Estimating tumor purity from single samples

A system comprising:

• one or more data processors;
• and
• a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform one or more operations comprising:
• obtaining nucleic acid sequence data from one or more sequencers that represent a plurality of nucleic acid molecules of a biological sample of a subject;
• aligning the nucleic acid sequence data to a reference genome;
• identifying, based on the aligned nucleic acid sequence data, a set of genomic regions, wherein each genomic region of the set of genomic regions includes one or more nucleotide-sequence variants relative to a corresponding genomic region of the reference genome;
• determining a B-allele frequency for each genomic region of the set of genomic regions;
• determining, based on the B-allele frequencies of the set of genomic regions, a B-allele frequency distribution for the biological sample;
• processing the B-allele frequency distribution using a trained machine learning model to estimate a probability of a true tumor purity as a function of a predicted tumor purity in the biological sample, wherein the trained machine-learning model is trained on a training dataset generated from nucleic acid sequence data derived from one or more tumor cells diluted into normal cells;
• and
• generating a report to inform a cancer feature and evaluate the treatment efficacy for the subject based on the estimated probability of a true tumor purity as a function of a predicted tumor purity in the biological sample.