15results about How to "Short sequence length" patented technology

The invention provides a novel IRES sequence suitable for circular RNA and a variant and an untranslated region sequence of the IRES sequence. The invention provides a circular RNA drug containing the IRES sequence, the untranslated region sequence and the protein coding sequence. The circular RNA drug platform has efficient protein translation ability (especially in immune cells), simplified sequence length and compatibility to various protein sequences, and the drug based on the circular RNA platform shows a good treatment effect in an animal tumor model.

The invention provides a method and a device for enhancing understanding of a long video aligned with audio information, and solves the problems that the audio information in the video is not considered and the training and reasoning cost of a large language model is high when video data is processed in the prior art. The method has the advantages that 1) through the cross attention module, video spatial-temporal feature fusion is enhanced, meanwhile, the sequence length of video picture features is reduced, and the training cost is further reduced; 2) audio modality and alignment in the video are realized by encoding audio information in the video and down-sampling to a sequence length of video picture characteristics; and 3) adding the audio mode and the picture mode which are aligned in time dimension to perform information fusion, aligning the audio mode with the length of the video picture mode which is selected at intervals through down-sampling to retain all information, and then adding with the picture mode to solve the problem of information loss caused by interval frame extraction in the picture mode.

The invention provides a controllable generation method and system for symbolic music, electronic equipment and a computer readable storage medium, and the method comprises the steps: carrying out the preprocessing of the pre-obtained music content and annotation information through a preset representation module, so as to form an original data set; performing masking processing on the original data set according to a preset chord condition rule to form an original masking data pair, and sending the original masking data pair into a preset music discrete diffusion framework for repeated training to form a music discrete diffusion model; and then performing preorder processing on the music frequency band and the music demand input by the user to form a music content representation and condition matrix, inputting the music content representation and condition matrix into the music discrete diffusion model, and enabling the music discrete diffusion model to perform music generation so as to output a target music score. The richness of music controllable generation can be realized, and the reliability and rationality can be improved.

The invention belongs to the technical field of biology, and particularly relates to an immune engineering cell for expressing a discontinuous truncated functional region of GM-CSF and application. The invention firstly provides a CAR-NK cell for expressing a discontinuous truncated functional region of GM-CSF, and the CAR-NK cell expresses a novel chimeric antigen receptor structure; the novel chimeric antigen receptor structure comprises a discontinuous truncated functional domain fragment of a GM-CSF protein and a chimeric antigen receptor; the non-continuous truncated functional domain fragment of the GM-CSF protein comprises an A helix fragment, a C helix fragment and an exon 2 fragment. The invention also provides a CAR-T cell for expressing the discontinuous truncated functional region of the GM-CSF as well.

The invention belongs to the technical field of biology, and particularly relates to an immune engineering cell for expressing an exon 2 functional area of GM-CSF and application. The invention firstly provides a CAR-NK cell which expresses a novel chimeric antigen receptor structure; the novel chimeric antigen receptor structure comprises an exon 2 functional domain fragment of a GM-CSF protein and a chimeric antigen receptor. The invention also provides a CAR-T cell of the exon 2 functional domain fragment which also expresses the GM-CSF. The invention provides a novel chimeric antigen receptor structure modified by a fragment only containing a unique functional region in the full-length GM-CSF, which not only retains the function equivalent to that of the traditional CAR and CAR-GM, but also obtains an improved function.

The application discloses a text reading comprehension method and device based on article difference perception representation, a storage medium and an electronic equipment, belongs to the field of natural language processing and artificial intelligence, and aims to solve the technical problems of how to effectively utilize article information to improve the accuracy of answer selection and how to realize effective matching between a question and options, thereby improving the prediction accuracy of a text reading comprehension system, and adopts the technical scheme that: ① a text reading comprehension method based on article difference perception representation comprises the following modules: a pre-training embedding representation module, a feature filtering module, an article difference perception representation interaction module and a label prediction module. ② a text reading comprehension device based on article difference perception representation comprises a text reading comprehension data set acquisition unit, a text reading comprehension model construction unit and a text reading comprehension model training unit.

This invention discloses a three-dimensional breast ABUS image classification method, electronic device, and computer-readable storage medium based on a tokenized bi-branch selective state-space model. The method preprocesses the three-dimensional ABUS volume data and inputs it into a hierarchical pyramidal classification network. The network constructs local convolutional branches and a global state-space branch in its basic modules: the local branch uses lightweight three-dimensional grouped convolution to extract texture and boundary morphology; the global branch aggregates features into a token map through voxel token generation, then performs multi-axis bi-directional selective state-space scanning and adaptive fusion using routing weights. After detoxing, the core features are injected through a gating mechanism. Finally, the classification result is output through three-dimensional global average pooling and a fully connected layer, enhancing the ability to model long-range dependencies across slices with near-linear complexity.

The present invention discloses a boiler level risk warning method based on CNN-Transformer. After the local features obtained by the CNN network are input into the multi-head attention mechanism of the Transformer model, the features extracted from the multi-head attention mechanism are returned to the pooling layer of the CNN network for pooling operation, and the data after pooling is returned to the Transformer model. The present invention has the advantages of being able to extract more important features, reduce sequence length, and improve processing efficiency.

The application discloses a three-dimensional feature representation-based intelligent text reading comprehension method and device, a storage medium and an electronic device, and belongs to the fields of natural language processing and artificial intelligence; the technical problem to be solved by the application is how to capture direct interaction features between three-sequence data and how to enhance sufficient interaction among an article, a question and options, so as to improve the prediction accuracy of an intelligent text reading comprehension system; the technical scheme adopted is as follows: ① a three-dimensional feature representation-based intelligent text reading comprehension method, comprising the following modules: a pre-training embedding representation module, a feature filtering module, a 3D CNN interaction feature module and a label prediction module; ② a three-dimensional feature representation-based intelligent text reading comprehension device, comprising: an intelligent text reading comprehension data set acquisition unit, an intelligent text reading comprehension model construction unit and an intelligent text reading comprehension model training unit.

The invention belongs to the technical field of biology, and particularly relates to an immune engineering cell for expressing a continuous truncated functional region of a GM-CSF and application of the immune engineering cell. The invention firstly provides a CAR-NK cell for expressing a continuous truncated functional region of GM-CSF, and the CAR-NK cell expresses a novel chimeric antigen receptor structure; the chimeric antigen receptor structure comprises a continuous truncated functional domain fragment of a GM-CSF protein and a chimeric antigen receptor; the continuous truncated functional domain fragment of the GM-CSF protein comprises an A helix fragment, an exon 1 fragment and a C helix fragment. The invention also provides a CAR-T cell which also expresses the continuous truncated functional region of the GM-CSF.

The invention discloses a porcine PR-39-derived anti-enzymolysis antibacterial peptide and a preparation method and application thereof, and belongs to the technical field of bioengineering, the sequence of the antibacterial peptide is shown as SEQ ID No.1, an Arg-Pro amino acid structure is used for ensuring the positive charge number and providing the trypsin enzymolysis resisting capacity at the same time, phenylalanine is added for improving the hydrophobicity, and the antibacterial peptide can be used for preparing an anti-enzymolysis antibacterial peptide. The sequence is obtained by taking an RPPF amino acid sequence as a basic structural unit and repeating for six times. The invention further discloses application of the antibacterial peptide in preparation of drugs for treating infectious diseases caused by gram-negative bacteria or / and gram-positive bacteria. The antibacterial peptide has extremely high antibacterial activity and extremely low cytotoxicity to various bacteria, the cell survival rate can still reach 80% or above under the high concentration, and in addition, the antibacterial peptide has high stability under the conditions of high-concentration trypsin and artificial intestinal juice; therefore, the antibacterial peptide has relatively strong potential of replacing antibiotics.

The invention provides a ViT model improvement method, system and device and a storage medium, and belongs to the technical field of computer vision. The method comprises the following steps: firstly, dividing an input image into a plurality of non-overlapped patches, and carrying out embedding processing on each patch to generate initial feature sequence representation; clustering the features of the adjacent patches by using a K-means clustering algorithm with spatial constraint, combining the adjacent patches with similar semantic features into K classes, and extracting the feature of each clustering center as a new feature representation; and finally, inputting the clustered feature sequence into ViT for self-attention calculation and feedforward network processing, and generating final image feature representation. According to the method, semantic similar patches are aggregated, the length of an input sequence is reduced, the calculation complexity is reduced, redundant information is reduced, the local semantic understanding ability is enhanced, and the method is suitable for visual tasks such as image classification and target detection.

The invention belongs to the technical field of biology, and particularly relates to an immune engineering cell for expressing an Ahelix functional region of a GM-CSF and application of the immune engineering cell. The invention firstly provides a CAR-NK cell which expresses a novel chimeric antigen receptor structure; the novel chimeric antigen receptor structure comprises an Ahelix functional domain fragment of a GM-CSF (Granulocyte-Macrophage-Colony-Stimulating Factor) protein and a chimeric antigen receptor. The invention also provides a CAR-T cell of the Ahelix functional domain fragment which also expresses the GM-CSF (granulocyte macrophage-macrophage colony-stimulating factor). The invention provides a novel chimeric antigen receptor structure modified by least functional region fragments only containing full-length GM-CSF, which not only retains the functions equivalent to those of traditional CAR and full-length GM-CSF CAR, but also obtains improved functions.

The application belongs to the field of molecular biology, and discloses a gene editing method suitable for A. terreus. First, an editing vector is constructed by using a codon-optimized EnAsCas12f1 gene, and then the editing vector is added to protoplasts of A. terreus, so that the editing of a target gene is realized through transformation. The editing vector has a higher transformation efficiency than Cas9 when the editing vector is used to transform A. terreus.

The invention discloses a wind power prediction method, device and equipment and a storage medium, and the method comprises the steps: inputting a current wind speed data sequence and an air pressure data sequence into a preset wind power prediction model, and outputting a wind power prediction sequence corresponding to a future moment; wherein the wind power prediction model comprises an encoder and a decoder; the encoder is used for performing distillation operation, one-dimensional convolution processing and maximum pooling processing on a wind speed prediction data sequence and an air pressure prediction data sequence, reducing the sequence lengths of the wind speed prediction data sequence and the air pressure prediction data sequence, and generating an input sequence of the decoder; and the decoder is used for generating a wind power prediction sequence corresponding to a future moment at one time according to a mask multi-head self-attention mechanism and the input sequence. According to the method, the problems that a large amount of memory is occupied by long-time sequence input and output and the secondary complexity of calculation time is relatively high can be solved.