Skip to content

Conversation

@PascalIversen
Copy link
Collaborator

@PascalIversen PascalIversen commented Mar 3, 2025

thereby we prevent failure of cross study prediction for unkown drugs, and the model can learn conditional sensitivity effects from the identity of a drug

also closes #150

@PascalIversen PascalIversen added bug Something isn't working enhancement New feature or request labels Mar 3, 2025
PascalIversen and others added 22 commits March 4, 2025 10:03
…dcoding has to stay. cross study pred from and to the Toy wont work with DIPK
…ts names. Also adds TOYv2. Its purpose ought to be testing cross study prediction or similiar endeavours
…hold

molir, superfeltr: remembering features from training dataset such that they can be subsetted in predict
test molir, superfeltr: sample a drug that is in study and cross study
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
Co-authored-by: Judith Bernett <38618495+JudithBernett@users.noreply.github.com>
@JudithBernett JudithBernett merged commit 81f90b8 into development Mar 6, 2025
22 of 25 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Cross study prediction: MOLIR, SuperFELTR fail

3 participants