9 results about "Biocomputer" patented technology

The application discloses a DNA nanocage probe for leukemia cell multi-specific membrane protein logic circuit analysis, a kit and a method thereof, and realizes in-situ imaging analysis on three target membrane proteins by using a probe of a cross-section octahedral DNA nanocage main frame, stable structure, and designing a three-specific recognition biological computing DNA molecule logic gate based on a nucleic acid aptamer (Sgc4f, TC01, Sgc8c), which provides a new tool and idea for early diagnosis of tumors and biomedical application of the DNA molecule logic gate in a complex cell system.

The application discloses a complex structure prediction method and device and a model training method and an electronic equipment, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and biological computing. The specific implementation scheme is as follows: obtaining the amino acid sequence of a receptor and the sequence information of a ligand to be combined, and the protein structure of the receptor, determining the orientation information of the ligand relative to the protein structure based on the protein structure of the receptor, and determining the target complex structure of the combination of the receptor and the ligand according to the orientation information of the ligand relative to the protein structure, the amino acid sequence of the receptor and the sequence information of the ligand.

This invention relates to synthetic biology, gene and cell therapy, and particularly to a gene translation system regulated by non-natural amino acids and its applications. This gene translation system precisely regulates gene expression initiation using non-natural amino acids. The invention also provides eukaryotic expression vectors, mammalian cell lines, microcapsules, vacuum fiber tubes, and non-natural amino acid cookies containing the aforementioned gene translation system. Furthermore, this invention discloses that the multifunctional platform can precisely regulate insulin expression and release for diabetes treatment; this gene expression regulation platform can be used to construct complex biological computer-controlled systems. This invention provides a powerful new gene expression regulation tool for gene therapy and cell therapy.

The application discloses a biological computing multi-tool unified calling method and system based on a large language model, relates to the fields of biological information and computational chemistry, and at least comprises a task planner, an executor and a tool layer three parts, the method applied to the tool layer in the biological computing multi-tool unified calling system based on the large language model comprises the following steps: based on a unified interactive interface, responding to an interactive instruction with the executor, calling a corresponding type tool to return an execution result of a to-be-executed task step to the executor, wherein, when executing each to-be-executed task in a sequence of executable steps step by step, the executor triggers an interactive instruction with the tool layer based on the type of each to-be-executed task step, and the sequence of executable steps is obtained after the task planner sequentially performs semantic analysis, determines corresponding targets and constraints and performs corresponding task decomposition processing on a to-be-processed file carried in a user input instruction. The application improves task processing efficiency.

The application discloses a training method and device of a protein structure generation model, a protein structure generation method and device, and relates to the technical field of computers, in particular to the fields of artificial intelligence such as biological computing and deep learning. The specific implementation scheme is as follows: a noisy protein structure and a reference semantic representation of an original protein structure corresponding to the noisy protein structure are obtained; in the process of denoising the noisy protein structure by using an initial protein structure generation model, an intermediate hidden variable representation is extracted from the initial protein structure generation model; and the initial protein structure generation model is trained according to the intermediate hidden variable representation and the reference semantic representation, so as to obtain a trained protein structure generation model.

The present disclosure provides a protein design method, device, equipment and medium, relates to the field of artificial intelligence, in particular to the technical field of deep learning, biological computing and large language model. The generation method comprises the following steps: constructing a plurality of candidate proteins, each of which comprises a first chain of an original protein and a non-natural sequence constructed based on a second chain of the original protein; retrieving a first multiple sequence alignment of the first chain and a second multiple sequence alignment of the non-natural sequence; matching the first multiple sequence alignment and the second multiple sequence alignment to obtain a cross-chain homologous sequence by using a pre-trained initial protein language model; predicting the structure and a first score of the candidate protein by using a protein structure prediction model; determining a reward value based on the first score and performing reinforcement learning training on the initial protein language model; determining a second score of each of the plurality of candidate proteins by using the trained target protein language model and the protein structure prediction model, so as to obtain a protein design result.

The invention discloses a method for predicting the harmfulness of synonymous mutation based on multilevel biological characteristics. The method comprises the following steps: 1, collecting and preprocessing a synonymous mutation sample; 2, carrying out DNA, RNA and protein level feature annotation on the obtained synonymous mutation sample by using a biological calculation tool, and carrying out pretreatment; 3, performing dimension reduction on the high-dimensional biological characteristic data by using a causal characteristic selection algorithm to obtain a plurality of causal characteristic subsets; 4, splicing an optimal feature set and performing model construction and training by using a machine learning classifier; and 5, predicting an external test set sample by using the trained optimal model to obtain a synonymous mutation harmfulness prediction score. According to the method, the features having the causal relationship with the target variable can be screened out from the multi-level high-dimensional biological features, and then the causal features of the three biological levels are fused for prediction, so that the synonymous mutation harmfulness prediction precision is improved.

This disclosure provides a training method, design method, apparatus, and device for a protein reverse folding model, relating to the field of computer science, and particularly to artificial intelligence and biological computing technologies. The training method includes: acquiring a training sample set, which includes structural information of the target protein and the binding protein; inputting the training samples into the protein reverse folding model to obtain multiple candidate amino acid sequences of the binding protein; calculating the binding performance indices of the target protein and each candidate amino acid sequence of the binding protein, including complex conformation quantification indices and / or binding affinity quantification indices; constructing positive and negative sample pairs based on the binding performance indices; and training the protein reverse folding model based on a reinforcement learning algorithm and the positive and negative sample pairs to obtain the trained protein reverse folding model. This disclosure can improve the ability of protein reverse folding models to generate binding protein sequences with superior binding performance.

This invention discloses a molecular representation method and system based on deep graph neural networks, relating to the field of artificial intelligence technology, particularly to the fields of biological computing and deep learning. It addresses the problem in existing technologies where excessive smoothing prevents graph neural networks from increasing the number of graph convolutions to expand the receptive field of nodes. This invention utilizes a third-party library to convert computer-stored molecular data into a molecular graph, which includes an adjacency matrix, nodes, and edges. The molecular graph is analyzed to obtain initial feature vectors for the nodes and edges. Based on the graph neural network and the adjacency matrix, dense residual graph convolution operations are performed on the initial feature vectors of the nodes and edges to obtain new feature vectors for the nodes and edges. Pooling operations are then performed on the new feature vectors of the nodes and edges to obtain the molecular representation. This invention is used for molecular representation.