GeinQSAR Studio
Home › The 3D-QSAR dashboard

The 3D-QSAR dashboard

What a 3D-QSAR run produced: the statistics and the chosen number of components, the per-compound predictions, the alignment the model rests on, the maps, and the contribution of each atom.

The dashboard opens when a 3D-QSAR workflow finishes, one per model: a run with KEFRA and the atom-based cubes opens two. It recomputes nothing. Every number is read from the output of the workflow, so the dashboard, the exported report and the files the workflow wrote always agree. The explanations are tooltips: rest the pointer on a card, a column heading or the help mark next to a section title.

A 3D-QSAR dashboard in the window, here the KEFRA model of the steroid sample. The run built both models, so the tab bar carries a dashboard for each and names them, and the one in front can be told from the other. The tabs Statistics, Compounds, Alignment, Maps and Molecule share one row with Export report; the inspector on the right summarises the model and gives the share each field contributes.
A 3D-QSAR dashboard in the window, here the KEFRA model of the steroid sample. The run built both models, so the tab bar carries a dashboard for each and names them, and the one in front can be told from the other. The tabs Statistics, Compounds, Alignment, Maps and Molecule share one row with Export report; the inspector on the right summarises the model and gives the share each field contributes.
TabShows
StatisticsThe selected model as cards, the rule that chose the number of components, the statistics for every number of components, the model statistics, the field contributions, observed against predicted, and the Y-scrambling and bootstrap results when they were run.
CompoundsOne row per compound with its set, observed and predicted values, and how far it reaches beyond the lattice.
AlignmentThe alignment the model was built on, molecule by molecule.
MapsThe model as a 3D contour or cube map with a ligand inside it.
MoleculeOne compound in 2D with its atoms coloured by their contribution to the prediction.

Statistics

The Statistics tab of a KEFRA model of the steroids, built here on the steric and electrostatic fields alone. The cards carry their PASS and FAIL badges against the 0.5 thresholds, and below them the model summary names the learner, the width scale and regularisation the inner cross-validation chose, and the scheme that chose them. Look at the two q2 cards together: the nested value, 0.6182, is the one to quote, and the selected value, 0.7447, is higher because the same compounds chose the settings.
The Statistics tab of a KEFRA model of the steroids, built here on the steric and electrostatic fields alone. The cards carry their PASS and FAIL badges against the 0.5 thresholds, and below them the model summary names the learner, the width scale and regularisation the inner cross-validation chose, and the scheme that chose them. Look at the two q2 cards together: the nested value, 0.6182, is the one to quote, and the selected value, 0.7447, is higher because the same compounds chose the settings.

An atom-based cube model is a PLS model and has these cards:

CardDefinitionThreshold
q2 (CV)1 - PRESS / SS from the cross-validation of the protocol (Cramer et al. 1988).Above 0.5
R21 - RSS / SS on the training set at the selected number of components.
SD (SEE)Standard error of estimate, sqrt(RSS / (n - A - 1)) for n compounds and A components.
SEPStandard error of prediction, sqrt(PRESS / n), from the cross-validation.
s PRESSsqrt(PRESS / (n - A - 1)), the cross-validated standard error the 3D-QSAR literature tabulates.
q2 SDStandard deviation of q2 over the repeats of a repeated cross-validation. Not shown for leave-one-out, which has none.
FFisher F of the fit, (R2 / A) / ((1 - R2) / (n - A - 1)).
Pearson-rCorrelation of observed and fitted activities.
Components, Columns fittedThe number of PLS components and of lattice columns left after the filters.
Q2 (test)Q2F1 of the test set: 1 - PRESS(test) / SS of the test values about the training mean (Shi et al. 2001).Above 0.5
cR2pR sqrt(R2 - mean R2 of the scrambled refits) (Mitra, Saha and Roy 2010). Shown when Y-scrambling was run.Above 0.5

A KEFRA model has no components, so its cards differ:

CardDefinitionThreshold
q2 (nested)Cross-validated q2 with the whole choice of widths and regularisation repeated inside every outer fold (Varma and Simon 2006): no compound influenced the model that predicted it. The number to quote.Above 0.5
q2 (selected)The inner leave-one-out q2 at the settings it chose. Biased upwards by that choice; shown for comparison.
R21 - RSS / SS on the training set.
SEPsqrt(PRESS / n) of the nested cross-validation.
RMSE fit / CVThe training RMSE divided by the cross-validated RMSE. Far below 1 means the fit is much better than the predictions: the model memorises its training compounds.
FieldsThe properties in the fitted kernel.
FFisher F of the fit with the effective degrees of freedom of the kernel model, the trace of its hat matrix (Hastie and Tibshirani 1990). The widths and the regularisation were chosen on the same compounds, so its p-value is optimistic. None is reported for kernel PLS.
Q2 (test), Test biasQ2F1 of the test set, and the mean of observed minus predicted over the test compounds.Above 0.5 for Q2

Below the cards the model summary names the component rule and the cross-validation scheme (SAMPLS when the sample-matrix engine was used), or for KEFRA the learner and the nested q2, and what the fields are computed from: for a hydrophobic field Wildman-Crippen atomic contributions or the data field the model was given instead. These rows are there so that a model is not taken for the output of another program, which would give other numbers for the same compounds.

Per-factor statistics and model statistics

Per-factor statistics of a cube model: SD, R2, R2 CV, s PRESS, R2 Scramble, Stability and F for each number of components, with Yes in Selected on the row the component rule chose.
Per-factor statistics of a cube model: SD, R2, R2 CV, s PRESS, R2 Scramble, Stability and F for each number of components, with Yes in Selected on the row the component rule chose.
Model statistics, every quantity of the model as the model step tabulates it: the model, the fields, the partial charges, the numbers of training, test and excluded compounds and the lattice points along each axis.
Model statistics, every quantity of the model as the model step tabulates it: the model, the fields, the partial charges, the numbers of training, test and excluded compounds and the lattice points along each axis.

The per-factor table shows how q2 rises and falls with the number of components, which is where over-fitting shows: R2 keeps rising while R2 CV levels off. R2 Scramble is the mean training R2 of the scrambled refits and Stability is RMSE / SEP; both are GeinQSAR definitions. For KEFRA the table lists the settings that were tried and the inner q2 of each. The model statistics list the columns each field kept and its block scale, the cross-validation, the fit, the test set, the field contributions and the resampling runs. Partial charges there names the charge model of the model step itself: when the charges were assigned by a separate step of the preparation, as the builder does for Gasteiger-Marsili charges, it reads As supplied, and the Preparation table of the Alignment tab names the method.

Field contributions gives the share of the model carried by each field or atom class: for the cubes the share of the total |StDev x Coeff|, the usual field fraction of 3D-QSAR.

Repeated cross-validation and cubes

A steroid model cross-validated by leave-group-out with repeats: the cards add q2 SD next to q2, and the cross-validation row reads Leave-group-out.
A steroid model cross-validated by leave-group-out with repeats: the cards add q2 SD next to q2, and the cross-validation row reads Leave-group-out.
An atom-based cube model of the steroids: 1304 columns, q2 0.7935, and the inspector lists the share of the atom classes that carry the model (D, H and W).
An atom-based cube model of the steroids: 1304 columns, q2 0.7935, and the inspector lists the share of the atom classes that carry the model (D, H and W).

When the model was built with region focusing, the Statistics tab says so in one line: q2 is then not an honest cross-validation and the model has to be judged by its test set. Warnings of the run, such as compounds without an activity, are listed at the end of the tab.

Save model

Save model, on the row of the Model title, writes the model as a .gqfm file, exactly as Save the model of the wizard does.

The Save model dialog over the Statistics tab of a KEFRA model, with the file named in full, Browse and Save. Unless it is changed the file goes to Documents\GeinQSAR\Output.
The Save model dialog over the Statistics tab of a KEFRA model, with the file named in full, Browse and Save. Unless it is changed the file goes to Documents\GeinQSAR\Output.

Compounds

Per-compound predictions of a steroid model: for each training compound the observed value, the fitted value and the value predicted by the model built without it. Test compounds fill Test predicted instead; Beyond lattice (Å) is empty because every compound lies inside the lattice.
Per-compound predictions of a steroid model: for each training compound the observed value, the fitted value and the value predicted by the model built without it. Test compounds fill Test predicted instead; Beyond lattice (Å) is empty because every compound lies inside the lattice.
ColumnMeaning
SetTraining, Test, or Excluded (no activity, or left out by the set column).
ObservedThe measured activity.
FittedThe model's value for a training compound.
CV predictedThe value of a training compound from the model built without it; the numbers q2 is computed from.
Test predictedThe value of a test compound, which took no part in the model.
Beyond lattice (Å)Atom-based cubes: how far the atoms of the compound reach outside the lattice. A compound that reaches beyond it has part of itself sampled nowhere, so its prediction is an extrapolation; the tab counts such compounds. Not shown for KEFRA, which has no lattice.

The observed against predicted chart is below the table. Rows selected in the table are highlighted in the chart, and a brush in the chart selects rows; Clear selection empties both. The camera button of the chart opens the figure dialog.

Alignment

Both models compare the molecules in the frame of the alignment, so this tab is where a weak model is diagnosed first: one molecule with a large RMSD or a low shape Tanimoto spoils the model.

The alignment of the steroid model: 31 of 31 molecules placed, a mean RMSD of 0.363 Å and a largest of 1.029 Å over 18 core atoms, a mean shape Tanimoto of 0.851, the method and the core SMARTS that was superposed.
The alignment of the steroid model: 31 of 31 molecules placed, a mean RMSD of 0.363 Å and a largest of 1.029 Å over 18 core atoms, a mean shape Tanimoto of 0.851, the method and the core SMARTS that was superposed.
The Molecules table of the same alignment: every molecule aligned on 18 matched atoms, with its RMSD and shape Tanimoto, and conformer 1 rather than 0 chosen for S06 and S10.
The Molecules table of the same alignment: every molecule aligned on 18 matched atoms, with its RMSD and shape Tanimoto, and conformer 1 rather than 0 chosen for S06 and S10.
ColumnMeaning
AlignedWhether the molecule could be placed.
TemplateMarks the molecule every other one was superposed onto.
ConformerThe stored conformer that was superposed, counted from 0 (the lowest in energy).
Atoms matchedThe atoms the fit of the molecule rests on.
RMSD (Å)Their deviation after the fit. Empty for a method that matches no atoms (As supplied, shape, inertial frame).
Shape TcGaussian shape Tanimoto with the template (Grant and Pickup 1995).
NoteWhy a molecule could not be placed, or how it was placed when not by the common core.
The Alignment tab of a model built on the thrombin inhibitors kept as supplied: 88 of 88 molecules aligned, the RMSD and core cards read n/a and the core SMARTS says None: the method superposes no common core, while the shape Tanimoto with the template (01) is still reported.
The Alignment tab of a model built on the thrombin inhibitors kept as supplied: 88 of 88 molecules aligned, the RMSD and core cards read n/a and the core SMARTS says None: the method superposes no common core, while the shape Tanimoto with the template (01) is still reported.

Below the molecules, Preparation lists every step the compounds of the model went through (standardisation, embedding, conformers, charges, alignment) with every parameter. That table is what the prediction wizard replays for new compounds.

Maps

The Maps tab draws the model as a 3D map with one compound inside it for orientation. How to read the maps, what the colours and levels mean, and every control of the panel are on Contour maps and atom cubes.

The Maps tab of a steroid model with aldosterone (S01) as the ligand. Each lobe encloses 1 % of the lattice (Lattice share at 99.0 %): green where more bulk raises the predicted activity, yellow where it lowers it, blue where positive and red where negative charge is favoured. The legend gives the iso-level of every lobe.
The Maps tab of a steroid model with aldosterone (S01) as the ligand. Each lobe encloses 1 % of the lattice (Lattice share at 99.0 %): green where more bulk raises the predicted activity, yellow where it lowers it, blue where positive and red where negative charge is favoured. The legend gives the iso-level of every lobe.

Molecule

The Molecule tab with S01 (aldosterone), a training compound observed at 6.279 and predicted at 6.233. Its atoms carry blue and red halos where the model attributes a positive or a negative contribution to the prediction; the table on the right lists the per-atom values.
The Molecule tab with S01 (aldosterone), a training compound observed at 6.279 and predicted at 6.233. Its atoms carry blue and red halos where the model attributes a positive or a negative contribution to the prediction; the table on the right lists the per-atom values.

Choose the compound in Compound. The line next to it gives its set and its observed and predicted values. The contribution of each region of space to the prediction is assigned to the atoms near it, so the 2D drawing shows which parts of the molecule the model credits and blames. Export figure writes the coloured compound as an SVG figure.

Opening a saved model

File > Open on a .gqfm file, or the file dropped on the window, opens a small workflow that reads it and this dashboard with the same statistics, compounds and maps. The tab is named after the file. Nothing is recomputed: the file holds the fitted model.

The dashboard of a model opened from its .gqfm file: the same cards as the run that saved it, here a model with four test compounds and a test-set Q2 of 0.9760.
The dashboard of a model opened from its .gqfm file: the same cards as the run that saved it, here a model with four test compounds and a test-set Q2 of 0.9760.
The Alignment tab of a saved model: the aligned molecules with their conformer, matched atoms, RMSD and shape, and below them the Preparation table, step by step: here the 3D structure generation with its Keep existing coordinates and Embedding attempts parameters.
The Alignment tab of a saved model: the aligned molecules with their conformer, matched atoms, RMSD and shape, and below them the Preparation table, step by step: here the 3D structure generation with its Keep existing coordinates and Embedding attempts parameters.

The Alignment tab of a saved model has no alignment report, because the file holds the aligned compounds and the record of their alignment, not the report of the alignment run; it does have the Preparation table. The model can be applied to new compounds with Wizards > Predict with a saved model (see Predicting new compounds).

Export report

Export report writes the report of the model as a PDF, a Word document and an Excel workbook, in whichever of the three you tick, with the statistics, the figures, the predictions and, when the workflow is still open, the workflow itself, so that the report can be reproduced. Tables as CSV also writes the per-factor statistics, the field contributions, the model statistics, the per-compound predictions, the alignment report and the contour levels as CSV files. See Reports and export.

The report carries two residual figures that the dashboard does not draw: the residuals against the observed activity, with the band at 2.5 standard deviations marked, and the distribution of the residuals of each set side by side. Read them together with the bias on the Statistics tab. What they are for is to show that the errors have no mean and no trend, which a single Q2 cannot show, and to name the compounds the model gets wrong instead of leaving them inside an average.