9976results about "Sequence analysis" patented technology

The technology disclosed assigns quality scores to bases called by a neural network-based base caller by (i) quantizing classification scores of predicted base calls produced by the neural network-based base caller in response to processing training data during training, (ii) selecting a set of quantized classification scores, (iii) for each quantized classification score in the set, determining a base calling error rate by comparing its predicted base calls to corresponding ground truth base calls, (iv) determining a fit between the quantized classification scores and their base calling error rates, and (v) correlating the quality scores to the quantized classification scores based on the fit.

Localized detection of RNA in a tissue sample that includes cells is accomplished on an array. The array include a number of features on a substrate. Each feature includes a different capture probe immobilized such that the capture probe has a free 3′ end. Each feature occupies a distinct position on the array and has an area of less than about 1 mm2. Each capture probe is a nucleic acid molecule, which includes a positional domain including a nucleotide sequence unique to a particular feature, and a capture domain including a nucleotide sequence complementary to the RNA to be detected. The capture domain can be at a position 3′ of the positional domain.

This disclosure relates to methods for spatial profiling of analytes present in a biological sample. Also provided are methods for using spatially barcoded substrates to detect a biological analyte in a cell culture, an organism, and organoid. Also provided are methods for using spatially barcoded substrates to detect the temporal profile of a biological analyte.

Localized detection of RNA in a tissue sample that includes cells is accomplished on an array. The array include a number of features on a substrate. Each feature includes a different capture probe immobilized such that the capture probe has a free 3′ end. Each feature occupies a distinct position on the array and has an area of less than about 1 mm2. Each capture probe is a nucleic acid molecule, which includes a positional domain including a nucleotide sequence unique to a particular feature, and a capture domain including a nucleotide sequence complementary to the RNA to be detected. The capture domain can be at a position 3′ of the positional domain.

A method for aligning a sample to an array is provided. An image of sample image of a sample can be received by a data processor. The sample image having a first resolution. An array image including an overlay of an array with the sample and an array fiducial can be received by the data processor. The array image having a second resolution lower than the first resolution of the sample image. The sample image can be regisered to the array image by aligning the sample image and the array image. An aligned image can be generated based on the registering. The aligned image can can include an overlay of the sample image with the array. The aligned image can be provided by the data processor. A method for detecing fiducials associated with an array is provided. Systems and non-transitory computer readable mediums performing the method are also provided.

The invention discloses an identification method and system of a short antibacterial peptide sequence, a terminal and a storage medium. Relates to the technical field of bioinformatics. A short antibacterial peptide data set is obtained in advance, a training set is obtained through division according to the short antibacterial peptide data set, and a pre-trained protein language model is finely adjusted according to the training set; obtaining sequence features of a to-be-classified sequence through the fine-tuned protein language model; obtaining physicochemical characteristics of the to-be-classified sequences through an analysis method based on pseudo amino acid components; inputting the sequence features and the physicochemical features into an attention model for feature fusion to obtain fusion features of the to-be-classified sequence; and inputting the fusion features into a classifier to obtain a prediction category of the to-be-classified sequence. According to the method, the pre-training model is finely adjusted by establishing a more perfect short antibacterial peptide data set, the sequence features and the physicochemical features of the to-be-classified sequences are fused, and the sequences are classified through the fused features, so that the recognition accuracy of the short antibacterial peptides can be effectively improved.

The invention discloses a traditional Chinese medicinal material authenticity identification platform, and relates to the technical field of traditional Chinese medicinal material authenticity identification, the traditional Chinese medicinal material authenticity identification platform comprises a data acquisition module, the data acquisition module is connected with a data analysis module, and the data analysis module is connected with a result display module; and the data acquisition module is used for acquiring appearance images, spectral data and background information of the traditional Chinese medicinal materials. According to the traditional Chinese medicine authenticity identification platform, traditional Chinese medicines are comprehensively analyzed from multiple angles, limitation of a single method is avoided, and identification accuracy is improved; the characteristics of the traditional Chinese medicinal materials are deeply analyzed to accurately judge authenticity and quality; the quality of the traditional Chinese medicinal materials is accurately evaluated by establishing a quantitative analysis model; the model is verified by adopting a cross validation method, so that the accuracy and stability are ensured, the identification accuracy is improved, and the problem that the traditional identification method is difficult to meet the requirement of quickly and accurately identifying the authenticity of the traditional Chinese medicinal materials is solved.

The invention discloses a whole course follow-up visit management system and method for gynaecology and obstetrics patients, and relates to the field of medical information management.The method comprises the steps that when a patient sees a doctor for the first time, basic information, medical related information, medical image data, gene detection data, sensor data and patient self-report data of the patient are input; preprocessing the input patient data, and integrating the preprocessed patient data into a personal health record; establishing a health assessment model of the patient based on the integrated personal health record, outputting a current health assessment score of the patient, and generating a follow-up visit plan according to the current health assessment score of the patient; and establishing an obstetrical complication prediction model based on the personal health record, and outputting a patient complication prediction value. Potential obstetrical complication risks are recognized in advance, especially when the health condition of the pregnant and lying-in woman changes, the prediction result can be dynamically updated, real-time monitoring and early warning of complication are achieved, and safety management of the lying-in woman is optimized.

The invention discloses a benign and malignant nodule grading evaluation system based on large model fusion ultrasonic imaging and thyroid gene markers, which can organically fuse non-invasive examination and serological detection, can simulate and diagnose multi-grade risk probability information provided by a gold standard, realizes similar risk grading estimation in a non-invasive mode, and has a wide application prospect. The thyroid nodule risk assessment method can provide visual explanation conforming to clinical logic based on comprehensive information of iconography and molecular biology, can significantly improve the accuracy of thyroid nodule risk assessment, can also effectively improve clinical decision-making efficiency and patient credibility, and has important clinical application prospects. The system comprises a data acquisition module, an ultrasonic image feature extraction module, a gene marker feature extraction module, a multi-modal fusion and hierarchical reasoning module and a generation module.

The invention provides a water pollutant traceability method based on environmental DNA and machine learning. The method comprises the following steps: S1, investigating and surveying a regional pollutant source and representing water characteristics; s2, environment DNA extraction, specific primer amplification and DNA sequencing quantification; s3, constructing and training a machine learning model by using the DNA data and the water quality data; and S4, collecting a water sample in an actual pollution area, inputting data to the model, and outputting a pollution source type and a proportion. According to the method, the environment DNA technology and the machine learning model are combined, the water pollutant tracing method which is suitable for various pollution sources, accurate and efficient is innovatively provided, and the method has high application value and wide popularization prospects.

This disclosure relates to methods for spatial profiling of analytes present in a biological sample. Also provided are methods for using spatially barcoded substrates to detect a biological analyte in a cell culture, an organism, and organoid. Also provided are methods for using spatially barcoded substrates to detect the temporal profile of a biological analyte.

Methods for making synthetic gene clusters are described.

The invention relates to the field of drug-target affinity prediction, in particular to a drug-target affinity prediction method based on a multi-scale mixed attention network. According to the method, global residue characteristics can be learned by protein pocket residues by utilizing a self-attention mechanism, so that the global characteristics of the protein are learned. In addition, a cross-modal feature fusion mechanism is utilized, protein and drug structural features are enhanced in sequence features, cross-modal feature fusion in entities is enhanced, meanwhile, a cross-entity interaction module is utilized to recognize key atoms of drug molecules or key residues of protein, and therefore the overall performance of the model is improved. Finally, multi-level protein feature extraction is further introduced to further extract protein features.

The invention discloses a space transcriptomics cell type deconvolution method based on a generative adversarial network and a comparative learning framework. The method comprises the following steps: firstly, enhancing a gene expression matrix by using a histological image and spatial position information; then, in combination with GraphSAGE and self-supervised comparative learning, optimizing feature representation of space transcriptomics data, and reconstructing high-quality space gene expression data; single-cell RNA sequencing data gene expression features are extracted by using a variational automatic encoder, and meanwhile, the quality of a generated sample is optimized by using a discriminator, so that efficient feature extraction and accurate gene expression reconstruction are realized; and finally, mapping single-cell RNA sequencing data into spatial points through comparative learning and mapping matrix learning based on low-rank representation, thereby predicting the cell type of each point. According to the model, multi-modal information in single-cell RNA sequencing and space transcriptomics data is comprehensively considered, and a mapping matrix is constructed and optimized, so that the cell type of each space point is predicted.

A method and system for determining one or more sources of a cell free deoxyribonucleic acid (cfDNA) test sample from a test subject. The cfDNA test sample contains a plurality of deoxyribonucleic acid (DNA) molecules with numerous CpG sites that may be methylated or unmethylated. A trained deconvolution model comprises a plurality of methylation parameters, including a methylation level at each CpG site for each source, and a function relating a sample vector as input and a source of origin prediction as output. The method generates a test sample vector comprising a site methylation metric relating to DNA molecules from the test sample that are methylated at that CpG site. The method inputs the test sample vector into the trained deconvolution model to generate a source of origin prediction indicating a predicted DNA molecule contribution of each source.

The invention discloses a drug and target interaction prediction method based on multi-scale convolution feature fusion, which comprises the following steps: acquiring drug molecule data, target protein data and drug and target interaction data, constructing a drug molecule map according to the drug molecule data, and coding a target protein sequence according to the target protein data; inputting the drug molecular map into a model, and obtaining drug features through a multi-scale map convolutional network and a dynamic gating attention mechanism; inputting a target protein sequence into the model, and obtaining target features through hierarchical cavity convolution and a bidirectional gating cycle unit; through multi-head cross attention, the drug features are aligned with the target features, local and global cross-modal fusion is carried out, and drug target fusion features are obtained; based on the drug target fusion features, outputting a drug and target interaction prediction probability; and training the model according to the drug and target interaction data and the prediction probability, and applying the trained model to drug and target interaction prediction.

The invention relates to the technical field of genomics, in particular to a gene detection data cleaning method and system based on artificial intelligence. The method comprises the following steps: acquiring gene detection data, and performing preliminary filtering on the gene detection data based on removal of low-quality reads to obtain preliminary filtering data; performing linker sequence identification and removal on the preliminarily filtered data, and performing sequencing error correction to generate gene sequence data; performing GC content analysis and repetitive sequence identification on the gene sequence data to obtain sequence feature data; performing dynamic quality threshold adjustment according to the sequence feature data, and performing secondary filtering on the gene sequence data to generate high-quality sequence data; and performing sequence pattern recognition on the high-quality sequence data to obtain sequence pattern feature data. According to the method, deep analysis is carried out by utilizing sequence characteristics such as GC content and nucleotide distribution, and the recognition capability on sequence complexity and variation modes is improved.

The invention relates to the technical field of health management, in particular to a gastrointestinal health assessment and management method based on big data, and the method comprises the following steps: S1, health data collection: collecting multi-dimensional health data of a user; s2, data preprocessing: preprocessing the collected multi-dimensional health data; s3, regulating and analyzing intestinal microecology, namely classifying and analyzing intestinal flora based on the intestinal flora gene sequencing data of the user in combination with living habits and diet data, identifying the condition of flora imbalance, and dynamically regulating flora balance through personalized regulation suggestions; s4, gastrointestinal health state evaluation: comprehensively evaluating the gastrointestinal health state of the user; and S5, generating a personalized health management scheme: generating the personalized health management scheme. According to the invention, by monitoring the health feedback of the user in real time, the scheme can be dynamically adjusted, so that the intervention is more flexible and targeted.

The invention discloses a DNA binding residue prediction method based on a multi-modal protein language model in the technical field of bioinformatics. The DNA binding residue prediction method based on the multi-modal protein language model comprises the following steps: sequentially using tools to respectively obtain feature files of a protein sequence P to be subjected to DNA binding residue prediction; inputting all the feature files into the ESM3 to obtain an embedded matrix M; the method comprises the following steps: processing a protein sequence into a residue sample, constructing an isovariant graph neural network model according to a protein structure diagram, constructing a data set by utilizing the protein sequence of known DNA binding residues, and training the constructed network; and inputting a residue sample of the protein sequence into the trained model to obtain a DNA binding residue of the protein sequence. According to the DNA binding residue prediction method based on the multi-modal protein language model, the efficiency and accuracy of DNA binding residue prediction are improved.

The invention relates to the technical field of drug research and development, and discloses a drug-like molecule screening system and method based on deep learning, and the system comprises a physical and chemical characteristic analysis module which is used for calculating molecular descriptors of compounds and generating a visual characteristic distribution chart; and the drug-like molecule screening module integrates a Lipinski rule, a Veber rule, a Ghose rule and a Muegge rule, and supports a user to customize a screening rule. Compound characteristics are comprehensively analyzed through the physical and chemical characteristic analysis module, flexible screening is achieved through the drug-like molecule screening module, toxicity risks are accurately recognized through the toxicity assessment module, the affinity assessment module is combined to assess the binding capacity in multiple ways, and the synthesis feasibility assessment module plans an efficient and low-cost synthesis path. The dynamic feedback optimization module continuously improves the system performance; all the modules work cooperatively, the problems of scattered tools, insufficient precision, low planning efficiency, optimization deficiency and the like in the prior art are effectively solved, the medicine research and development efficiency is greatly improved, and the research and development risk and cost are reduced.

The invention discloses an emergency prediction and early warning method for an overwater oil spill and hazardous chemical substance leakage accident. The method comprises the following steps: establishing an inland river basic database; constructing an environmental ecological effect model of the oil spill event; biological population changes under the influence of the oil spill event are identified; evaluating the influence of the oil spill event on the ecological system by using an eDNA macro stripe code technology; based on a biostatistics method, analyzing the relationship between the microbial community and the environmental elements; multi-dimensional real-time monitoring and early warning are carried out on an oil spill event; and a targeted sewage disposal scheme and ecological restoration measures are provided. According to the method, aerial remote sensing, ship and shore-based radar, video monitoring and buoy data are combined, multi-dimensional real-time monitoring and early warning of oil spill events are achieved through a multi-source data fusion technology, a traditional method usually only depends on a single data source, the monitoring accuracy and timeliness are improved, and the method is suitable for popularization and application. And after an oil spilling event occurs, a response can be made more quickly, and the damage of the accident to the environment and the economy is effectively reduced.

Described are DNA sequencing systems and methods. Systems and methods may calculate a genomic null distribution of read pairs on a flow cell having approximately zero probability of being linked with one another and calculate a spatial null distribution of read pairs having approximately zero probability of being spatially linked. The system may generate a link quality score representing a probability of incorrectly assigning a link between the two polynucleotide reads based on the calculated genomic null distribution and the calculated spatial null distribution.

The present disclosure relates to methods, compositions and systems for droplet processing. For example, methods can include (a) providing a first emulsion comprising a first droplet population, wherein droplets of the first droplet population comprise a lysis reagent, and a second emulsion comprising a second droplet population, wherein a droplet of the second droplet population comprises i) a cell or a nucleus, and ii) a plurality of nucleic acid barcode molecules; (b) subjecting the first emulsion and second emulsion to conditions sufficient to transfer the lysis reagent to the second droplet population via micelles comprising the lysis reagent; and (c) lysing the cell or the nucleus within the droplet of the second droplet population with the lysis reagent.

The present disclosure relates to methods, compositions and systems for droplet processing. For example, a method can include (a) partitioning a plurality of cells into a plurality of aqueous droplets, wherein an aqueous droplet of the plurality of aqueous droplets comprises a cell of the plurality of cells; and delivering a micellized lysis agent to the cell in the aqueous droplet.

Embodiments of this invention provide methods, systems, and apparatus for determining whether a fetal chromosomal aneuploidy exists from a biological sample obtained from a pregnant female. Nucleic acid molecules of the biological sample are sequenced, such that a fraction of the genome is sequenced. Respective amounts of a clinically-relevant chromosome and of background chromosomes are determined from results of the sequencing. The determination of the relative amounts may count sequences of only certain length. A parameter derived from these amounts (e.g. a ratio) is compared to one or more cutoff values, thereby determining a classification of whether a fetal chromosomal aneuploidy exists. Prior to sequencing, the biological sample may be enriched for DNA fragments of a particular sizes.

The invention provides a method for predicting the relative abundance of antibiotic resistance genes in surface water and application. The method comprises the following steps: acquiring ARGs relative abundance, water quality physicochemical indexes and genus level bacteria relative abundance of a water sample to be detected, and judging potential bacterial hosts of ARGs by Spearman correlation; the method comprises the following steps: taking water quality physicochemical indexes and relative abundance of potential bacterial hosts as characteristic variables, and respectively taking relative abundance of multidrug ARGs and total ARGs as target variables; adopting automatic machine learning to screen an optimal algorithm; determining an optimal feature set through feature importance ranking and model comparison; and establishing an optimal prediction model to predict the relative abundance of the multi-drug ARGs and the total ARGs of the water sample to be detected. According to the method, the water environment ARGs are predicted based on environmental factors and bacterial indexes, the model accuracy is high, and main driving factors and potential bacterial hosts influencing propagation and proliferation of the ARGs can be identified through interpretable analysis between features and target variables.

A method for predicting one or more features of an antigen-binding protein is provided, comprising: providing the amino acid sequence of at least part of one or more chains of the antigen-binding protein or an encoded sequence derived therefrom as input to a deep learning model comprising a sequence encoding module configured to take as input an amino acid sequence and to produce as output an embedding corresponding to the input sequence, and predicting the one or more features of the antigen-binding protein using the embedding produced by the sequence encoding module The sequence encoding module has been trained as part of a machine learning model comprising a structure encoding module, and using training sequence data and structure data from a plurality of antigen-binding proteins. Related methods, systems and products are also described.

The invention belongs to the technical field of allele typing, and discloses a gene haplotype typing method and device based on sequencing data and a medium, and the method comprises the following steps: obtaining to-be-detected gene sequencing data from a to-be-detected sample; splitting the sequencing data into genes according to a reference sequence, and performing variation information detection and variation information filtering; after sequence splitting is carried out on the basis of the sequence obtained after variation information filtering, the haplotype sequence obtained after sequence splitting is corrected, and a to-be-detected gene haplotype typing result of the to-be-detected sample is obtained. According to the method, complex calculation is simplified by adopting a mode of firstly splitting sequences into genes, the method does not completely depend on sequence comparison results, and similar typing is finally evaluated by adopting a mode of combining comparison with backtracking variation information scoring, so that typing difference information can be effectively refined, and interference of sequencing data noise on the results is reduced; and a haplotype result is verified for multiple times by adopting a primary typing and correction mode, so that the result accuracy is higher.

Provided are a protein language model training method, a method for extracting an amino acid sequence representation by using a protein language model, a method for obtaining a new amino acid sequence by using a protein language model, a method for obtaining a related amino acid sequence by using a protein language model, a method for predicting an amino acid sequence perplexity by using a protein language model, an electronic device, a computer-readable medium, and a program product. The protein language model training method comprises: during a training process, executing at least one training sub-task amongst two training sub-tasks included in a first type of training task and a second type of training task; and, on the basis of a first loss value corresponding to the first type of training task and a loss value corresponding to the second type of training task, adjusting parameters of a protein language model to obtain a trained protein language model.