• Mus_musculus.GRCm39.cdna.all.fa.gz was downloaded from Ensemble
• Homo_sapiens.GRCh38.cdna.all.fa.gz was downloaded from Ensemble

• 00_get_seqs_mouse.ipynb
• 00_get_seqs_human.ipynb

• get_aa_seq_mouse.py
• get_aa_seq_human.py

• 03_inspect_aa_seq_human.ipynb
• 04_inspect_aa_seq.ipynb

• prot_nuc_seqs_mouse.csv
• prot_nuc_seqs_human.csv

We used Nucleotide Transformer models to embed sequences with a maximum length of 5952 nucleotides. Sequences longer than 5952 nucleotides were truncated. Specifically, we used the 500M_human_ref and 500M_multi_species_v2 models for human and mouse respectively.

• 04_nuc_nt_emb_mouse.ipynb
• 05_nuc_nt_emb_human.ipynb

• See the nautilex-esm repository

We performed Leiden clustering for nt-emb and esm3-emb, along with 2d umap projections. Results are merged with those from MMIDAS joint clustering for further visualization.

• 06_make_df.ipynb
• 07_static_plots.ipynb
• 08_dynamic_plots.ipynb
• 09_enrichr_vignettes.ipynb

• Rohan Gala
• Yeganeh Marghi