Tweaks

The original description was for pretty much only the original algorithm, I've adapted it to describe more what we're doing now. 

I've removed the instructions for installing molecule from source since it is now included in the environment.

README.md

@@ -1,14 +1,7 @@
 # PySIDT
-This repository contains PySIDT, a low-data machine-learning algorithm that predicts chemical properties. PySIDT is a general implementation of the subgraph isomorphic tree generation (SIDT) machine learning algorithm developed in <a href="https://chemrxiv.org/engage/chemrxiv/article-details/62c5c941c79aca239053967e">Johnson and Green 2021</a>. While the algorithm in that work was specific to rate coefficients, this implementation can be applied to predict arbitrary properties. 
+This repository contains PySIDT, a package containing a set of low-data machine-learning algorithms for prediction of chemical properties based on the subgraph isomorphic tree generation (SIDT) approach originally developed in <a href="https://doi.org/10.1039/D3RE00684K">Johnson and Green 2021</a>. 
 
 # Installation from source
-- Install [molecule](https://github.com/ReactionMechanismGenerator/molecule/tree/ts_len_improvements) from source
-    - `git clone https://github.com/ReactionMechanismGenerator/molecule.git`
-    - `cd molecule`
-    - `conda env create -f environment.yml --name=pysidt`
-    - `conda activate pysidt`
-    - `make`
-    - `pip install -e .`
 - Install PySIDT from source
     - `git clone https://github.com/zadorlab/PySIDT.git`
     - `cd PySIDT`