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 cancer type 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. Based on the sequence read data, endpoint positions of the DNA fragments with respect to a reference genome are identified. Further, input features are determined based on the endpoint positions of the DNA fragments with respect to the reference genome. The example method further includes predicting, using a classifier and based on the input features, a primary type of cancer of the subject.

Abstract: Techniques for identifying a predictive profile of a subject are described. In an example method, sequence read data is identified in a sample obtained from a subject. 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 selecting a predictive profile 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. The predictive profile of the subject is determined by using a model based on the input features.

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 a cellular phenotype indicative of a condition of a subject are described. The techniques can include identifying sequence read data indicating sequences of DNA fragments from a sample from a subject; determining, based on the sequence read data, endpoint positions of the DNA fragments; determining input features based on the endpoint positions of the DNA fragments; and predicting, using a classifier and based on the input features, a cellular phenotype indicative of a condition, such as a cancer, within the subject.