arranged on the surface of the DNA Microarray. After these probes hybridize with the target nucleic acid sequences in the sample, the presence and abundance of the target sequences are reflected by the fluorescence signal intensity. However, accurate prediction of hybridization efficiency and fluorescence signals has always been one of the key factors affecting the performance of DNA Microarrays. Traditional methods mostly rely on single sequence features (such as GC content) for prediction, with limited accuracy. Therefore, this application provides a model based on multiple features of oligonucleotide probe sequences to meet the requirements. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a model based on multiple features of oligonucleotide probe sequences to solve the existing problems.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] A model based on multiple features of oligonucleotide probe sequences, comprising the following steps:

[0007] S1. Probe Design: Oligonucleotide probes with a length of 25 nt are arranged on the DNA Microarray.

[0008] S2. Feature Extraction: For each oligonucleotide probe sequence, multiple feature parameters are extracted. The feature parameters include GC content, secondary structure propensity, thermodynamic stability, sequence complexity, and base stacking energy, totaling five features.

[0009] S3. Model Construction: Based on the five extracted features, a prediction model is constructed using a machine learning algorithm.

[0010] S4. Signal Prediction: The model is applied to a new oligonucleotide probe sequence to predict the fluorescence signal intensity generated during hybridization.

[0011] Preferably, the specific steps of S2 are as follows:

[0012] S201. Select an oligonucleotide probe sequence with a length of 25 nt;

[0013] S202. For each oligonucleotide probe sequence, calculate the following five features: GC content: Calculate the proportion of GC bases; Secondary structure propensity: Predict the possibility of the oligonucleotide probe sequence forming a secondary structure; Thermodynamic stability: Thermodynamic stability is usually measured by the melting temperature or the free energy of the secondary structure, reflecting the stability of the oligonucleotide sequence during hybridization; Sequence complexity: Sequence complexity measures the diversity and repetition of bases in the sequence. High-complexity sequences usually have less repetition and higher diversity; Base stacking energy: Base stacking energy refers to the interaction energy between adjacent base pairs, which affects the stability of the secondary structure. Higher stacking energy usually means a more stable structure.

[0014] Preferably, the specific steps of S3 are as follows:

[0015] S301. Collect a large dataset of oligonucleotide probes with known fluorescence signal intensities;

[0016] S302. Perform the above feature extraction on each oligonucleotide probe sequence to form a feature vector;

[0017] S303. Use the feature vector and the corresponding fluorescence signal intensity as training data and input them into a selected machine learning algorithm for model training;

[0018] S304. Evaluate the prediction accuracy of the model using methods such as cross-validation and optimize the model parameters to improve performance.

[0019] Preferably, the specific steps of S4 are as follows:

[0020] S401. Perform feature extraction on the newly designed 25-nt oligonucleotide probe;

[0021] S402. Input the feature vector into the trained model to output the predicted fluorescence signal intensity;

[0022] S403. Optimize the probe design according to the prediction results to improve the overall performance and accuracy of the DNA microarray chip.

[0023] Compared with the prior art, the present invention has at least the following beneficial effects:

[0024] In the above solution, by using the five features of the oligonucleotide probe together for model construction, a closed-loop optimization of the DNA microarray chip probe design is achieved, improving the probe design efficiency and reducing the test production cost. Description of the Drawings

[0025] The drawings incorporated herein and constituting a part of the specification illustrate embodiments of the present disclosure and, together with the specification, are further used to explain the principles of the present disclosure and enable those skilled in the relevant art to implement and use the present disclosure.

[0026] Figure 1 It is a flowchart of a model based on multiple features of oligonucleotide probe sequences. Detailed Description of the Invention

[0027] A model based on multiple features of oligonucleotide probe sequences provided by the present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technical fields, those skilled in the art can also implement them in other alternative ways; moreover, the drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0028] It should be noted that in the specification, references to "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not every embodiment necessarily includes such specific features, structures, or characteristics. Additionally, when combining embodiments to describe specific features, structures, or characteristics, implementing such features, structures, or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0029] Generally, terms can be understood at least in part from their use in context. For example, at least in part depending on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense or can be used to describe a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather, at least in part depending on the context, can allow for the existence of other factors that may not be explicitly described.

[0030] It can be understood that the meanings of "on...", "above...", and "over..." in the present disclosure should be construed in the broadest manner such that "on..." not only means "directly on" something, but also includes the meaning of being "on" something with intervening features or layers therebetween, and "above..." or "over..." not only means "above" or "over" something, but also can include the meaning of being "above" or "over" something with no intervening features or layers therebetween.

[0031] In addition, spatial relative terms such as "under", "below", "lower", "above", "upper", etc. may be used herein for convenience of description to describe the relationship of one element or feature with another or more elements or features, as shown in the drawings. The spatial relative terms are intended to cover different orientations in the use or operation of the device in addition to the orientation depicted in the drawings. The device may be oriented in other ways, and the spatial relative descriptors used herein may be interpreted accordingly.

[0032] Such as Figure 1 , including the following steps:

[0033] S1. Probe design: Oligonucleotide probes with a length of 25 nt are arranged on the DNA microarray chip;

[0034] S2. Feature extraction: For each oligonucleotide probe sequence, multiple feature parameters are extracted. The feature parameters include GC content, secondary structure propensity, thermodynamic stability, sequence complexity, and base stacking energy, a total of five features;

[0035] S3. Model construction: Based on the five extracted features, a prediction model is constructed using a machine learning algorithm;

[0036] S4. Signal prediction: The model is applied to a new oligonucleotide probe sequence to predict the fluorescence signal intensity generated during hybridization.

[0037] It should be further noted in this embodiment that the specific steps of S2 are as follows:

[0038] S201. Select an oligonucleotide probe sequence with a length of 25 nt;

[0039] S202. For each oligonucleotide probe sequence, calculate the following five features: GC content: Calculate the proportion of GC bases; Secondary structure propensity: Predict the possibility of the oligonucleotide probe sequence forming a secondary structure; Thermodynamic stability: Thermodynamic stability is usually measured by the melting temperature or the free energy of the secondary structure, reflecting the stability of the oligonucleotide sequence during hybridization; Sequence complexity: Sequence complexity measures the diversity and repetition degree of bases in the sequence. High-complexity sequences usually have less repetition and higher diversity; Base stacking energy: Base stacking energy refers to the interaction energy between adjacent base pairs, which affects the stability of the secondary structure. Higher stacking energy usually means a more stable structure.

[0040] It should be further noted in this embodiment that the specific steps of S3 are as follows:

[0041] S301. Collect a large dataset of oligonucleotide probes with known fluorescence signal intensities;

[0042] S302. Extract the above-mentioned features for each oligonucleotide probe sequence to form a feature vector;

[0043] S303. Use the feature vector and the corresponding fluorescence signal intensity as training data and input them into the selected machine learning algorithm for model training;

[0044] S304. Evaluate the prediction accuracy of the model using methods such as cross-validation, and optimize the model parameters to improve performance.

[0045] It should be further noted in this embodiment that the specific steps of S4 are as follows:

[0046] S401. Extract features for the newly designed 25-nt oligonucleotide probe;

[0047] S402. Input the feature vector into the trained model to output the predicted fluorescence signal intensity;

[0048] S403. Optimize the probe design according to the prediction results to improve the overall performance and accuracy of the DNA microarray chip.

[0049] The present invention covers any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of the present invention. To enable the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention without these detailed descriptions. In addition, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0050] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned embodiment methods can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc.

[0051] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A model based on multiple features of oligonucleotide probe sequences, characterized in that: The following steps are involved: S1. Probe design: Oligonucleotide probes of 25 nt in length were arrayed on a DNA microarray chip; S2. Feature extraction: for each oligonucleotide probe sequence, multiple feature parameters are extracted, including GC content, secondary structure tendency, thermodynamic stability, sequence complexity, and base stacking energy, a total of five features; S3, model construction: based on the five extracted features, a prediction model is constructed using a machine learning algorithm; S4. Signal prediction: Apply the model to new oligonucleotide probe sequences to predict the fluorescence signal intensity generated during hybridization.

2. A model based on multiple features of oligonucleotide probe sequences according to claim 1, characterized in that: The specific steps of S2 are: S201, selecting an oligonucleotide probe sequence of 25 nt in length; S202. For each oligonucleotide probe sequence, the following five characteristics are calculated: GC content: calculate the ratio of GC bases; secondary structure tendency: predict the possibility of the oligonucleotide probe sequence to form a secondary structure; thermodynamic stability: thermodynamic stability is usually measured by melting temperature or free energy of secondary structure, reflecting the stability of the oligonucleotide sequence during hybridization; sequence complexity: sequence complexity measures the diversity and repetition of bases in the sequence. High-complexity sequences usually have fewer repetitions and higher diversity; base stacking energy: base stacking energy refers to the interaction energy between adjacent base pairs, which affects the stability of the secondary structure. Higher stacking energy usually means a more stable structure.

3. A model based on multiple features of oligonucleotide probe sequences according to claim 1, characterized in that: The specific steps of S3 are: S301, collecting a large number of oligonucleotide probe data sets with known fluorescence signal intensities; S302, performing the above feature extraction on each oligonucleotide probe sequence to form a feature vector; S303, using the feature vector and the corresponding fluorescence signal intensity as training data, and inputting them into the selected machine learning algorithm for model training; S304. Use methods such as cross-validation to evaluate the prediction accuracy of the model and optimize model parameters to improve performance.

4. A model based on multiple features of oligonucleotide probe sequences according to claim 1, characterized in that: The specific steps of S4 are: S401, feature extraction of the newly designed 25nt oligonucleotide probe; S402, inputting the feature vector into the trained model, and outputting the predicted fluorescence signal intensity; S403. Optimize probe design based on the prediction results to improve the overall performance and accuracy of the DNA microarray chip.

Images