Determination of base modifications of nucleic acids

A method for detecting a modification of a nucleotide in a nucleic acid molecule, the method comprising:

• receiving an input data structure, the input data structure corresponding to a window of nucleotides sequenced in a sample nucleic acid molecule, wherein the sample nucleic acid molecule is sequenced by measuring pulses in an optical signal corresponding to the nucleotides, the input data structure comprising values for the following properties:
• for each nucleotide within the window:
• an identity of the nucleotide,
• a position of the nucleotide with respect to a target position within the respective window,
• a width of the pulse corresponding to the nucleotide, and
• an interpulse duration representing a time between the pulse corresponding to the nucleotide and a pulse corresponding to a neighboring nucleotide;
• inputting the input data structure into a model, the model trained by:
• receiving a first plurality of first data structures, each first data structure of the first plurality of data structures corresponding to a respective window of nucleotides sequenced in a respective nucleic acid molecule of a plurality of first nucleic acid molecules, wherein each of the first nucleic acid molecules is sequenced by measuring pulses in the optical signal corresponding to the nucleotides, wherein the modification has a known first state in a nucleotide at a target position in each window of each first nucleic acid molecule, each first data structure comprising values for the same properties as the input data structure,
• storing a plurality of first training samples, each including one of the first plurality of first data structures and a first label indicating the first state of the nucleotide at the target position, and
• optimizing, using the plurality of first training samples, parameters of the model based on outputs of the model matching or not matching corresponding labels of the first labels when the first plurality of first data structures is input to the model, wherein an output of the model specifies whether the nucleotide at the target position in the respective window has the modification,
• determining, using the model, whether the modification is present in a nucleotide at the target position within the window in the input data structure.