• Looking at your statistical models...

    I do not think I have ever blogged the paper that played an important role in my thesis (doi:10.1021/ci990038z); research of one of the papers in my thesis, started with the hypothesis proposed therein. The paper had a really good idea; but, unfortunately, it did not contain the data to support the hypothesis. That gets me to one important lesson I learned: a QSAR data set of less than 100 molecules is not enough to make untargeted statistical models.
  • QSPR modeling with signatures

    I had to dig deep to find posts on QSAR modeling. There are quite a few on QSAR in Bioclipse, but that focuses on the descriptor calculation. In a quick scan, I could only spot two modeling posts:
  • My OpenTox Workshop contribution: The Lost Slides

    During the nice presentations at the recent OpenTox Workshop, I noted that My OpenTox Workshop contribution: Linking explicit and implicit knowledge was lacking two slides. The slides should have had screenshot of the excellent Bioclipse applications Ola Spjuth has written in the area of computational toxicology. But here they are.
  • I’m just a sucker with no self esteem

    Don’t let anyone fool you: The Offspring is really just talking about Science:
  • CDK-JChemPaint #6: rendering atom numbers

    I have made a few new CDK-JChemPaint patches in the past two days, the latest being patch 15. With the help from Gilleain, all rendering parameters are now using the new API, as explained earlier in this series.
  • And now for something completely different...

    A cake so good, you like to protect it with whatever force you have.
  • My OpenTox Workshop contribution: Linking explicit and implicit knowledge

    Please find below the views I have expressed at the OpenTox Workshop in the nice Potsdam area near Berlin: