Construction, prediction method and device of multimodal comparative drug synergy prediction model

Abstract

A method for constructing a multimodal comparative drug synergy prediction model, a prediction method, and an apparatus, the construction method comprising: obtaining first and second modal features representing drug-drug-cell line triplet information in the same dimension in two different modalities based on entity embedding features and phenotypic features of multiple drugs and cell lines; determining sample positive pairs, sample negative pairs, and sample semi-positive pairs based on the effectiveness prediction results of preset real samples after predicting drug synergy based on each feature sample in the first and second modal features, and further determining a target loss function; and then determining multiple models based on the loss function. Through the above method, it is possible to effectively reduce the impact of invalid features that have no effect or have a negative impact on drug synergy prediction in any modality on drug prediction, avoiding the problem in related technologies where each modality adopts an equal treatment strategy that affects the accuracy of the prediction results.

Description

Technical Field

[0001] The present application relates to the field of drug synergy prediction, and specifically to the construction, prediction method and device of a multi-modal comparative drug synergy prediction model. Background Art

[0002] In cancer treatment, cancer cells exhibit complex compensatory mechanisms that significantly increase the likelihood of developing resistance to single-drug therapy, becoming the greatest obstacle to single-drug treatment. Therefore, drug combination therapy has become a better approach to cancer treatment, as it can reduce toxicity and mitigate drug resistance.

[0003] Combination therapy involves the use of two or more drugs to enhance the therapeutic effect of cancer. However, not all drug combinations are synergistic; drugs with antagonistic effects may cause unnecessary harm to patients. To optimize treatment options, enhance clinical efficacy, and ensure patient safety, it is essential to systematically identify and validate synergistic drug combinations.

[0004] Multimodal data provides information about different aspects of drugs, and integrating multimodal data can further improve the performance of prediction models. SynergyX, an existing multimodal method in the field of drug synergy prediction, introduces a mutual attention mechanism into the drug synergy prediction process to introduce multi-dimensional cross-modal interactions. The network is characterized by a "sandwich"-like module consisting of multiple mutual attention modules and self-attention modules, which allows the extraction of drug-cell and drug-drug interactions. These methods focus on integrating multiple phenotypic characteristics of drugs and cell lines to form a more effective joint representation for drug synergy prediction. However, this method usually tends to integrate features of different modalities with equal weights and extract multimodal representations through techniques such as aggregation or contrast fusion, but often ignores the negative effects that may be caused by invalid single-modal features. Summary of the Invention

[0005] The present application provides a construction, prediction method and device of a multi-modal comparative drug synergy prediction model, which can solve the related technical problems existing in the above-mentioned prior art.

[0006] In a first aspect, the present invention provides a method for constructing a multi-modal comparative drug synergy prediction model, which employs the following technical solutions:

[0007] A method for constructing a multi-modal comparative drug synergy prediction model, the method comprising:

[0008] Obtaining phenotypic characteristics of the first drug, the second drug, and the cell line;

[0009] Obtaining entity embedding features corresponding to the first drug, the second drug, and the cell line according to a heterogeneous graph consisting of drugs, targets, and cell lines involved in the first drug, the second drug, and the cell line and a preset first model;

[0010] According to the entity embedding feature and the phenotypic feature, a first modality feature and a second modality feature of two different modalities representing drug-drug-cell line triple information in the same dimension are obtained;

[0011] Obtaining a prediction result of the effectiveness of a preset real sample after predicting drug synergy based on each feature sample in the first modal feature and the second modal feature using a preset prediction model;

[0012] If the prediction results of the two feature samples corresponding to the same real sample in the first modal feature and the second modal feature are both correct, then both are determined to be sample positive pairs; if both are wrong, then both are determined to be sample negative pairs; if only one of them is correct, then both are determined to be sample semi-positive pairs;

[0013] Determining a target loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs;

[0014] Determine whether the target loss function meets the preset requirements. If not, adjust the multiple models used in the previous step and calculate the target loss function again. If it meets the requirements, determine that the multiple models used this time are combined to form a multi-modal comparative drug synergistic prediction model.

[0015] In combination with the first aspect, in one embodiment, in determining the target loss function based on the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs,

[0016] A target loss function is determined according to the cosine similarity of the sample positive pairs, the sample negative pairs and the sample semi-positive pairs and a preset temperature coefficient.

[0017] In combination with the first aspect, in one embodiment, the target loss function is determined based on the cosine similarity of the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs and a preset temperature coefficient, using the following formula:

[0018]

[0019] Where n is a paired feature sample of the first modal feature and the second modal feature, P is a set of positive pairs, S is a set of semi-positive pairs, and B is the set of all sample positive pairs, sample negative pairs, and the sample semi-positive pairs. is the first modal feature, is the second mode characteristic, and τ is the temperature coefficient.

[0020] In combination with the first aspect, in one embodiment, determining the target loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs includes the following steps:

[0021] Determining a first loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs;

[0022] Determining a second loss function based on the effectiveness prediction results of drug synergy predictions performed on each feature sample in the first modal feature and the second modal feature relative to preset real samples using the prediction model;

[0023] Determining a third loss function based on the effectiveness prediction result of drug synergy prediction relative to a preset real sample after using the prediction model to predict the fusion feature obtained by concatenating the first modal feature and the second modal feature;

[0024] The target loss function is determined based on at least the first loss function, the second loss function, and the third loss function.

[0025] In combination with the first aspect, in one embodiment, the second loss function is determined by using the following formula to predict the effectiveness of the drug synergy prediction relative to the preset real samples after using the prediction model for each feature sample in the first modal feature and the second modal feature:

[0026]

[0027] Among them, y k is the label of the kth sample in the first modal feature and the second modal feature, is the softmax output of the kth sample in the corresponding modality feature i.

[0028] In combination with the first aspect, in one embodiment, the third loss function is determined based on the effectiveness prediction result of the drug synergy prediction relative to the preset real sample after the fusion feature obtained by concatenating the first modal feature and the second modal feature is used using the prediction model, and the following formula is used:

[0029]

[0030] Among them, y k is the predicted value of the kth sample, p k is the softmax output of the kth sample in the fusion feature.

[0031] In combination with the first aspect, in one embodiment, obtaining, based on the entity embedding feature and the phenotypic feature, a first modal feature and a second modal feature representing drug-drug-cell line triple information in two different modalities in the same dimension includes the following steps:

[0032] Different types of drugs and cell line features are dimensionally aligned according to the preset projection equation;

[0033] Obtaining a first basic modality feature and a second basic modality feature for representing drug-drug-cell line triplet connection information according to the entity embedding feature and the phenotypic feature;

[0034] Based on the first basic modal feature, the second basic modal feature and the preset second model, potential features that have an impact on drug synergy are determined from both the first basic modal feature and the second basic modal feature, and the first modal feature and the second modal feature are obtained based on the potential features of the two.

[0035] In a second aspect, the present invention provides a multi-modal comparative drug synergy prediction method based on the model constructed by the above-described construction method, which adopts the following technical solutions:

[0036] A multi-modal comparative drug synergy prediction method, comprising the following steps:

[0037] Obtaining phenotypic characteristics of target drug 1, target drug 2, and target cell line 3;

[0038] Obtaining entity embedding features corresponding to the target drug one, the target drug two, and the target cell line according to a heterogeneous graph consisting of drugs, targets, and cell lines involved in the target drug one, the target drug two, and the target cell line and the first model;

[0039] According to the entity embedding feature and the phenotypic feature, a modal feature 1 and a modal feature 2 for representing drug-drug-cell line triplet information in two different modalities in the same dimension are obtained;

[0040] Concatenating the modal feature 1 and the modal feature 2 to form a fusion feature;

[0041] Drug synergy prediction is performed on each feature sample in the fusion feature according to the prediction model to determine whether the target drug 1 and the target drug 2 have synergistic effect in the target cell line.

[0042] In a third aspect, the present invention provides a device for constructing a multi-modal comparative drug synergy prediction model, which employs the following technical solutions:

[0043] A device for constructing a multi-modal comparative drug synergy prediction model, the device comprising:

[0044] A phenotypic characteristic acquisition module configured to acquire phenotypic characteristics of the first drug, the second drug, and the cell line;

[0045] an entity embedding feature acquisition module configured to acquire entity embedding features corresponding to the first drug, the second drug, and the cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the first drug, the second drug, and the cell line and a preset first model;

[0046] a single-modal feature representation module configured to obtain, based on the entity embedding feature and the phenotypic feature, a first modal feature and a second modal feature representing information about a drug-drug-cell line triplet in two different modalities in the same dimension;

[0047] A single-modal feature guided learning module is configured to obtain the effectiveness prediction results of the preset prediction model after predicting the drug synergy of each feature sample in the first modal feature and the second modal feature relative to the preset real sample; if the prediction results of the two feature samples corresponding to the same real sample in the first modal feature and the second modal feature are both correct, then both are determined to be sample positive pairs; if both are wrong, then both are determined to be sample negative pairs; if only one of them is correct, then both are determined to be sample semi-positive pairs; based on the sample positive pairs, sample negative pairs and sample semi-positive pairs, a target loss function is determined; whether the target loss function meets the preset requirements is judged; if not, the multiple models used in the previous step are adjusted and the target loss function is calculated again; if it meets, it is determined that the multiple model combination used this time constitutes a multi-modal comparative drug synergy prediction model.

[0048] In a fourth aspect, the present invention provides a prediction device for a multi-modal comparative drug synergy prediction method, which adopts the following technical solutions:

[0049] A prediction device for implementing the above-mentioned multi-modal comparative drug synergy prediction method, comprising:

[0050] a phenotypic characteristic module configured to obtain phenotypic characteristics of target drug 1, target drug 2, and target cell line;

[0051] an entity embedding feature module, which obtains entity embedding features corresponding to the target drug 1, the target drug 2, and the target cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the target drug 1, the target drug 2, and the target cell line and the first model;

[0052] A multimodal fusion prediction module is configured to obtain modal feature one and modal feature two representing drug-drug-cell line triple information in two different modalities in the same dimension based on the entity embedding feature and the phenotypic feature; concatenate the modal feature one and modal feature two to form a fusion feature; predict drug synergy for each feature sample in the fusion feature according to the prediction model, and determine whether the target drug one and the target drug two have synergistic effect in the target cell line.

[0053] The beneficial effects of the technical solutions provided in the embodiments of the present application include:

[0054] By obtaining the phenotypic characteristics and entity embedding characteristics corresponding to the first drug, the second drug and the cell line, the feature representation of the drug-drug-cell line connection information under the two modalities is obtained, namely the first modal feature and the second modal feature. Subsequently, the two modal features are further used to predict the drug synergy separately to confirm whether each sample in the first modal feature and the second modal feature is valid, and the sample positive pairs that can be correctly predicted under both modalities, the sample semi-positive pairs that can be correctly predicted only under one modality, and the sample negative pairs that cannot be correctly predicted under both modalities are clearly identified. The sample positive pairs, sample semi-positive pairs and sample negative pairs are further calculated to obtain the target loss function for adjusting the model used. The obtained target loss function can effectively reduce the impact of invalid features that have no effect or have a negative impact on the prediction of drug synergy in any modality on drug prediction in the process of training and constructing the final prediction model, avoiding the problem of affecting the accuracy of the prediction results due to the equal treatment strategy of each modality in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a flow chart of an embodiment of a method for constructing a multi-modality comparative drug synergy prediction model of the present application;

[0056] Figure 2 This is a schematic diagram of the functional modules of an embodiment of a device for constructing a multi-modality comparative drug synergy prediction model of the present application;

[0057] Figure 3 This is a flow chart of an embodiment of the multi-model comparative drug synergy prediction method of the present application;

[0058] Figure 4 This is a schematic diagram of the functional modules of an embodiment of the multi-model comparative drug synergy prediction device of the present application. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0061] Combination therapy involves the use of two or more drugs to enhance the therapeutic effect of cancer. However, not all drug combinations are synergistic; drugs with antagonistic effects may cause unnecessary harm to patients. To optimize treatment options, enhance clinical efficacy, and ensure patient safety, it is essential to systematically identify and validate synergistic drug combinations.

[0062] Multimodal data provides information about different aspects of drugs, and integrating multimodal data can further improve the performance of prediction models. SynergyX, an existing multimodal method in the field of drug synergy prediction, introduces a mutual attention mechanism into the drug synergy prediction process to introduce multi-dimensional cross-modal interactions. The network is characterized by a "sandwich"-like module consisting of multiple mutual attention modules and self-attention modules, which allows the extraction of drug-cell and drug-drug interactions. These methods focus on integrating multiple phenotypic characteristics of drugs and cell lines to form a more effective joint representation for drug synergy prediction. However, this method usually tends to integrate features of different modalities with equal weights and extract multimodal representations through techniques such as aggregation or contrast fusion, but often ignores the negative effects that invalid single-modal features may bring.

[0063] Based on the above problems, the present application provides a method for constructing a multimodal comparative drug synergy prediction model, a prediction method and a device. The key point of the invention is that a multimodal comparative drug synergy prediction model that can effectively predict drug synergy is constructed using the provided method for constructing a multimodal comparative drug synergy prediction model. In the process of constructing the method, by obtaining the phenotypic characteristics and entity embedding characteristics corresponding to the first drug, the second drug and the cell line, the characteristic representation of the drug-drug-cell line connection information under the two modalities is obtained, namely the first modal characteristics and the second modal characteristics. Subsequently, the two modal characteristics are further used to predict the drug synergy separately to confirm whether each sample in the first modal characteristics and the second modal characteristics is valid, and the sample positive pairs that can be correctly predicted in both modalities, the sample semi-positive pairs that can be correctly predicted in only one modality, and the sample negative pairs that cannot be correctly predicted in both modalities are clarified. The sample positive pairs, sample semi-positive pairs and sample negative pairs are further calculated to obtain the target loss function for adjusting the model used. The obtained target loss function can effectively reduce the impact of invalid features that have no effect or have a negative impact on the prediction of drug synergy in any modality on drug prediction in the process of training and constructing the final prediction model, avoiding the problem of affecting the accuracy of the prediction results due to the equal treatment strategy of each modality in the related technology.

[0064] In a first aspect, an embodiment of the present application provides a method for constructing a multi-modal comparative drug synergy prediction model.

[0065] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for constructing a multi-modal comparative drug synergy prediction model of this application. Figure 1 As shown, the method for constructing a multi-modal comparative drug synergy prediction model includes the following steps:

[0066] S100, obtaining phenotypic characteristics of the first drug, the second drug, and the cell line;

[0067] Specifically, the process of obtaining the phenotypic characteristics of the first drug, the second drug, and the cell line will first obtain the SMILES strings of the two drugs, and then use the method in RDKit to calculate the molecular fingerprint. This method represents the molecular structure as a series of atom pairs and hashes each atom pair to generate a unique fingerprint. These fingerprints are converted into bit vectors to represent the characteristics of the drug molecules, marked as For the phenotypic characteristics of cell lines, gene expression characteristics are directly used, marked as

[0068] S200, obtaining entity embedding features corresponding to the first drug, the second drug, and the cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the first drug, the second drug, and the cell line and a preset first model;

[0069] The specific process of using the first model to obtain entity embedding features is as follows:

[0070] Get a heterogeneous graph consisting of two drugs, targets, and cell lines, represented as It contains multiple entity types and multiple relationship types. Represent object set, edge set, node type set and edge type set respectively,

[0071] The heterogeneous graph consists of three nodes, drug (D), protein (P), and cell line (C), and five edges. and For each of the five subgraphs with different relationships, a graph attention network (GATConv) is used to learn node embedding features for each subgraph. HeteroConv in the graph attention network allows different convolution operations to be applied to different types of edges, thereby performing effective message passing and feature aggregation in heterogeneous graphs.

[0072]

[0073] Each biological entity node v i (1≤i≤N n ) is represented as a vector where N n =|V| represents the number of biological entity nodes; d represents the feature dimension. Thus, a biological entity node feature matrix is ​​obtained h i =H[i,:]. GATCov is one of the core components of GAT, which improves the learning ability of the model by introducing an attention mechanism to dynamically assign weights to the neighbors of each node.

[0074] For each node v, GATCnv calculates the attention coefficient α between it and its neighbor node u v，u These coefficients are calculated using the following formula:

[0075]

[0076] Where W is the learnable weight matrix, a is the parameter vector in the attention mechanism, and h v and h u are the feature vectors of nodes v and u respectively.

[0077] The new representation of a node is obtained by weighting the features of its neighboring nodes:

[0078]

[0079] Where σ is the activation function, is the neighboring node of node v.

[0080] For each subgraph, the corresponding feature matrix H″ will be obtained after two learnings D-p , H″ P-D , H″ P-P ,H″ C-P and H″ P-C Finally, the features of the corresponding nodes in each subgraph are summed up as the final entity embedding features of each node in the heterogeneous graph.

[0081] H″=H″ D-P +H″ P-D +H″ P-P +H″ C-P +H″ P-C (4)

[0082] Finally, the drug representation is extracted from H″ and cell line expression They are respectively used as the entity embedding features of the two drugs and the entity embedding features of the cell lines.

[0083] S300, obtaining, based on the entity embedding feature and the phenotypic feature, a first modal feature and a second modal feature of two different modalities representing drug-drug-cell line triple information in the same dimension;

[0084] Specifically, in this embodiment, step S300 includes the following steps:

[0085] S310, dimensionally aligning drug and cell line features of different types, i.e., phenotypic feature modalities and entity embedded feature modalities, according to a preset projection equation;

[0086] The projection equation used is:

[0087] g(x)=σ(Wx+b) (5)

[0088] Where W is the weight, b is the bias, and σ is the activation function ReLU. The projection equation can be obtained: Represents phenotypic characteristics of drugs and cell lines. Entity embedding features representing the corresponding entity feature modality.

[0089] S320: Obtain a first basic modality feature and a second basic modality feature representing drug-drug-cell line triple connection information based on the entity embedding feature and the phenotypic feature;

[0090] After obtaining the phenotypic features and real embedding features, we obtain the triplet information representing the connection information of the drug-drug-cell line triplet in each dimension of the two modalities: and They are concatenated into the first basic modal feature and the second basic modal feature respectively.

[0091]

[0092] S330. Based on the first basic modal feature, the second basic modal feature and a preset second model, determine potential features that have an impact on drug synergy from both the first basic modal feature and the second basic modal feature, and obtain the first modal feature and the second modal feature based on the potential features of the two.

[0093] Previous work has mostly concatenated the features of drug A, drug B, and cell line and fed them directly into the classifier for prediction. However, this simple concatenation of features from different entities fails to capture potential connection information. In this embodiment, to obtain more effective joint features, the Highway Network is used for processing in step S330. The core of this process is the introduction of two gating mechanisms. These two gating mechanisms determine how information is transmitted and modified as it passes through the network layer. The mathematical formulas are as follows:

[0094]

[0095] Non_linear uses the ReLU activation function. T represents the transformation gate, σ represents the sigmoid activation function, and C = 1-T represents the carry gate. It captures the combined features The combined features of the potential features. Ultimately, the first modal features and the second modal features under the two modalities are formed.

[0096] S400: Obtaining effectiveness prediction results of a preset real sample after predicting drug synergy using a preset prediction model for each feature sample in the first modal feature and the second modal feature;

[0097] Specifically, the first modal features and the second modal features under the two modes obtained in the above steps are used As the input of the unimodal prediction task, the preset prediction model in this embodiment specifically uses a multi-layer perceptron (MLP) as a unimodal classifier, and the mathematical formula is as follows:

[0098]

[0099] When the prediction results When the relative true sample is correct, It is considered to be an effective feature that has a positive effect on the prediction results, otherwise It is considered an invalid feature.

[0100] S500: If the prediction results of the two feature samples corresponding to the same real sample in the first modal feature and the second modal feature are both correct, then both are determined to be sample positive pairs; if both are incorrect, then both are determined to be sample negative pairs; if only one of them is correct, then both are determined to be sample semi-positive pairs;

[0101] Specifically, after step S400, there are three situations: When all are valid features, they are considered as positive pairs, and the set of all positive pairs is represented as P. and When both are invalid features, we regard them as negative pairs and record them as N. When one of them is a valid feature and the other is an invalid feature, we regard it as a semi-positive pair, denoted by S.

[0102] S600, determining a target loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs;

[0103] Specifically, in this embodiment, the target loss function is determined based on the cosine similarity of the sample positive pair, the sample negative pair, and the sample semi-positive pair and a preset temperature coefficient, using the following formula:

[0104]

[0105] Where n is a paired feature sample of the first modal feature and the second modal feature, P is a set of positive pairs, S is a set of semi-positive pairs, and B is the set of all sample positive pairs, sample negative pairs, and the sample semi-positive pairs. is the first modal feature, is the second mode characteristic, and τ is the temperature coefficient.

[0106] S700. Determine whether the target loss function meets the preset requirements. If not, adjust the multiple models used in the previous step and recalculate the target loss function. If it meets the requirements, determine that the multiple models used this time are combined to form a multi-modal comparative drug synergistic prediction model.

[0107] Specifically, by determining the target loss function based on the sample positive pairs, the sample negative pairs and the sample semi-positive pairs, and then using the target loss function to adjust the multiple models used in the aforementioned steps, that is, the first model, the second model and the prediction model used in the above text, during the adjustment process, for the positive pairs, we can align them with each other. For the semi-positive pairs, the adjusted models can be aligned to a more effective modality to reduce the negative impact of the invalid modality on the prediction results. For the negative pairs, the adjusted models can maximize the difference between the two modalities and capture the complementary information of the multimodal as much as possible.

[0108] Furthermore, in some embodiments, the process of determining the target loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs in step S600 includes the following steps:

[0109] S610. Determine a first loss function based on the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs; wherein the first loss function is the loss function calculated by the formula (10) described above.

[0110] S620: Determine a second loss function based on the effectiveness prediction results of drug synergy prediction using the prediction model for each feature sample in the first modal feature and the second modal feature relative to a preset real sample. Specifically, the second loss function is determined using the following formula:

[0111]

[0112] Among them, y k is the label of the kth sample in the first modal feature and the second modal feature, is the softmax output of the kth sample in the corresponding modality feature i.

[0113] S630, determining a third loss function based on the effectiveness prediction result of drug synergy prediction relative to a preset real sample after using the prediction model to predict the fusion feature obtained by concatenating the first modal feature and the second modal feature;

[0114] Specifically, all the multimodal features that have passed the comparison module, namely the first modal features and the second modal features, are connected in series to obtain the fusion features, which are expressed as Then, based on the prediction model, the fusion features are predicted using the formula (9) mentioned above, and the third loss function is calculated for the prediction results using the following formula:

[0115]

[0116] Among them, y k is the predicted value of the kth sample, p kis the softmax output of the kth sample in the fusion feature. S640, determine the target loss function based on at least the first loss function, the second loss function and the third loss function. That is:

[0117]

[0118] In addition, since the dropout mechanism randomly drops some neurons during each pass, in order to improve the robustness of the model, we use the model to output two different prediction values and Regularized dropout (R-drop) regularizes the output predictions by minimizing the Kullback-Leibler (KL) divergence between the two output distributions, which is calculated as follows:

[0119]

[0120] Finally, the expression of the objective loss function is further optimized as follows:

[0121]

[0122] Finally, to demonstrate the superiority of the model ultimately obtained by this construction method, we conducted comparative experiments with the following advanced deep learning models:

[0123] HypergraphSynergy: Using biochemical features of drugs and cell lines as node attributes, it captures and explains multidirectional relationships between drug combinations and cell lines through a hypergraph, and finally predicts drug synergy through a multilayer perceptron.

[0124] MatchMaker: Two parallel subnetworks are designed, one for each drug, to learn drug-specific representations on specific cell lines. The joint representation of drug pairs becomes the input to the third subnetwork, which learns to predict the synergistic effects of drug pairs.

[0125] KGANSynergy uses the layered propagation of KG to find the neighbors of drugs / cell lines, and then uses the attention network to obtain the corresponding neighborhood representation of drugs or cell lines. A well-defined scoring function is then used to obtain the prediction score of potential synergy.

[0126] About the experimental setup:

[0127] In this example, the collaborative dataset was first randomly shuffled and divided into a cross-validation set and an independent test set at a ratio of 9:1. Five-fold cross-validation was used to train the prediction model on the cross-validation set. The five best-performing results from the cross-validation phase were then tested on the independent test set to evaluate the performance of the prediction model.

[0128] In addition, three practical scenarios on the cross-validation set are considered.

[0129] 1. Random division: The cross-validation set is randomly divided into 5 equal parts. This simulates the prediction of drug combinations that may have synergistic effects when anticancer drugs and cancer cell lines are known.

[0130] 2. Cell Line-Level Partitioning: Perform randomized partitioning at the cell line level. Use a subset of cell lines from the collaborative dataset as a validation set to ensure that these cell lines are not included in the training set. Simulate the model's response to the introduction of new cell lines and evaluate its predictive power for unseen cell lines.

[0131] 3. Drug combination-level partitioning: Random partitioning was performed at the drug combination level. A subset of drug pairs in the synergy dataset was used as a validation set to ensure that these drug combinations were not present in the training set. This examined the model's adaptability and accuracy when encountering novel drug combinations.

[0132] To obtain more objective results, we used independent test sets to evaluate the performance of the model and the baseline under all three partitioning methods. We used the following five metrics to measure model performance: accuracy (ACC), area under the receiver operating characteristic curve (ROC-AUC), precision (Prec), recall (Rec), and F1 score. The evaluation metrics were calculated as follows:

[0133]

[0134] Where TP is true positive, TN is true negative, FP is false positive, and FN is false negative. Using these evaluation metrics, we can accurately and comprehensively evaluate our prediction model.

[0135] We evaluated the performance of our model in three practical scenarios on the DrugCombDB and OncologyScreen datasets. Table 1 shows that our method outperforms the other three advanced methods in all performance indicators in the random partitioning scenario, and surpasses the best baseline model HypergraphSynergy, with an ACC score 1.69% higher and a ROC-AUC score 2.44% higher, demonstrating the powerful ability of our method in predicting synergistic drug combinations on large datasets. In terms of cell line-level and drug combination-level partitioning, our model's performance is also largely superior to that of the other baseline models, indicating that our model also has the best predictive performance when encountering unknown cell lines and drug combinations. Table 2 shows the performance of our model on small-scale datasets. The results show that KGANSynergy is more adaptable to small-scale datasets and has the best prediction effect. However, the overall performance of our model is second only to this baseline model.

[0136] Table 1: Performance comparison of MCDSP and baselines on the DrugCombDB dataset

[0137]

[0138] The first, second, and third rows of each method correspond to randomization, cell line-level partitioning, and drug combination-level partitioning, respectively.

[0139] Table 2: Performance comparison of MCDSP and baselines on the OncologyScreen dataset

[0140]

[0141] The first, second, and third rows of each method correspond to randomization, cell line-level partitioning, and drug combination-level partitioning, respectively.

[0142] In a second aspect, an embodiment of the present application further provides a device for constructing a multi-modal comparative drug synergy prediction model, the device comprising:

[0143] A phenotypic characteristic acquisition module configured to acquire phenotypic characteristics of the first drug, the second drug, and the cell line;

[0144] an entity embedding feature acquisition module configured to acquire entity embedding features corresponding to the first drug, the second drug, and the cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the first drug, the second drug, and the cell line and a preset first model;

[0145] a single-modal feature representation module configured to obtain, based on the entity embedding feature and the phenotypic feature, a first modal feature and a second modal feature representing information about a drug-drug-cell line triplet in two different modalities in the same dimension;

[0146] A single-modal feature guided learning module is configured to obtain the effectiveness prediction results of the preset prediction model after predicting the drug synergy of each feature sample in the first modal feature and the second modal feature relative to the preset real sample; if the prediction results of the two feature samples corresponding to the same real sample in the first modal feature and the second modal feature are both correct, then both are determined to be sample positive pairs; if both are wrong, then both are determined to be sample negative pairs; if only one of them is correct, then both are determined to be sample semi-positive pairs; based on the sample positive pairs, sample negative pairs and sample semi-positive pairs, a target loss function is determined; whether the target loss function meets the preset requirements is judged; if not, the multiple models used in the previous step are adjusted and the target loss function is calculated again; if it meets, it is determined that the multiple model combination used this time constitutes a multi-modal comparative drug synergy prediction model.

[0147] Among them, the functional implementation of each module in the above-mentioned multi-modal comparative drug synergistic prediction model construction device corresponds to the various steps in the above-mentioned multi-modal comparative drug synergistic prediction model construction method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0148] In a third aspect, an embodiment of the present application further provides a multimodal comparative drug synergy prediction method based on the model constructed by the method for constructing the multimodal comparative drug synergy prediction model as described above, the prediction method comprising the following steps:

[0149] F100, obtain the phenotypic characteristics of target drug 1, target drug 2, and target cell line 3;

[0150] F200. Obtain entity embedding features corresponding to the target drug 1, the target drug 2, and the target cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the target drug 1, the target drug 2, and the target cell line and the first model;

[0151] F300, obtaining modal feature 1 and modal feature 2 for representing drug-drug-cell line triplet information in two different modalities in the same dimension based on the entity embedding feature and the phenotypic feature;

[0152] Specifically, the following steps are included:

[0153] F310, dimensionally align different types of drug and cell line features according to the preset projection equation;

[0154] F320. Obtaining a first basic modality feature and a second basic modality feature representing drug-drug-cell line triple connection information based on the entity embedding feature and the phenotypic feature;

[0155] F330. Based on the first basic modal features, the second basic modal features and the trained second model, determine the potential features that have an impact on drug synergy from both the first basic modal features and the second basic modal features, and obtain the first modal features and the second modal features based on the potential features of the two.

[0156] F400, concatenating the modal feature 1 and the modal feature 2 to form a fusion feature;

[0157] F500. Predict drug synergy for each feature sample in the fusion feature according to the prediction model, and determine whether the target drug 1 and the target drug 2 have synergistic effect in the target cell line.

[0158] In a fourth aspect, an embodiment of the present application further provides a prediction device for implementing the above-mentioned multi-modal comparison drug synergy prediction method, the prediction device comprising:

[0159] a phenotypic characteristic module configured to obtain phenotypic characteristics of target drug 1, target drug 2, and target cell line;

[0160] an entity embedding feature module, which obtains entity embedding features corresponding to the target drug 1, the target drug 2, and the target cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the target drug 1, the target drug 2, and the target cell line and the first model;

[0161] A multimodal fusion prediction module is configured to obtain modal feature one and modal feature two representing drug-drug-cell line triple information in two different modalities in the same dimension based on the entity embedding feature and the phenotypic feature; concatenate the modal feature one and modal feature two to form a fusion feature; predict drug synergy for each feature sample in the fusion feature according to the prediction model, and determine whether the target drug one and the target drug two have synergistic effect in the target cell line.

[0162] Among them, the functional implementation of each module in the above-mentioned prediction device corresponds to the various steps in the above-mentioned multi-modality comparison drug synergy prediction method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0163] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0164] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit the "first", "second" and "third" to different types.

[0165] In the description of the embodiments of this application, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0166] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0167] In some processes described in the embodiments of the present application, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be performed in the order in which they appear in the embodiments of the present application or may be performed in parallel. The sequence numbers of the operations are only used to distinguish between different operations, and the sequence numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations or steps may be performed in sequence or in parallel, and these operations or steps may be combined.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of the present application.

[0169] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for constructing a multimodal comparative drug synergy prediction model, characterized in that: The construction method comprises: Obtaining phenotypic characteristics of the first drug, the second drug, and the cell line; Obtaining entity embedding features corresponding to the first drug, the second drug, and the cell line according to a heterogeneous graph consisting of drugs, targets, and cell lines involved in the first drug, the second drug, and the cell line and a preset first model; According to the entity embedding feature and the phenotypic feature, a first modality feature and a second modality feature of two different modalities representing drug-drug-cell line triple information in the same dimension are obtained; Obtaining a prediction result of the effectiveness of a preset real sample after predicting drug synergy based on each feature sample in the first modal feature and the second modal feature using a preset prediction model; If the prediction results of the two feature samples corresponding to the same real sample in the first modal feature and the second modal feature are both correct, then both are determined to be sample positive pairs; if both are wrong, then both are determined to be sample negative pairs; if only one of them is correct, then both are determined to be sample semi-positive pairs; Determining a target loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs; Determine whether the target loss function meets the preset requirements. If not, adjust the multiple models used in the previous step and calculate the target loss function again. If it meets the requirements, determine that the multiple models used this time are combined to form a multi-modal comparative drug synergistic prediction model.

2. The construction method according to claim 1, wherein In determining the target loss function according to the sample positive pairs, the sample negative pairs and the sample semi-positive pairs, A target loss function is determined according to the cosine similarities of the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs and a preset temperature coefficient.

3. The construction method according to claim 2, wherein: The target loss function is determined based on the cosine similarity of the sample positive pair, the sample negative pair and the sample semi-positive pair and a preset temperature coefficient, using the following formula: Where n is a paired feature sample of the first modal feature and the second modal feature, P is a set of positive pairs, S is a set of semi-positive pairs, and B is the set of all sample positive pairs, sample negative pairs, and the sample semi-positive pairs. is the first modal feature, is the second mode characteristic, and τ is the temperature coefficient.

4. The construction method according to claim 1, wherein Determining a target loss function based on the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs comprises the following steps: Determining a first loss function according to the sample positive pairs, the sample negative pairs, and the sample semi-positive pairs; Determining a second loss function based on the effectiveness prediction results of drug synergy predictions performed on each feature sample in the first modal feature and the second modal feature relative to preset real samples using the prediction model; Determining a third loss function based on the effectiveness prediction result of drug synergy prediction relative to a preset real sample after using the prediction model to predict the fusion feature obtained by concatenating the first modal feature and the second modal feature; The target loss function is determined based on at least the first loss function, the second loss function, and the third loss function.

5. The construction method according to claim 4, wherein: The second loss function is determined by using the following formula to predict the effectiveness of the drug synergy prediction relative to the preset real samples after using the prediction model for each feature sample in the first modal feature and the second modal feature: in, is the first modal feature and the second modal feature The labels of samples, is the corresponding modal feature Middle of samples Output, M is the number of modes, K is the number of samples.

6. The construction method according to claim 4, wherein: The third loss function is determined by using the following formula to predict the effectiveness of the drug synergy prediction relative to the preset real sample after the fusion feature obtained by concatenating the first modal feature and the second modal feature is used. in, For the The predicted value of the sample, The first of samples Output, K is the number of samples.

7. The construction method according to claim 1, wherein: The method of obtaining, based on the entity embedding feature and the phenotypic feature, a first modal feature and a second modal feature of two different modalities representing drug-drug-cell line triple information in the same dimension comprises the following steps: Different types of drugs and cell line features are dimensionally aligned according to the preset projection equation; Obtaining a first basic modality feature and a second basic modality feature for representing drug-drug-cell line triplet connection information according to the entity embedding feature and the phenotypic feature; Based on the first basic modal feature, the second basic modal feature and the preset second model, potential features that have an impact on drug synergy are determined from both the first basic modal feature and the second basic modal feature, and the first modal feature and the second modal feature are obtained based on the potential features of the two.

8. A method for predicting multimodal drug synergy using a model constructed by the method for constructing a multimodal drug synergy prediction model according to any one of claims 1 to 7, characterized in that: The prediction method comprises the following steps: Obtaining phenotypic characteristics of target drug 1, target drug 2, and target cell line 3; Obtaining entity embedding features corresponding to the target drug one, the target drug two, and the target cell line according to a heterogeneous graph consisting of drugs, targets, and cell lines involved in the target drug one, the target drug two, and the target cell line and the first model; According to the entity embedding feature and the phenotypic feature, a modal feature 1 and a modal feature 2 for representing drug-drug-cell line triplet information in two different modalities in the same dimension are obtained; Concatenating the modal feature 1 and the modal feature 2 to form a fusion feature; Drug synergy prediction is performed on each feature sample in the fusion feature according to the prediction model to determine whether the target drug 1 and the target drug 2 have synergistic effect in the target cell line.

9. A device for constructing a multi-modal comparative drug synergy prediction model, characterized in that: The construction device comprises: A phenotypic characteristic acquisition module configured to acquire phenotypic characteristics of the first drug, the second drug, and the cell line; an entity embedding feature acquisition module configured to acquire entity embedding features corresponding to the first drug, the second drug, and the cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the first drug, the second drug, and the cell line and a preset first model; a single-modal feature representation module configured to obtain, based on the entity embedding feature and the phenotypic feature, a first modal feature and a second modal feature representing information about a drug-drug-cell line triplet in two different modalities in the same dimension; A single-modal feature guided learning module is configured to obtain the effectiveness prediction results of the preset prediction model after predicting the drug synergy of each feature sample in the first modal feature and the second modal feature relative to the preset real sample; if the prediction results of the two feature samples corresponding to the same real sample in the first modal feature and the second modal feature are both correct, then both are determined to be sample positive pairs; if both are wrong, then both are determined to be sample negative pairs; if only one of them is correct, then both are determined to be sample semi-positive pairs; based on the sample positive pairs, sample negative pairs and sample semi-positive pairs, a target loss function is determined; whether the target loss function meets the preset requirements is judged; if not, the multiple models used in the previous step are adjusted and the target loss function is calculated again; if it meets, it is determined that the multiple model combination used this time constitutes a multi-modal comparative drug synergy prediction model.

10. A prediction device for implementing the multi-modal comparative drug synergistic prediction method according to claim 8, characterized in that: It includes: a phenotypic characteristic module configured to obtain phenotypic characteristics of target drug 1, target drug 2, and target cell line; an entity embedding feature module, which obtains entity embedding features corresponding to the target drug 1, the target drug 2, and the target cell line based on a heterogeneous graph consisting of drugs, targets, and cell lines involved in the target drug 1, the target drug 2, and the target cell line and the first model; A multimodal fusion prediction module is configured to obtain modal feature one and modal feature two representing drug-drug-cell line triple information in two different modalities in the same dimension based on the entity embedding feature and the phenotypic feature; concatenate the modal feature one and modal feature two to form a fusion feature; predict drug synergy for each feature sample in the fusion feature according to the prediction model, and determine whether the target drug one and the target drug two have synergistic effect in the target cell line.

Images