Improving the precision oncology pipeline by providing binding affinity purtubations predictions on a pirori identified cancer driver genes.

• Data preprocessing
  • PDBbind - simple enough to use. Protein seq were downloaded from UniProt.
  • PLATINUM - Working on getting mutated sequence data (done with mutalyzer)
  • KIBA and Davis - Kinase proteins are not super relevant but could be useful for pretraining since datasets are limited.
  • GENIE - This will require some physical docking methods since we have no binding affinity data for this.
• Docking baseline
  • Set up Docking on cluster
  • Build scripts to automate ligand and protein prep (including grid for binding site).
  • Run docking on PDBbind dataset
• Model baseline
  • DGraphDTA
    • Evaluate pretrained model on PDBbind dataset
    • Train model on refined-set PDBbind dataset and evaluate
    • Train model on general PDBbind dataset and evaluate

See README/VINA_PROCEDURE.md for detailed steps

Try to follow conventional commits.

• feat: new feature
• fix(scope): bug in scope
• feat!: breaking change / feat(scope)!: rework API
• chore(deps): update dependencies

• build: Changes that affect the build system or external dependencies (example scopes: gulp, broccoli, npm)
• ci: Changes to CI configuration files and scripts (example scopes: Travis, Circle, BrowserStack, SauceLabs)
• chore: Changes which doesn't change source code or tests e.g. changes to the build process, auxiliary tools, libraries
• docs: Documentation only changes
• feat: A new feature
• fix: A bug fix
• perf: A code change that improves performance
• refactor: A code change that neither fixes a bug nor adds a feature
• revert: Revert something
• style: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc)
• test: Adding missing tests or correcting existing tests

• Put newline before extended commit body
• More details at conventionalcommits.org