{ "version": "https://jsonfeed.org/version/1.1", "title": "chem-bla-ics", "description": "Chemblaics (pronounced chem-bla-ics) is the science that uses open science and computers to solve problems in chemistry, biochemistry and related fields.", "home_page_url": "https://chem-bla-ics.linkedchemistry.info/", "feed_url": "https://chem-bla-ics.linkedchemistry.info/2008/04/07/cdkmetabolomicschemometrics.json", "icon": "https://chem-bla-ics.linkedchemistry.info/assets/images/chem-bla-ics_logo.png", "language": "en", "authors": [ { "name": "Egon Willighagen", "url": "https://orcid.org/0000-0001-7542-0286", "_orcid": "0000-0001-7542-0286" } ], "items": [ { "id": "https://doi.org/10.59350/f2ajz-tmr63", "url": "https://chem-bla-ics.linkedchemistry.info/2008/04/07/cdkmetabolomicschemometrics.html", "title": "The CDK/Metabolomics/Chemometrics Unconference results", "content_html": "

As announced earlier , Miguel, Velitchka,\nChristoph and I held a small CDK/Metabolomics/Chemometrics\nunconference. We started late, and did not have an evening program, resulting in not overly much results. However, we did do\nmolecular chemometrics.

\n\n

We used the R statistics software together with Rajarshi’s rcdk\npackage (an R wrapper around the CDK library) and Ron’s (my PhD supervisor) PLS\npackage (see this paper), to predict retention indices for a number of metabolites.

\n\n

We ended up with this R script:

\n\n
library(\"rJava\")\nlibrary(\"rcdk\")\nlibrary(\"pls\")\nmols = load.molecules(\"data_cdk.sdf\")\nselection = get.desc.names()\nselection = selection[-which(selection==\"org.openscience.cdk.qsar.descriptors.molecular.AminoAcidCountDescriptor\")]\nx = eval.desc(mols, selection, verbose=TRUE)\nx2 = x[,apply(x, 2, function(a) {all(!is.na(a))})]\ny = read.table(\"data_cdk_RI\")\ninput = data.frame(x2, y)\npls.model = plsr(V1 ~ ., 50, data=input, validation=\"CV\")\nsummary(pls.model)\nplot(RMSEP(pls.model))\nplot(pls.model, ncomp=20)\nabline(0,1, col=\"red\")\nplot(pls.model, \"loadings\", comps=1:2)\nsavehistory(\"finalHistory.R\")\n
\n\n

The AminoAcidCountDescriptor threw us a NullPointerException and there were a few NAs in the resulting matrix. The CV results were\nnot so good as Velitchka’s best models, but still a good start:

\n\n

\"\"

\n\n

No variable selection; 200 objects, 190 variables.

\n\n

Questions:

\n\n\n\n

References

\n
\n
Mevik, B.-H., & Wehrens, R. (2007). The                    pls                    Package: Principal Component and Partial Least Squares Regression in                    R. Journal of Statistical Software, 18(2). https://doi.org/10.18637/jss.v018.i02 CrossRef Scholia
\n
", "summary": "As announced earlier , Miguel, Velitchka, Christoph and I held a small CDK/Metabolomics/Chemometrics unconference. We started late, and did not have an evening program, resulting in not overly much results. However, we did do molecular chemometrics.", "image": "https://chem-bla-ics.linkedchemistry.info/assets/images/riPred.png", "date_published": "2008-04-07T00:10:00+00:00", "date_modified": "2025-10-11T00:00:00+00:00", "tags": ["cdk","defense","phd","metabolomics","cheminf","chemometrics"], "_references": [ { "url": "https://doi.org/10.18637/jss.v018.i02", "doi": "10.18637/jss.v018.i02" } ], "authors": [ { "name": "Egon Willighagen", "url": "https://orcid.org/0000-0001-7542-0286" } ] } ] }