Skip to content

This is an implementation of Compound Complexity for use in the SMART-PMI as described by Sherer et al. It contains derived training data as required by the described Random Forest Model in order to replicate data presented in paper as well as applying to novel data.

License

Notifications You must be signed in to change notification settings

Merck/compoundcomplexity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Compound Complexity Calculator

USAGE: bin/compoundcomplexity.sh [ -sdf <sdfile> | -smi <smilefile> ]

NOTES: This is an implementation of Compound Complexity for use in the 
  SMART-PMI as described by Sherer et al. 
  It contains derived training data as required by the described Random Forest
  Model in order to replicate data presented in paper as well as applying to 
  novel data.

  Use of SDF input is strongly recommended.

  Eq 1.
          SMART-PMI = (0.13 × MW) + (177 × Complexity) - 252

ABSTRACT: An important metric for gauging the impact a synthetic route has on
  chemical resources, cost, and sustainability is process mass intensity
  (PMI). Calculating the overall PMI or step PMI for a given synthesis from a
  process description is more and more common across the industry. Our company
  has established a strong track record of delivering on our Corporate
  Sustainability goals, being recognized with seven EPA Green Chemistry
  Challenge Awards in the last 15 years. While green chemistry principles help
  in optimizing PMI and developing more sustainable processes, a key challenge
  for the field is defining what ‘good’ looks like for any given molecule.
  Predicting aspirational PMI for a synthetic target is not yet possible from
  chemical structure alone. The only tool chemists have at their disposal to
  predict PMI requires the synthetic route to be available, which is inherently
  retrospective. We have developed SMART-PMI (in-Silico MSD Aspirational
  Research Tool) to fill this glaring gap. Using only a 2D chemical structure,
  which enables a measure of molecular complexity, we can generate a predicted
  SMART-PMI using historical PMI data from our company’s clinical and
  commercial portfolio of processes. From this SMART-PMI prediction, we have
  established target ranges for Successful, World Class, and Aspirational PMI.
  Using this model, chemists can develop powerful synthetic strategies that
  make the biggest impact on PMI and, in turn, drive improvements to the model.
  The potential of SMART-PMI to set industry-wide aspirational PMI targets is
  discussed

Requirements
- MOE (http://www.chemcomp.com)
- Perl 5.22.1+

About

This is an implementation of Compound Complexity for use in the SMART-PMI as described by Sherer et al. It contains derived training data as required by the described Random Forest Model in order to replicate data presented in paper as well as applying to novel data.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published