From WebChem Wiki
Jump to: navigation, search

NEEMP features three modes: calculation, parametrization and validation. Each mode can be selected specifying one of the following keywords after the option --mode or -m:

Calculation mode : charges (calculate EEM charges)

Parametrization mode : params (calculate EEM parameters)

Validation mode : cover (display how many molecules are covered by the given parameters set) and quality (perform EEM parameters quality assay)

Additional functionality: NEEMP enables the user to display information about the provided training set, upon calling the keywords -m info or --mode info. Specifically, number of molecules, the total number of atoms and number of atoms for each atomic type are printed; the latter being defined by default as the chemical element and the maximal bond order. For details on the usage syntax, see the examples or option list paragraph.

Calculation mode

BASIC USAGE: ./neemp -m charges --sdf-file examples/set01.sdf --par-file examples/ElemBond.par --chg-out-file eem_charges

To compute EEM charges with NEEMP, it is necessary to provide the SDF file with molecules for which the charges will be computed (option --sdf-file) and the PAR file with EEM parameters (option --par-file). EEM charges will be written into the file specified by --chg-out-file option.

The user should keep in mind that, because of the EEM method itself, the EEM charges cannot be computed for atoms or atomic types for which the parameters are missing. This situation is well depicted by Figure 1. On the left side the parameter set contains values for all the atomic types in set01.sdf, on the other hand in the right side image it is evident how the same parameter set is lacking values for several atomic types present in set02.sdf, leading to the discard of many molecules (for details on the syntax, see the examples or option list section).

Chg new1.png Chg new2.png
Figure 1: The lack of parameter values in the parameter set file ElemBond.par for the atomic types highlighted in the right side image causes the discarding of several molecules from set02.sdf, emphasized by the drop in the covered molecules percentage.

Parametrization mode

This mode serves for calculation of EEM parameters. Three main components make up the input for this mode:

  • a training set of molecules (argument of --sdf-file option)
  • a set of QM charges for each molecule in the sdf file (argument of --chg-file option)
  • the specification of the parametrization approach (by -p or --params-method) and its specific options.

Linear Regression (LR)

BASIC USAGE: ./neemp -m params -p lr-full --sdf-file examples/set01.sdf --chg-file examples/set01.chg --par-out-file new_parameters.par

LR (--params-method lr-full or -p lr-full) is the default parametrization approach in NEEMP, since its application in the parametrization process is well documented and described in literature. The main extension in respect to previous version is the ability for the user to define by which metrics the best performing parameter set will be selected (see figure):

-s R2 or --sort-by R2 to select the parameter set with the highest squared Pearson coefficient (R2)
-s RMSD or --sort-by RMSD to select the parameter set with the lowest atomic type root mean square difference (avg(RMSDa))
LR full R2.png LR full RMSD.png
Figure 2: Detailed view of the LR parametrization settings for two distinct NEEMP executions differing in the best-performance selection metrics (R2 in left side image and RMSD in the right side image).

Additionally, the quality of the parameter set may benefit from the usage of a discarding procedure (-d simple or --discard simple). In fact it has been proved that using a subset of the original training set often leads to EEM charges that better agree with the reference QM charges. For useful examples on the LR parametrization approach and the discarding procedure see respectively examples 3/4 and 5. In particular the latter introduces the --limit-iters and --limit-time options, which modulate the behaviour of the discarding procedure, setting respectively an upper bound in the number of iterations and/or in the execution time.

Differential Evolution + Minimization (DE-MIN)

BASIC USAGE: ./neemp -m params -p de --sdf-file examples/set01.sdf --chg-file examples/charges.chg --par-out-file new_parameter.par

In parallel we developed an advanced EEM parametrization approach specifically tailored to cope with heterogeneous data, which in the past presented quite a challenge in the EEM parametrization framework. It consists in the combination of differential evolution method with a local minimization technique (NEWUOA), hence the acronym DE-MIN. To call this approach in NEEMP use the option --params-method de or -p de.

Figure 3: Abridged DE-MIN approach output for structural file examples/set01.sdf and charge file examples/set01.chg. In the upper block are displayed the specifics for the de-min parametrization procedure. Note as the bottom block presents the same structure as for other parametrization approaches and options (compare here).

The behaviour of the DE-MIN approach can be modulated by several options, but to make life easier we provide the user with reasonable default values that have been tuned to output optimal parameter set (for a complete view of the options refer to the option list and the examples section).

NB: the default quality evaluating metrics for DE-MIN approach is (avg(RMSDa)).

Validation mode

This mode allows us to perform two types of EEM parameter set validation - coverage validation and quality validation.

Coverage validation

BASIC USAGE: ./neemp -m cover -sdf-file examples/set01.sdf --par-file examples/Element.par

Figure 4: Percentage of molecules in set examples/set01.sdf covered by the displayed parameters set examples/Element.par

To see how many molecules from the set are covered by the provided parameters, simply pass NEEMP those two files (options --sdf-file and --par-file). Figure 4 shows a close-up from the cover mode output for set01.sdf and the parameters set Element.par, both present in the examples directory (for details on the syntax and the complete output, see the examples or option list paragraph)

Quality validation

BASIC USAGE: ./neemp -m quality --sdf-file examples/set01.sdf --chg-file examples/set01.chg --par-file examples/Element.par

To assess the quality of the EEM parameters on a different set than one they were based on, NEEMP's quality mode can be called.

Required input files are: EEM parameters (passed as argument of option --par-file) and a new set of molecular structures for which ab-initio charges have been computed (arguments of respectively --sdf-file and --chg-file).

To redirect to a file helpful information about the per-atom QM vs EEM charge comparison, utilize --chg-stats-out-file filename option. As describe in the next section this file is required for the generation of the charge correlation graphs and the quality assessment reports (see here).

For details on the syntax and additional output, see the examples or option list section.