Lecture 6&7 - Chemometrics

Question 1

what is chemometrics

Answer 1

a multivariate statistical analysis that is computationally intensive and is applied to chemical systems or processes to find patterns and trends in the data

Question 2

what does multivariate mean

Answer 2

analyses multiple variables

Question 3

what does computationally intensive mean

Answer 3

the need for a computer and algorithms

Question 4

name 6 things chemometrics can help us do

Answer 4

• reduce complex datasets
• identify and quantify sample groups
• optimise our experimental parameters
• identify covariance and pick out important variables
• give reproducible measures of data
• visualise the data (a picture is better)

Question 5

what is meant by covariance

Answer 5

which parts of the data are associated/not independent

Question 6

what effect does chemometrics have on subjectivity

Answer 6

reduces it in the analysis of data but does not eliminate it completely as human still interpret the data

Question 7

what can chemometric reveal that may have not been noticed

Answer 7

underlying/ not obvious trends between variables

Question 8

what is the main aim of chemometrics

Answer 8

to maximise output and quality with minimal cost

Question 9

chemometrics has been used in forensic science since 2009 - what benefits has this provided

Answer 9

improved efficiency in forensic workflow
better quality of the use of resources for forensic purposes

Question 10

how is chemometric applicable to forensic science (6)

Answer 10

statistical framework

replaces use of unique and match without use of stats to support (subjectivity)

can counteract bias

quicker than manual data interpretation

don’t need an expert but someone does need to be able to interpret the output data

can predict trace behaviour

Question 11

what can be identified using multivariate analysis that may not be seen in univariate analysis

Answer 11

outliers

Question 12

what is univariate analysis

Answer 12

analysis that only considers one variable

Question 13

give an example of where multivariate analysis may be beneficial in forensic analysis and the variables that could be considered

Answer 13

pollen dispersion
considering time of year and weather

fingermarks
considering sweatiness of someone and weather conditions

Question 14

what are the 4 broad categories of chemometrics

Answer 14

experiment design (DOE)
exploratory data analysis (EDA - what is the data showing me)
classification
regression

Question 15

what does the DOE (design of experiment) affect in forensic science

Answer 15

evidence collection, storage, analysis instrument selection and optimisation

Question 16

what can the DOE part of chemometrics be used to streamline in forensics in the future

Answer 16

efficiency, quality and reproducibility by establishing optimised workflows

Question 17

what does the regression part of chemometrics involve

Answer 17

a version calibration curves based on a linear y=mx+c relationship which maps the effect of multivariate independent variables

we can make educated predictions based of the curve

Question 18

What happens in the EDA part of chemometrics

Answer 18

data is reduced by an algorithm that looks how variables correspond

identifies groupings of samples in complex datasets

visualises trends

making the data more manageable

Question 19

EDA is an unsupervised technique - what does this mean

Answer 19

it explores the data without any prior assumptions or knowledge of the samples (reducing human bias and subjectivity)

Question 20

what is a supervised technique

Answer 20

the building of classification rules for grouping samples together - done from EDA analysis

Question 21

name the two most commonly used EDA techniques

Answer 21

CA = cluster analysis
PCA = principal component analysis

Question 22

name 3 features of cluster analysis (CA)

Answer 22

unsupervised technique

samples are grouped into clusters based on a measure of similarity (a calculated distance)

the output is a dendrogram

Question 23

what are the two types of cluster analysis

Answer 23

ACA - agglomerative cluster analysis
HCA - hierarchical cluster analysis

Question 24

what is agglomerative cluster analysis (ACA)

Answer 24

individual samples are grouped into clusters

Question 25

what is hierarchical cluster analysis (HCA)

Answer 25

clusters are split into individual samples

Question 26

in cluster analysis which samples are the most similar

Answer 26

the ones grouped closest to zero

Question 27

how are the number of clusters decided in cluster analysis

Answer 27

the analyst decides on the stopping rules - where the subjectivity is introduced

Question 28

what is a limitation of cluster analysis

Answer 28

the visualisation of relationships is made clear but it can not tell WHY these grouping occur

Question 29

what happens in PCA analysis

Answer 29

an algorithm an unsupervised technique assesses all variable in a dataset and decides which are relevant and correlated

Question 30

in PCA when the algorithm finds a correlation what is this defined as

Answer 30

a Principal Component (PC)

Question 31

what does the PC describe in PCA analysis

Answer 31

the largest variation between samples with PC1 being given the highest priority

Question 32

For 'good' data how many principal components would you expect to see in PCA

Answer 32

more than 1 multiple PC's are identified by the algorithm until all the variability within the dataset has been modelled

Question 33

what is data comprised of

Answer 33

structure and noise or model and error where data = spectra and chromatograms structure/model = useful info (explained variance) noise/error = not useful info to data interpretation (instrument noise, lab temp fluctuation) (residual variance)

Question 34

how are principal components represented in PCA

Answer 34

a straight line = a linear combination of the original variables

Question 35

in PCA what assigns a sample a 'score'

Answer 35

the distance along the PC line from the mean (can be positive or negative) each sample has a different score for each principal component

Question 36

how many PCs can a model have in PCA

Answer 36

as many as the number of original variables

Question 37

what type of plot reveals the optimum number of PCs for a given number of variables in PCA

Answer 37

an explained variance or scree plot the % on this plot (y axis) is the variance in the data set keep on adding PCs until you are adding less than 1% variance as here you are likely to be looking at noise this is a poor method of decides how many PCs to use

Question 38

what is a better method to use than scree/explained variance plots

Answer 38

scores plots

Question 39

what is a scores plot

Answer 39

a map of the samples where each data point is a sample and similar samples are clusters samples closer to each other are more similar and vice versa the x and y axis correspond to two PC's these can be any plotting different PCs against eachother gives different clusters

Question 40

how can you tell by looking at scores plots that a PC is modelling noise and not useful information

Answer 40

if plotting PC1 vs PC4 and then PC1 vs PC5 gives very similar sample clusters then it is likely that PC5 is just modelling noise and isn't adding any value to the data

Question 41

what is a benefit of PCA over CA

Answer 41

PCA can tell you why samples cluster but CA can't

Question 42

scores plots however do not always reveal immediate trends so what type of plot can be used instead

Answer 42

skittles plots

Question 43

what is a skittles plot

Answer 43

again this is plotting PCs against each other e.g PC1 vs PC2 samples are then grouped according to predefined categories e.g creams, liquids, loose powders, pressed powders and mousses

Question 44

what is the benefit of 3D scores plots

Answer 44

for even better data visualisation different combinations of PCs can be plotted for better groupings

Question 45

what is a PCA loading plot

Answer 45

the link between a scores plot and the chemistry of the samples - tells us why certain samples group together (why PCA is better than CA) (scores plots = map of samples loadings = map of variables) y axis = loading x axis = raman shift (example) the loading value can be +ve or -ve

Question 46

what do loading values represent

Answer 46

The weight of a particular variable - e.g in slide 19 lecture 7 the blue line tells you that anything grouped into PC1 will have the long peak at the start in the spectrum

Question 47

name one type of supervised chemometric technique

Answer 47

LDA = linear discriminant analysis

Question 48

what happens in LDA = linear discriminant analysis

Answer 48

PCs are used to create classification rules classifying unknown samples

Question 49

LDA mathematically works similarly to PCA but what are PCs and scores called instead why are loadings also calculated in LDA

Answer 49

PCs = discriminant functions scores = discriminant values loadings are also calculated like in PCA to maximise separation between known sample groupings

Question 50

briefly explain how PCA and LDA differ

Answer 50

PCA - looks for most variation between samples - applied loading weight where variation is found plots PC1 vs PC2 (or any PC number) LDA - tries to minimise variation within sample groups to maximise the separation of groupings by prioritising the loading values plots class 1 vs class 2

Question 51

in LDA what are samples in the same group given

Answer 51

similar discriminant values (PCs) those in different groups are given different discriminant values

Question 52

name 4 limitations to using chemometrics for trace evidence analysis

Answer 52

- can't make up for poor data - data preprocessing can be important but less is more (overprocessing data can cause issues if you are trying to force the data to show what it doesn'y) - sample size is better if bigger but this is hard in trace analysis - do the samples use accurately reflect the population

Question 53

what are things that can happen during sample collection and analysis that chemometrics does not take into account

Answer 53

contamination degradation replicates taken controlled sample collection reproducibility

Question 54

what is chemometric not a substitution for

Answer 54

human data interpretation the user must be able to understand and explain the methods to the judge and jury