Blind denoising of sequencing data

A computer-implemented method, comprising:

• receiving a plurality of read sequences associated with a scaffold sequence, wherein at least one read sequence of the plurality of read sequences is a noisy read sequence that fails to match the scaffold sequence;
• applying a sequence denoising model that
• determines an encoding associated with the plurality of read sequences, and
• generates, based at least on the encoding associated with the plurality of read sequences, a denoised scaffold sequence corresponding to the scaffold sequence;
• and
• providing, based at least on the denoised scaffold sequence, an analysis of a molecule associated with the scaffold sequence.

A non-transitory computer readable medium storing instructions, which when executed by at least one data processor, result in operations comprising:

• receiving a plurality of read sequences associated with a scaffold sequence, wherein least one read sequence of the plurality of read sequences is a noisy read sequence that fails to match the scaffold sequence;
• applying a sequence denoising model that
• determines an encoding associated with the plurality of read sequences, and
• generates, based at least on the encoding associated with the plurality of read sequences, a denoised scaffold sequence corresponding to the scaffold sequence;
• and
• analyzing, based at least on the denoised scaffold sequence, a molecule associated with the scaffold sequence.