Chemometrics, DTW, MCR

Question

Hello,

we are in touch with a customer who have potential users in Analytical department who will likely stop using Unscrambler for sake of cost.

1) Does someone has an idea of the cost of UNscrambler or SIMCA which seems to be the usual tools for Chemometrics ?

2) JMP is able to do PCA, PLS, ... we have the "Spectral tool" add-in to import and smooth the data. However DTW, available in the FDE platform, seems very important. Is there a way to do DTW other than through FDE ? For instance if they don't have JMP Pro or want to do DTW prior to PCA or PLS.

3) can we do MCR (Multivariate Curve Resolution) ?

Emmanuel

Phil_Kay · Accepted Answer

Hi Emmanuel,

1. Check out the SWOT for SIMCA, which includes pricing. It is possible that it is has changed, of course. I imagine Unscrambler is similar.

2. DTW in JMP? I really don't think so. Pro is a better comparison with SIMCA/Unscrambler. Even with Pro there will still be capabilities that they would not have. So it depends what they need to do. "Chemometrics" can mean lots of different things. It might be that all they need is JMP for some simple PCA.

3. I don't think so.

Cheers,

Phil

Bill_Worley · Accepted Answer

Hi Emmanuel,

Just to add to @Phil_Kay comments.

1. Unscrambler is owned by aspentech.  They have Aspen Unscrambler and Aspen Unscrambler HSI.  The HSI stands for hyperspectral images.  Unscrambler was originally  from Camo software and I saw a price of $3000 for a standard version and $1500 for an academic license.  I am pretty sure those numbers are not current.

2. Agree with Phil here , and I would add PLS as an option for chemometrics in regular JMP.

3.  Here is the Wiki definition for MCR:

Multivariate curve resolution[edit]

In chemometric parlance, multivariate curve resolution seeks to deconstruct data sets with limited or absent reference information and system knowledge. Some of the earliest work on these techniques was done by Lawton and Sylvestre in the early 1970s.[14][15] These approaches are also called self-modeling mixture analysis, blind source/signal separation, and spectral unmixing. For example, from a data set comprising fluorescence spectra from a series of samples each containing multiple fluorophores, multivariate curve resolution methods can be used to extract the fluorescence spectra of the individual fluorophores, along with their relative concentrations in each of the samples, essentially unmixing the total fluorescence spectrum into the contributions from the individual components. The problem is usually ill-determined due to rotational ambiguity (many possible solutions can equivalently represent the measured data), so the application of additional constraints is common, such as non-negativity, unimodality, or known interrelationships between the individual components (e.g., kinetic or mass-balance constraints).

I agree with Phil here too, but I believe the Wavelet modeling and filtering capability coming in JMP Pro 17 for FDE is a move in the MCR direction.