Abstract: The present disclosure relates to an application of gene markers in multi-cancer early detection, a method for constructing an early detection model, and a detection device. In the present disclosure, low-coverage whole-genome sequencing is conducted on cell-free DNAs (cfDNAs) from a plasma sample, and according to high-throughput sequencing results, six differential features of the cfDNA fragments are analyzed for each cancer. Then the training and modeling are conducted with a convolutional neural network to allow the early detection of a plurality of cancers at a low sequencing depth. Then the training and modeling are conducted with a generalized linear model (GLM), a gradient boosting machine, a random forest model, a deep learning model, and an extreme gradient boosting model, and staking is conducted with a GLM to construct a multi-feature algorithm, to allow the tissue-of-origin-based detection of cancers.

Abstract: The present disclosure relates to an application of gene markers in multi-cancer early detection, a method for constructing an early detection model, and a detection device. In the present disclosure, low-coverage whole-genome sequencing is conducted on cell-free DNAs (cfDNAs) from a plasma sample, and according to high-throughput sequencing results, six differential features of the cfDNA fragments are analyzed for each cancer. Then the training and modeling are conducted with a convolutional neural network to allow the early detection of a plurality of cancers at a low sequencing depth. Then the training and modeling are conducted with a generalized linear model (GLM), a gradient boosting machine, a random forest model, a deep learning model, and an extreme gradient boosting model, and staking is conducted with a GLM to construct a multi-feature algorithm, to allow the tissue-of-origin-based detection of cancers.

Abstract: A sequencing data analysis method, a device and a computer-readable medium for microsatellite instability. The present invention can use NGS sequencing results to determine whether the microsatellite instability is present. The sequencing data analysis method can significantly improve detection sensitivity without reducing specificity, and can quickly and automatically evaluate a stable or unstable status of each MSI locus with high throughput, high sensitivity, and high specificity. By combining the statuses for all MSI loci in each sample, the samples can be comprehensively evaluated as MSS, MSI-L, or MSI-H.

Abstract: A DNA probe library for hybridization with microsatellite loci associated with microsatellite instability (MSI) detection. The said DNA probe library comprises one or more DNA probes that are capable of hybridizing with the MSI status-related microsatellite loci. Among the said DNA probes, probes for the MSI-related microsatellite loci are shown in the following sequences: SEQ ID NOS. 1-66. In addition, the present invention provides a method for enriching and detecting the MSI-related microsatellite loci using the probe library. The combination of this method and next-generation sequencing technology (NGS) can greatly improve the sensitivity, accuracy and comprehensiveness of the MSI detection.