From 96cdfdd5d35b5549c33061faf1d9afb898b2ad70 Mon Sep 17 00:00:00 2001 From: George Batchkala Date: Wed, 16 Sep 2020 17:52:16 +0100 Subject: [PATCH] add github links --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index fcc64a5..021b1d5 100644 --- a/README.md +++ b/README.md @@ -68,7 +68,7 @@ To convert molecules from their [SMILES](https://pubs.acs.org/doi/abs/10.1021/ci [Wu *et al.*](https://pubs.rsc.org/en/content/articlelanding/2018/SC/C7SC02664A#!divAbstract) suggest to use their Python library, [DeepChem](https://www.deepchem.io/), to reproduce the results. We decided not to use it, since the user API only gives high-level access to the user, while I wanted to have more control of the implementation. To have comparable results, I decided to use the tools which the DeepChem library is built on. -For most of the machine learning pipeline, I used Scikit-Learn ([article](https://www.jmlr.org/papers/v12/pedregosa11a.html), [GitHub](https://github.com/scikit-learn/scikit-learn)) for preprocessing, splitting, modelling, prediction, and validation. To obtain the confidence intervals for Random Forests, I used the forestci ([article](https://joss.theoj.org/papers/10.21105/joss.00124), [GitHub](https://github.com/scikit-learn-contrib/forest-confidence-interval)) extension for Scikit-Learn. The implementation of a custom Tanimoto (Jaccard) kernel for Gaussian Process Regression and all the following GP experiments were performed with GPflow ([article](http://jmlr.org/papers/v18/16-537.html), [GitHub](https://github.com/GPflow/GPflow)). +For most of the machine learning pipeline, I used Scikit-Learn ([article](https://www.jmlr.org/papers/v12/pedregosa11a.html), [GitHub](https://github.com/scikit-learn/scikit-learn)) for preprocessing, splitting, modelling, prediction, and validation. To obtain the confidence intervals for Random Forests, I used the forestci ([article](https://joss.theoj.org/papers/10.21105/joss.00124), [GitHub](https://github.com/scikit-learn-contrib/forest-confidence-interval)) extension for Scikit-Learn. The implementation of a custom Tanimoto (Jaccard) kernel for Gaussian Process Regression and all the following GP experiments were performed with [GPflow (article](http://jmlr.org/papers/v18/16-537.html), [GitHub)](https://github.com/GPflow/GPflow). # Set-up