268results about "DNA computers" patented technology

Systems, methods, and apparatus for generating a DNA / gene sequence output, given a protein sequence input. In one aspect, the protein-to-DNA mapping system includes a protein language model (embedder) that generates a high-dimensional protein embedding from a low-dimensional protein sequence input; and the system includes a protein-to-DNA translator that processes the protein embedding and generates a DNA sequence output, based on the protein embedding. The protein-to-DNA translator is a neural network (e.g., a Seq2Seq model) and is configured with translation coefficients that may be trained with a training dataset, comprising the training protein and DNA embeddings. Training the translation coefficients can include supervised learning that maps the protein embedding (input) to a DNA sequence (target). The systems, methods, and apparatus may increase protein yield / expression, improve protein functionality, enhance gene therapy efficacy, streamline synthetic biology design, and / or broaden functional genomics studies, all leading to reduced costs, better performance, and increased accessibility.

Polymers synthesized by solid-phase synthesis are selectively released from a solid support by reversing the bias of spatially addressable electrodes. Change in the current and voltage direction at one or more of the spatially addressable electrodes changes the ionic environment which triggers cleavage of linkers that leads to release of the attached polymers. The spatially addressable electrodes may be implemented as CMOS inverters embedded in an integrated circuit (IC). The IC may contain an array of many thousands of spatially addressable electrodes. Control circuity may independently reverse the bias on any of the individual electrodes in the array. This provides fine-grained control of which polymers are released from the solid support. Examples of polymers that may be synthesized on this type of array include oligonucleotides and peptides.

The invention provides a wind and light storage-based building integrated energy microgrid capacity planning and operation optimization method, which comprises the following steps of: S1, constructing a system total cost model based on wind power and photovoltaic power characteristics, and determining wind power and photovoltaic capacity configuration; s2, constructing a worst operation scene power supply model according to wind power and photovoltaic uncertainty; s3, constructing an energy storage stock optimal configuration model according to the system total cost model and the worst operation scene power supply model, and calculating an energy storage stock optimal configuration strategy; and S4, evaluating the actual operation condition of the system according to the energy storage stock optimal configuration strategy, and optimizing the system according to the feedback of the actual operation condition. By means of multiple energy forms such as wind power, photovoltaic power and energy storage, the energy utilization efficiency can be improved, energy consumption and carbon emission are reduced, and clean, efficient and sustainable supply of energy is achieved.

The invention discloses an energy storage frequency modulation instruction prediction method and system with complementary advantages, and relates to the field of energy storage frequency modulation instruction prediction.The method comprises the steps that VMD decomposition and CEEMDAN decomposition are conducted on a frequency modulation instruction to be predicted, and a first subsequence set and a second subsequence set are obtained respectively; sequence interspersing is carried out, and first judgment is carried out; carrying out sequence fragment exchange on all mutually matched subsequences based on the result of the first judgment; predicting the subsequences after sequence fragment exchange through a GRU network, and correcting a prediction result to obtain a final energy storage frequency modulation instruction prediction result; according to the method, the advantages of VMD and CEEMDAN decomposition methods are integrated, the influence of noise and initial conditions on the decomposition effect is reduced, and the stability and reliability of decomposition are improved; the prediction accuracy of the frequency modulation instruction is improved; the size of the frequency modulation instruction is predicted in advance, the super capacitor / battery acts in advance, the response time difference is reduced, and the profit value of the power plant is improved.

In some embodiments, a method for encrypting a file includes receiving a file comprising file data and file metadata; retrieving a genomic differentiation object and genomic regulation instructions that define a set of operations that modify the genomic differentiation object; modifying the genomic differentiation object into a modified genomic differentiation object based on the genomic regulation instructions; extracting a sequence of bits from a predetermined set of bit locations of the file metadata; generating a genomic engagement factor based on the modified genomic differentiation object and the extracted sequence; and encrypting at least one portion of the file data using the genomic engagement factor.

The invention discloses a deep learning-based mixed-shooting image correction method and system, and relates to the field of computer vision, and the method comprises the steps: carrying out the illumination normalization processing of a mixed-shooting image group, and constructing a Gaussian pyramid image group; inputting the Gaussian pyramid image group into a ResNet-34 network to extract a multi-scale feature map, and generating spatial position and channel statistical information; and converting the spatial position and the channel statistical information into a DNA sequence fragment through a DNA base mapping rule. Illumination normalization is achieved through Retinex decomposition and Gaussian filtering, the exposure difference of different devices is effectively eliminated, the input quality of follow-up processing is guaranteed, traditional feature description is converted into biological sequence comparison through DNA base coding, geometric parameters are optimized in combination with quantum annealing, and the accuracy of the method is improved. The matching precision of a low-texture area and the correction effect of a large-view-angle-difference scene are remarkably improved, and the sub-pixel-level matching precision is achieved based on weighted RANSAC and multi-scale pyramid fusion.

The invention discloses a multi-parameter cooperative control method for non-excavation repair of a drainage pipe network in urban updating, and relates to the technical field of municipal engineering, and the method comprises the steps: firstly constructing a quantum entanglement sensing pipe network digital twinborn model, fusing multi-source data, monitoring micro-strain in real time through a nano sensor, deploying a self-organizing intelligent node and terahertz imaging equipment, and constructing a quantum entanglement sensing pipe network digital twinborn model; multi-dimensional features are extracted, repair parameters are dynamically regulated and controlled through technologies such as magnetofluid plugging and multi-robot cooperation based on digital twinning virtual simulation, finally, the repair effect is evaluated and the scheme is optimized in combination with cognitive calculation and microbial self-healing technologies, and full-process intelligent control is achieved. The intelligent level of non-excavation repair of the drainage pipe network is improved, the problem that traditional monitoring is one-sided is solved through high-precision data fusion, precise construction control is achieved through cooperation of magnetofluid leaking stoppage and the robot, durability is enhanced through the microorganism self-healing technology, repair quality and efficiency are improved, and urban updating and sustainable development are promoted.

The present disclosure, among other things, provides machine-learning technologies for identifying and localizing particular genomic elements (e.g., gene elements and / or regulatory elements) within nucleotide sequences, such as DNA and / or RNA sequences. In certain embodiments, similar to the manner in which image processing methods can be used to localize particular objects in images at pixel level resolution, referred to as “segmentation,” systems and methods of the present disclosure predict presence and locations of certain genomic elements within nucleotide sequences, thereby “segmenting” nucleotide sequences. Accordingly, genomic element segmentation technologies described herein may be used to generate annotations that identify and label portions of nucleotide sequences according to their predicted (e.g., via machine learning models described herein) function—e.g., as protein-coding genes, untranslated regions, splice sites, promotors, enhancers, etc. Among other things, these genomic annotations may be used to inform underlying biological processes driving diseases and facilitate development of new therapies.

A method for the production and use of scalable co-transcriptional RNA strand displacement (ctRSD) circuits using RNA toehold exchange gates is described. The ctRSD circuits described address the limitations of existing DNA-based strand displacement circuits by isothermally producing circuit components via transcription.

There is a demand for reliable, durable, and accurate methods of authentication in markets of specialty goods, e.g., luxury items and / or security-sensitive products. Currents methods of object authentication, including the incorporation of extrinsic and / or intrinsic markers, remain amenable to counterfeiting. This disclosure provides methods of object authentication and counterfeit protection using DNA sequences, including having multiple data cassettes assigned to a given bit code, and writing data using a mixture of the multiple cassettes in predetermined proportions, thereby providing validation and authenticity of the data.

The invention provides an invasive species identification method and device based on deep learning and DNA storage and electronic equipment, and relates to the technical field of invasive organism prevention and control, and the method comprises the steps: obtaining a to-be-identified invasive species image, and generating a first DNA sequence of a to-be-identified invasive species in the invasive species image through a deoxyribonucleic acid DNA encoder; obtaining a plurality of second DNA sequences to be hybridized from the invasive species database, and obtaining the hybridization yield of the first DNA sequence and each second DNA sequence by using a hybridization yield predictor; and determining the species category corresponding to the DNA sequence with the highest hybridization yield as the species category of the invasive species to be identified. According to the method provided by the invention, the strong feature extraction capability of deep learning is combined with the advantages of ultrahigh density and ultra-long stability of DNA as a data storage medium, so that end-to-end mapping and recognition from a species image to an exclusive DNA sequence thereof are realized.

The invention discloses an encryption communication method and system based on biological genetic coding chaos driving, and the method comprises the steps: receiving an original bit stream and an initial secret key, and generating a chaos sequence group according to the initial secret key through two hyperchaos models; performing DNA coding encryption on the original bit stream by using the chaos sequence to obtain a gene transmission sequence, and performing DNA decoding on the gene transmission sequence to obtain a transmission bit stream; performing constellation mapping on the transmission bit stream to obtain a constellation diagram, and performing subcarrier scrambling, symbol scrambling and constellation rotation on the constellation diagram according to the chaos sequence; performing OCDM modulation on the constellation diagram through an inverse discrete Fresnel transformation matrix to obtain a transmission signal; hiding the initial key in a frame header of a transmission signal, and sending the transmission signal to a receiver through a transmitter; according to the invention, multi-layer encryption of the OCDM signal and dynamic secret key follow-up transmission are realized.

A DNA-based storage system implements a sub-code architecture for error correction capability (ECC) purposes. The sub-code architecture enables a long DNA strand to be divided into two or more short DNA strands. Each short DNA strand has its own unique parity information. Additionally, each short DNA strand is separately decodable from the other short DNA strands. The parity information associated with a particular short DNA strand is used to correct any errors that occur or are detected during the decoding process. However, if the decoding and error correction processes are not successful using the parity information associated with the particular short DNA strand, global parity information is used to decode the particular short DNA strand and correct the errors. Global parity information includes information from each short DNA strand and the parity information associated with each short DNA strand.

RNA editing tools for use in systems designed to measure RNA in vivo and manipulate specific cell types are disclosed herein. An RNA sensor system comprising a) a single-stranded RNA (ssRNA) sensor comprising a stop codon and a payload; optionally wherein the ssRNA sensor further comprises a normalizing gene; and b) an adenosine deaminase acting on RNA (ADAR) deaminase; wherein the sensor is capable of binding to a ssRNA target to form a double-stranded RNA (dsRNA) duplex that becomes a substrate for the ADAR deaminase; wherein the substrate comprises a mispairing within the stop codon; and wherein the mispairing is editable by the ADAR deaminase, which editing can effectively remove the stop codon so as to enable translation and expression of the payload. A method of quantifying ribonucleic acid (RNA) levels using the RNA sensor system is also disclosed.

A cryoelectron microscope density map refinement method based on a mixed attention mechanism belongs to the field of bioinformatics, and comprises the following steps: firstly, constructing a training data set containing an experimental density map and a corresponding atomic structure, extracting feature embedding representation of the atomic structure by using a protein large language model, and generating a corresponding simulated density map according to the atomic structure; cutting each experimental density map and the corresponding simulated density map into blocks; thirdly, the experimental density map blocks and the structural features are embedded and input into a Transform deep learning network based on a mixed attention mechanism, and prediction density map blocks are generated; then calculating a loss difference value between each group of prediction density map blocks and the corresponding simulation density map block, and updating network parameters through a back propagation difference value; and finally, segmenting a to-be-processed cryoelectron microscope density map into a plurality of density map blocks, and predicting and assembling the density map blocks through the trained network to obtain a final refined density map. The method can improve the quality of the density map, and is high in robustness.

The present disclosure is directed to compositions and methods that use the principles of DNA origami to package and archive data stored in multiple indexed DNA oligonucleotides. These structures allow for selective physical data access and retrieval from a molecular pool of DNA origami (DNAO) nanostructures comprising the data bearing oligonucleotides.

The invention discloses an intelligent contract malicious transaction detection and analysis method based on data dynamic storage, and relates to the technical field of cloud computing, and the method comprises the steps: extracting transaction hash from a block, and obtaining transaction data from a block chain according to the transaction hash; performing synchronous simulation on the transaction data in the virtual machine to generate intermediate data; in a transaction simulation execution process, performing high-density dynamic storage on the intermediate data by adopting a DNA computing technology, establishing an index structure for quick retrieval, and reversely deducing a complete execution logic of the transaction; after data storage and logic inverse deduction are completed, a simulation execution task of a transaction is processed in parallel through distributed edge nodes, malicious transaction behaviors are identified through matching of an attack feature library, and a detection report is generated; according to the invention, by introducing a DNA calculation technology, high-density dynamic storage and rapid retrieval of intermediate data are realized; the simulation execution task of the transaction is processed in parallel through the distributed edge nodes, so that the malicious transaction detection efficiency is greatly improved.

A method for storage of an item of information (210) is disclosed. The method comprises encoding bytes (720) in the item of information (210), and representing using a schema the encoded bytes by a DNA nucleotide to produce a DNA sequence (230). The DNA sequence (230) is broken into a plurality of overlapping DNA segments (240) and indexing information (250) added to the plurality of DNA segments. Finally, the plurality of DNA segments (240) is synthesized (790) and stored (795).

The invention provides a Word document processing method and system based on a DNA genetic model, and relates to the technical field of document processing, and the method comprises the following steps: carrying out homogenization determination on two basic Word documents; splitting the document which is judged to be homogeneous into a chain A and a chain B, and performing variation processing on a title block; crossing and recombining to form two sub-documents; and evaluating the sub-documents based on the adaptive function, and adding the sub-documents with evaluation results higher than a threshold value into a resource pool. According to the method, diversified documents are generated by simulating a DNA genetic mechanism, the document generation efficiency is improved, different user requirements are met, and the content creation cost is reduced.

A system is provided for generating an electronic data fabric using virtualized photocrosslinking-based parallel computing process. In particular, the system may, using an artificial intelligence (“AI”) model, identify one or more users and a subject or description of a communication in order to determine the data needs of the one or more users, where such data may reside within one or more databases, websites, applications, tools, and / or the like. The system may then use a simulated photocrosslinking based process to assimilate various combinations of datasets and place the data sets within a virtualized environment. The virtualized data may then be linked to a data fabric to identify the linkages and / or sublinkages between the virtualized data and the underlying data. Subsequently, upon receiving a data request from a user, the system may use the metadata within the data fabric to dynamically recall the relevant data in real time.

The present invention relates to the field of data storage, and discloses a DNA-based dynamic balancing system, a data storage method, and a decoding method. During the process of encoding the first data to obtain a DNA molecular chain, various constraints are added to the first address and the second address, enabling the encoded data to be read efficiently and accurately. For example, the Hamming distance between the first address and the second address is greater than or equal to half of the length of the first address, reducing the possibility of address selection errors during reading; the prefix of the first address is different from the prefix of the second address and the suffix of the second address, avoiding the possibility of matching errors during the reading process; the content of guanine and cytosine in the prefix of each primer accounts for a preset ratio of the total content of guanine, cytosine, adenine, and thymine contained in the primer, resulting in high accuracy when sequencing is required to read the encoded data in advance.

Compositions, methods, and systems for handling liquids, for example, liquids containing one or more biological substances or chemical reagents, or combinations thereof. The liquid can be an "ink" containing nucleic acids (e.g., DNA) for "nucleic acid "printing" or "writing." These nucleic acids can include one or more components of nucleic acid molecules that encode digital information ("identifiers") that can be used in methods and systems for encoding digital information in nucleic acid. Described in this specification are technologies including an ink supply system and associated ecosystem for a DNA writing device for use with the technologies for encoding, storing, reading, and / or processing digital information in nucleic acid molecules.

Presented herein are writeable polymers (e.g., writeable nucleic acid polymers) and related methods for data storage. In general, writeable polymers (e.g., nucleic acid polymers) contain one or more convertible residues (e.g., convertible nucleic acid bases) that can be converted from a first state to a second state, and the first state and the second state are different. Various methods, such as polymerase extension by rolling circle reaction or chemical synthesis and ligation, can be used to generate writeable nucleic acid polymers. Also presented herein are various methods for writing or encoding into writeable nucleic acid polymers by selectively converting nucleic acid bases to a second state. Also presented herein are various methods for reading or decoding data from encoded nucleic acid polymers.

The disclosed technology relates to constructing a convolutional neural network based classifier for variant classification. More specifically, it relates to training a convolutional neural network based classifier on training data using a back-propagation gradient update method, which gradually matches the output of the convolutional neural network based classifier with the corresponding true value label. The convolutional neural network based classifier includes a residual block group, each residual block group is parameterized by the number of convolution filters in the residual block, the convolution window size of the residual block, and the hole convolution rate of the residual block, the convolution window size varies between the residual block groups, and the hole convolution rate varies between the residual block groups. The training data includes benign training examples and pathogenic training examples of translation sequence pairs generated from benign variants and pathogenic variants.

The present disclosure, among other things, provides machine-learning technologies for identifying and localizing particular genomic elements (e.g., gene elements and / or regulatory elements) within nucleotide sequences, such as DNA and / or RNA sequences. In certain embodiments, similar to the manner in which image processing methods can be used to localize particular objects in images at pixel level resolution, referred to as "segmentation," systems and methods of the present disclosure predict presence and locations of certain genomic elements within nucleotide sequences, thereby "segmenting" nucleotide sequences. Accordingly, genomic element segmentation technologies described herein may be used to generate annotations that identify and label portions of nucleotide sequences according to their predicted (e.g., via machine learning models described herein) function – e.g., as protein-coding genes, untranslated regions, splice sites, promotors, enhancers, etc. Among other things, these genomic annotations may be used to inform underlying biological processes driving diseases and facilitate development of new therapies.

Methods, systems, and apparatuses to encode data for storage in genetic materials. For example, a computing system may segment user data into a plurality of data blocks and generate seed data characterizing a plurality of fountain code seeds. Additionally, the computing system may, for each data block, implement a set of operations that generate one or more data packets. In some instances, the set of operations may include, for each of the plurality of fountain code seeds, determining a bit value and corresponding metaCode value and determining which of the fountain code seeds has a metaCode value of the bit value that matches a value of the bit position identified in the metadata. Moreover, the computing system may, for each data packet, cause an implementation of a second set of operations that synthesize a polynucleotide strand in accordance with at least bit values of the corresponding data packet.

A messenger RNA (mRNA) vaccine has emerged as a promising direction to combat the COVID-19 pandemic. This requires an mRNA sequence that is stable and highly productive in protein expression, features to benefit from greater mRNA secondary structure folding stability and optimal codon usage. Sequence design remains challenging due to the exponentially many synonymous mRNA sequences encoding the same protein. The present disclosure presents embodiments of a linear-time approximation (LinearDesign) reducing the design to an intersection between a Stochastic Context Free Grammar (SCFG) and a Deterministic Finite Automaton (DFA). Embodiments of the LinearDesign may implement an mRNA sequence design using much reduced time with very limited loss. Various methodologies, e.g., finding alternative sequences based on k-best parsing or directly incorporating codon optimality, are presented for incorporating the codon optimality into the design. Embodiments of the LinearDesign may provide efficient computational tools to speed up and improve mRNA vaccine development.

The invention provides a multimodal transport alternative path and transport scheme generation method based on road network node interruption. The method comprises the following steps: acquiring road network interruption information; if the road network interruption information is updated, for each original path, judging whether the original path comprises the road network interruption information or not; if yes, marking a break point in the original path, constructing an upstream candidate loading and unloading point set and a downstream candidate loading and unloading point set based on a first constraint condition, and selecting a loading and unloading node from each of the upstream candidate loading and unloading point set and the downstream candidate loading and unloading point set by adopting an upper-layer model by taking the minimum duration as a first objective function; inputting the selected first loading and unloading node and the selected second loading and unloading node into a lower-layer model, wherein the lower-layer model adopts a genetic algorithm to construct a multimodal transport replacement path set; and when the transportation unit travels to one end of the path, determining a final path based on the consumed time of each path, and constructing a multimodal transportation scheme.

The present patent application relates to the field of digital data storage onto a biomolecule, more particularly onto a nucleic acid.