I am trying to build a machine learning/deep learning model that takes multiple DNA reads of a specific gene as its inputs(preferably .fasta files)
In order to train the said model, i require multiple DNA reads of the said gene taken from different healthy donors.
Whole genome sequences of healthy donors are readily available from multiple different sources on the internet.
However extracting specific sequences of my gene of interest from hundreds, possibly thousand individuals would be really iterative and computationally intensive procedure.
I would be very thankful if someone could share/offer a source from which i could get multiple DNA reads of a specific gene from different healthy individuals.