An anti-cancer drug response prediction method based on heterogeneous multi-branch

Abstract

The present application relates to a kind of based on the reaction prediction method of anticancer drug of isomorphism multi-branch, applied in bioinformatics field.The method includes: S1: data is preprocessed, obtains cell line multi-omics data, drug substructure fingerprint data, drug molecular graph data and cell line-drug reaction data;S2: similarity global feature extraction module (SGFE) is constructed to carry out feature extraction, obtain cell line similarity feature, drug similarity feature, drug global feature;S3: isomorphism multi-branch feature extraction module (HHFE) is constructed to obtain multi-branch cell line feature and multi-branch drug feature;S4: multi-branch multi-layer fusion module (MFML) is constructed, obtains cell line fusion feature and drug fusion feature, and the correlation of both is calculated;S5: the reaction between cell line and drug is predicted using correlation, and the prediction result is output.The present application makes full use of known cell line data and drug data, and improves the generalization ability of model.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of bioinformatics, and particularly relates to an anti-cancer drug response prediction method based on isosimilar multi-branching. BACKGROUND

[0002] Cancer is a disease caused by gene mutation, and the heterogeneity of cancer makes patients with the same cancer type may have different responses to the same drug. In the context of precision medicine, anti-cancer drug response prediction (CDR) can help to screen drugs and provide more precise and targeted drug treatment plans for patients.

[0003] With the development of gene sequencing technology, more and more genome databases have been established, and more and more genomics data related to genes and their response data to drugs have been gradually expanded. The rich and valuable data provide data support for the research of anti-cancer drug response prediction, and make it possible to provide personalized treatment for cancer patients.

[0004] Previous studies have greatly promoted the development of CDR, but there are still problems of insufficient utilization of cell line and drug data and poor model generalization ability. In order to solve this problem, GraphDRP uses graph convolutional network (GCN) to extract the graph representation features of drugs, and uses somatic mutation and copy number variation data to represent cell lines, so as to improve the feature abundance of cell lines by increasing the types of cell line omics data; GraphTransDRP uses the Transformer technology to mine the structural features of drugs according to the molecular graph of drugs, extracts more comprehensive drug features by using a more complex network structure, and uses gene expression data to represent cell lines. However, these models do not fully consider the characteristics of various forms of data when selecting data, which may result in feature redundancy or feature missing. In addition, when extracting features, the network structure cannot be selected to extract appropriate features for different data, so that the features are not comprehensive, which affects the generalization ability and prediction performance of the model. Therefore, analyzing the characteristics of various forms of data, combining different forms of data, and developing a network model that can fully extract the features of various forms of data for CDR prediction have practical significance for shortening the drug discovery time and providing guidance for drug screening. SUMMARY

[0005] In order to solve the above technical problems, the application provides an anti-cancer drug response prediction method based on isosimilar multi-branching, which provides guidance for the drug discovery process.

[0006] In particular, the method comprises the following steps:

[0007] S1: preprocessing data, obtaining cell line multi-omics data, drug substructure fingerprint data, drug molecular graph data, and cell line-drug reaction data;

[0008] S2: constructing a similarity global feature extraction module (SGFE) for feature extraction to obtain cell line similarity features, drug similarity features, and drug global features;

[0009] S3: constructing a same-different structure multi-branch feature extraction module (HHFE) to extract cell line similarity features and drug similarity features to obtain multi-branch cell line features and multi-branch drug features;

[0010] S4: constructing a multi-branch multi-layer fusion module (MFML) to fuse multi-branch cell line features to obtain cell line fusion features, fuse drug global features and multi-branch drug features to obtain drug fusion features, and calculate the correlation between them;

[0011] S5: using the correlation to predict the reaction between the cell line and the drug, and outputting the prediction result.

[0012] Preferably, S1 comprises the following steps:

[0013] S1.1: collecting cell line-drug reaction tables in GDSC and CCLE databases;

[0014] S1.2: collecting cell line gene expression, copy number variation, and somatic mutation data from GDSC and CCLE databases according to the reaction table;

[0015] S1.3: screening out cell lines with three modalities, obtaining 962 and 436 cell line data in GDSC and CCLE, respectively;

[0016] S1.4: obtaining PubChem ID of each drug according to the cell line-drug reaction table;

[0017] S1.5: obtaining SMILES sequence of the drug from PubChem database according to PubChem ID;

[0018] S1.6: using RDKit toolkit to obtain substructure fingerprint and molecular graph data corresponding to the drug according to the SMILES sequence of the drug.

[0019] Preferably, S2 comprises the following steps:

[0020] S2.1: fusing multi-omics data of the cell line to obtain cell line similarity features;

[0021] S2.2: Calculate drug similarity features based on drug substructure fingerprints;

[0022] S2.3: Calculate the global characteristics of the drug based on the drug's molecular graph data;

[0023] Preferably, S2.1 includes the following steps:

[0024] The gene expression data is Gaussian regularized, which can be described as:

[0025]

[0026] exp i represents the expression value of the i-th gene in the cell line, represents the regularized expression value of the i-th gene, μ i and δ i represent the mean and standard deviation of the expression of the ith gene in all cell lines, respectively;

[0027] Calculate the similarity of each omics data of the cell line separately. This operation can be described as:

[0028]

[0029] x i and x j They represent the i-th and j-th specific omics data, 1≤i,j≤962, ||||2 represents the second normal form, ε is a hyperparameter, E ij Indicates the similarity of specific omics data in cell lines;

[0030] The full kernel matrix F and sparse kernel matrix S are calculated for each omics data. This operation can be described as:

[0031]

[0032] N i represents the top N cell lines most similar to the i-th cell line;

[0033] According to the calculated full-nuclear matrix GF and sparse-nuclear matrix GS of gene expression, full-nuclear matrix CF and sparse-nuclear matrix CS of copy number variation, full-nuclear matrix MF and sparse-nuclear matrix MS of somatic mutation, let GF0=GF, CF0=CF, MF0=MF, and iteratively update the full-nuclear matrix. This operation can be described as:

[0034]

[0035] t represents the number of iterations, * T Indicates transposing the matrix*

[0036] Finally, the cell line similarity feature RC is obtained, and the calculation formula is as follows:

[0037]

[0038] Preferably, S2.2 includes the following steps:

[0039] According to the substructure fingerprint of the drug, the Tanimoto similarity is calculated to obtain the drug similarity feature RD. This operation can be described as:

[0040]

[0041] d i and d j Represent the substructure fingerprints of the i-th and j-th drugs, respectively, 1≤i,j≤228;

[0042] Preferably, S2.3 includes the following steps:

[0043] Extract features from the drug's molecular graph to obtain the drug's global features f molD , the operation can be described as:

[0044]

[0045] is the feature of node i in the k+1 layer, represents the set of neighbor nodes of node i, W (k) is the weight matrix of the kth layer, σ is the activation function, is the attention coefficient between node i and its neighbor node j, and is calculated as follows:

[0046]

[0047] α (k) is the learned attention weight vector, || represents the concatenation operation, and LeakyRelu is the activation function;

[0048] Preferably, S3 includes the following steps:

[0049] S3.1: Extract features of cell line similarity features and drug similarity features. By fusing features of subgraphs of different scales, we obtain branch features of cell line subgraphs and branch features of drug subgraphs respectively.

[0050] S3.2: Extract cell line similarity features and drug similarity features through message passing to obtain cell line heterogeneous branch features and drug heterogeneous branch features;

[0051] S3.3: Extract features from the cell line isomorphism graph to obtain cell line isomorphism branch features;

[0052] S3.4: feature extraction in the drug isomorphic graph to obtain drug isomorphic branch features;

[0053] Preferably, S3.1 includes the following steps:

[0054] Different scales of subgraphs are constructed by downsampling, feature extraction is performed on the subgraphs, and the features of the subgraphs of each scale are fused to obtain cell line subgraph branch features f UC and drug subgraph branch features f UD The operation can be described as:

[0055] y = X l p l / ||p l ||

[0056] idx = rank(y, k)

[0057]

[0058] A l+1 = A l (idx, idx)

[0059]

[0060] X l represents the node feature of the l-th layer, p l is a trainable vector, ||p l || represents the length of the vector p l , y is the projection scalar value of X l on the vector p l , rank(y, k) represents selecting the largest k values from y, idx records the subscripts of the largest k values, is the feature corresponding to the k nodes, A l+1 is the adjacency matrix composed of the k nodes, W l is the weight matrix, H (l+1) is the updated node feature, and σ is the activation function.

[0061] Preferably, S3.2 includes the following steps:

[0062] Feature extraction is performed in the cell line-drug isomorphic graph using a message passing method to obtain cell line isomorphic branch features f HeC and drug isomorphic branch features f HeD The operation can be described as:

[0063]

[0064] represents the normalized adjacency matrix.

[0065] Preferably, S3.3 includes the following steps:

[0066] The cell line isomorphism branch features f are extracted using message passing in the cell line isomorphism graph. HoC , the operation can be described as:

[0067] A c =A*A T

[0068]

[0069] A is the cell line-drug response matrix, D c It's A c The degree matrix of is the normalized adjacency matrix in the cell line isomorphism graph, and σ is the activation function;

[0070] Preferably, S3.4 includes the following steps:

[0071] The drug isomorphism branch feature f is extracted using message passing in the drug isomorphism graph HoD , the operation can be described as:

[0072] A d =A T *A

[0073]

[0074] A is the cell line-drug response matrix, D d It's A d The degree matrix of is the normalized adjacency matrix in the drug isomorphism graph, and σ is the activation function;

[0075] Preferably, S4 includes the following steps:

[0076] S4.1: Fusion of cell line branch characteristics yields a cell line fusion signature; fusion of drug branch characteristics and drug global characteristics yields a drug fusion signature;

[0077] S4.2: Perform linear transformation on cell line fusion signatures and drug fusion signatures to adjust them to the same dimension.

[0078] S4.3: Calculate the correlation between the adjusted cell line fusion signature and the drug fusion signature;

[0079] Preferably, S4.1 includes the following steps:

[0080] The cell line subgraph branch features f UC , cell line heterogeneous branching characteristicsfHeC , cell line isomorphic branch characteristics f HoC Fusion to obtain cell line fusion characteristics H 1-c , the drug subgraph branch feature f UD , drug isomerization branch characteristics f HeD , drug isomorphic branch characteristics f HoD , drug global characteristics f molD Fusion to obtain drug fusion feature H 1-d , the operation can be described as:

[0081] H 1-c =(f UC +f HeC +f HoC ) / 3

[0082] H 1-d =((f UD +f HeD ) / 2+f HoD +f molD ) / 3

[0083] Preferably, S4.2 includes the following steps:

[0084] The cell line fusion features and drug fusion features are adjusted to the same dimension through linear transformation, and then the correlation between the two after transformation is calculated. This operation can be described as:

[0085] H (2-c) =H (1-c) W (2-c)

[0086] H (2-d) =H (1-d) W (2-d)

[0087] Here, W (2-c) ∈R c*k and W (2-d) ∈R d*k are the weight matrices for linear transformation of cell lines and drugs, c is the dimension of cell line fusion features, d is the dimension of drug fusion features, k represents the feature dimension after linear transformation, H (2-c) and H (2-d) They are the k-dimensional cell line fusion features and k-dimensional drug fusion features after linear transformation;

[0088] Preferably, S4.3 includes the following steps:

[0089] Calculate the correlation between the k-dimensional cell line fusion features and the k-dimensional drug fusion features. This operation can be described as:

[0090]

[0091] h i is the i-th cell line feature in the k-dimensional cell line fusion feature, h j is the j-th drug feature in the k-dimensional drug fusion feature, μ i and μ j are the mean values of h i and h j , respectively, 1≤i≤962, 1≤j≤228;

[0092] Preferably, S5 comprises the following steps:

[0093] S5.1: sigmoid activation output on the correlation result, output the prediction result;

[0094] Preferably, S5.1 comprises the following steps:

[0095] The correlation coefficient calculated through S4 ranges from -1 to 1, and the sigmoid function is used for activation output to ensure that the probability value of each cell line-drug sensitivity predicted ranges from 0 to 1, and a cell line-drug response matrix is obtained. This operation can be described as:

[0096]

[0097] h is the correlation coefficient, γ is the predicted cell line-drug response matrix, and α is a hyperparameter used to accelerate parameter updating.

[0098] The method has the following advantages: the method uses three types of omics data of gene expression, copy number variation, and somatic mutation of cell lines to obtain similarity features between cell lines; uses substructure fingerprint calculation of drugs to obtain Tanimoto similarity features between drugs, and further obtains global features of drugs according to molecular graphs. According to the similar reactions of similar cell lines to the same drugs, the similarity between cell lines and drugs is used to predict the cell line-drug reaction. At the same time, by analyzing the characteristics of different drug data, the similarity is calculated according to the substructure fingerprint, and the molecular graph data is used to enrich the feature information of the drug data; on the other hand, the same and different structure multi-branch networks are used to extract the internal relationship between cell lines and drugs in the cell line isomorphic graph and the drug isomorphic graph, respectively, and a double-branch network structure is used in the cell line-drug heterogeneous graph to extract comprehensive information flow and capture the relationship features of different types of nodes. Finally, the feature fusion is performed to enhance the generalization of the model and improve the prediction ability of the model. Finally, experiments are performed in the GDSC and CCLE data sets to verify the prediction ability of the method for drug reactions. The method can fully mine the feature information of cell lines and drugs, and improve the ability to predict cell line-drug reactions. BRIEF DESCRIPTION OF DRAWINGS

[0099] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the prior art and the drawings required for use in the embodiments. The following drawings are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0100] Figure 1 It is a schematic flow diagram of the present invention;

[0101] Figure 2 It is a system structure diagram of the present invention;

[0102] Figure 3 Schematic diagram of similarity global feature extraction module of the present invention;

[0103] Figure 4 Schematic diagram of the isomorphic multi-branch feature extraction module of the present invention;

[0104] Figure 5 Schematic diagram of the multi-branch multi-layer fusion module of the present invention; Specific implementation plan

[0105] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making creative work are within the scope of protection of the present invention.

[0106] The embodiment of the present invention provides an anticancer drug reaction prediction method based on heterogeneous and homomorphic multi-branching, which is used to predict the reaction between drugs and cancer cell lines and provide guidance for drug screening.

[0107] Reference Figure 1 , the method comprises the following steps:

[0108] S1: Preprocess the data to obtain cell line multi-omics data, drug substructure fingerprint data, drug molecular graph data, and cell line-drug reaction data;

[0109] S2: Build a similarity global feature extraction module (SGFE) to extract features and obtain cell line similarity features, drug similarity features, and drug global features;

[0110] S3: Construct a heterogeneous multi-branch feature extraction module (HHFE) to extract the cell line similarity features and drug similarity features to obtain multi-branch cell line features and multi-branch drug features;

[0111] S4: Construct a multi-branch multi-layer fusion module (MFML) to fuse multi-branch cell line features to obtain cell line fusion features, fuse drug global features and multi-branch drug features to obtain drug fusion features, and calculate the correlation between the two;

[0112] S5: Use the correlation to predict the reaction between cell lines and drugs and output the prediction results.

[0113] Furthermore, S1 includes the following steps:

[0114] S1.1: Cell line-drug response tables collected in the GDSC and CCLE databases;

[0115] S1.2: Based on the response table, gene expression, copy number variation, and somatic mutation data of the cell lines were collected from the GDSC and CCLE databases, respectively;

[0116] S1.3: Screening for cell lines that exhibit all three modalities;

[0117] S1.4: Response datasets for 962 cell lines and 228 drugs were obtained from GDSC; response datasets for 436 cell lines and 24 drugs were obtained from CCLE;

[0118] S1.5: Obtain the PubChem ID of each drug based on the cell line-drug reaction table;

[0119] S1.6: Based on the PubChem ID, the SMILES sequence of the drug was obtained from the PubChem library;

[0120] S1.7: Use the RDKit toolkit to obtain the substructure fingerprint and molecular graph data corresponding to the drug based on the SMILES sequence of the drug.

[0121] Further, refer to Figure 3 , S2 includes the following steps:

[0122] S2.1: Perform similarity fusion on the multi-omics data of cell lines to obtain cell line similarity features;

[0123] S2.2: Calculate drug similarity features based on drug substructure fingerprints;

[0124] S2.3: Calculate the global characteristics of the drug based on the drug's molecular graph data;

[0125] Furthermore, S2.1 includes the following steps:

[0126] The gene expression data is Gaussian regularized, which can be described as:

[0127]

[0128] exp i represents the expression value of the i-th gene in the cell line, represents the regularized expression value of the i-th gene, μ i and δ i represent the mean and standard deviation of the expression of the ith gene in all cell lines, respectively;

[0129] Calculate the similarity of each omics data of the cell line separately. This operation can be described as:

[0130]

[0131] x i and x j Represent the i-th and j-th specific omics data, 1≤i,j≤962, ||||2 represents the second normal form, E ij represents the similarity of specific omics data in cell lines, and ε is set to 2;

[0132] The full kernel matrix F and sparse kernel matrix S are calculated for each omics data. This operation can be described as:

[0133]

[0134] N i represents the top N cell lines most similar to the i-th cell line;

[0135] According to the calculated full-nuclear matrix GF and sparse-nuclear matrix GS of gene expression, full-nuclear matrix CF and sparse-nuclear matrix CS of copy number variation, full-nuclear matrix MF and sparse-nuclear matrix MS of somatic mutation, let GF0=GF, CF0=CF, MF0=MF, and iterate the full-nuclear matrix three times to update it. This operation can be described as:

[0136]

[0137] t represents the number of iterations, here it is 3, * T Indicates transposing the matrix*

[0138] Finally, the cell line similarity feature RC is obtained, and the calculation formula is as follows:

[0139]

[0140] Where RC∈R 962*962, R represents a real number.

[0141] Furthermore, S2.2 includes the following steps:

[0142] According to the substructure fingerprint of the drug, the Tanimoto similarity is calculated to obtain the drug similarity feature RD. This operation can be described as:

[0143]

[0144] d i and d j Represent the substructure fingerprints of the i-th and j-th drugs, 1≤i,j≤228, RD∈R 228*228 , R represents a real number.

[0145] Furthermore, S2.3 includes the following steps:

[0146] Extract features from the drug's molecular graph to obtain the drug's global features f molD , the operation can be described as:

[0147]

[0148] is the feature of node i in the k+1 layer, where k=2, and 3 layers of feature extraction are performed. represents the set of neighbor nodes of node i, W (k) is the weight matrix of the kth layer, σ is the activation function, and the relu activation function is used here. is the attention coefficient between node i and its neighbor node j, and is calculated as follows:

[0149]

[0150] α (K) is the learned attention weight vector, || represents the concatenation operation;

[0151] Further, refer to Figure 4 , S3 includes the following steps:

[0152] S3.1: Extract features of cell line similarity features and drug similarity features. By fusing features of subgraphs of different scales, we obtain branch features of cell line subgraphs and branch features of drug subgraphs respectively.

[0153] S3.2: Extract cell line similarity features and drug similarity features through message passing to obtain cell line heterogeneous branch features and drug heterogeneous branch features;

[0154] S3.3: Extract features from the cell line isomorphism graph to obtain cell line isomorphism branch features;

[0155] S3.4: Extract features from the drug isomorphism graph to obtain drug isomorphism branch features;

[0156] Furthermore, S3.1 includes the following steps:

[0157] Based on the extracted cell line similarity features RC and drug similarity features and RD, we concatenate the node features to obtain the node feature matrix X of the heterogeneous graph: The cell line-drug response table is used as the adjacency matrix A, and the original adjacency matrix is ​​expanded to obtain the adjacency matrix on the heterogeneous graph where A∈R 962*228 , I c is the identity matrix of 962*962, I d It is a 228*228 unit matrix. By downsampling, subgraphs of different sizes are constructed, and features are extracted from the subgraphs. The features of subgraphs of different sizes are fused to obtain the branch features f of the cell line subgraphs. UC and drug subgraph branch features f UD , the operation can be described as:

[0158] y=X l p l / ||p l ||

[0159] idx=rank(y,k)

[0160]

[0161] X l represents the node features of the lth layer, p l is a trainable vector, ||p l || represents vector p l The length of X, y is l In the vector p l The projection scalar value on , rank(y,k) means selecting the largest k values ​​from y, and idx records the subscript of the largest k values. is the node feature of the subgraph consisting of k nodes, A l+1 is the adjacency matrix of the l+1th layer, W l is the weight matrix, H (l +1) is the updated node feature, l is 3, and a total of 3 layers of downsampling feature extraction are performed.

[0162] Furthermore, S3.2 includes the following steps:

[0163] In the cell line-drug heterogeneous graph, feature extraction is performed using message passing, and RC and RD are concatenated to obtain the node feature matrix of the heterogeneous graph. The heterogeneous branch characteristics of cell lines were obtained respectively HeC and drug isomeric branching characteristics f HeD , the operation can be described as:

[0164]

[0165] in Represents the normalized adjacency matrix, l is 2, and a total of 3 layers of feature extraction are performed;

[0166] Furthermore, S3.3 includes the following steps:

[0167] The cell line isomorphism branch features f are extracted using message passing in the cell line isomorphism graph. HoC , the operation can be described as:

[0168] A c =A*A T

[0169]

[0170] A is the cell line-drug response matrix, A c is the adjacency matrix of the cell line isomorphism graph, is the normalized adjacency matrix in the cell line isomorphism graph, D c It's A c The degree matrix, σ is the activation function, here we use the relu activation function, l is 2, and a total of 3 layers of feature extraction are performed;

[0171] Furthermore, S3.4 includes the following steps:

[0172] The drug isomorphism branch feature f is extracted using message passing in the drug isomorphism graph HoD , the operation can be described as:

[0173] A d =A T *A

[0174]

[0175] A is the cell line-drug response matrix, A c is the adjacency matrix of the drug isomorphism graph, is the normalized adjacency matrix in the drug isomorphism graph, D d It's A d The degree matrix, σ is the activation function, here we use the relu activation function, l is 2, and a total of 3 layers of feature extraction are performed.

[0176] Further, refer to Figure 5 , S4 includes the following steps:

[0177] S4.1: Fusion of cell line branch characteristics yields a cell line fusion signature; fusion of drug branch characteristics and drug global characteristics yields a drug fusion signature;

[0178] S4.2: Perform linear transformation on cell line fusion signatures and drug fusion signatures to adjust them to the same dimension.

[0179] S4.3: Calculate the correlation between the adjusted cell line fusion signature and the drug fusion signature;

[0180] Furthermore, S4.1 includes the following steps:

[0181] The cell line subgraph branch features f UC , cell line heterogeneous branching characteristicsf HeC , cell line isomorphic branch characteristics f Hoc Fusion to obtain cell line fusion characteristics H 1-C , the drug subgraph branch feature f UD , drug isomerization branch characteristics f HeD , drug isomorphic branch characteristics f HoD , drug global characteristics f molD Fusion to obtain drug fusion feature H 1-d , the operation can be described as:

[0182] H 1-c =(f UC +f HeC +f HoC ) / 3

[0183] H 1-d =((f UD +f HeD ) / 2+f HoD +f molD ) / 3

[0184] Furthermore, S4.2 includes the following steps:

[0185] The cell line fusion features and drug fusion features are adjusted to the same dimension through linear transformation, and then the correlation between the two after transformation is calculated. This operation can be described as:

[0186] H (2-c) =H (1-c) W (2-c)

[0187] H (2-d) =H (1-d) W (2-d)

[0188] W (2-c) ∈R 962*128 and W (2-d)∈ R 228*128 are weight matrices for linear transformation of cell lines and drugs respectively, 962 is the dimension of cell line fused features, 228 is the dimension of drug fused features, 128 represents the feature dimension after linear transformation, H (2-c) and H (2-d) are 128-dimensional cell line fused features and 128-dimensional drug fused features after linear transformation respectively.

[0189] Further, S4.3 includes the following steps:

[0190] Calculate the correlation between 128-dimensional cell line fused features and 128-dimensional drug fused features, which can be described as:

[0191]

[0192] h i is the i-th cell line feature in 128-dimensional cell line fused features, h j is the j-th drug feature in 128-dimensional drug fused features, μ i and μ j are the mean of h i and h j , 1≤i≤962, 1≤j≤228;

[0193] Further, S5 includes the following steps:

[0194] S5.1: sigmoid activation output on the correlation result, output the prediction result;

[0195] Further, S5.1 includes the following steps:

[0196] The correlation coefficient calculated by S4 is in the range of [-1, 1], and the sigmoid function is used for activation output to ensure that the probability value of each cell line-drug sensitivity predicted is in the range of [0, 1], and the cell line-drug reaction matrix is obtained, which can be described as:

[0197]

[0198] h is the correlation coefficient, γ is the predicted cell line-drug reaction matrix, α is the hyperparameter, which is 5 here, used to accelerate parameter update.

[0199] In order to evaluate the performance of the model, some indicators are used to evaluate the prediction results of the model on two data sets, and the specific evaluation formula of the evaluation index is as follows:

[0200] AUC stands for Area Under the ROC Curve. The horizontal axis is FPR (False Positive Rate) and the vertical axis is TRP (True Positive Rate). It is an indicator used to measure the performance of a binary classification model. The AUC range is [0,1]. The closer the value is to 1, the better the model effect.

[0201] FPR is calculated as follows, which represents the proportion of samples that are actually negative that are incorrectly predicted to be positive:

[0202]

[0203] TPR is calculated as follows, which represents the proportion of samples that are actually positive that are correctly predicted to be positive:

[0204]

[0205] AUPRC stands for Area Under the Prediction Curve (AUPRC). The horizontal axis represents recall, which ranges from 0 to 1, and the vertical axis represents precision, which ranges from 0 to 1. The AUPR range is [0, 1]. The closer the value is to 1, the better the model performance.

[0206] Other indicators are calculated as follows:

[0207]

[0208] Among them: TP means that the actual class is positive and the model predicts it is also positive; FP means that the actual class is negative and the model predicts it is positive; TN means that the actual class is negative and the model predicts it is also negative; FN means that the actual class is positive and the model predicts it is negative.

[0209] In order to evaluate the superiority of this application, in addition to evaluating this model, comparative experiments were conducted with other advanced CDR methods. The results are shown in Tables 1 and 2. In addition, Table 3 shows the 20 cell line-drug pairs with the highest probability in the prediction results, of which 19 pairs have been experimentally confirmed and 1 pair has not yet been experimentally verified. The results demonstrate the excellent predictive ability of this application:

[0210] Table 1. Comparison of independent test performance on the GDSC dataset

[0211]

[0212] Table 2 Independent test performance comparison results on the CCLE dataset

[0213]

[0214] Table 3 Predicted top 20 cell line-drug pairs with the highest correlation probability

[0215]

[0216]

Claims

1. A method for predicting anticancer drug response based on heterogeneous and homomorphic multi-branching, characterized in that: The method comprises the following steps: S1: Preprocess the data to obtain cell line multi-omics data, drug substructure fingerprint data, drug molecular graph data, and cell line-drug reaction data; S2: Build a similarity global feature extraction module to extract features and obtain cell line similarity features, drug similarity features, and drug global features; S2 includes the following steps: S2.1: Perform similarity fusion on the multi-omics data of cell lines to obtain cell line similarity signatures. The multi-omics data of cell lines include gene expression, copy number variation, and somatic mutation data. S2.2: Calculate drug similarity features based on drug substructure fingerprints; S2.3: Calculate the global characteristics of the drug based on the drug's molecular graph data; S3: Construct a heterogeneous and homogeneous multi-branch feature extraction module to extract the cell line similarity features and drug similarity features to obtain multi-branch cell line features and multi-branch drug features; S3 includes the following steps: S3.1: Extract features of cell line similarity features and drug similarity features. By fusing features of subgraphs of different scales, we obtain branch features of cell line subgraphs and branch features of drug subgraphs respectively. S3.2: Extract cell line similarity features and drug similarity features through message passing to obtain cell line heterogeneous branch features and drug heterogeneous branch features respectively; S3.3: Extract features from the cell line isomorphism graph to obtain cell line isomorphism branch features; S3.4: Extract features from the drug isomorphism graph to obtain drug isomorphism branch features; Among them, S3.1 includes the following steps: By downsampling, we construct subgraphs of different scales, extract features from the subgraphs, and fuse the features of subgraphs of different scales to obtain the branch features f of the cell line subgraphs. UC and drug subgraph branch features f UD , the operation is described as: y=X l p l / ||p l || idx=rank(y,k) A l+1 =A l (idx,idx) X l represents the node features of the lth layer, p l is a trainable vector, ||p l || represents vector p l The length of X, y is l In the vector p l The projection scalar value on , rank(y,k) means selecting the largest k values ​​from y, and idx records the subscript of the largest k values. is the node feature corresponding to k nodes, A l+1 is the adjacency matrix of the corresponding nodes, W l is the weight matrix of layer l, H (l+1) is the updated node feature, σ is the activation function; Among them, S3.2 includes the following steps: In the cell line-drug heterogeneous graph, feature extraction is performed using message passing, and the cell line heterogeneous branch features f are obtained. Hec and drug isomeric branching characteristics f HeD , the operation is described as: here represents the normalized adjacency matrix, σ is the activation function; S3.3 includes the following steps: The cell line isomorphism branch features f are extracted using message passing in the cell line isomorphism graph. HoC , the operation is described as: A c =A*A T A is the cell line-drug response matrix, D c It's A c The degree matrix of is the normalized adjacency matrix in the cell line isomorphism graph, and σ is the activation function; Among them, S3.4 includes the following steps: The drug isomorphism branch feature f is extracted using message passing in the drug isomorphism graph HoB , the operation is described as: A d =A T *A A is the cell line-drug response matrix, D d It's A d The degree matrix of is the normalized adjacency matrix in the drug isomorphism graph, and σ is the activation function; S4: Construct a multi-branch multi-layer fusion module to fuse the multi-branch cell line features to obtain the cell line fusion feature, fuse the global drug feature and the multi-branch drug feature to obtain the drug fusion feature, and calculate the correlation between the two; S5: Use the correlation to predict the reaction between cell lines and drugs and output the prediction results.

2. The method for predicting anticancer drug response based on heterogeneous and homomorphic multi-branching according to claim 1, characterized in that: S1 includes the following steps: S1.1: Cell line-drug response tables collected in the GDSC and CCLE databases; S1.2: Based on the response table, gene expression, copy number variation, and somatic mutation data of the cell lines were collected from the GDSC and CCLE databases, respectively; S1.3: Cell lines with all three modalities were screened, and data for 962 and 436 cell lines were obtained in GDSC and CCLE, respectively. S1.4: Obtain the PubChemID for each drug based on the cell line-drug reaction table; S1.5: Based on the PubChem ID, the SMILES sequence of the drug was obtained from the PubChem library; S1.6: Use the RDKit toolkit to obtain the substructure fingerprint and molecular graph data corresponding to the drug based on the SMILES sequence of the drug.

3. The method for predicting anticancer drug response based on heterogeneous and homomorphic multi-branching according to claim 1, characterized in that: S2 includes the following steps: S2.1: Perform similarity fusion on the multi-omics data of cell lines to obtain cell line similarity signatures. The multi-omics data of cell lines include gene expression, copy number variation, and somatic mutation data. S2.2: Calculate drug similarity features based on drug substructure fingerprints; S2.3: Calculate the global characteristics of the drug based on the drug's molecular graph data; S2.1 includes the following steps: The gene expression data is Gaussian regularized, which is described as: exp i represents the expression value of the i-th gene in the cell line, represents the regularized expression value of the i-th gene, μ i and δ i represent the mean and standard deviation of the expression of the ith gene in all cell lines, respectively; Calculate the similarity of each omics data of the cell line separately. The operation is described as: x i and x j denote the specific omics data of the i-th cell line and the j-th cell line, 1≤i,j≤962, ||||2 denotes the second normal form, ε is a hyperparameter, E ij Indicates the similarity of specific omics data in cell lines; The full kernel matrix F and sparse kernel matrix S are calculated for each omics data. The operation is described as: N i represents the top N cell lines most similar to the i-th cell line; According to the calculated full-nuclear matrix GF and sparse-nuclear matrix GS of gene expression, full-nuclear matrix CF and sparse-nuclear matrix CS of copy number variation, full-nuclear matrix MF and sparse-nuclear matrix MS of somatic mutation, let GF0=GF, CF0=CF, MF0=MF, and iteratively update the full-nuclear matrix. The operation is described as: t represents the number of iterations, * T Indicates transposing the matrix* Finally, the cell line similarity feature RC is obtained, and the calculation formula is as follows: Among them, S2.2 includes the following steps: According to the substructure fingerprint of the drug, the Tanimoto similarity is calculated to obtain the drug similarity feature RD. The operation is described as: d i and d j Represent the substructure fingerprints of the i-th and j-th drugs, respectively, 1≤i,j≤228; Among them, S2.3 includes the following steps: Extract features from the drug's molecular graph to obtain the drug's global features f molD , the operation is described as: is the feature of node i in the k+1 layer, represents the set of neighbor nodes of node i, W (k) is the weight matrix of the kth layer, σ is the activation function, is the attention coefficient between node i and its neighbor node j, and is calculated as follows: α (k) is the learned attention weight vector, || represents the concatenation operation, and LeakyRelu is the activation function.

4. The method for predicting anticancer drug response based on heterogeneous and homomorphic multi-branching according to claim 1, characterized in that: S4 includes the following steps: S4.1: Fusion of cell line branch characteristics yields cell line fusion characteristics; The drug fusion characteristics are obtained by integrating the characteristics of each branch of the drug and the global characteristics of the drug; S4.2: Perform linear transformation on cell line fusion signatures and drug fusion signatures to adjust them to the same dimension. S4.3: Calculate the correlation between the adjusted cell line fusion signature and the drug fusion signature; Among them, S4.1 includes the following steps: The cell line subgraph branch features f UC , cell line heterogeneous branching characteristicsf HeC , cell line isomorphic branch characteristics f HoC Fusion to obtain cell line fusion characteristics H 1-c , the drug subgraph branch feature f UD , drug isomerization branch characteristics f HeD , drug isomorphic branch characteristics f HoD , drug global characteristics f molD Fusion to obtain drug fusion feature H 1-d , the operation is described as: H 1-c =(f UC +f HeC +f HoC ) / 3 H 1-d =((f UD +f HeD ) / 2+f HoD +f molD ) / 3 Among them, S4.2 includes the following steps: The cell line fusion features and drug fusion features are adjusted to the same dimension through linear transformation, and then the correlation between the two after transformation is calculated. This operation is described as: H (2-c) =H (1-c) W (2-c) H (2-d) =H (1-d) W (2-d) Here, W (2-c) ∈R c*k and W (2-d) ∈R d*k are the weight matrices for linear transformation of cell lines and drugs, c is the dimension of cell line fusion features, d is the dimension of drug fusion features, k represents the feature dimension after linear transformation, H (2-c) and H (2-d) They are the k-dimensional cell line fusion features and k-dimensional drug fusion features after linear transformation; Among them, S4.3 includes the following steps: Calculate the correlation between the k-dimensional cell line fusion features and the k-dimensional drug fusion features. The operation is described as: h i is the i-th cell line feature in the k-dimensional cell line fusion feature, h j is the jth drug feature in the k-dimensional drug fusion feature, μ i and μ j They are h i and h j The mean of , 1≤i≤962, 1≤j≤228.

5. The method for predicting anticancer drug response based on heterogeneous and homomorphic multi-branching according to claim 1, characterized in that: S5 includes the following steps: S5.1: Perform sigmoid activation on the correlation results and output the prediction results; S5.1 includes the following steps: The correlation coefficient calculated by S4 is in the range of [-1, 1]. The sigmoid function is used for activation output to ensure that the predicted probability value of each cell line-drug sensitivity pair is in the range of [0, 1]. The cell line-drug response matrix is ​​obtained. The operation is described as follows: h is the correlation coefficient, γ is the predicted cell line-drug response matrix, and α is a hyperparameter used to accelerate parameter updates.

Images