25.12.2014 Views

Best practices for chemical data curation and QSAR model ...

Best practices for chemical data curation and QSAR model ...

Best practices for chemical data curation and QSAR model ...

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

The <strong>QSAR</strong> <strong>model</strong>s do not predict the majority of the<br />

64 HTS ‘Hits’ as binders in agreement with<br />

experimental study by Shoichet group<br />

The average class number<br />

2.1<br />

2.0<br />

1.9<br />

1.8<br />

1.7<br />

1.6<br />

1.5<br />

1.4<br />

1.3<br />

1.2<br />

1.1<br />

1.0<br />

0.9<br />

5<br />

20<br />

0 20 40 60 80 100 120<br />

No. of <strong>model</strong>s in prediction<br />

predicted as nonbinder<br />

predicted as inhibitor<br />

Z = 0.5; Accuracy = 20/25 = 0.8<br />

The average class number<br />

2.1<br />

2.0<br />

1.9<br />

1.8<br />

1.7<br />

1.6<br />

1.5<br />

1.4<br />

1.3<br />

1.2<br />

1.1<br />

1.0<br />

0.9<br />

47<br />

8<br />

0 50 100 150 200 250 300 350<br />

No. of <strong>model</strong>s <strong>for</strong> prediction<br />

Z = 3.0; Accuracy = 47/55 = 0.85<br />

assigned as nonbinder<br />

assigned as inhibitor<br />

Babaoglu et al. J Med Chem. 2008 Apr 24;51(8):2502-11

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!