Lennart Eriksson
Research Subjects
Lennart Eriksson has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Erik Johansson
MKS Umetrics AB, SE-907 19 Umeå, Sweden
9 shared publicationsSvante Wold
Institute of Chemistry, Umeå University, SE-901 87 Umeå, Sweden
6 shared publicationsJohan Trygg
Computational Life Science Cluster (CLiC), Department of Chemistry, Umeå University, SE-901 87 Umeå, Sweden
5 shared publicationsMats Tysklind
Umeå University
3 shared publications- Johan Gottfries
AstraZeneca R&D, Mölndal, Sweden
2 shared publications Patrik L. Andersson
Umeå University
2 shared publications
Latest Publications
- 16 April 2012
- Published by Wiley in Molecular Informatics
- Vol. 31 (6-7) , 414-419
Orthogonal PLS (OPLS) Modeling for Improved Analysis and Interpretation in Drug Design
Partial least squares (PLS) regression is a flexible data analytical approach, which can be made even more versatile and useful by various modifications. In this article we describe the extension into orthogonal PLS modeling, in terms of two new methods, called OPLS and O2PLS, with similar prediction capacity but improved model interpretation.
- 16 April 2012
- Published by Wiley in Molecular Informatics
- Vol. 31 (6-7) , 414-419
Orthogonal PLS (OPLS) Modeling for Improved Analysis and Interpretation in Drug Design
Partial least squares (PLS) regression is a flexible data analytical approach, which can be made even more versatile and useful by various modifications. In this article we describe the extension into orthogonal PLS modeling, in terms of two new methods, called OPLS and O2PLS, with similar prediction capacity but improved model interpretation.
- 25 November 2009
- Published by Springer Nature in Molecular Diversity
- Vol. 14 (4) , 709-718
Extensions to amino acid description
A new set of amino acid descriptor scales was recently introduced. The new scales relate to amino acid side chain (i) rigidity and (ii) flexibility. These two properties were found to be orthogonal to each other. In this study, (i) the understanding of their meaning is improved, (ii) their utility further corroborated, and (iii) the scope of their applicability is broadened. Notably, the rigidity and flexibility scales are benchmarked against previous amino acid description precedence and found to contribute (1) new information, and (2) direct interpretation. The suggested description extensions were tested using empirical data from peptide description and in quantitative structure–activity relationships (QSAR).
- 25 November 2009
- Published by Springer Nature in Molecular Diversity
- Vol. 14 (4) , 709-718
Extensions to amino acid description
A new set of amino acid descriptor scales was recently introduced. The new scales relate to amino acid side chain (i) rigidity and (ii) flexibility. These two properties were found to be orthogonal to each other. In this study, (i) the understanding of their meaning is improved, (ii) their utility further corroborated, and (iii) the scope of their applicability is broadened. Notably, the rigidity and flexibility scales are benchmarked against previous amino acid description precedence and found to contribute (1) new information, and (2) direct interpretation. The suggested description extensions were tested using empirical data from peptide description and in quantitative structure–activity relationships (QSAR).
- Open Access
- 3 November 2009
- Published by Wiley in Journal of Chemometrics
- Vol. 23 (11) , 569-580
PLS‐trees®, a top‐down clustering approach
A hierarchical clustering approach based on a set of PLS models is presented. Called PLS‐Trees®, this approach is analogous to classification and regression trees (CART), but uses the scores of PLS regression models as the basis for splitting the clusters, instead of the individual X‐variables. The split of one cluster into two is made along the sorted first X‐score (t1) of a PLS model of the cluster, but may potentially be made along a direction corresponding to a combination of scores. The position of the split is selected according to the improvement of a weighted combination of (a) the variance of the X‐score, (b) the variance of Y and (c) a penalty function discouraging an unbalanced split with very different numbers of observations. Cross‐validation is used to terminate the branches of the tree, and to determine the number of components of each cluster PLS model. Some obvious extensions of the approach to OPLS‐Trees and trees based on hierarchical PLS or OPLS models with the variables divided in blocks depending on their type, are also mentioned. The possibility to greatly reduce the number of variables in each PLS model on the basis of their PLS w‐coefficients is also pointed out. The approach is illustrated by means of three examples. The first two examples are quantitative structure‐activity relationship (QSAR) data sets, while the third is based on hyper‐spectral images of liver tissue for identifying different sources of variability in the liver samples. Copyright © 2009 John Wiley & Sons, Ltd.
- 3 November 2009
- Published by Wiley in Journal of Chemometrics
- Vol. 23 (11) , 569-580
Open AccessPLS‐trees®, a top‐down clustering approach
A hierarchical clustering approach based on a set of PLS models is presented. Called PLS‐Trees®, this approach is analogous to classification and regression trees (CART), but uses the scores of PLS regression models as the basis for splitting the clusters, instead of the individual X‐variables. The split of one cluster into two is made along the sorted first X‐score (t1) of a PLS model of the cluster, but may potentially be made along a direction corresponding to a combination of scores. The position of the split is selected according to the improvement of a weighted combination of (a) the variance of the X‐score, (b) the variance of Y and (c) a penalty function discouraging an unbalanced split with very different numbers of observations. Cross‐validation is used to terminate the branches of the tree, and to determine the number of components of each cluster PLS model. Some obvious extensions of the approach to OPLS‐Trees and trees based on hierarchical PLS or OPLS models with the variables divided in blocks depending on their type, are also mentioned. The possibility to greatly reduce the number of variables in each PLS model on the basis of their PLS w‐coefficients is also pointed out. The approach is illustrated by means of three examples. The first two examples are quantitative structure‐activity relationship (QSAR) data sets, while the third is based on hyper‐spectral images of liver tissue for identifying different sources of variability in the liver samples. Copyright © 2009 John Wiley & Sons, Ltd.
- Top Cited Papers
- 12 November 2008
- Published by Wiley in Journal of Chemometrics
- Vol. 22 (11-12) , 594-600
CV‐ANOVA for significance testing of PLS and OPLS® models
This report describes significance testing for PLS and OPLS® (orthogonal PLS) models. The testing is applicable to single‐Y cases and is based on ANOVA of the cross‐validated residuals (CV‐ANOVA). Two variants of the CV‐ANOVA are introduced. The first is based on the cross‐validated predictive residuals of the PLS or OPLS model while the second works with the cross‐validated predictive score values of the OPLS model. The two CV‐ANOVA diagnostics are shown to work well in those cases where PLS and OPLS work well, that is, for data with many and correlated variables, missing data, etc. The utility of the CV‐ANOVA diagnostic is demonstrated using three datasets related to (i) the monitoring of an industrial de‐inking process; (ii) a pharmaceutical QSAR problem and (iii) a multivariate calibration application from a sugar refinery. Copyright © 2008 John Wiley & Sons, Ltd.
- 12 November 2008
- Published by Wiley in Journal of Chemometrics
- Vol. 22 (11-12) , 594-600
Top Cited PapersCV‐ANOVA for significance testing of PLS and OPLS® models
This report describes significance testing for PLS and OPLS® (orthogonal PLS) models. The testing is applicable to single‐Y cases and is based on ANOVA of the cross‐validated residuals (CV‐ANOVA). Two variants of the CV‐ANOVA are introduced. The first is based on the cross‐validated predictive residuals of the PLS or OPLS model while the second works with the cross‐validated predictive score values of the OPLS model. The two CV‐ANOVA diagnostics are shown to work well in those cases where PLS and OPLS work well, that is, for data with many and correlated variables, missing data, etc. The utility of the CV‐ANOVA diagnostic is demonstrated using three datasets related to (i) the monitoring of an industrial de‐inking process; (ii) a pharmaceutical QSAR problem and (iii) a multivariate calibration application from a sugar refinery. Copyright © 2008 John Wiley & Sons, Ltd.
- 1 August 2006
- Published by Wiley in Journal of Chemometrics
- Vol. 20 (8-10) , 352-361
Separating Y‐predictive and Y‐orthogonal variation in multi‐block spectral data
Spectral data (X) may contain (a) variation that is correlated to concentrations or properties (Y) of samples and (b) variation that is unrelated to the same Y. This paper outlines an approach by which both such sources of variation may be resolved. The approach is based on a combination of hierarchical modelling and orthogonal partial least squares (OPLS). OPLS is first used at the base hierarchical level. The output is a labelling of the resulting score vectors as representing Y‐predictive or Y‐orthogonal variation. OPLS is then also used at the top hierarchical level together with principal components analysis (PCA). With PCA the Y‐orthogonal X‐variation is analysed and interpreted. With OPLS the Y‐predictive X‐variation is examined. The applicability of the proposed strategy is illustrated using one multi‐block spectral data set. Copyright © 2007 John Wiley & Sons, Ltd.
- 1 August 2006
- Published by Wiley in Journal of Chemometrics
- Vol. 20 (8-10) , 352-361
Separating Y‐predictive and Y‐orthogonal variation in multi‐block spectral data
Spectral data (X) may contain (a) variation that is correlated to concentrations or properties (Y) of samples and (b) variation that is unrelated to the same Y. This paper outlines an approach by which both such sources of variation may be resolved. The approach is based on a combination of hierarchical modelling and orthogonal partial least squares (OPLS). OPLS is first used at the base hierarchical level. The output is a labelling of the resulting score vectors as representing Y‐predictive or Y‐orthogonal variation. OPLS is then also used at the top hierarchical level together with principal components analysis (PCA). With PCA the Y‐orthogonal X‐variation is analysed and interpreted. With OPLS the Y‐predictive X‐variation is examined. The applicability of the proposed strategy is illustrated using one multi‐block spectral data set. Copyright © 2007 John Wiley & Sons, Ltd.
- 27 June 2006
- Published by Springer Nature in Molecular Diversity
- Vol. 10 (2) , 187-205
Megavariate Analysis of Environmental QSAR Data. Part II – Investigating Very Complex Problem Formulations Using Hierarchical, Non-Linear and Batch-Wise Extensions of PCA and PLS
Three extensions of the basic PCA and PLS methodologies are described. These extensions are hierarchical, non-linear and batch-based in nature. The objectives of these methods are to assist in problem understanding and problem solving in very complex (QSAR) problem formulations. The method extensions are illustrated using two example QSAR data sets containing many X- and Y-variables.
- 27 June 2006
- Published by Springer Nature in Molecular Diversity
- Vol. 10 (2) , 187-205
Megavariate Analysis of Environmental QSAR Data. Part II – Investigating Very Complex Problem Formulations Using Hierarchical, Non-Linear and Batch-Wise Extensions of PCA and PLS
Three extensions of the basic PCA and PLS methodologies are described. These extensions are hierarchical, non-linear and batch-based in nature. The objectives of these methods are to assist in problem understanding and problem solving in very complex (QSAR) problem formulations. The method extensions are illustrated using two example QSAR data sets containing many X- and Y-variables.
- 13 June 2006
- Published by Springer Nature in Molecular Diversity
- Vol. 10 (2) , 169-186
Megavariate analysis of environmental QSAR data. Part I – A basic framework founded on principal component analysis (PCA), partial least squares (PLS), and statistical molecular design (SMD)
This paper introduces principal component analysis (PCA), partial least squares projections to latent structures (PLS), and statistical molecular design (SMD) as useful tools in deriving multi- and megavariate quantitative structure-activity relationship (QSAR) models. Two QSAR data sets from the fields of environmental toxicology and environmental chemistry are worked out in detail, showing the benefits of PCA, PLS and SMD. PCA is useful when overviewing a data set and exploring relationships among compounds and relationships among variables. PLS is the regression extension of PCA and is used for establishing QSARs. SMD is essential for selecting informative training and test sets of compounds for QSAR calibration and validation.
- 13 June 2006
- Published by Springer Nature in Molecular Diversity
- Vol. 10 (2) , 169-186
Megavariate analysis of environmental QSAR data. Part I – A basic framework founded on principal component analysis (PCA), partial least squares (PLS), and statistical molecular design (SMD)
This paper introduces principal component analysis (PCA), partial least squares projections to latent structures (PLS), and statistical molecular design (SMD) as useful tools in deriving multi- and megavariate quantitative structure-activity relationship (QSAR) models. Two QSAR data sets from the fields of environmental toxicology and environmental chemistry are worked out in detail, showing the benefits of PCA, PLS and SMD. PCA is useful when overviewing a data set and exploring relationships among compounds and relationships among variables. PLS is the regression extension of PCA and is used for establishing QSARs. SMD is essential for selecting informative training and test sets of compounds for QSAR calibration and validation.
- 1 May 2005
- Published by Wiley in Journal of Chemometrics
- Vol. 19 (5-7) , 393-403
Multivariate analysis of congruent images (MACI)
The multivariate analysis of congruent images (MACI) is discussed. Here, each image represents one observation and the data set contains a set of congruent images. With ‘congruent images’ we mean a set of images, properly pre‐processed, oriented and aligned, so that each data element (‘feature’, pixel) corresponds to the same element across all images. An example may be a set of frames from a fixed video camera looking at a stable process. The purpose of a MACI is to find and express patterns over a set of images for the purpose of classification or quantitative regression‐like relationships. This is in contrast to standard image analysis, which is usually concerned with a single image and the identification of parts of the image, for example tumour tissue versus normal. We also extend MACI to the case with a set of images that initially are not fully congruent, but are made so by the use of wavelet analysis and the distributions of the wavelet coefficients. Thus, the resulting description forms a set of congruent vectors amenable to multivariate data analysis. The MACI approach will be illustrated by four data sets, three easy‐to‐understand tutorial image data sets and one industrial image data set relating to quality control of steel rolls. Copyright © 2006 John Wiley & Sons, Ltd.
- 1 May 2005
- Published by Wiley in Journal of Chemometrics
- Vol. 19 (5-7) , 393-403
Multivariate analysis of congruent images (MACI)
The multivariate analysis of congruent images (MACI) is discussed. Here, each image represents one observation and the data set contains a set of congruent images. With ‘congruent images’ we mean a set of images, properly pre‐processed, oriented and aligned, so that each data element (‘feature’, pixel) corresponds to the same element across all images. An example may be a set of frames from a fixed video camera looking at a stable process. The purpose of a MACI is to find and express patterns over a set of images for the purpose of classification or quantitative regression‐like relationships. This is in contrast to standard image analysis, which is usually concerned with a single image and the identification of parts of the image, for example tumour tissue versus normal. We also extend MACI to the case with a set of images that initially are not fully congruent, but are made so by the use of wavelet analysis and the distributions of the wavelet coefficients. Thus, the resulting description forms a set of congruent vectors amenable to multivariate data analysis. The MACI approach will be illustrated by four data sets, three easy‐to‐understand tutorial image data sets and one industrial image data set relating to quality control of steel rolls. Copyright © 2006 John Wiley & Sons, Ltd.
- 29 October 2004
- Published by Taylor & Francis in SAR and QSAR in Environmental Research
- Vol. 15 (5-6) , 481-499
Three-block bi-focal PLS (3BIF-PLS) and its application in QSAR
When X and Y are multivariate, the two-block partial least squares (PLS) method is often used. In this paper, we outline an extension addressing a special case of the three-block (X/Y/Z) problem, where Z sits "under" Y. We have called this approach three-block bi-focal PLS (3BIF-PLS). It views the X/Y relationship as the dominant problem, and seeks to use the additional information in Z in order to improve the interpretation of the Y-part of the X/Y association. Two data sets are used to illustrate 3BIF-PLS. Example I relates to single point mutants of haloalkane dehalogenase from Sphingomonas paucimobilis UT26 and their ability to transform halogenated hydrocarbons, some of which are found as organic pollutants in soil. Example II deals with soil remediation capability of bacteria. Whole bacterial communities are monitored over time using "DNA-fingerprinting" technology to see how pollution affects population composition. Since the data sets are large, hierarchical multivariate modelling is invoked to compress data prior to 3BIF-PLS analysis. It is concluded that the 3BIF-PLS approach works well. The paper contains a discussion of pros and cons of the method, and hints at further developmental opportunities.
- 29 October 2004
- Published by Taylor & Francis in SAR and QSAR in Environmental Research
- Vol. 15 (5-6) , 481-499
Three-block bi-focal PLS (3BIF-PLS) and its application in QSAR
When X and Y are multivariate, the two-block partial least squares (PLS) method is often used. In this paper, we outline an extension addressing a special case of the three-block (X/Y/Z) problem, where Z sits "under" Y. We have called this approach three-block bi-focal PLS (3BIF-PLS). It views the X/Y relationship as the dominant problem, and seeks to use the additional information in Z in order to improve the interpretation of the Y-part of the X/Y association. Two data sets are used to illustrate 3BIF-PLS. Example I relates to single point mutants of haloalkane dehalogenase from Sphingomonas paucimobilis UT26 and their ability to transform halogenated hydrocarbons, some of which are found as organic pollutants in soil. Example II deals with soil remediation capability of bacteria. Whole bacterial communities are monitored over time using "DNA-fingerprinting" technology to see how pollution affects population composition. Since the data sets are large, hierarchical multivariate modelling is invoked to compress data prior to 3BIF-PLS analysis. It is concluded that the 3BIF-PLS approach works well. The paper contains a discussion of pros and cons of the method, and hints at further developmental opportunities.