Phylo Transfer Learning Summer project to-do

Georgia’s List

• Get lab notebook setup
  
• Schedule lab meetings - update calendar
  - [ ] Group meeting once a week
  - [ ] 1-1 meetings also weekly or as-needed
  
• Implement tuner method in adage class
  
• E coli gene lists for enrichment analyses
  
• S aureus gene lists for enrichment analysis
  
• Get DNA sequences into google drive

Mukundan’s List

• Choose 3 papers to read
  
• Make an OSF account: https://osf.io/dashboard

RNA/expression data

• Load new e coli data for adage model
  
• Descriptive stats on e coli and s aureus compendia
  - [ ] Genes to drop - low expression across samples
  - [ ] Samples to drop - too many unexpressed genes
  - [ ] Plots of PCA, UMAP, t-SNE, etc.
  
• Hyper-parameter search for e coli only model
  
• Hyper-parameter search for s aureus only model
  
• PCA as linear control

DNA/Genomic data

• Find blast python library (nt and aa alignment
  
• Find foldseek python library (structural alignment)
  - [ ] alt : just use commandline tool
  
• Test such lib in colab
  
• Make e coli and s aureus pangenomes into blast dbs
  
• Reciprocal search of e coli genes to s aureus db and vice versa
  
• Descriptive stats/plots of hits and their e-scores, lengths, recall, precision, etc.
  
• Filter for best set of mutual hits (1-1 mapping of homologous genes)