Abstract: Techniques for classifying cancers using fragmentomic features are described. An example method includes identifying data indicative of circulating tumor DNA (ctDNA) from a sample derived from a subject. The example method further includes identifying fragmentomic features based on the data. Input data, including the fragmentomic features, is input into a model configured to generate at least one probability that a tumor is within at least one category. The example method further includes generating a report based on the at least one probability that the tumor is within the at least one category.

Abstract: Techniques for calculating a tumor fraction of a subject are described. In an example method, sequence read data of a sample obtained from a subject is identified. The sequence read data indicates sequences of DNA fragments. The example method further includes determining endpoint positions of the DNA fragments with respect to a reference genome; determining input features; and calculating a tumor fraction of the subject. The endpoint positions of the DNA fragments can be determined based on the sequence read data. The input features are based on the endpoint positions of the DNA fragments with respect to the reference genome and can be determined by using a classifier. The tumor fraction can be calculated based on the input features.

Abstract: Techniques for identifying a condition, such as a tumor classification, of a subject are described. In an example method, sequence read data of a sample obtained from the subject is identified. The sequence read data is indicative of endpoint positions of nucleic acid molecules in the sample. The example method further comprises determining endpoint positions of the nucleic acid molecules, generating input features based on the endpoint positions of the nucleic acid molecules, and classifying, using a classifier, the condition of the subject based on the input features.

Abstract: Techniques for identifying a copy number state of a subject are described. An example method includes identifying sequence read data indicating sequences of DNA fragments of a sample obtained from the subject. Based on the sequence read data, fragmentomic features of the DNA fragments with respect to a reference genome are determined. Further, the example method includes determining input features based on the fragmentomic features and determining, using a classifier and based on the input features, the copy number state of the subject.

Abstract: Techniques for identifying a condition subtype of a subject are described. An example method includes identifying sequence read data indicating sequences of DNA fragments of a sample obtained from a subject with cancer; and determining, based on the sequence read data, endpoint positions of the DNA fragments with respect to a reference genome. Input features are determined based on the endpoint positions of the DNA fragments with respect to the reference genome. Using a classifier, and based on the input features, a subtype of the cancer of the subject is determined.

Abstract: Techniques for identifying conditions of a subject are described. An example method includes identifying sequence read data of a sample obtained from a subject. The sequence read data is in a spatial domain corresponding to genomic position. The example method further includes generating transformed data by transforming the sequence read data into an alternative domain; generating input features based on the transformed data; and classifying, using a classifier, a condition of the subject based on the input features.