chris1221 / goldi

R Package for Gene Ontology Label Discernment and Identification.

Hi there, I'm Chris.

I am currently a lead scientist at Deep Genomics in Toronto. My work involves using machine learning and AI to identify causal drug targets from human genetics data. I previously completed my DPhil working with Gerton Lunter and Thomas Milne at the University of Oxford. Check out my website for a breakdown of previous projects and repositories of interest.

goldi's Issues

Put temp into .tmp, and clean up better at the end.

Proper logging with options

API changes caused tests to fail.

Tests are now failing due to the changes in the API. Fix this before submission of presub inquiry.

Precompute TDM function

Allow the user to precompute TDMs if this makes more sense (looping around many articles with one list of terms, or looping around maybe term lists with one article)

disable reporting above length i terms

where i is maximum length given

$$ \vec{J} = \begin{bmatrix} \frac{\partial f}{\partial{V}} & \frac{\partial f}{\partial{W}} \\ \frac{\partial g}{\partial{V}} & \frac{\partial g}{\partial{W}} \end{bmatrix} $$

Issues before publication

Journal of Open Source Research software

• Make into R package style
• Write documentation
• Write config functions
• Package up dependencies (pdf2text etc)
• Create toy data and examples of use

Incorporate synonym function

make these words alternately identified in the main function

Integrate in CARD (Comprehensive Antibiotic Resistance Database)

See https://card.mcmaster.ca/home

[CRAN / BIOC] Return S4 goldi class

Instead of returning a data frame, include more information and create a class goldi

setClass("goldi", representations(terms = "vector", context = "vector", counts = "vector", ...)

Windows Compatibility

binary file has to be different

[v0.2.1.9000] Cpp Integration

Comparison section

Term overexpression Vignette

Add /chunks/ to .ignore

[v0.2.9.9000] Overwriting of terms variable

4 seperate instances; redefine some of them

Impliment unit testing

Presubmission Inquiry

See here and here.

Fix Figures

Toy data and Rmd

Write to JSON

Semi-specific long terms still included for some reason

else if(row > 10){

  if(any(sums == 10)){
    terms <- c(terms, paste(name, sum(sums == 10, na.rm = TRUE)))
  }

[v0.2.0.9000] LAPACK missing for Appveyor CI

Somehow add this into the .yml