21 results about "Nucleic acid methylation" patented technology

Provided are systems and methods for cell-free nucleic acid sequencing to assess a condition.Generally, cell-free nucleic acid samples are used to perform methyl sequencing, targeting specific regions associated with abnormal methylation.The methylation of cell-free nucleic acid molecules can be evaluated based on sequencing results.Various features can be derived from methylation evaluation and used in computational models to assess cell-free nucleic acid samples for a condition.

The present disclosure provides methods and systems for screening or detecting a colorectal cancer or following colorectal disease progression that may be applied to cell-free nucleic acids such as cell-free DNA. The method may use detection of methylation signals within a single sequencing read in identified genomic regions as input features to train a machine learning model and generate a classifier useful for stratifying populations of individuals. The method may comprise extracting DNA from a cell-free sample obtained from a subject, converting the DNA for methylation sequencing, generating sequencing reads, and detecting colon proliferative cell disorder-associated signals in the sequencing information and training a machine learning model to provide a discriminator capable of distinguishing groups in a subject population such as healthy, cancer or distinguishing disease subtype or stage. The method may be used for, e.g., predicting, prognosticating, and / or monitoring response to treatment, tumor load, relapse, or colorectal cancer development.

The disclosure relates to methods for determining the methylation profile of nucleic acids. The methods use base conversion methods in combination with methylation-based partitioning methods to resolve multiple types of methylation in a single workflow.

The present disclosure provides methods and systems for screening or detecting colorectal cancer or subsequent colorectal disease progression, which can be applied to cell-free nucleic acids, such as cell-free DNA. The methods can train a machine learning model using detection of methylation signals within single sequencing reads in identified genomic regions as input features, and generate a classifier suitable for stratifying a population of individuals. The methods can include extracting DNA from a cell-free sample obtained from a subject, transforming the DNA for methylation sequencing, generating sequencing reads, and detecting colon proliferative cell disorder related signals in the sequencing information, and training a machine learning model to provide a discriminator capable of distinguishing between groups such as healthy, cancer, etc. in a population of subjects, or distinguishing between disease subtypes or stages. The methods can be used, for example, to predict, prognosticate, and / or monitor response to treatment, tumor burden, recurrence, or progression of colorectal cancer.

Methods and systems provided herein address current limitations of bisulfite-based methylation sequencing by improving the quality and accuracy of nucleic acid methylation sequencing and uses thereof for detection of disease. Methods that include minimally-destructive conversion methods for methylation sequencing as well as specialized UMI adapters provide for improved quality of sequencing libraries and sequencing information. Greater accuracy and more complete methylation-state information permits higher quality feature generation for use in machine learning models and classifier generation.

Methods and systems provided herein address current limitations of bisulfite-based methylation sequencing by improving the quality and accuracy of nucleic acid methylation sequencing and uses thereof for detection of disease. Methods that include minimally-destructive conversion methods for methylation sequencing as well as specialized UMI adapters provide for improved quality of sequencing libraries and sequencing information. Greater accuracy and more complete methylation-state information permits higher quality feature generation for use in machine learning models and classifier generation.

The present disclosure provides methods and systems for detecting colorectal cancer by nucleic acid methylation analysis. In particular, the present disclosure provides methods and systems for screening or detecting colorectal cancer or subsequent colorectal disease progression, which can be applied to cell-free nucleic acids, such as cell-free DNA. The method may train a machine learning model using detection of methylation signals within a single sequencing read in an identified genomic region as an input feature and generate a classifier suitable for layering a population of individuals. The method may include extracting DNA from a cell-free sample obtained from a subject, transforming the DNA for methylation sequencing, generating a sequencing read, and detecting a colonic proliferative cell disorder related signal in sequencing information, and training a machine learning model to provide a discriminator, the discriminator is capable of differentiating groups, such as health, cancer, or differentiating disease subtypes or stages, in a population of subjects. The methods are useful, for example, in predicting, prognosing, and / or monitoring response to treatment, tumor load, recurrence, or progression of colorectal cancer.

A computer-implemented method for characterizing disease progression is provided. The computer-implemented method may include: receiving, at a computing device, a set of nucleic acid methylation data; receiving, at the computing device, a designation of one or more genomic regions; generating, using a processor of the computing device, a trajectory of disease progression; identifying, using the processor and within the set of nucleic acid methylation data, one or more temporal methylation features associated with progression along the trajectory; and mapping, using the processor, the one or more temporal methylation features to the one or more genomic regions.

The present disclosure is concerned with modified proteins, methods, compositions, and kits for mapping of methylation status of nucleic acids, including 5-methylcytosine and 5-hydroxymethyl cytosine (5hmC). The proteins selectively act on certain modified cytosines of target nucleic acids and include one or more substitution mutations that enhance the selectivity of the proteins for certain modified cytosines, enhance the stability of the proteins, or enhance both selectivity and stability. Also provided are compositions and kits that include one or more of the proteins and methods for using one or more of the proteins.

The invention discloses a medical data processing method and system and a medium. The method comprises the following steps: acquiring test data; inputting the test data into a trained methylation marker screening model to obtain a screening result, performing feature extraction on the test data, and performing classification by using a two-layer classifier to obtain the screening result; and based on the screening result, outputting the screening result to a user side for visual display. According to the method, DNA methylation data of normal tissues and cancer tissues and serum circulating nucleic acid methylation data of healthy people and cancer patients are combined, a methylation marker screening method is constructed from an alpha value, meanwhile, four data characteristics are developed from the alpha value and a beta value, an ensemble learning model is constructed from four data dimensions, and the methylation marker screening method is established. Therefore, the sensitivity and the specificity of cancer early screening are remarkably improved.

A method for discriminating a cancer state is provided. A first dataset is obtained for a plurality of subjects having a first cancer state. Each subject has a plurality of nucleic acid methylation fragments with methylation patterns comprising CpG site methylation states. An autoencoder including an encoder and decoder is trained by evaluating the error in the autoencoder reconstruction of the methylation pattern and nucleic acid sequence of each nucleic acid methylation fragment in the first dataset. A second dataset is obtained for a plurality of subjects having a second cancer state. A plurality of features is identified by inputting the methylation pattern and nucleic acid sequence of each nucleic acid methylation fragment in the second dataset into the trained autoencoder and computing a score determined by the autoencoder reconstruction of the methylation pattern. The plurality of features is used to train a supervised model that discriminates a cancer state.

The present disclosure is concerned with proteins, methods, compositions, and kits for mapping of methylation status of nucleic acids. In one embodiment, proteins are provided that selectively act on certain modified cytosines of target nucleic acids and converts them to thymine. Also provided are compositions and kits that include one or more of the proteins and methods for using one or more of the proteins.

The present disclosure is concerned with altered cytidine deaminases, methods, compositions, and kits for mapping of methylation status of nucleic acids. In one embodiment, altered cytidine deaminases are provided that selectively act on certain modified cytosines of target nucleic acids and converts them to thymidine. Also provided are compositions and kits that include one or more of the proteins and methods for using one or more of the proteins.

Disclosed herein are compositions for preparing a target nucleic acid molecule comprising one or more 5-formylcytosine bases or adducts of 5-formylcytosine. Also disclosed herein are methods of efficiently synthesizing a nucleic acid molecule comprising one or more 5-formylcytosine bases from a target nucleic acid molecule comprising one or more 5-hydroxymethylcytosine bases. The disclosure also provides methods of detecting epigenetic modifications in a target nucleic acid molecule, such as those characterized by the methylation of cytosine at position 5 (e.g., 5-methylcytosine, 5-hydroxymethylcytosine).

Methods and systems provided herein address current limitations of bisulfite-based methylation sequencing by improving the quality and accuracy of nucleic acid methylation sequencing and uses thereof for detection of disease. Methods that include minimally-destructive conversion methods for methylation sequencing as well as specialized UMI adapters provide for improved quality of sequencing libraries and sequencing information. Greater accuracy and more complete methylation-state information permits higher quality feature generation for use in machine learning models and classifier generation.

This disclosure provides compositions for use in the preparation of target nucleic acid molecules, comprising one or more 5-formylcytosine bases or adducts of 5-formylcytosine. Also disclosed herein is a method for efficiently synthesizing nucleic acid molecules comprising one or more 5-formylcytosine bases from target nucleic acid molecules comprising one or more 5-hydroxymethylcytosine bases. This disclosure also provides a method for detecting epigenetic modifications in target nucleic acid molecules, such as epigenetic modifications characterized by methylation of cytosine at position 5 (e.g., 5-methylcytosine; 5-hydroxymethylcytosine).

A method for discriminating a cancer state is provided. A first dataset is obtained for a plurality of subjects having a first cancer state. Each subject has a plurality of nucleic acid methylation fragments with methylation patterns comprising CpG site methylation states. An autoencoder including an encoder and decoder is trained by evaluating the error in the autoencoder reconstruction of the methylation pattern and nucleic acid sequence of each nucleic acid methylation fragment in the first dataset. A second dataset is obtained for a plurality of subjects having a second cancer state. A plurality of features is identified by inputting the methylation pattern and nucleic acid sequence of each nucleic acid methylation fragment in the second dataset into the trained autoencoder and computing a score determined by the autoencoder reconstruction of the methylation pattern. The plurality of features is used to train a supervised model that discriminates a cancer state.

Methods and systems provided herein address limitations in standard nucleic acid library preparation used in conjunction with methylation sequencing which can increase library yield, achieve more uniform library amplification yields, and reduce undesired PCR products thereby minimizing signal loss and reducing biases that can be introduced in standard library preparation methods as well as improve the quality and accuracy of nucleic acid methylation sequencing and uses thereof, for example, in detection of disease. More accurate and complete information regarding methylation state permits higher quality feature generation for use in machine learning models and classifier generation, and the uses thereof for detection of disease by improving the quality, sensitivity, and accuracy.

The invention discloses a trace nucleic acid methylation library building method of exosome DNA and application of the trace nucleic acid methylation library building method, and belongs to the technical field of biology. The method comprises the following steps: breaking exosome DNA by using symmetric single-linker Tn5 transposase, connecting a 5'end linker, and not carrying out notch completion; transforming the exosome DNA by using an enzyme method; connecting a 3'end joint; and amplifying the exosome DNA which is subjected to breaking, enzymatic conversion and joint connection, so as to obtain the methylation sequencing library. The method can be applied to methylation library establishment of trace DNA of exosomes from various sources including body fluid, cell culture, tissue and the like, and is also suitable for methylation library establishment of all trace long fragment DNA. According to the method, the defects that the library building efficiency of the traditional asymmetric joint Tn5 is only 50% and methylation deviation is introduced during gap completion are overcome. The symmetric single-linker transposase is connected with the single-linker, so that the method has high gene comparison rate and conversion rate, and has good development and application prospects.

The present invention relates to a method for diagnosing, monitoring the effect of a treatment, monitoring the progression of a disease, or screening for a compound for treating a cerebral creatine deficiency syndrome, said method comprising the steps of measuring the level of nucleic acid methylation in a biological sample, and comparing the measured level with a control nucleic acid methylation level. The present invention also relates to folate and derivatives thereof for use in the treatment of a cerebral creatine deficiency syndrome.

The present application relates to a composition for determining the presence or absence of methylation of a nucleic acid and a method for determining the presence or absence of methylation of a nucleic acid.