inspired by techniques used in PathoLM paper, "PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model"
(non pre processed - want to run some more of the tests on external compute to get any type of validated data)
Dip, S.A., Shuvo, U.A., Chau, T., Song, H., Choi, P., Wang, X., & Zhang, L. (2024). PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model. bioRxiv. https://arxiv.org/pdf/2406.13133
i wanted to run the pathoLM model on my own but because the paper is a preprint and under review process, the authors haven't open sourced the code + model infrastructure. So I decided to make my own replica of it based on the contents in the paper.