Rahul Paul

@VanishingRasengan @teituroli Hi I am having a similar issue with SHAP. Do you have a solution on how to use SHAP for pycox?

@davivieirab My model: xgbse_model = XGBSEKaplanTree(params) bootstrap_estimator = XGBSEBootstrapEstimator(xgbse_model, n_estimators=100) Shap model: shap_values = shap.Explainer(bootstrap_estimator.predict, data,feature_names=feature_names,max_evals=2000) shaps = shap_values(data)

@davivieirab if i dont use the max_evals in the shap.explainer, it wont run at all. with max_evals=2000, the shap was running but it was showing 10hrs projected time to finish....

@Augustin-Zidek Yes they are started with > (i added them here as well, but for some reason > is removed from the comment)

@Augustin-Zidek When i ran the first sequence ( > EUXXXX) alone -monomer pipeline. And it ran fine but when i tried to ran multimer or protein protein interaction pipeline its...

@Augustin-Zidek input command: --fasta_paths=input.fasta \ --max_template_date=2022-08-29 \ --model_preset=multimer \

@DanilZherebtsov Thank you for the links. I was looking for any published papers. But medium links should be okay. I utilized NanImputer for the current project.

@DanilZherebtsov Thanks for letting me know. Hopefully, the new version will be helpful for my other projects where there are several missing data and make it faster. I am submitting...