Recent Changes

Sunday, December 13

  1. page Assignment 6 Aliaksandr Krukau edited ... {NovyPharmacophore2.png} Pharmacophore with the second highest test score {NovyPharmacophore…
    ...
    {NovyPharmacophore2.png} Pharmacophore with the second highest test score
    {NovyPharmacophore3.png} Pharmacophore with the third highest test score
    ForOur pharmacophore is much more compact than pharmacophores in the recent paper by Abhik Seal et al. (Journal of Cheminformatics 2013, vol. 5: 2). It appears that ligand-based pharmacophores for this problem are more compact in size than docking-based pharmacophores.
    For
    screening, I
    ...
    decoy sets.
    The performance of the pharmacophore with the highest score on the test set was rather poor. Therefore, I first show the results for pharmacophore with the second highest score. I obtained the following receiver operating curve (ROC):
    {ROC-graph-2.PNG} ROC curve for the pharmacophore with the second highest test score.
    ...
    comparison, in a recentthe paper by
    ...
    Seal et al. (Journal of Cheminformatics 2013, vol. 5: 2),al., sensitivity for
    The pharmacophore with the highest score on the test set had rather poor performance for enrichment factors.
    For top 1%, top 5%, and top 10% hits, the enrichment factor is, respectively, 0.0, 1.1, 2.5. Investigation in LigandScout has shown that the first and the second pharmacophore are rather similar, but they put an H-bond donor in different places.
    (view changes)
    6:57 pm
  2. page Assignment 6 Aliaksandr Krukau edited In this assignment, we need to create a pharmacophore ligand-based model for PKNB kinase. I downloa…
    In this assignment, we need to create a pharmacophore ligand-based model for PKNB kinase. I downloaded the test set of 73 inhibitors of PKNB kinase, from Pubchem (bioassay with AID 624753). I excluded compound with SID 136935277
    from further analysis because the structure of this compound was not available. All compounds with 10000 nM Kd or more were considered inactive, and the remaining compounds as active. Pharmacore model was created using 3.12.0.0 version of Ligandscout software from Inteligand GmbH. As pharmacophore generation is very expensive, I chose to use only a subset of the original bioassay. I selected 14 compounds with the lowest values of Kd as actives, and added 3 inactive compounds. For the test set, I used 4 active compounds with CID 11667893, 9809715, 44551653, and 3 inactive compounds with CID 5329102, 11213558, 16725726. For training set, I used 10 compounds with CID 44259, 16722836, 11427553, 9977819, 10138259, 11409972, 11338033, 5291, 123631, and 151194. For all the compounds in training and test set, I generated conformers using BEST settings (with 500 conformers). I then generated merge features pharmacophore using default settings. I show three pharamacophore models with the highest score below.
    {NovyPharmacophore1.png} Pharmacophore with the highest test score
    {NovyPharmacophore2.png} Pharmacophore with the second highest test score
    {NovyPharmacophore3.png} Pharmacophore with the third highest test score
    For screening, I used the test set provided by Abhik Seal with 36 actives and 999 decoy sets.
    The performance of the pharmacophore with the highest score on the test set was rather poor. Therefore, I first show the results for pharmacophore with the second highest score. I obtained the following receiver operating curve (ROC):
    ...
    For top 1%, top 5%, and top 10% hits, the enrichment factor is, respectively, 0.0, 1.1, 2.5. Investigation in LigandScout has shown that the first and the second pharmacophore are rather similar, but they put an H-bond donor in different places.
    Out of 36 active compounds, screening method classified 31 as active, so classifier sensitivity is still high, 81%. ROC curve is:
    {ROC-graph-1.PNG} Receiver operating curve for pharmacophore with the highest test score
    (view changes)
    6:50 pm
  3. page Assignment 6 Aliaksandr Krukau edited ... The enrichment factor is the share of true positives among the molecules with the highest fit …
    ...
    The enrichment factor is the share of true positives among the molecules with the highest fit score. For top 1%, top 5%, and top 10% hits, the enrichment factor is, respectively, 14.4, 7.3, 6.1. Area under operating curve is 0.77. Out of 36 active compounds, screening method classified 31 as active, so classifier sensitivity is rather high, 86%. Classifier specificity is much lower, 38%, because of the large number of false positives. Classifier precision, i.e. the share of true positives among all hits, is also low, around 5.5%. For comparison, in a recent paper by Abhik Seal et al. (Journal of Cheminformatics 2013, vol. 5: 2), sensitivity for the pharmacophore I is 68%, and specificity is 71%.
    The pharmacophore with the highest score on the test set had rather poor performance for enrichment factors.
    ...
    1.1, 2.5. Investigation in LigandScout has shown that the first and the second pharmacophore are rather similar, but they put an H-bond donor in different places.
    Out of 36 active compounds, screening method classified 31 as active, so classifier sensitivity is still high, 81%. ROC curve is:
    {ROC-graph-1.PNG}
    (view changes)
    6:48 pm
  4. page Assignment 6 Aliaksandr Krukau edited ... {NovyPharmacophore3.png} For screening, I used the test set provided by Abhik Seal with 36 a…
    ...
    {NovyPharmacophore3.png}
    For screening, I used the test set provided by Abhik Seal with 36 actives and 999 decoy sets.
    ForThe performance of the pharmacophore with the highest score on the test set was rather poor. Therefore, I first show the results for pharmacophore with the second highest score. I obtained
    ...
    curve (ROC):
    {ROC-curve-1.PNG} Receiver operating

    {ROC-graph-2.PNG} ROC
    curve for
    ...
    with the second highest test set score.
    The
    ...
    the share of true positives among the molecules with the highest fit score. For top
    ...
    high, 86%. But classifierClassifier specificity is much lower, 37.8%,38%, because of
    ...
    71%.
    The performance of the pharmacophorespharmacophore with the second highest score on the test set had rather poor performance for enrichment factors.
    For top 1%, top 5%,
    and top 10% hits, the third highest score is similar,enrichment factor is, respectively, 0.0, 1.1, 2.5.
    Out of 36 active compounds, screening method classified 31 as active,
    so I do not show the results here.classifier sensitivity is still high, 81%. ROC curve is:
    {ROC-graph-1.PNG}

    (view changes)
    6:40 pm
  5. file ROC-graph-2.PNG uploaded
    6:31 pm
  6. file ROC-graph-1.PNG uploaded
    6:08 pm
  7. file ROC-curve-1.PNG uploaded
    6:05 pm
  8. page Assignment 6 Aliaksandr Krukau edited ... For the first I obtained the following receiver operating curve (ROC): {ROC-curve-1.PNG} Rece…
    ...
    For the first I obtained the following receiver operating curve (ROC):
    {ROC-curve-1.PNG} Receiver operating curve for the pharmacophore with the highest test set score.
    ...
    factor is theForthe share For top 1%,
    ...
    is 71%.
    The performance of the pharmacophores with the second highest and the third highest score is similar, so I do not show the results here.

    (view changes)
    5:27 pm
  9. page Assignment 6 Aliaksandr Krukau edited ... For the first I obtained the following receiver operating curve (ROC): {ROC-curve-1.PNG} Rece…
    ...
    For the first I obtained the following receiver operating curve (ROC):
    {ROC-curve-1.PNG} Receiver operating curve for the pharmacophore with the highest test set score.
    ForThe enrichment factor is theFor top 1%,
    (view changes)
    5:09 pm
  10. page Assignment 6 Aliaksandr Krukau edited ... {NovyPharmacophore2.png} {NovyPharmacophore3.png} ... decoy sets. For the first I ob…
    ...
    {NovyPharmacophore2.png}
    {NovyPharmacophore3.png}
    ...
    decoy sets.
    For the first
    I obtained
    ...
    curve (ROC):
    {ROC1.PNG}
    For

    {ROC-curve-1.PNG} Receiver operating curve for the pharmacophore with the highest test set score.
    For
    top 1%,
    ...
    and top 20%,10% hits, the enrichment factor is, respectively, 14.4, 7.3, 6.1. Area under operating curve is 0.77. Out of 36 active compounds, screening method classified 31 as active, so classifier sensitivity is rather high, 86%. But classifier specificity is much lower, 37.8%, because of the large number of false positives. Classifier precision, i.e. the share of true positives among all hits, is also low, around zero. This may suggest some errors while generating pharmacophore.5.5%. For comparison, in a recent paper by Abhik Seal et al. (Journal of Cheminformatics 2013, vol. 5: 2), sensitivity for the pharmacophore I is 68%, and specificity is 71%.
    (view changes)
    5:02 pm

More