A molecular structure prediction system based on a multimodal fine-grained molecular pre-training model based on prompt learning

Abstract

A molecular structure prediction system based on a multimodal fine-grained molecular pre-training model based on prompt learning. The present invention relates to the field of molecular structure prediction, and in particular to a molecular structure prediction system. The purpose of the present invention is to solve the problems of low accuracy and efficiency in processing complex molecular data and low accuracy in predicting intermolecular interactions caused by data scarcity and insufficient task applicability in existing methods. The system includes: a data acquisition module for acquiring sample data in a multimodal molecular pre-training data set and sample data in a downstream task data set; a processing module for establishing a multimodal fine-grained molecular pre-training model based on prompt learning, and acquiring a trained multimodal fine-grained molecular pre-training model based on prompt learning; a prediction module for predicting the properties and drug interaction relationships of the molecular structure to be tested based on the trained multimodal fine-grained molecular pre-training model based on prompt learning, and obtaining a prediction result.

Description

Technical Field

[0001] The present invention relates to the field of molecular structure prediction, and in particular to a molecular structure prediction system. Background Art

[0002] With the continuous advancement of artificial intelligence technology, deep learning has become a key tool for accelerating research and development. Traditional discovery methods are limited by professional skills and experimental conditions, and their development is relatively slow. Currently, molecular representation learning methods based on machine learning rely on supervised models, which provide new perspectives for research and development by analyzing features such as molecular fingerprints, SMILES strings, two-dimensional molecular graphs, and three-dimensional structures. However, the scarcity of data and the complexity of annotations have limited the development of these models. To overcome these limitations, researchers have begun to focus on large-scale pre-trained language models (PTMs) in the field of natural language processing (NLP), such as BERT, the GPT series, and T5. These models perform unsupervised pre-training on large-scale text data. By fine-tuning with a small amount of annotated data, they reduce their dependence on a large amount of annotated data, improve the generalization ability of the model, and enable it to demonstrate excellent performance in a variety of tasks.

[0003] Inspired by multimodal models such as CLIP, BLIP2, and LLaVA, researchers have adopted self-supervised learning methods to explore the intrinsic connections between molecules of different modalities. Some studies regard SMILES strings as languages ​​with special grammar and use masked language model tasks to understand their relationship with molecular structure. Models like the T5 backbone use the attention mechanism of the Transformer to learn the serialized representation of molecular structure. This processing method makes the expression of molecular structure more concise and flexible, but the SMILES string representation has limitations, especially the difficulty in expressing the structural space information within the molecule. In order to fully capture the structural characteristics of molecules, researchers have considered representing molecules in other forms. The topological structure of molecules provides an intuitive representation of spatial arrangement, which helps to understand the intrinsic connections and properties and functions of molecules. Researchers simulate the molecular topology by converting SMILES strings into two-dimensional molecular graphs, and use graph neural networks to aggregate and propagate information between atoms and chemical bonds to learn the complex characteristics of molecules. Although these methods have made progress in molecular modeling, they may destroy the integrity of the molecular topology when reconstructing the masked internal structure, resulting in the inability to fully capture the unique structural characteristics of the molecule, which in turn affects the accuracy of the model's prediction of the properties and functions of the molecule.

[0004] Multimodal, fine-grained molecular pre-training models have made significant progress in molecular property prediction, molecule-to-text generation, and molecular optimization. However, the potential of these models for predicting intermolecular interactions has not yet been fully explored. Currently, fine-tuning pre-trained language models through transfer learning has become a common practice to improve the performance of models on specific tasks. Although this strategy has achieved significant performance improvements in natural language processing tasks, the traditional full-model micro-computation and storage costs are increasingly high as the size of pre-trained models grows. Recently, parameter-efficient fine-tuning methods have been proposed to alleviate this problem by updating only a small portion of the model parameters. While maintaining similar performance, they exhibit modular design, strong adaptability, and protection against catastrophic forgetting. Hint tuning has emerged as a promising approach, reducing the amount of parameter tuning by introducing a trainable hint vector into the input. However, improper initialization can prevent the model from effectively leveraging the knowledge acquired during pre-training, which in turn affects its performance on specific tasks. Summary of the Invention

[0005] The purpose of this invention is to solve the problems of low accuracy and efficiency in processing complex molecular data and low accuracy in predicting intermolecular interactions caused by data scarcity and insufficient task applicability of existing methods, and to propose a molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning.

[0006] The prediction system of the multimodal fine-grained molecular pre-training model based on prompt learning includes: a data acquisition module, a processing module, and a prediction module;

[0007] The data acquisition module is used to acquire sample data in the multimodal molecular pre-training dataset and sample data in the downstream task dataset;

[0008] The processing module is used to establish a multimodal fine-grained molecular pre-training model based on prompt learning and obtain the trained multimodal fine-grained molecular pre-training model based on prompt learning;

[0009] The prediction module is used to predict the properties and drug interaction relationships of the molecular structure to be tested based on the trained multimodal fine-grained molecular pre-training model of prompt learning to obtain prediction results.

[0010] The beneficial effects of the present invention are:

[0011] This paper proposes a multimodal fine-grained molecular pre-training model MolFinePrompt based on prompt learning, which takes into account the integrity of molecular structure when learning complex structures, accurately predicts the interactions between molecules, and gives full play to the potential of instruction fine-tuning in different tasks to improve the accuracy and efficiency of drug discovery.

[0012] The present invention uses a contrastive learning strategy on a dataset containing 316k pairs of molecular texts to effectively align molecular features with textual information. By integrating substructures that reflect chemical properties into molecular topology, the multimodal fine-grained molecular pre-training model based on prompt learning improves the accuracy and efficiency of processing complex molecular data.

[0013] In order to enhance the adaptability of the multimodal fine-grained molecular pre-training model based on prompt learning to diverse downstream tasks, the present invention designs a corresponding prompt template for each task, guiding the multimodal fine-grained molecular pre-training model based on prompt learning to more effectively identify and utilize task-related features, thereby enhancing the generalization and adaptability of the multimodal fine-grained molecular pre-training model based on prompt learning in diverse tasks.

[0014] By deeply analyzing the interaction patterns between different drug molecules, the multimodal fine-grained molecular pre-training model MolFinePrompt based on prompt learning can more accurately understand the properties of molecules and potential synergistic effects, providing a basis for the development of drug combination therapy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural diagram of the system of the present invention. DETAILED DESCRIPTION

[0016] Specific embodiment 1: The molecular structure prediction system of the multimodal fine-grained molecular pre-training model based on prompt learning in this embodiment includes: a data acquisition module, a processing module, and a prediction module;

[0017] The data acquisition module is used to acquire sample data in the multimodal molecular pre-training dataset and sample data in the downstream task dataset;

[0018] The processing module is used to establish a prompt-based learning multimodal fine-grained molecular pre-training model MolFinePrompt and obtain the trained prompt-based learning multimodal fine-grained molecular pre-training model;

[0019] The MolFinePrompt is Fine-Grained Multimodal Molecular PretrainingLarge Model via Prompt-Learning;

[0020] The prediction module is used to predict the properties and drug interaction relationships of the molecular structure to be tested based on the trained multimodal fine-grained molecular pre-training model of prompt learning to obtain prediction results.

[0021] The molecular structure to be measured and the data acquired by the data acquisition module come from the same domain (the same data type means that there are molecular text pairs, such as the molecular structure CC(=O)O and the corresponding text description: Acetic acid is a product of the oxidation of ethanol and of the destructive distillation of wood. It is used locally, occasionally internally, as a counterirritant and also as an areagent. Acetic acid otic (for the ear) is an antibiotic that treats infections caused by bacteria or fungus.

[0022] Specific embodiment 2: This embodiment differs from specific embodiment 1 in that: the data acquisition module is used to acquire sample data in the multimodal molecular pre-training data set and sample data in the downstream task data set; the specific process is:

[0023] The sample data in the multimodal molecular pre-training dataset are molecule-text pairs;

[0024] The sample data in the downstream task dataset is molecular structure (only structure without text, text is prompt, and the molecular structure uses the trained GIN);

[0025] The sample data in the dataset and the sample data in the downstream task dataset both include molecular structure G and text description T;

[0026] The molecular structure G and text description T are 316k molecule-text pairs collected from the public dataset Pubchem, where k is in thousand;

[0027] For example: the fine-grained molecular structure diagram G′ and the standardized molecular text description T′ in the pre-training dataset are used as the input of the MolFinePrompt model, and the fine-grained molecular structure diagram G' and specific task instruction text in the downstream task dataset are used as the input of the pre-training model, and the model outputs the result of the prediction task.

[0028] Other steps and parameters are the same as those in the first embodiment.

[0029] Specific embodiment three: This embodiment differs from specific embodiment one or two in that: the processing module is used to establish a multimodal fine-grained molecular pre-training model based on prompt learning, and obtain the trained multimodal fine-grained molecular pre-training model based on prompt learning; the specific process is:

[0030] The multimodal fine-grained molecular pre-training model based on prompt learning includes: a fine-grained molecular graph construction module, a molecular and text description representation learning module, a self-supervised collaborative comparison optimization module, and an instruction fine-tuning downstream task module;

[0031] The fine-grained molecular graph construction module uses a specific decomposition rule to decompose the molecular structure graph G in the sample data in the multimodal molecular pre-training dataset into sub-structure units, and constructs a fine-grained molecular graph G' based on the sub-structure units;

[0032] The molecular and text description representation learning module is used to input the text description T in the sample data in the multimodal molecular pre-training dataset into the text encoder, and the text encoder outputs semantic features; input the fine-grained molecular graph G″ corresponding to 1.65 million molecular structures in the PubChem dataset into the molecular encoder, and the molecular encoder outputs a molecular feature vector; train the molecular encoder GIN to obtain a pre-trained molecular encoder GIN;

[0033] The self-supervised collaborative contrast optimization module uses a contrastive learning method to train the pre-trained molecular encoder GIN and text encoder to obtain a trained molecular encoder GIN and text encoder; the trained molecular encoder GIN and text encoder constitute a multimodal fine-grained molecular pre-training model; and improve the model's ability to understand and represent molecular multimodal data;

[0034] The instruction fine-tuning downstream task module is used to use prompt learning to guide the multimodal fine-grained molecular pre-training model to understand downstream tasks, and obtain a trained multimodal fine-grained molecular pre-training model based on prompt learning.

[0035] Improve its applicability and flexibility in specific application scenarios.

[0036] Based on the above, the present invention constructs a fine-grained molecular structure diagram, combines it with text information, uses contrastive learning to optimize the multimodal fine-grained molecular pre-training model, and uses prompt learning technology to apply the multimodal fine-grained molecular pre-training model to key specific tasks in the discovery field.

[0037] Other steps and parameters are the same as those in the first or second embodiment.

[0038] Specific embodiment 4: This embodiment differs from any one of specific embodiments 1 to 3 in that: the fine-grained molecular graph construction module uses a specific decomposition rule to decompose the molecular structure graph G in the sample data in the multimodal molecular pre-training dataset into sub-structure units, and constructs a fine-grained molecular graph G' based on the sub-structure units;

[0039] The specific process is:

[0040] 1) Using the RDKit tool, we obtain the chemical element characteristics of each atom in the molecular structure represented by the SMILES string in the sample data in the multimodal molecular pre-training dataset;

[0041] The chemical element characteristics of each atom include the atomic number, connectivity, bond type between atoms (single bond, double bond, triple bond) and atomic ring type (whether ring-forming);

[0042] Use connectivity features as node features;

[0043] The bond type between atoms and the type of atoms forming a ring are used as bond characteristics;

[0044] The connectivity is the number of chemical bonds connecting atoms;

[0045] 2) In order to more comprehensively and completely describe the chemical properties of the molecular structure, the molecular structure represented by the SMILES string in the sample data in the multimodal molecular pre-training dataset is converted into a 2D topological graph G = (V, E) based on the RDKit tool;

[0046] Where V represents the node set of the 2D topological graph G, and E represents the edge set of the 2D topological graph G;

[0047] V represents the corresponding atom in the molecule, and E is the chemical bond between atoms;

[0048] 3) Decompose the molecular structure of the sample data in the multimodal molecular pre-training dataset based on the BRICS decomposition method to obtain substructure units; the specific process is as follows:

[0049] Based on the BRICS decomposition method, the molecular structure in the sample data in the multimodal molecular pre-training dataset is preliminarily decomposed to obtain multiple substructure units after the preliminary decomposition;

[0050] Decompose each substructure unit after the preliminary decomposition to obtain multiple minimum substructure units (if it can be decomposed, perform this step; if it cannot be decomposed, take the multiple substructure units after the preliminary decomposition as the minimum multiple substructure units); for example, the SMIELS structure of the molecule is represented by C1=CC=C2C(=C1)N(C(=O)N2CCO)CCO, which can be decomposed into three substructure units: CCO, C1=CC=C2C(=C1)N(C(=O)N2), and CCO through the BRICS decomposition method. According to the decomposition rule, C1=CC=C2C(=C1)N(C(=O)N2) is further decomposed into C1=CC=C2C(=C1), C=O, C1N=CN=C1, and finally the molecule has five substructure units: CCO, C1=CC=C2C(=C1), C=O, C1N=CN=C1, and CCO;

[0051] 4) Use the substructure unit as the new node V f Add to the topology map;

[0052] The connection relationship E between each substructure unit and the nodes it contains f Added to the topology graph as a new edge;

[0053] Construct an empty graph-level node V g , the graph-level node V g With all new nodes V f Connect to get the connection relationship E g , based on V,V f ,V g ,E,E f ,E g Form a fine-grained molecular graph G' to mine the deep semantic information hidden in molecules;

[0054] G′=(V′,E'),V′=[V,V f ,V g ],E′=[E,E f ,E g ].

[0055] The other steps and parameters are the same as those in the first to third embodiments.

[0056] Specific embodiment 5: This embodiment differs from any one of specific embodiments 1 to 4 in that: the molecular and text description representation learning module is used to input the text description T in the sample data in the multimodal molecular pre-training dataset into the text encoder, and the text encoder outputs semantic features; input the fine-grained molecular graph G″ corresponding to 1.65 million molecular structures in the PubChem dataset into the molecular encoder, and the molecular encoder outputs a molecular feature vector; and train the molecular encoder GIN to obtain a pre-trained molecular encoder GIN;

[0057] The specific process is:

[0058] Step 1) Change the molecule name in the text of the molecule text pair in the sample data in the multimodal molecule pre-training dataset to a unified format of "The molecule is";

[0059] The text in the unified format of "The molecule is" is input into the text encoder, and the text encoder outputs semantic features;

[0060] The text encoder is SciBERT based on the BERT architecture;

[0061] Textual descriptions serve as supplementary knowledge to the molecular graph, summarizing the molecule's related functions, properties, and other aspects in natural language. To prevent the leakage of the collected molecular text data and eliminate bias in molecular names, we changed the textual names in the 316k molecule-text pairs to a unified format of "The molecule is". This enhances the generalization and interpretability of the model, allowing it to focus on the intrinsic connection between molecular structure and properties rather than relying on specific molecular names.

[0062] SciBERT provides richer and more accurate semantic domain knowledge for molecules by pre-training on a large number of corpora in fields such as biochemistry and medicine.

[0063] Step 2) Input the fine-grained molecular graph G″ corresponding to the 1.65 million molecular structures in the PubChem dataset and the node features and bond features corresponding to the 1.65 million molecular structures in the PubChem dataset into the molecular encoder GIN, which outputs a feature vector;

[0064] The molecular encoder GIN consists of the following sequence: input layer, hidden layer, hidden layer, hidden layer, hidden layer;

[0065] The molecular encoder GIN is optimized using the self-supervised learning method of generation task and prediction task until convergence, and a pre-trained molecular encoder GIN is obtained;

[0066] Use the feature vector corresponding to V and E to complete the generation task;

[0067] Using V g ,E g The corresponding feature vector completes the prediction task;

[0068] The generated tasks are the connectivity of atoms, the type of atoms corresponding to their serial numbers (carbon, hydrogen, and oxygen belong to different atomic types), and the bond types between atoms;

[0069] The prediction task is the number of atoms in the molecular structure (how many atoms are there in the molecule) and the number of bonds (how many chemical bonds are there in the molecule);

[0070] The first layer of the molecular encoder GIN receives the original node features as input, and the second to fourth layers are hidden layers. Each layer takes the output of the previous layer as input, aggregates the features of neighboring nodes, updates the node representation through a learnable multi-layer perceptron (MLP), and adds residual connections (adding the node representation of the current layer to the node representation of the previous layer). The node features after that are the output of each layer;

[0071] For molecular structure processing, we adopted a Graph Isomorphism Network (GIN) to encode the topological structure. This is a variant of the Graph Neural Network (GNN) widely used in the field of molecular representation learning. GIN excels in capturing and expressing the topological features of molecules with its excellent ability.

[0072] Using the RDKit tool, 1.65 million molecular structures from the PubChem dataset were processed to obtain node and bond features. These features were then fed into a five-layer GIN model, which then output feature vectors. The GIN was then optimized using two self-supervised learning tasks, generation and prediction, until convergence, resulting in a pre-trained GIN model.

[0073] Our model is able to learn and generalize the structural information of molecules more accurately.

[0074] The other steps and parameters are the same as those in the first to fourth embodiments.

[0075] Specific embodiment 6: This embodiment differs from any one of specific embodiments 1 to 5 in that: the self-supervised collaborative contrast optimization module uses a contrastive learning method to train the pre-trained molecular encoder GIN and text encoder to obtain the trained molecular encoder GIN and text encoder; the trained molecular encoder GIN and text encoder constitute a multimodal fine-grained molecular pre-training model; and the model's ability to understand and represent molecular multimodal data is improved;

[0076] The specific process is:

[0077] The training set (molecule-text pairs) is the sample data in the multimodal molecule pre-training dataset;

[0078] The loss function is the InfoNCE loss function;

[0079] The optimization method is contrastive learning method;

[0080] The molecular feature vector V output by the pre-trained molecular encoder GIN g ,E g The corresponding eigenvector is represented as the eigenvector of the numerator.

[0081] Train the text encoder and the pre-trained molecular encoder GIN until convergence to obtain the trained text encoder and molecular encoder GIN;

[0082] The trained text encoder and molecular encoder GIN constitute a multimodal fine-grained molecular pre-training model to achieve the best alignment between molecular structure features and semantic features;

[0083] The InfoNCE loss function is:

[0084]

[0085] in, Input the pre-trained molecular encoder GIN to the molecules in the i-th pair of samples, and the image feature vector output by the pre-trained molecular encoder GIN;

[0086] Input the text encoder to the text in the i-th pair of samples, and output the text feature vector of the text encoder;

[0087] Input the text encoder for the text in the jth sample, and output the text feature vector of the text encoder;

[0088] sim() is a function to measure the similarity between two modal features, τ is a temperature parameter, and N is the total number of molecule-text pairs.

[0089] The multimodal contrastive learning method is used to enhance the semantic relevance between molecules and texts. This method improves the matching quality of molecules and texts by continuously optimizing the model while ensuring that mismatched molecule-text pairs maintain a certain distance in the embedding space. n ,t n ), where g i ,t i are the text descriptions corresponding to the i-th molecule and the i-th molecule, respectively;

[0090] Verify the multimodal fine-grained molecular pre-training model:

[0091] Zero-shot retrieval of new molecular structures / texts based on a multimodal fine-grained molecular pre-training model. The specific process is as follows:

[0092] Obtain new molecular structure text pair datasets PCDes and MoMu (new molecular structure text pairs);

[0093] Freeze the zero-shot molecular structure / text retrieval task based on the multimodal fine-grained molecular pre-training model;

[0094] The zero-shot molecular structure retrieval task inputs the molecular structure and text of the new molecular structure text pair into a multimodal fine-grained molecular pre-training model to obtain the molecular structure feature h g and semantic features h t , calculate the molecular structure characteristics h g and semantic feature vector h t The cosine similarity of , a cosine similarity matrix is ​​obtained, each element in the cosine similarity matrix represents the similarity between a molecular structure feature vector and all semantic feature vectors;

[0095] Determine the index of the text representation that is most similar to each molecular structure, and compare it with the index of the correct text representation (the first text corresponding to the first molecular structure, the second text corresponding to the second molecular structure). If the indexes match, the retrieval is considered successful, and the retrieval accuracy is calculated;

[0096] For each molecular structure feature vector, the semantic feature vectors are sorted by similarity and the most similar items are retrieved. If the molecular structure feature vector is among the top 20 most similar items after sorting, the retrieval is successful. The proportion of correct retrievals is calculated as the average recall rate.

[0097] The other steps and parameters are the same as those in the first to fifth embodiments.

[0098] Specific embodiment seven: This embodiment differs from any one of specific embodiments one to six in that: the instruction fine-tuning downstream task module is used to use prompt learning to guide the multimodal fine-grained molecular pre-training model to understand the downstream task, thereby obtaining a trained multimodal fine-grained molecular pre-training model based on prompt learning;

[0099] The specific process is:

[0100] To improve model performance on specific molecular prediction tasks, this project employed a combination of expert-guided prompts and parameters to efficiently fine-tune the model to suit specific molecular prediction tasks. Specifically, initialization prompts were customized for each task to ensure the model understood the task objectives and requirements. By designing specialized prompts for property prediction and drug-drug interaction (DDI) tasks, these prompts provided rich context and target information, helping the model understand the relevant biological and chemical principles and ensuring that it could identify and utilize key molecular features.

[0101] 1) Build the instruction prompt text; the specific process is:

[0102] 11) Obtain attribute prediction tasks in the training set (structure only without text, text is prompt, and the molecular structure uses the trained GIN) from the sample data in the downstream task dataset;

[0103] The attribute prediction task includes six subtasks: BBBP, Bace, Sider, Tox21, ToxCast, and HIV. Each subtask corresponds to a dataset, that is, the attribute prediction task includes six datasets;

[0104] The BBBP is blood-brain barrier penetrant;

[0105] The Bace is a β-amyloid precursor protein cleaving enzyme;

[0106] The Sider is a side effect;

[0107] The Tox21 is a 21st century toxicology test;

[0108] The ToxCast is a multi-year toxicology prediction research project initiated by the U.S. Environmental Protection Agency (EPA);

[0109] The HIV is human immunodeficiency virus;

[0110] The BBBP dataset contains 2039 molecular structures and corresponding attribute labels;

[0111] The Bace dataset contains 1513 molecular structures and corresponding attribute labels;

[0112] The Sider dataset contains 1427 molecular structures and corresponding attribute labels;

[0113] The Tox21 dataset contains 7831 molecular structures and corresponding attribute labels;

[0114] The ToxCast dataset contains 8576 molecular structures and corresponding attribute labels;

[0115] The HIV dataset contains 41,127 molecular structures and corresponding attribute labels;

[0116] 12) Obtain the drug interaction task in the training set (only structure without text, text is prompt, and the molecular structure uses the trained GIN) from the sample data in the downstream task dataset;

[0117] The drug interaction task includes three subtasks: ZhangDDI, ChChMiner, and DeepDDI. Each subtask corresponds to a dataset, that is, the drug interaction task includes three datasets.

[0118] The ZhangDDI dataset contains 48,548 molecular structure pairs (two molecular structures) and corresponding drug interaction relationship labels;

[0119] The ChChMiner dataset contains 48,514 molecular structure pairs (two molecular structures) and corresponding drug interaction relationship labels;

[0120] The DeepDDI dataset contains 192,284 molecular structure pairs (two molecular structures) and corresponding drug interaction relationship labels;

[0121] 13) Construct instruction prompt text based on the task objectives, task background, guiding principles and task requirements of each subtask;

[0122] Take the BBBP task as an example:

[0123] For example, the prompt for the BBBP (blood-brain barrier penetrability) task: "ThistaskisBBBP, our objectiveistopredict whether adrugmoleculecanpenetratetheblood-brainbarrier,whichiscomposedofbrain capillaryendothelialcells.Theblood-brainbarrierishighlyselective,allowingonlycertain substancestopassthrough.Weneedtoanalyzethefollowingmolecularstructural characteristics:lipophilicity,molecularweight,chargestate,proteinbindingcapacity,presenceofhydrophobicgroups,activityofmetabolicproducts,andthecyclicstructureofthemolecule. ismorelikelytopenetratetheblood-brainbarrier.Pleaseusetheseguidingprinciplesto This task is a BBBP task. We have designed the task objective, task background, guiding principles, and task requirements. Task objective: Predict whether a drug molecule can penetrate the blood-brain barrier. Task background: The blood-brain barrier is composed of endothelial cells lining the brain capillaries. The blood-brain barrier is highly selective, allowing only certain substances to pass through. Guiding principles: Molecules with high lipophilicity, low molecular weight, lack of charge, minimal protein binding, hydrophobic groups, no active metabolites, and being polycyclic compounds are more likely to penetrate the blood-brain barrier. Task requirements: Please use these guiding principles to determine whether the molecule has the ability to penetrate the blood-brain barrier.

[0124] Bace (β-amyloid precursor protein cleavage enzyme) task prompt: ThistaskisBACE,ourgoalistopredict whetheradrugmoleculecaneffectivelyinhibitBACEenzyme,whichisakeytargetforthe treatment ofAlzheimer'sdisease.TheactivityofBACEenzymeiscloselyrelatedtothe productionofbeta-amyloidprotein.Weneedtoanalyzethefollowingmolecularstructural characteristics:bindingaffinity,molecularweight,lipophilicity,hydrogenbondcapability,stereoisomerism,andmetabolicstability.Ifthemoleculedemonstratesstrongbindingaffinity withtheactivesiteofBACEenzyme,possesskeychemicalgroupstoformnecessaryhydrogenbonds,andisstableunderphysiologicalconditionswithgoodcellmembrane permeability,itmaybeaneffectiveBACEinhibitor.Pleaseusetheseguidingprinciplesto Analyze and determine whether this molecule has the potential for BACE inhibition. (This task is the BACE task. We have designed the task goal, task background, guiding principles and task requirements. Task goal: Predict whether a drug molecule can effectively inhibit the BACE enzyme, which is a key target for the treatment of Alzheimer's disease. Task background: The activity of the BACE enzyme is closely related to the production of β-amyloid protein. Guiding principles: We need to analyze the following molecular structural characteristics: binding affinity, molecular weight, lipophilicity, hydrogen bonding ability, stereoisomerism and metabolic stability.If a molecule exhibits strong binding affinity to the active site of the BACE enzyme, possesses key chemical groups that form the necessary hydrogen bonds, and is stable under physiological conditions and has good cell membrane permeability, it is likely to be a potent BACE inhibitor. Task Requirement: Use these guidelines to analyze and determine whether this molecule has BACE inhibitory potential).

[0125] Sider (side effects) task prompt: ThistaskisSIDE, ourgoalistopredictthepotentialsideeffectsthatadrugmoleculemightcause.Predictingdrugsideeffectsiscrucialforthesafetyassessmentofmedications.Weneedtoanalyzethefollowingmolecularstructuralcharacteristics:pharmacologicalmechanismsofactionsuchasreceptorbindingorenzymeinhibition,propertieslikemolecularweight,lipophilicity,andsolubility,andpharmacokinetic characteristicssuchasabsorption,distribution,metabolism,andexcretion.Pleaseusetheseguidelinestoanalyzeandpredictthepotentialsideeffectsthatthisdrugmoleculemay This task is called SIDE. We have designed the task objective, task background, guiding principles, and task requirements. Task objective: Predict potential side effects that a drug molecule may cause. Task background: Predicting drug side effects is crucial for drug safety assessment. Guiding principles: We need to analyze the following molecular structural characteristics: pharmacological mechanisms such as receptor binding or enzyme inhibition, properties such as molecular weight, lipophilicity, and solubility, and pharmacokinetic characteristics such as absorption, distribution, metabolism, and excretion. Task requirements: Please use these guiding principles to analyze and predict the potential side effects that this drug molecule may cause.

[0126] Tox21 (21st Century Toxicology Testing) Task Tip: ThistaskisTOX21,ourgoalistoppredictwhethera pharmaceuticalmoleculemightinducearangeofbiologicaleffectsassociatedwithtoxicity.TheTOX21projectaimstoidentifythepotentialtoxicityofchemicalsubstances,including hormonedisruption,genotoxicity,andmore.Weneedtoanalyzemolecularstructural characteristics: the presence of aromatic rings, the balance between lipophilicity and hydrophilicity, metabolicstability, and permeability. If a molecule affects the pharmaceutical action of known toxicity-related targets, shows metabolic instability, or is likely to produce This task is TOX21, and our goal is to predict whether a drug molecule will induce a range of toxicity-related biological effects. The TOX21 project aims to determine the potential toxicity of chemical substances, including hormone disruption and genotoxicity. We need to analyze molecular structural features: the presence of aromatic rings, the balance between lipophilicity and hydrophilicity, metabolic stability, and permeability. If a molecule affects the pharmacology of a known toxicity-related target, exhibits metabolic instability, or may produce toxic metabolites, or exhibits poor cellular permeability, it may have TOX21 properties. Please use these guiding principles to predict whether a drug molecule has TOX21 characteristics.

[0127] ToxCast (a multi-year toxicology prediction research project started by the U.S. Environmental Protection Agency (EPA)) task prompt: Thistaskis ToxCast,ourgoalistoassessthepotentialtoxicityofchemicalsubstancestobiologicalsystems.TheToxCastprojectisalarge-scale,high-throughputscreeningprojectthatusesavarietyofbiologicalteststopredictthetoxicityofchemicalsubstances.Weneedtoanalyzethefollowing molecularstructuralcharacteristics:molecularweight,solubility,lipophilicity,etc.Ifamoleculehasalargemolecularweight,lowsolubility,highlipophilicity,andactivemetabolites,itis morelikelytoexhibitspecifictoxicity.Pleasejudgewhetherthismoleculehaspotentialtoxicity This task is ToxCast, and we have designed the task objectives, task background, guiding principles, and task requirements. Task Objective: Evaluate the potential toxicity of chemicals to biological systems. Task Background: The ToxCast project is a large-scale, high-throughput screening project that uses various biological tests to predict the toxicity of chemicals. Guiding Principles: We need to analyze the following molecular structure characteristics: molecular weight, solubility, lipophilicity, etc. Molecules with large molecular weight, low solubility, high lipophilicity, and strong metabolite activity are more likely to exhibit specific toxicity. Task Requirements: Please use these guiding principles to determine whether the molecule is potentially toxic.

[0128] HIV (human immunodeficiency virus) task prompt: ThistaskisHIV,ourgoalistoassessthepotential inhibitoryeffectofdrugmoleculesonHIV.HIVisavirusthatattacksthehumanimmune system, particularly affecting CD4+T cells, leading to Acquired Immunodeficiency Syndrome (AIDS). Weneed to analyze the following molecular structural characteristics: lipophilicity, molecular weight, chargestate, protein binding capacity, hydrophobic groups, and the activity of metabolic products. If the molecule has an optimized chemical structure targeting HIV'skey proteins,asmallermolecularweight,strongproteinbindingcapacity,hydrophobicgroups,andgoodmetabolicstability,thenitismorelikelytohaveaninhibitoryeffectonHIV.Pleasejudge Whether this molecule has antiviral potential of specific drug molecules. (This task is HIV. We have designed the task objective, task background, guiding principles, and task requirements. Task objective: Evaluate the potential inhibitory effect of drug molecules on HIV. Task background: HIV is a virus that attacks the human immune system, especially affecting CD4+ T cells, leading to acquired immunodeficiency syndrome (AIDS). Guiding principles: We need to analyze the following molecular structural characteristics: lipophilicity, molecular weight, charge state, protein binding ability, hydrophobic groups, and metabolite activity. If a molecule has an optimized chemical structure for HIV key proteins, a small molecular weight, strong protein binding ability, hydrophobic groups, and good metabolic stability, then it is more likely to have an inhibitory effect on HIV. Task requirement: Please use these guiding principles to predict the antiviral potential of a specific drug molecule.)

[0129] Task prompts for the drug interaction task: This task is Drug-Drug Interaction, which refers to the phenomenon where the simultaneous use of two or more drugs in the body can lead to an enhancement or reduction in their efficacy, or even cause adverse reactions, due to the mutual influence between the drugs. Determine if the interaction between these two drugs is positive or not. (This task is drug interaction. We have designed the task objectives, task background, guiding principles and task requirements; Task objectives: refers to the phenomenon that due to the mutual influence between drugs, the simultaneous use of two or more drugs in the body can lead to an enhancement or reduction in their efficacy, or even cause adverse reactions. Task requirements: Please determine whether there is an interaction between the two drugs.); Drug interactions are different types of drugs. It is just a matter of judging whether there is an interaction between each pair of drugs.

[0130] 2) Based on the instruction prompt text constructed in 1), obtain the feature vector h of the prompt text p ;

[0131] 3) Based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text, attribute prediction is performed on the molecular structure (without attribute labels);

[0132] 4) Predict drug interaction relationships for molecular structure pairs (without interaction relationships) based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text;

[0133] 5) Repeat 1) to 4) until convergence to obtain a trained multimodal fine-grained molecular pre-training model based on prompt learning.

[0134] Other steps and parameters are the same as those in Specific Implementations 1 to 6-1.

[0135] Specific embodiment eight: This embodiment differs from any one of specific embodiments one to seven in that: in said 2), based on the instruction prompt text constructed in 1), the feature vector h of the prompt text is obtained. p ; The specific process is:

[0136] Create a hint embedding layer P∈R (l×d), where l is the number of virtual tokens, d is the dimension of embedding; R is a real number;

[0137] Input the instruction prompt text constructed in 1) into the word segmenter corresponding to the trained text encoder, and the word segmenter outputs a token ID sequence;

[0138] The token ID sequence is input into the trained text encoder, and the word embedding layer in the trained text encoder outputs the word embedding vector;

[0139] The word embedding vector is used as the initial weight of the created prompt embedding layer P to obtain the initialized prompt embedding layer;

[0140] Input the virtual token in the initialized prompt embedding layer into the trained text encoder, and the trained text encoder outputs the feature vector h corresponding to the instruction prompt text p .

[0141] Each subtask corresponds to many molecular structures, and each molecular structure corresponds to an h p , h in 1 subtask p are the same.

[0142] Other steps and parameters are the same as those in Specific Embodiments 1 to 7-1.

[0143] Specific embodiment 9: This embodiment differs from any one of specific embodiments 1 to 8 in that: in 3), attribute prediction is performed on the molecular structure (without attribute labels) based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text; the specific process is as follows:

[0144] 31) Input the molecular structure of BBBP (blood-brain barrier permeability) (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g1 ;

[0145] Based on the instruction prompt text constructed by BBBP in 1), the feature vector h of the prompt text is obtained according to 2). p1 ;

[0146] The feature vector h of the prompt text p1 and structural feature vector h g1 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of BBBP after prompt guidance;

[0147]

[0148] in,

[0149] h property1It is the attribute feature representation corresponding to the molecular structure of BBBP after prompt guidance;

[0150] α is the weight parameter, For splicing;

[0151] Input the attribute feature representation corresponding to the molecular structure of the BBBP after prompt guidance into the classifier for classification (obtaining attributes);

[0152] 32) Input the molecular structure of Bace (β-amyloid precursor protein cleaving enzyme) (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g2 ;

[0153] Based on the instruction prompt text constructed by Bace in 1), the feature vector h of the prompt text is obtained according to 2). p2 ;

[0154] The feature vector h of the prompt text p2 and structural feature vector h g2 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of Bace after prompt guidance;

[0155]

[0156] in,

[0157] h property2 It is the attribute feature representation corresponding to the molecular structure of Bace after prompt guidance;

[0158] α is the weight parameter, For splicing;

[0159] The attribute feature representation corresponding to the molecular structure of Bace after prompt guidance is input into the classifier for classification (obtaining attributes);

[0160] 33) Input the molecular structure of Sider (side effect) (without attribute label) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g3 ;

[0161] Based on the instruction prompt text constructed by Sider in 1), the feature vector h of the prompt text is obtained according to 2). p3 ;

[0162] The feature vector h of the prompt text p3 and structural feature vector h g3 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of Sider after prompt guidance;

[0163]

[0164] in,

[0165] h property3 It is the attribute feature representation corresponding to the molecular structure of Sider after prompt guidance;

[0166] α is the weight parameter, For splicing;

[0167] The attribute feature representation corresponding to the molecular structure of Sider after prompt guidance is input into the classifier for classification (obtaining attributes);

[0168] 34) Input the molecular structure of Tox21 (21st Century Toxicology Test) (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g4 ;

[0169] Based on the instruction prompt text constructed by Tox21 in 1), the feature vector h of the prompt text is obtained according to 2). p4 ;

[0170] The feature vector h of the prompt text p4 and structural feature vector h g4 After fusion, the attribute feature representation corresponding to the molecular structure of Tox21 after prompt guidance is obtained;

[0171]

[0172] in,

[0173] h property4 It is the attribute feature representation corresponding to the molecular structure of Tox21 after prompt guidance;

[0174] α is the weight parameter, For splicing;

[0175] Input the attribute feature representation corresponding to the molecular structure of Tox21 guided by the prompt into the classifier for classification (obtaining attributes);

[0176] 35) Input the molecular structure (without attribute labels) of ToxCast (a multi-year toxicology prediction research project initiated by the U.S. Environmental Protection Agency (EPA)) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g5 ;

[0177] Based on the instruction prompt text constructed by ToxCast in 1), the feature vector h of the prompt text is obtained according to 2). p5 ;

[0178] The feature vector h of the prompt text p5 and structural feature vector h g5 After fusion, the attribute feature representation corresponding to the molecular structure of ToxCast after prompt guidance is obtained;

[0179]

[0180] in,

[0181] h property5 It is the attribute feature representation corresponding to the molecular structure of ToxCast after prompt guidance;

[0182] α is the weight parameter, For splicing;

[0183] Input the attribute feature representation corresponding to the molecular structure of ToxCast after prompt guidance into the classifier for classification (obtaining attributes);

[0184] 36) Input the molecular structure of HIV (human immunodeficiency virus) (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g6 ;

[0185] Based on the instruction prompt text constructed by HIV in 1), the feature vector h of the prompt text is obtained according to 2). p6 ;

[0186] The feature vector h of the prompt text p6 and structural feature vector h g6 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of HIV after prompt guidance;

[0187]

[0188] in,

[0189] h property6 It is a representation of the attribute characteristics corresponding to the molecular structure of HIV after prompting;

[0190] α is the weight parameter, For splicing;

[0191] Input the attribute feature representation corresponding to the molecular structure of HIV after prompt guidance into the classifier for classification (obtaining attributes);

[0192] Each subtask corresponds to a data set, each data set contains multiple molecular structures and corresponding attribute labels; each subtask corresponds to many molecular structures, and each molecular structure corresponds to an h p , h in 1 subtask p are the same.

[0193] The other steps and parameters are the same as those in Specific Embodiments 1 to 8.

[0194] Specific embodiment ten: This embodiment differs from any one of specific embodiments one to nine in that: in the above 4), drug interaction relationships are predicted for molecular structure pairs (without interaction relationships) based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text; the specific process is as follows:

[0195] 41) Input the molecular structure pair of ZhangDDI (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g7 and h g8 ;

[0196] Based on the instruction prompt text constructed by ZhangDDI in 1), the feature vector h of the prompt text is obtained according to 2). p7 ;

[0197] The structural feature vector h g7 、h g8 and the feature vector h of the prompt text p7 After splicing, the molecular structure of ZhangDDI is obtained to obtain the corresponding drug interaction relationship feature representation;

[0198]

[0199] in,

[0200] h ddi1 To indicate the characteristic representation of drug interaction relationship between the molecular structure of ZhangDDI after guidance;

[0201] For splicing;

[0202] The molecular structure of ZhangDDI after prompt guidance is input into the classifier for classification (attribute acquisition);

[0203] 42) Input the molecular structure pair of ChChMiner (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g9 and hg10 ;

[0204] Based on the instruction prompt text constructed by ChChMiner in 1), the feature vector h of the prompt text is obtained according to 2). p8 ;

[0205] The structural feature vector h g9 、h g10 and the feature vector h of the prompt text p8 After splicing, the molecular structure of ChChMiner guided by hints is obtained, and the corresponding drug interaction relationship feature representation is obtained;

[0206]

[0207] in,

[0208] h ddi2 To indicate the characteristic representation of drug interaction relationships between molecular structures of ChChMiner after guidance;

[0209] The molecular structure of ChChMiner after prompt guidance and the corresponding drug interaction relationship feature representation are input into the classifier for classification (attribute acquisition);

[0210] 43) Input the molecular structure pair of DeepDDI (without attribute labels) into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g11 and h g12 ;

[0211] Based on the instruction prompt text constructed by DeepDDI in 1), the feature vector h of the prompt text is obtained according to 2). p9 ;

[0212] The structural feature vector h g11 and h g12 and the feature vector h of the prompt text p9 Perform splicing to obtain the molecular structure of DeepDDI guided by hints and the corresponding drug interaction relationship feature representation;

[0213]

[0214] in,

[0215] h ddi3 To indicate the drug interaction relationship characteristics corresponding to the molecular structure of DeepDDI after guidance;

[0216] The molecular structure of DeepDDI guided by the prompt is input into the classifier to classify the corresponding drug interaction relationship feature representation (obtain attributes).

[0217] Each subtask corresponds to a data set, each of which contains multiple molecular structure pairs (two molecular structures) and corresponding drug interaction relationship labels; each subtask corresponds to many molecular structures, and each molecular structure corresponds to an h p , h in 1 subtask p are the same.

[0218] Other steps and parameters are the same as those in Specific Implementations 1 to 9-1.

[0219] The present invention may have many other embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art may make various corresponding changes and modifications based on the present invention, but these corresponding changes and modifications should all fall within the scope of protection of the claims attached to the present invention.

Claims

1. A molecular structure prediction system based on a multimodal fine-grained molecular pre-training model with prompt learning, characterized by: The system includes: a data acquisition module, a processing module, and a prediction module; The data acquisition module is used to acquire sample data in the multimodal molecular pre-training dataset and sample data in the downstream task dataset; The processing module is used to establish a multimodal fine-grained molecular pre-training model based on prompt learning and obtain the trained multimodal fine-grained molecular pre-training model based on prompt learning; The prediction module is used to predict the properties and drug interaction relationships of the molecular structure to be tested based on the trained multimodal fine-grained molecular pre-training model of prompt learning to obtain prediction results; The data acquisition module is used to acquire sample data in the multimodal molecular pre-training dataset and sample data in the downstream task dataset; The specific process is: The sample data in the multimodal molecular pre-training dataset are molecule-text pairs; The sample data in the downstream task dataset is molecular structure; The processing module is used to establish a multimodal fine-grained molecular pre-training model based on prompt learning, and obtain the trained multimodal fine-grained molecular pre-training model based on prompt learning; The specific process is: The multimodal fine-grained molecular pre-training model based on prompt learning includes: a fine-grained molecular graph construction module, a molecular and text description representation learning module, a self-supervised collaborative comparison optimization module, and an instruction fine-tuning downstream task module; The fine-grained molecular graph construction module uses a specific decomposition rule to decompose the molecular structure graph G in the sample data in the multimodal molecular pre-training dataset into sub-structure units, and constructs a fine-grained molecular graph G' based on the sub-structure units; The molecular and text description representation learning module is used to input the text description T in the sample data in the multimodal molecular pre-training dataset into the text encoder, and the text encoder outputs semantic features; input the fine-grained molecular graph G″ corresponding to 1.65 million molecular structures in the PubChem dataset into the molecular encoder, and the molecular encoder outputs a molecular feature vector; train the molecular encoder GIN to obtain a pre-trained molecular encoder GIN; The self-supervised collaborative contrast optimization module uses a contrastive learning method to train the pre-trained molecular encoder GIN and text encoder to obtain the trained molecular encoder GIN and text encoder; the trained molecular encoder GIN and text encoder constitute a multimodal fine-grained molecular pre-training model; The instruction fine-tuning downstream task module is used to use prompt learning to guide the multimodal fine-grained molecular pre-training model to understand the downstream task, thereby obtaining a trained multimodal fine-grained molecular pre-training model based on prompt learning; The fine-grained molecular graph construction module uses a specific decomposition rule to decompose the molecular structure graph G in the sample data in the multimodal molecular pre-training dataset into sub-structure units, and constructs a fine-grained molecular graph G' based on the sub-structure units; The specific process is: 1) Using the RDKit tool, we obtain the chemical element characteristics of each atom in the molecular structure represented by the SMILES string in the sample data in the multimodal molecular pre-training dataset; The chemical element characteristics of each atom include the atomic number, connectivity, interatomic bond type and atomic ring type; Use connectivity features as node features; The bond type between atoms and the type of atoms forming a ring are used as bond characteristics; The connectivity is the number of chemical bonds connecting atoms; 2) Based on the RDKit tool, the molecular structure represented by the SMILES string in the sample data in the multimodal molecular pre-training dataset is converted into a 2D topological graph G = (V, E); Where V represents the node set of the 2D topological graph G, and E represents the edge set of the 2D topological graph G; 3) Decompose the molecular structure of the sample data in the multimodal molecular pre-training dataset based on the BRICS decomposition method to obtain substructure units; the specific process is as follows: Based on the BRICS decomposition method, the molecular structure in the sample data in the multimodal molecular pre-training dataset is preliminarily decomposed to obtain multiple substructure units after the preliminary decomposition; Decompose each substructure unit after the preliminary decomposition to obtain multiple minimum substructure units; 4) Use the substructure unit as the new node V f Add to the topology map; The connection relationship E between each substructure unit and the nodes it contains f Added to the topology graph as a new edge; Construct an empty graph-level node V g , the graph-level node V g With all new nodes V f Connect to get the connection relationship E g , based on V,V f ,V g ,E,E f ,E g Forming a fine-grained molecular graph G'; G′=(V′,E′),V′=[V,V f ,V g ],E′=[E,E f ,E g ]。 2. The molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning according to claim 1, characterized in that: The molecular and text description representation learning module is used to input the text description T in the sample data in the multimodal molecular pre-training dataset into the text encoder, and the text encoder outputs semantic features; input the fine-grained molecular graph G″ corresponding to 1.65 million molecular structures in the PubChem dataset into the molecular encoder, and the molecular encoder outputs a molecular feature vector; train the molecular encoder GIN to obtain a pre-trained molecular encoder GIN; The specific process is: Step 1) Change the molecule name in the molecule text pair in the sample data in the multimodal molecule pre-training dataset to a unified format of "The molecule is"; The text in the unified format of "The molecule is" is input into the text encoder, and the text encoder outputs semantic features; The text encoder is SciBERT based on the BERT architecture; Step 2) Input the fine-grained molecular graph G″ corresponding to the 1.65 million molecular structures in the PubChem dataset and the node features and bond features corresponding to the 1.65 million molecular structures in the PubChem dataset into the molecular encoder GIN, which outputs a feature vector; The molecular encoder GIN consists of the following sequence: input layer, hidden layer, hidden layer, hidden layer, hidden layer; The molecular encoder GIN is optimized using the self-supervised learning method of generation task and prediction task until convergence, and a pre-trained molecular encoder GIN is obtained; The generated tasks are the connectivity of atoms, the types corresponding to the atomic numbers, and the bond types between atoms; The prediction task is the number of atoms and the number of bonds in a molecular structure.

3. The molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning according to claim 2, characterized in that: The self-supervised collaborative contrast optimization module uses a contrastive learning method to train the pre-trained molecular encoder GIN and text encoder to obtain the trained molecular encoder GIN and text encoder; the trained molecular encoder GIN and text encoder constitute a multimodal fine-grained molecular pre-training model; The specific process is: The training set is the sample data in the multimodal molecular pre-training dataset; The loss function is the InfoNCE loss function; The optimization method is contrastive learning method; Train the text encoder and the pre-trained molecular encoder GIN until convergence to obtain the trained text encoder and molecular encoder GIN; The trained text encoder and molecular encoder GIN constitute a multimodal fine-grained molecular pre-training model.

4. The molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning according to claim 3, characterized in that: The instruction fine-tuning downstream task module is used to use prompt learning to guide the multimodal fine-grained molecular pre-training model to understand the downstream task, thereby obtaining a trained multimodal fine-grained molecular pre-training model based on prompt learning; The specific process is: 1) Build the instruction prompt text; the specific process is: 11) Obtaining attribute prediction tasks in the training set from sample data in the downstream task dataset; The attribute prediction task includes six subtasks: BBBP, Bace, Sider, Tox21, ToxCast, and HIV. Each subtask corresponds to a dataset, that is, the attribute prediction task includes six datasets; The BBBP is blood-brain barrier penetrant; The Bace is a β-amyloid precursor protein cleaving enzyme; The Sider is a side effect; The Tox21 is a 21st century toxicology test; The ToxCast is a multi-year toxicology prediction research project initiated by the EPA; The HIV is human immunodeficiency virus; The BBBP dataset contains 2039 molecular structures and corresponding attribute labels; The Bace dataset contains 1513 molecular structures and corresponding attribute labels; The Sider dataset contains 1427 molecular structures and corresponding attribute labels; The Tox21 dataset contains 7831 molecular structures and corresponding attribute labels; The ToxCast dataset contains 8576 molecular structures and corresponding attribute labels; The HIV dataset contains 41,127 molecular structures and corresponding attribute labels; 12) Obtaining drug interaction tasks in the training set from sample data in the downstream task dataset; The drug interaction task includes three subtasks: ZhangDDI, ChChMiner, and DeepDDI. Each subtask corresponds to a dataset, that is, the drug interaction task includes three datasets; The ZhangDDI dataset contains 48,548 molecular structure pairs and corresponding drug interaction relationship labels; The ChChMiner dataset contains 48,514 molecular structure pairs and corresponding drug interaction relationship labels; The DeepDDI dataset contains 192,284 molecular structure pairs and corresponding drug interaction relationship labels; 13) Construct instruction prompt text based on the task objectives, task background, guiding principles and task requirements of each subtask; 2) Based on the instruction prompt text constructed in 1), obtain the feature vector h of the prompt text p ; 3) Predicting molecular structure attributes based on a multimodal fine-grained molecular pre-training model and the feature vector of the prompt text; 4) Predict drug interaction relationships for molecular structure pairs based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text; 5) Repeat 1) to 4) until convergence to obtain a trained multimodal fine-grained molecular pre-training model based on prompt learning.

5. The molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning according to claim 4, characterized in that: In the above 2), based on the instruction prompt text constructed in 1), the feature vector h of the prompt text is obtained. p ; The specific process is: Create a prompt embedding layer P∈R( l×d ), where l is the number of virtual tokens, d is the dimension of embedding; R is a real number; Input the instruction prompt text constructed in 1) into the word segmenter corresponding to the trained text encoder, and the word segmenter outputs a token ID sequence; The token ID sequence is input into the trained text encoder, and the word embedding layer in the trained text encoder outputs the word embedding vector; The word embedding vector is used as the initial weight of the created prompt embedding layer P to obtain the initialized prompt embedding layer; Input the virtual token in the initialized prompt embedding layer into the trained text encoder, and the trained text encoder outputs the feature vector h corresponding to the instruction prompt text p .

6. The molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning according to claim 5, characterized in that: In the above 3), based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text, the molecular structure is predicted; The specific process is: 31) Input the molecular structure of BBBP into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h gg ; Based on the instruction prompt text constructed by BBBP in 1), the feature vector h of the prompt text is obtained according to 2). p1 ; The feature vector h of the prompt text p1 and structural feature vector h g1 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of BBBP after prompt guidance; in, h property1 It is the attribute feature representation corresponding to the molecular structure of BBBP after prompt guidance; α is the weight parameter, For splicing; The attribute feature representation corresponding to the molecular structure of BBBP after prompt guidance is input into the classifier for classification; 32) Input the molecular structure of Bace into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g2 ; Based on the instruction prompt text constructed by Bace in 1), the feature vector h of the prompt text is obtained according to 2). p2 ; The feature vector h of the prompt text p2 and structural feature vector h g2 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of Bace after prompt guidance; in, h property2 It is the attribute feature representation corresponding to the molecular structure of Bace after prompt guidance; α is the weight parameter, For splicing; The attribute feature representation corresponding to the molecular structure of Bace after prompt guidance is input into the classifier for classification; 33) Input the molecular structure of Sider into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g3 ; Based on the instruction prompt text constructed by Sider in 1), the feature vector h of the prompt text is obtained according to 2). p3 ; The feature vector h of the prompt text p3 and structural feature vector h g3 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of Sider after prompt guidance; in, h property3 It is the attribute feature representation corresponding to the molecular structure of Sider after prompt guidance; α is the weight parameter, For splicing; The attribute feature representation corresponding to the molecular structure of Sider after prompt guidance is input into the classifier for classification; 34) Input the molecular structure of Tox21 into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g4 ; Based on the instruction prompt text constructed by Tox21 in 1), the feature vector h of the prompt text is obtained according to 2). p4 ; The feature vector h of the prompt text p4 and structural feature vector h g4 After fusion, the attribute feature representation corresponding to the molecular structure of Tox21 after prompt guidance is obtained; in, h property4 It is the attribute feature representation corresponding to the molecular structure of Tox21 after prompt guidance; α is the weight parameter, For splicing; The attribute feature representation corresponding to the molecular structure of Tox21 guided by the prompt is input into the classifier for classification; 35) Input the molecular structure of ToxCast into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g5 ; Based on the instruction prompt text constructed by ToxCast in 1), the feature vector h of the prompt text is obtained according to 2). p5 ; The feature vector h of the prompt text p5 and structural feature vector h g5 After fusion, the attribute feature representation corresponding to the molecular structure of ToxCast after prompt guidance is obtained; in, h property5 It is the attribute feature representation corresponding to the molecular structure of ToxCast after prompt guidance; α is the weight parameter, For splicing; The attribute feature representation corresponding to the molecular structure of ToxCast after prompt guidance is input into the classifier for classification; 36) Input the molecular structure of HIV into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g6 ; Based on the instruction prompt text constructed by HIV in 1), the feature vector h of the prompt text is obtained according to 2). p6 ; The feature vector h of the prompt text p6 and structural feature vector h g6 Fusion, to obtain the attribute feature representation corresponding to the molecular structure of HIV after prompt guidance; in, h property6 It is a representation of the attribute characteristics corresponding to the molecular structure of HIV after prompting; α is the weight parameter, For splicing; The attribute feature representation corresponding to the molecular structure of HIV after prompt guidance is input into the classifier for classification.

7. The molecular structure prediction system based on a multimodal fine-grained molecular pre-training model of prompt learning according to claim 6, characterized in that: In the above 4), based on the multimodal fine-grained molecular pre-training model and the feature vector of the prompt text, the drug interaction relationship of the molecular structure pair is predicted; the specific process is: 41) Input the molecular structure of ZhangDDI into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g7 and h g8 ; Based on the instruction prompt text constructed by ZhangDDI in 1), the feature vector h of the prompt text is obtained according to 2). p7 ; The structural feature vector h g7 、h g8 and the feature vector h of the prompt text p7 After splicing, the molecular structure of ZhangDDI is obtained to obtain the corresponding drug interaction relationship feature representation; in, h ddi1 To indicate the characteristic representation of drug interaction relationship between the molecular structure of ZhangDDI after guidance; For splicing; The molecular structure of ZhangDDI guided by the hint is input into the classifier for classification. 42) Input the molecular structure of ChChMiner into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g9 and h g10 ; Based on the instruction prompt text constructed by ChChMiner in 1), the feature vector h of the prompt text is obtained according to 2). p8 ; The structural feature vector h g9 、h g10 and the feature vector h of the prompt text p8 After splicing, the molecular structure of ChChMiner guided by hints is obtained, and the corresponding drug interaction relationship feature representation is obtained; in, h ddi2 To indicate the characteristic representation of drug interaction relationships between molecular structures of ChChMiner after guidance; The molecular structure of ChChMiner guided by the hint is input into the classifier for classification. 43) Input the molecular structure of DeepDDI into the trained molecular encoder GIN in the multimodal fine-grained molecular pre-training model, and the trained molecular encoder GIN outputs the structural feature vector h g11 and h g12 ; Based on the instruction prompt text constructed by DeepDDI in 1), the feature vector h of the prompt text is obtained according to 2). p9 ; The structural feature vector h g11 and h g12 It is then concatenated with the feature vector hp9 of the prompt text to obtain the characteristic representation of the drug interaction relationship corresponding to the molecular structure of the prompt-guided DeepDDI. in, h ddi3 To indicate the drug interaction relationship characteristics corresponding to the molecular structure of DeepDDI after guidance; The molecular structure of DeepDDI guided by the prompt is input into the classifier for classification of the corresponding drug interaction relationship feature representation.

Images