Umeå universitets logga

YY1-mediated chromatin loops play substantial roles in basic biological processes like gene regulation, cell differentiation, and DNA replication. YY1-mediated chromatin loop prediction is important to understand diverse types of biological processes which may lead to the development of new therapeutics for neurological disorders and cancers. Existing deep learning predictors are capable to predict YY1-mediated chromatin loops in two different cell lines however, they showed limited performance for the prediction of YY1-mediated loops in the same cell lines and suffer significant performance deterioration in cross cell line setting. To provide computational predictors capable of performing large-scale analyses of YY1-mediated loop prediction across multiple cell lines, this paper presents two novel deep learning predictors. The two proposed predictors make use of Word2vec, one hot encoding for sequence representation and long short-term memory, and a convolution neural network along with a gradient flow strategy similar to DenseNet architectures. Both of the predictors are evaluated on two different benchmark datasets of two cell lines HCT116 and K562. Overall the proposed predictors outperform existing DEEPYY1 predictor with an average maximum margin of 4.65%, 7.45% in terms of AUROC, and accuracy, across both of the datases over the independent test sets and 5.1%, 3.2% over 5-fold validation. In terms of cross-cell evaluation, the proposed predictors boast maximum performance enhancements of up to 9.5% and 27.1% in terms of AUROC over HCT116 and K562 datasets.

Ripening is the most crucial process step in cheese manufacturing and constitutes multiple biochemical alterations that describe the final cheese quality and its perceived sensory attributes. The assessment of the cheese-ripening process is challenging and requires the effective analysis of a multitude of biochemical changes occurring during the process. This study monitored the biochemical and sensory attribute changes of paraffin wax-covered long-ripening hard cheeses (n = 79) during ripening by collecting samples at different stages of ripening. Near-infrared hyperspectral (NIR-HS) imaging, together with free amino acid, chemical composition, and sensory attributes, was studied to monitor the biochemical changes during the ripening process. Orthogonal projection-based multivariate calibration methods were used to characterize ripening-related and orthogonal components as well as the distribution map of chemical components. The results approve the NIR-HS imaging as a rapid tool for monitoring cheese maturity during ripening. Moreover, the pixelwise evaluation of images shows the homogeneity of cheese maturation at different stages of ripening. Among the chemical compositions, fat content and moisture are the most important variables correlating to NIR-HS images during the ripening process.

Background: Monoclonal antibodies (mAbs) are leading types of ‘blockbuster’ biotherapeutics worldwide; they have been successfully used to treat various cancers and chronic inflammatory and autoimmune diseases. Biotherapeutics process development and manufacturing are complicated due to lack of understanding the factors that impact cell productivity and product quality attributes. Understanding complex interactions between cells, media, and process parameters on the molecular level is essential to bring biomanufacturing to the next level. This can be achieved by analyzing cell culture metabolic levels connected to vital process parameters like viable cell density (VCD). However, VCD and metabolic profiles are dynamic parameters and inherently correlated with time, leading to a significant correlation without actual causality. Many time-series methods deal with such issues. However, with metabolic profiling, the number of measured variables vastly exceeds the number of experiments, making most of existing methods ill-suited and hard to interpret. Methods and Major

Results: Here we propose an alternative workflow using hierarchical dimension reduction to visualize and interpret the relation between evolution of metabolic profiles and dynamic process parameters. The first step of proposed method is focused on finding predictive relation between metabolic profiles and process parameter at all time points using OPLS regression. For each time point, the p(corr) obtained from OPLS model is considered as a differential metabogram and is further assessed using principal components analysis (PCA).

Conclusions: Compared to traditional batch modeling, applying proposed methodology on metabolic data from Chinese Hamster Ovary (CHO) antibody production characterized the dynamic relation between metabolic profiles and critical process parameters.

In this paper, various preprocessing methods were tested on data generated by X-ray powder diffraction (XRPD) in order to enhance the partial least-squares (PLS) regression modeling performance. The preprocessing methods examined were 22 different discrete wavelet transforms, Fourier transform, Savitzky-Golay, orthogonal signal correction (OSC), and combinations of wavelet transform and OSC, and Fourier transform and OSC. Root mean square error of prediction (RMSEP) of an independent test set was used to measure the performance of the various preprocessing methods. The best PLS model was obtained with a wavelet transform (Symmlet 8), which at the same time compressed the data set by a factor of 9.5. With the use of wavelet and X-ray powder diffraction, concentrations of less than 10% of one crystal from could be detected in a binary mixture. The linear range was found to be in the range 10-70% of the crystalline form of phenacetin, although semiquantitative work could be carried out down to a level of approximately 2%. Furthermore, the wavelet-pretreated models were able to handle admixtures and deliberately added noise.

Subcellular localization of Ribonucleic Acid (RNA) molecules provide significant insights into the functionality of RNAs and helps to explore their association with various diseases. Predominantly developed single-compartment localization predictors (SCLPs) lack to demystify RNA association with diverse biochemical and pathological processes mainly happen through RNA co-localization in multiple compartments. Limited multi-compartment localization predictors (MCLPs) manage to produce decent performance only for target RNA class of particular sub-type. Further, existing computational approaches have limited practical significance and potential to optimize therapeutics due to the poor degree of model explainability. The paper in hand presents an explainable Long Short-Term Memory (LSTM) network “EL-RMLocNet”, predictive performance and interpretability of which are optimized using a novel GeneticSeq2Vec statistical representation learning scheme and attention mechanism for accurate multi-compartment localization prediction of different RNAs solely using raw RNA sequences. GeneticSeq2Vec generates optimized statistical vectors of raw RNA sequences by capturing short and long range relations of nucleotide k-mers. Using sequence vectors generated by GeneticSeq2Vec scheme, Long Short Term Memory layers extract most informative features, weighting of which on the basis of discriminative potential for accurate multi-compartment localization prediction is performed using attention layer. Through reverse engineering, weights of statistical feature space are mapped to nucleotide k-mers patterns to make multi-compartment localization prediction decision making transparent and explainable for different RNA classes and species. Empirical evaluation indicates that EL-RMLocNet outperforms state-of-the-art predictor for subcellular localization prediction of 4 different RNA classes by an average accuracy figure of 8% for Homo Sapiens species and 6% for Mus Musculus species. EL-RMLocNet is freely available as a web server at (https://sds_genetic_analysis.opendfki.de/subcellular_loc/).

A comprehensive understanding of miRNA sub-cellular localization may leads towards better understanding of physiological processes and support the fixation of diverse irregularities present in a variety of organisms. To date, diverse computational methodologies have been proposed to automatically infer sub-cellular localization of miR-NAs solely using sequence information, however, existing approaches lack in performance. Considering the success of data transformation approaches in Natural Language Processing which primarily transform multi-label classification problem into multi-class classification problem, here, we introduce three different data transformation approaches namely binary relevance, label power set, and classifier chains. Using data transformation approaches, at 1st stage, multi-label miRNA sub-cellular localization problem is transformed into multi-class problem. Then, at 2nd stage, 3 different machine learning classifiers are used to estimate which classifier performs better with what data transformation approach for hand on task. Empirical evaluation on independent test set indicates that L2S-MirLoc selected combination based on binary relevance and deep random forest outperforms state-of-the-art performance values by significant margin.

Background and objective: Interactions of long non-coding ribonucleic acids (lncRNAs) with micro-ribonucleic acids (miRNAs) play an essential role in gene regulation, cellular metabolic, and pathological processes. Existing purely sequence based computational approaches lack robustness and efficiency mainly due to the high length variability of lncRNA sequences. Hence, the prime focus of the current study is to find optimal length trade-offs between highly flexible length lncRNA sequences.

Method: The paper at hand performs in-depth exploration of diverse copy padding, sequence truncation approaches, and presents a novel idea of utilizing only subregions of lncRNA sequences to generate fixed-length lncRNA sequences. Furthermore, it presents a novel bag of tricks-based deep learning approach “Bot-Net” which leverages a single layer long-short-term memory network regularized through DropConnect to capture higher order residue dependencies, pooling to retain most salient features, normalization to prevent exploding and vanishing gradient issues, learning rate decay, and dropout to regularize precise neural network for lncRNA–miRNA interaction prediction.

Results: BoT-Net outperforms the state-of-the-art lncRNA–miRNA interaction prediction approach by 2%, 8%, and 4% in terms of accuracy, specificity, and matthews correlation coefficient. Furthermore, a case study analysis indicates that BoT-Net also outperforms state-of-the-art lncRNA–protein interaction predictor on a benchmark dataset by accuracy of 10%, sensitivity of 19%, specificity of 6%, precision of 14%, and matthews correlation coefficient of 26%.

Conclusion: In the benchmark lncRNA–miRNA interaction prediction dataset, the length of the lncRNA sequence varies from 213 residues to 22,743 residues and in the benchmark lncRNA–protein interaction prediction dataset, lncRNA sequences vary from 15 residues to 1504 residues. For such highly flexible length sequences, fixed length generation using copy padding introduces a significant level of bias which makes a large number of lncRNA sequences very much identical to each other and eventually derail classifier generalizeability. Empirical evaluation reveals that within 50 residues of only the starting region of long lncRNA sequences, a highly informative distribution for lncRNA–miRNA interaction prediction is contained, a crucial finding exploited by the proposed BoT-Net approach to optimize the lncRNA fixed length generation process.

Small non-coding RNAs (ncRNAs) are attracting increasing attention as they are now considered potentially valuable resources in the development of new drugs intended to cure several human diseases. A prerequisite for the development of drugs targeting ncRNAs or the related pathways is the identification and correct classification of such ncRNAs. State-of-the-art small ncRNA classification methodologies use secondary structural features as input. However, such feature extraction approaches only take global characteristics into account and completely ignore co-relative effects of local structures. Furthermore, secondary structure based approaches incorporate high dimensional feature space which is computationally expensive. The present paper proposes a novel Robust and Precise ConvNet (RPC-snRC) methodology which classifies small ncRNAs into relevant families by utilizing their primary sequence. RPC-snRC methodology learns hierarchical representation of features by utilizing positioning and information on the occurrence of nucleotides. To avoid exploding and vanishing gradient problems, we use an approach similar to DenseNet in which gradient can flow straight from subsequent layers to previous layers. In order to assess the effectiveness of deeper architectures for small ncRNA classification, we also adapted two ResNet architectures having a different number of layers. Experimental results on a benchmark small ncRNA dataset show that the proposed methodology does not only outperform existing small ncRNA classification approaches with a significant performance margin of 10% but it also gives better results than adapted ResNet architectures. To reproduce the results Source code and data set is available at https://github.com/muas16/small-non-coding-RNA-classification.

MicroRNAs (miRNA) are small noncoding RNA sequences consisting of about 22 nucleotides that are involved in the regulation of almost 60% of mammalian genes. Presently, there are very limited approaches for the visualization of miRNA locations present inside cells to support the elucidation of pathways and mechanisms behind miRNA function, transport, and biogenesis. MIRLocator, a state-of-the-art tool for the prediction of subcellular localization of miRNAs makes use of a sequence-to-sequence model along with pretrained k-mer embeddings. Existing pretrained k-mer embedding generation methodologies focus on the extraction of semantics of k-mers. However, in RNA sequences, positional information of nucleotides is more important because distinct positions of the four nucleotides define the function of an RNA molecule. Considering the importance of the nucleotide position, we propose a novel approach (kmerPR2vec) which is a fusion of positional information of k-mers with randomly initialized neural k-mer embeddings. In contrast to existing k-mer-based representation, the proposed kmerPR2vec representation is much more rich in terms of semantic information and has more discriminative power. Using novel kmerPR2vec representation, we further present an end-to-end system (MirLocPredictor) which couples the discriminative power of kmerPR2vec with Convolutional Neural Networks (CNNs) for miRNA subcellular location prediction. The effectiveness of the proposed kmerPR2vec approach is evaluated with deep learning-based topologies (i.e., Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN)) and by using 9 different evaluation measures. Analysis of the results reveals that MirLocPredictor outperform state-of-the-art methods with a significant margin of 18% and 19% in terms of precision and recall.

The whole-genome response of Arabidopsis (Arabidopsis thaliana) exposed to different types and durations of abiotic stress has now been described by a wealth of publicly available microarray data. When combined with studies of how gene expression is affected in mutant and transgenic Arabidopsis with altered ability to transduce the low temperature signal, these data can be used to test the interactions between various low temperature-associated transcription factors and their regulons. We quantized a collection of Affymetrix microarray data so that each gene in a particular regulon could vote on whether a cis-element found in its promoter conferred induction (+1), repression (–1), or no transcriptional change (0) during cold stress. By statistically comparing these election results with the voting behavior of all genes on the same gene chip, we verified the bioactivity of novel cis-elements and defined whether they were inductive or repressive. Using in silico mutagenesis we identified functional binding consensus variants for the transcription factors studied. Our results suggest that the previously identified ICEr1 (induction of CBF expression region 1) consensus does not correlate with cold gene induction, while the ICEr3/ICEr4 consensuses identified using our algorithms are present in regulons of genes that were induced coordinate with observed ICE1 transcript accumulation and temporally preceding genes containing the dehydration response element. Statistical analysis of overlap and cis-element enrichment in the ICE1, CBF2, ZAT12, HOS9, and PHYA regulons enabled us to construct a regulatory network supported by multiple lines of evidence that can be used for future hypothesis testing.

Systemic lupus erythematosus (SLE) is a chronic inflammatory autoimmune disease which can affect most organ systems including skin, joints and the kidney. Clinically, SLE is a heterogeneous disease and shares features of several other rheumatic diseases, in particular primary Sjögrens syndrome (pSS) and systemic sclerosis (SSc), why it is difficult to diag- nose The pathogenesis of SLE is not completely understood, partly due to the heterogeneity of the disease. This study demonstrates that metabolomics can be used as a tool for improved diagnosis of SLE compared to other similar autoimmune diseases. We observed differences in metabolic profiles with a classification specificity above 67% in the comparison of SLE with pSS, SSc and a matched group of healthy individuals. Selected metabolites were also significantly different between studied diseases. Biochemical pathway analysis was conducted to gain understanding of underlying pathways involved in the SLE pathogenesis. We found an increased oxidative activity in SLE, supported by increased xanthine oxidase activity and an increased turnover in the urea cycle. The most discriminatory metabolite observed was tryptophan, with decreased levels in SLE patients compared to control groups. Changes of tryptophan levels were related to changes in the activity of the aromatic amino acid decarboxylase (AADC) and/or to activation of the kynurenine pathway. 

Metabolic phenotyping is an important tool in translational biomedical research. The advanced analytical technologies commonly used for phenotyping, including mass spectrometry (MS) and nuclear magnetic resonance (NMR) spectroscopy, generate complex data requiring tailored statistical analysis methods. Detailed protocols have been published for data acquisition by liquid NMR, solid-state NMR, ultra-performance liquid chromatography (LC-)MS and gas chromatography (GC-)MS on biofluids or tissues and their preprocessing. Here we propose an efficient protocol (guidelines and software) for statistical analysis of metabolic data generated by these methods. Code for all steps is provided, and no prior coding skill is necessary. We offer efficient solutions for the different steps required within the complete phenotyping data analytics workflow: scaling, normalization, outlier detection, multivariate analysis to explore and model study-related effects, selection of candidate biomarkers, validation, multiple testing correction and performance evaluation of statistical models. We also provide a statistical power calculation algorithm and safeguards to ensure robust and meaningful experimental designs that deliver reliable results. We exemplify the protocol with a two-group classification study and data from an epidemiological cohort; however, the protocol can be easily modified to cover a wider range of experimental designs or incorporate different modeling approaches. This protocol describes a minimal set of analyses needed to rigorously investigate typical datasets encountered in metabolic phenotyping.

The investigation presented here describes a protocol designed to perform high-throughput metabolic profiling analysis on human blood plasma by ultra-performance liquid chromatography/mass spectrometry (UPLC/MS). To address whether a previous extraction protocol for gas chromatography (GC)/MS-based metabolic profiling of plasma could be used for UPLC/MS-based analysis, the original protocol was compared with similar methods for extraction of low-molecular-weight compounds from plasma via protein precipitation. Differences between extraction methods could be observed, but the previously published extraction method was considered the best. UPLC columns with three different stationary phases (C8, C18, and phenyl) were used in identical experimental runs consisting of a total of 60 injections of extracted male and female plasma samples. The C8 column was determined to be the best for metabolic profiling analysis on plasma. The acquired UPLC/MS data of extracted male and female plasma samples was subjected to principal component analysis (PCA) and orthogonal projections to latent structures discriminant analysis (OPLS–DA). Furthermore, a strategy for compound identification was applied here, demonstrating the strength of high-mass-accuracy time-of-flight (TOF)/MS analysis in metabolic profiling.

Purpose:

Survival for high-grade gliomas is poor, at least partly explained by intratumoral heterogeneity contributing to treatment resistance. Radiological evaluation of treatment response is in most cases limited to assessment of tumor size months after the initiation of therapy. Diffusion-weighted magnetic resonance imaging (MRI) and its estimate of the apparent diffusion coefficient (ADC) has been widely investigated, as it reflects tumor cellularity and proliferation. The aim of this study was to investigate texture analysis of ADC images in conjunction with multivariate image analysis as a means for identification of pretreatment imaging biomarkers.

Methods:

Twenty-three consecutive high-grade glioma patients were treated with radiotherapy (2 Gy/60 Gy) with concomitant and adjuvant temozolomide. ADC maps and T1-weighted anatomical images with and without contrast enhancement were collected prior to treatment, and (residual) tumor contrast enhancement was delineated. A gray-level co-occurrence matrix analysis was performed on the ADC maps in a cuboid encapsulating the tumor in coronal, sagittal, and transversal planes, giving a total of 60 textural descriptors for each tumor. In addition, similar examinations and analyses were performed at day 1, week 2, and week 6 into treatment. Principal component analysis (PCA) was applied to reduce dimensionality of the data, and the five largest components (scores) were used in subsequent analyses. MRI assessment three months after completion of radiochemotherapy was used for classifying tumor progression or regression.

Results:

The score scatter plots revealed that the first, third, and fifth components of the pretreatment examinations exhibited a pattern that strongly correlated to survival. Two groups could be identified: one with a median survival after diagnosis of 1099 days and one with 345 days, p = 0.0001.

Conclusions:

By combining PCA and texture analysis, ADC texture characteristics were identified, which seems to hold pretreatment prognostic information, independent of known prognostic factors such as age, stage, and surgical procedure. These findings encourage further studies with a larger patient cohort. (C) 2014 Author(s).

In recent years, texture analysis of medical images has become increasingly popular in studies investigating diagnosis, classification and treatment response assessment of cancerous disease. Despite numerous applications in oncology and medical imaging in general, there is no consensus regarding texture analysis workflow, or reporting of parameter settings crucial for replication of results. The aim of this study was to assess how sensitive Haralick texture features of apparent diffusion coefficient (ADC) MR images are to changes in five parameters related to image acquisition and pre-processing: noise, resolution, how the ADC map is constructed, the choice of quantization method, and the number of gray levels in the quantized image. We found that noise, resolution, choice of quantization method and the number of gray levels in the quantized images had a significant influence on most texture features, and that the effect size varied between different features. Different methods for constructing the ADC maps did not have an impact on any texture feature. Based on our results, we recommend using images with similar resolutions and noise levels, using one quantization method, and the same number of gray levels in all quantized images, to make meaningful comparisons of texture feature results between different subjects.

Tension wood (TW) is a specialized tissue with contractile properties that is formed by the vascular cambium in response to gravitational stimuli. We quantitatively analysed the proteomes of Populus tremula cambium and its xylem cell derivatives in stems forming normal wood (NW) and TW to reveal the mechanisms underlying TW formation. Phloem-, cambium-, and wood-forming tissues were sampled by tangential cryosectioning and pooled into nine independent samples. The proteomes of TW and NW samples were similar in the phloem and cambium samples, but diverged early during xylogenesis, demonstrating that reprogramming is an integral part of TW formation. For example, 14-3-3, reactive oxygen species, ribosomal and ATPase complex proteins were found to be up-regulated at early stages of xylem differentiation during TW formation. At later stages of xylem differentiation, proteins involved in the biosynthesis of cellulose and enzymes involved in the biosynthesis of rhamnogalacturonan-I, rhamnogalacturonan-II, arabinogalactan-II and fasciclin-like arabinogalactan proteins were up-regulated in TW. Surprisingly, two isoforms of exostosin family proteins with putative xylan xylosyl transferase function and several lignin biosynthesis proteins were also up-regulated, even though xylan and lignin are known to be less abundant in TW than in NW. These data provided new insight into the processes behind TW formation.

The technological advances in the instrumentation employed in life sciences have enabled the collection of a virtually unlimited quantity of data from multiple sources. By gathering data from several analytical platforms, with the aim of parallel monitoring of, e.g. transcriptomic, metabolomic or proteomic events, one hopes to answer and understand biological questions and observations. This 'systems biology' approach typically involves advanced statistics to facilitate the interpretation of the data. In the present study, we demonstrate that the O2PLS multivariate regression method can be used for combining 'omics' types of data. With this methodology, systematic variation that overlaps across analytical platforms can be separated from platform-specific systematic variation. A study of Populus tremula x Populus tremuloides, investigating short-day-induced effects at transcript and metabolite levels, is employed to demonstrate the benefits of the methodology. We show how the models can be validated and interpreted to identify biologically relevant events, and discuss the results in relation to a pairwise univariate correlation approach and principal component analysis.

Background

During generation of microarray data, various forms of systematic biases are frequently introduced which limits accuracy and precision of the results. In order to properly estimate biological effects, these biases must be identified and discarded.

Results

We introduce a normalization strategy for multi-channel microarray data based on orthogonal projections to latent structures (OPLS); a multivariate regression method. The effect of applying the normalization methodology on single-channel Affymetrix data as well as dual-channel cDNA data is illustrated. We provide a parallel comparison to a wide range of commonly employed normalization methods with diverse properties and strengths based on sensitivity and specificity from external (spike-in) controls. On the illustrated data sets, the OPLS normalization strategy exhibits leading average true negative and true positive rates in comparison to other evaluated methods.

Conclusions

The OPLS methodology identifies joint variation within biological samples to enable the removal of sources of variation that are non-correlated (orthogonal) to the within-sample variation. This ensures that structured variation related to the underlying biological samples is separated from the remaining, bias-related sources of systematic variation. As a consequence, the methodology does not require any explicit knowledge regarding the presence or characteristics of certain biases. Furthermore, there is no underlying assumption that the majority of elements should be non-differentially expressed, making it applicable to specialized boutique arrays.

Background

cDNA microarray technology has emerged as a major player in the parallel detection of biomolecules, but still suffers from fundamental technical problems. Identifying and removing unreliable data is crucial to prevent the risk of receiving illusive analysis results. Visual assessment of spot quality is still a common procedure, despite the time-consuming work of manually inspecting spots in the range of hundreds of thousands or more.

Results

A novel methodology for cDNA microarray spot quality control is outlined. Multivariate discriminant analysis was used to assess spot quality based on existing and novel descriptors. The presented methodology displays high reproducibility and was found superior in identifying unreliable data compared to other evaluated methodologies.

Conclusion

The proposed methodology for cDNA microarray spot quality control generates non-discrete values of spot quality which can be utilized as weights in subsequent analysis procedures as well as to discard spots of undesired quality using the suggested threshold values. The MASQOT approach provides a consistent assessment of spot quality and can be considered an alternative to the labor-intensive manual quality assessment process.

Tree biotechnology will soon reach a mature state where it will influence the overall supply of fiber, energy and wood products. We are now ready to make the transition from identifying candidate genes, controlling important biological processes, to discovering the detailed molecular function of these genes on a broader, more holistic, systems biology level. In this paper, a strategy is outlined for informative data generation and integrated modeling of systematic changes in transcript, protein and metabolite profiles measured from hybrid aspen samples. The aim is to study characteristics of common changes in relation to genotype-specific perturbations affecting the lignin biosynthesis and growth. We show that a considerable part of the systematic effects in the system can be tracked across all platforms and that the approach has a high potential value in functional characterization of candidate genes.

The characteristics of the OPLS method have been investigated for the purpose of discriminant analysis (OPLS-DA). We demonstrate how class-orthogonal variation can be exploited to augment classification performance in cases where the individual classes exhibit divergence in within-class variation, in analogy with soft independent modelling of class analogy (SIMCA) classification. The prediction results will be largely equivalent to traditional supervised classification using PLS-DA if no such variation is present in the classes. A discriminatory strategy is thus outlined, combining the strengths of PLS-DA and SIMCA classification within the framework of the OPLS-DA method. Furthermore, resampling methods have been employed to generate distributions of predicted classification results and subsequently assess classification belief. This enables utilisation of the class-orthogonal variation in a proper statistical context. The proposed decision rule is compared to common decision rules and is shown to produce comparable or less class-biased classification results.

Background: Kernel-based classification and regression methods have been successfully applied to modelling a wide variety of biological data. The Kernel-based Orthogonal Projections to Latent Structures (K-OPLS) method offers unique properties facilitating separate modelling of predictive variation and structured noise in the feature space. While providing prediction results similar to other kernel-based methods, K-OPLS features enhanced interpretational capabilities; allowing detection of unanticipated systematic variation in the data such as instrumental drift, batch variability or unexpected biological variation.

Results: We demonstrate an implementation of the K-OPLS algorithm for MATLAB and R, licensed under the GNU GPL and available at http://www.sourceforge.net/projects/kopls/. The package includes essential functionality and documentation for model evaluation (using cross-validation), training and prediction of future samples. Incorporated is also a set of diagnostic tools and plot functions to simplify the visualisation of data, e.g. for detecting trends or for identification of outlying samples. The utility of the software package is demonstrated by means of a metabolic profiling data set from a biological study of hybrid aspen.

Conclusion: The properties of the K-OPLS method are well suited for analysis of biological data, which in conjunction with the availability of the outlined open-source package provides a comprehensive solution for kernel-based analysis in bioinformatics applications.

Background: An increased understanding of leaf area development is important in a number of fields: in food and non-food crops, for example short rotation forestry as a biofuels feedstock, leaf area is intricately linked to biomass productivity; in paleontology leaf shape characteristics are used to reconstruct paleoclimate history. Such fields require measurement of large collections of leaves, with resulting conclusions being highly influenced by the accuracy of the phenotypic measurement process.

Results: We have developed LAMINA (Leaf shApe deterMINAtion), a new tool for the automated analysis of images of leaves. LAMINA has been designed to provide classical indicators of leaf shape (blade dimensions) and size (area), which are typically required for correlation analysis to biomass productivity, as well as measures that indicate asymmetry in leaf shape, leaf serration traits, and measures of herbivory damage (missing leaf area). In order to allow Principal Component Analysis (PCA) to be performed, the location of a chosen number of equally spaced boundary coordinates can optionally be returned.

Conclusion: We demonstrate the use of the software on a set of 500 scanned images, each containing multiple leaves, collected from a common garden experiment containing 116 clones of Populus tremula (European trembling aspen) that are being used for association mapping, as well as examples of leaves from other species. We show that the software provides an efficient and accurate means of analysing leaf area in large datasets in an automated or semi-automated work flow.

MASQOT-GUI provides an open-source, platform-independent software pipeline for two-channel microarray spot quality control. This includes gridding, segmentation, quantification, quality assessment and data visualization. It hosts a set of independent applications, with interactions between the tools as well as import and export support for external software. The implementation of automated multivariate quality control assessment, which is a unique feature of MASQOT-GUI, is based on the previously documented and evaluated MASQOT methodology. Further abilities of the application are outlined and illustrated. AVAILABILITY: MASQOT-GUI is Java-based and licensed under the GNU LGPL. Source code and installation files are available for download at http://masqot-gui.sourceforge.net/

Objective The objective of this study was to investigate the association of clinical and renal disease activity with circulating sphingolipids in patients with systemic lupus erythematosus.

Methods We used liquid chromatography tandem mass spectrometry to measure the levels of 27 sphingolipids in plasma from 107 female systemic lupus erythematosus patients and 23 controls selected using a design of experiment approach. We investigated the associations between sphingolipids and two disease activity indices, the Systemic Lupus Activity Measurement and the Systemic Lupus Erythematosus Disease Activity Index. Damage was scored according to the Systemic Lupus International Collaborating Clinics damage index. Renal activity was evaluated with the British Island Lupus Activity Group index. The effects of immunosuppressive treatment on sphingolipid levels were evaluated before and after treatment in 22 female systemic lupus erythematosus patients with active disease.

Results Circulating sphingolipids from the ceramide and hexosylceramide families were increased, and sphingoid bases were decreased, in systemic lupus erythematosus patients compared to controls. The ratio of C-16:0-ceramide to sphingosine-1-phosphate was the best discriminator between patients and controls, with an area under the receiver-operating curve of 0.77. The C-16:0-ceramide to sphingosine-1-phosphate ratio was associated with ongoing disease activity according to the Systemic Lupus Activity Measurement and the Systemic Lupus Erythematosus Disease Activity Index, but not with accumulated damage according to the Systemic Lupus International Collaborating Clinics Damage Index. Levels of C-16:0- and C-24:1-hexosylceramides were able to discriminate patients with current versus inactive/no renal involvement. All dysregulated sphingolipids were normalized after immunosuppressive treatment.

Conclusion We provide evidence that sphingolipids are dysregulated in systemic lupus erythematosus and associated with disease activity. This study demonstrates the utility of simultaneously targeting multiple components of a pathway to establish disease associations.

In general, applications of metabonomics using biofluid NMR spectroscopic analysis for probing abnormal biochemical profiles in disease or due to toxicity have all relied on the use of chemometric techniques for sample classification. However, the well-known variability of some chemical shifts in 1H NMR spectra of biofluids due to environmental differences such as pH variation, when coupled with the large number of variables in such spectra, has led to the situation where it is necessary to reduce the size of the spectra or to attempt to align the shifting peaks, to get more robust and interpretable chemometric models. Here, a new approach that avoids this problem is demonstrated and shows that, moreover, inclusion of variable peak position data can be beneficial and can lead to useful biochemical information. The interpretation of chemometric models using combined back-scaled loading plots and variable weights demonstrates that this peak position variation can be handled successfully and also often provides additional information on the physicochemical variations in metabonomic data sets.

We describe here the implementation of the statistical total correlation spectroscopy (STOCSY) analysis method for aiding the identification of potential biomarker molecules in metabonomic studies based on NMR spectroscopic data. STOCSY takes advantage of the multicollinearity of the intensity variables in a set of spectra (in this case 1H NMR spectra) to generate a pseudo-two-dimensional NMR spectrum that displays the correlation among the intensities of the various peaks across the whole sample. This method is not limited to the usual connectivities that are deducible from more standard two-dimensional NMR spectroscopic methods, such as TOCSY. Moreover, two or more molecules involved in the same pathway can also present high intermolecular correlations because of biological covariance or can even be anticorrelated. This combination of STOCSY with supervised pattern recognition and particularly orthogonal projection on latent structure-discriminant analysis (O-PLS-DA) offers a new powerful framework for analysis of metabonomic data. In a first step O-PLS-DA extracts the part of NMR spectra related to discrimination. This information is then cross-combined with the STOCSY results to help identify the molecules responsible for the metabolic variation. To illustrate the applicability of the method, it has been applied to 1H NMR spectra of urine from a metabonomic study of a model of insulin resistance based on the administration of a carbohydrate diet to three different mice strains (C57BL/6Oxjr, BALB/cOxjr, and 129S6/SvEvOxjr) in which a series of metabolites of biological importance can be conclusively assigned and identified by use of the STOCSY approach.

The zebrafish embryo is a popular model for drug screening, disease modelling and molecular genetics. In this study, samples were obtained from zebrafish at different developmental stages. The stages that were chosen were 3/4, 4/5, 24, 48, 72 and 96 hours post fertilization (hpf). Each sample included fifty embryos. The samples were analysed using gas chromatography time-of-flight mass spectrometry (GC-TOF-MS). Principle component analysis (PCA) was applied to get an overview of the data and orthogonal projection to latent structure discriminant analysis (OPLS-DA) was utilised to discriminate between the developmental stages. In this way, changes in metabolite profiles during vertebrate development could be identified. Using a GC-TOF-MS metabolomics approach it was found that nucleotides and metabolic fuel (glucose) were elevated at early stages of embryogenesis, whereas at later stages amino acids and intermediates in the Krebs cycle were abundant. This agrees with zebrafish developmental biology, as organs such as the liver and pancreas develop at later stages. Thus, metabolomics of zebrafish embryos offers a unique opportunity to investigate large scale changes in metabolic processes during important developmental stages in vertebrate development. In terms of stability of the metabolic profile and viability of the embryos, it was concluded at 72 hpf was a suitable time point for the use of zebrafish as a model system in numerous scientific applications.

We have performed transcript and metabolite profiling of isolated cambial meristem cells of the model tree aspen during the course of their activity–dormancy cycle to better understand the environmental and hormonal regulation of this process in perennial plants. Considerable modulation of cambial transcriptome and metabolome occurs throughout the activity–dormancy cycle. However, in addition to transcription, post-transcriptional control is also an important regulatory mechanism as exemplified by the regulation of cell-cycle genes during the reactivation of cambial cell division in the spring. Genes related to cold hardiness display temporally distinct induction patterns in the autumn which could explain the step-wise development of cold hardiness. Factors other than low temperature regulate the induction of early cold hardiness-related genes whereas abscisic acid (ABA) could potentially regulate the induction of late cold hardiness-related genes in the autumn. Starch breakdown in the autumn appears to be regulated by the ‘short day’ signal and plays a key role in providing substrates for the production of energy, fatty acids and cryoprotectants. Catabolism of sucrose and fats provides energy during the early stages of reactivation in the spring, whereas the reducing equivalents are generated through activation of the pentose phosphate shunt. Modulation of gibberellin (GA) signaling and biosynthesis could play a key role in the regulation of cambial activity during the activity–dormancy cycle as suggested by the induction of PttRGA which encodes a negative regulator of growth in the autumn and that of a GA-20 oxidase, a key gibberellin biosynthesis gene during reactivation in spring. In summary, our data reveal the dynamics of transcriptional and metabolic networks and identify potential targets of environmental and hormonal signals in the regulation of the activity–dormancy cycle in cambial meristem.

Two new orthogonal projections to latent structures (OPLS) based methods were proposed to analyze hyperspectral images, enabling the visualization ofmultiple chemical compounds in onematrix without the need of extensive preprocessing. Both proposed methods delivered images representing the chemical distribution in the ribbon similar to the more traditional multivariate curve resolution–alternating least squares (MCR-ALS) method, but their image background was less dynamic resulting in a stronger chemical contrast. This indicated that the methods successfully removed structured variation orthogonal to the chemical information (pure spectra of individual compounds), which was confirmed by the fact that physical scattering effects caused by grooves and edges were captured in the images visualizing the orthogonal components of the model. Hereby, the OPLS-based method employing the pure spectra as weights in the OPLS algorithm was more successful in distinguishing compounds with a similar spectral signal than the transposed OPLS algorithm(pure spectra of individual compounds were used as response in OPLS model). It should be noted that for the main compounds, the MCR-ALS method enabled easier visual interpretation compared to the OPLS-based methods by setting all values below zero to zero, resulting in a higher contrast between pixels containing the studied compound and pixels not containing that compound.

Roll compaction is gaining importance in pharmaceutical industry for the dry granulation of heat or moisture sensitive powder blends with poor flowing properties prior to tabletting. We studied the influence of microcrystalline cellulose (MCC) properties on the roll compaction process and the consecutive steps in tablet manufacturing. Four dissimilar MCC grades, selected by subjecting their physical characteristics to principal components analysis, and three speed ratios, i.e. the ratio of the feed screw speed and the roll speed of the roll compactor, were included in a full factorial design. Orthogonal projection to latent structures was then used to model the properties of the resulting roll compacted products (ribbons, granules and tablets) as a function of the physical MCC properties and the speed ratio. This modified version of partial least squares regression separates variation in the design correlated to the considered response from the variation orthogonal to that response. The contributions of the MCC properties and the speed ratio to the predictive and orthogonal components of the models were used to evaluate the effect of the design variation. The models indicated that several MCC properties, e.g. bulk density and compressibility, affected all granule and tablet properties, but only one studied ribbon property: porosity. After roll compaction, Ceolus KG 1000 resulted in tablets with obvious higher tensile strength and lower disintegration time compared to the other MCC grades. This study confirmed that the particle size increase caused by roll compaction is highly responsible for the tensile strength decrease of the tablets.

Light microscopy combined with well-established protocols of two-dimensional cell culture facilitates high-throughput quantitative imaging to study biological phenomena. Accurate segmentation of individual cells in images enables exploration of complex biological questions, but can require sophisticated imaging processing pipelines in cases of low contrast and high object density. Deep learning-based methods are considered state-of-the-art for image segmentation but typically require vast amounts of annotated data, for which there is no suitable resource available in the field of label-free cellular imaging. Here, we present LIVECell, a large, high-quality, manually annotated and expert-validated dataset of phase-contrast images, consisting of over 1.6 million cells from a diverse set of cell morphologies and culture densities. To further demonstrate its use, we train convolutional neural network-based models using LIVECell and evaluate model segmentation accuracy with a proposed a suite of benchmarks.

A strategy for optimizing LC-MS metabolomics data processing is proposed. We applied this strategy on the XCMS open source package written in R on both human and plant biology data. The strategy is a sequential design of experiments (DoE) based on a dilution series from a pooled sample and a measure of correlation between diluted concentrations and integrated peak areas. The reliability index metric, used to define peak quality, simultaneously favors reliable peaks and disfavors unreliable peaks using a weighted ratio between peaks with high and low response linearity. DoE optimization resulted in the case studies in more than 57% improvement in the reliability index compared to the use of the default settings. The proposed strategy can be applied to any other data processing software involving parameters to be tuned, e.g., MZmine 2. It can also be fully automated and used as a module in a complete metabolomics data processing pipeline.

In metabolomics studies there is a clear increase of data. This indicates the necessity of both having a battery of suitable analysis methods and validation procedures able to handle large amounts of data. In this review, an overview of the metabolomics data processing pipeline is presented. A selection of recently developed and most cited data processing methods is discussed. In addition, commonly used chemometric and machine learning analysis methods as well as validation approaches are described.

A personal view is given about the gradual development of projection methods-also called bilinear, latent variable, and more-and their use in chemometrics. We start with the principal components analysis (PCA) being the basis for more elaborate methods for more complex problems such as soft independent modeling of class analogy, partial least squares (PLS), hierarchical PCA and PLS, PLS-discriminant analysis, Orthogonal projection to latent structures (OPLS), OPLS-discriminant analysis and more. From its start around 1970, this development was strongly influenced by Bruce Kowalski and his group in Seattle, and his realization that the multidimensional data profiles emerging from spectrometers, chromatographs, and other electronic instruments, contained interesting information that was not recognized by the current one variable at a time approaches to chemical data analysis. This led to the adoption of what in statistics is called the data analytical approach, often called also the data driven approach, soft modeling, and more. This approach combined with PCA and later PLS, turned out to work very well in the analysis of chemical data. This because of the close correspondence between, on the one hand, the matrix decomposition at the heart of PCA and PLS and, on the other hand, the analogy concept on which so much of chemical theory and experimentation are based. This extends to numerical and conceptual stability and good approximation properties of these models. The development is informally summarized and described and illustrated by a few examples and anecdotes.

This article describes the applicability of multivariate projection techniques, such as principal-component analysis (PCA) and partial least-squares (PLS) projections to latent structures, to the large-volume high-density data structures obtained within genomics, proteomics, and metabonomics. PCA and PLS, and their extensions, derive their usefulness from their ability to analyze data with many, noisy, collinear, and even incomplete variables in both X and Y. Three examples are used as illustrations: the first example is a genomics data set and involves modeling of microarray data of cell cycle-regulated genes in the microorganism Saccharomyces cerevisiae. The second example contains NMR-metabonomics data, measured on urine samples of male rats treated with either of the drugs chloroquine or amiodarone. The third and last data set describes sequence-function classification studies in a set of G-protein-coupled receptors using hierarchical PCA.

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.

This second volume has two parts, the first with specialized applications of multi- and mega-variate analysis, namely:

QSAR (quantitative structure-activity relationships) describes how series of molecular structures can be translated to quantitative data and how these data then are used to model and predict biological activity measurements made on the corresponding molecules. Chapters on how the QSAR concept applies in peptide QSAR, lead finding and optimization, combinatorial chemistry, and chem-and bio-informatics, are included.

The multi- and megavariate analysis of “omics” data, has a special chapter, i.e., data from metabonomics, proteomics, genomics and other areas.

Then follow six chapters on extensions of the basic projection methods (PCA and PLS):

Orthogonal PLS (OPLS) showing how a PLS model can be “rotated” so that all y-related information appears in the first component, which facilitates the model interpretation.

Hierarchical modeling, both PC and PLS, allowing variables of different types to be handled in separate blocks, which greatly simplifies the handling of datasets with very many variables.

Non-linear PLS describes various approaches to the modeling of non-linear relationships between predictors X and responses Y.

The Image Analysis chapter shows how multivariate analysis applies to the analysis of series of digital images.

Data Mining and Integration has a discussion of how to get useful information out of large and complicated data sets, and how to manage and organize data in complex investigations.

The second volume ends with a chapter on preference and sensory data, followed by an appendix summarizing the multivariate approach, statistical notes, and references.

Design of experiments (DOE) and multivariate data analysis (MVDA) are two strong links in a chain of chemometrics and data analytics. DOE and MVDA can be applied well in aquatic toxicology and can be used independently of one another, but when used in conjunction they equip the researcher with high quality data and model results with a faithful interpretation. Two example aquatic toxicity datasets are used to describe the benefits of DOE and MVDA in aquatic toxicology. The popular data analytical tools principal components analysis (PCA) and partial least squares (PLS) are outlined in detail and exemplified. A modification of PLS called orthogonal partial least squares (OPLS) is introduced and it is shown how it can simplify model interpretation. When using chemometrics to establish quantitative structure-activity relationships (QSAR), a central questions is that of whether to derive a single-response QSAR model involving a single Y-variable, or a multi-response QSAR covering multiple responses. It is demonstrated how an initial PCA model on a matrix of response data can be used to figure out when a multi-response QSAR model might be a viable alternative to several single-response QSAR models.

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.

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.

In this paper, multivariate calibration of complicated process fluorescence data is presented. Two data sets related to the production of white sugar are investigated. The first data set comprises 106 observations and 571 spectral variables, and the second data set 268 observations and 3997 spectral variables. In both applications, a single response, ash content, is modelled and predicted as a function of the spectral variables. Both data sets contain certain features making multivariate calibration efforts non-trivial. The objective is to show how principal component analysis (PCA) and partial least squares (PLS) regression can be used to overview the data sets and to establish predictively sound regression models. It is shown how a recently developed technique for signal filtering, orthogonal signal correction (OSC), can be applied in multivariate calibration to enhance predictive power. In addition, signal compression is tested on the larger data set using wavelet analysis. It is demonstrated that a compression down to 4% of the original matrix size - in the variable direction - is possible without loss of predictive power. It is concluded that the combination of OSC for pre-processing and wavelet analysis for compression of spectral data is promising for future use.

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.

A hierarchical clustering approach based on a set of PLS models is presented. Called PLS-Trees (R), 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 (t(1)) 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 hyperspectral images of liver tissue for identifying different sources of variability in the liver samples.

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.

Peptidoglycan is a fundamental structure for most bacteria. It contributes to the cell morphology and provides cell wall integrity against environmental insults. While several studies have reported a significant degree of variability in the chemical composition and organization of peptidoglycan in the domain Bacteria, the real diversity of this polymer is far from fully explored. This work exploits rapid ultraperformance liquid chromatography and multivariate data analysis to uncover peptidoglycan chemical diversity in the Class Alphaproteobacteria, a group of Gram negative bacteria that are highly heterogeneous in terms of metabolism, morphology and life-styles. Indeed, chemometric analyses revealed novel peptidoglycan structures conserved in Acetobacteria: amidation at the alpha-(L)-carboxyl of meso-diaminopimelic acid and the presence of muropeptides cross-linked by (1-3) L-Ala-D-(meso)diaminopimelate cross-links. Both structures are growth-controlled modifications that influence sensitivity to Type VI secretion system peptidoglycan endopeptidases and recognition by the Drosophila innate immune system, suggesting relevant roles in the environmental adaptability of these bacteria. Collectively our findings demonstrate the discriminative power of chemometric tools on large cell wall-chromatographic data sets to discover novel peptidoglycan structural properties in bacteria.



Pre-processing plays a vital role in cDNA-microarray data analysis. Without proper pre-processing it is likely that the biological conclusions will be misleading. However, there are many alternatives and in order to choose a proper pre-processing procedure it is necessary to understand the effect of different methods. This chapter discusses several pre-processing steps, including image analysis, background correction, normalization, and filtering. Spike-in data are used to illustrate how different procedures affect the analytical ability to detect differentially expressed genes and estimate their regulation. The result shows that pre-processing has a major impact on both the experiment’s sensitivity andits bias. However, general recommendations are hard to give, since pre-processing consists of several actions that are highly dependent on each other. Furthermore, it is likely that pre-processing have a major impact on downstream analysis, such as clustering and classification, and pre-processing methods should be developed and evaluated with this in mind.

Cell Painting is an established community-based microscopy-assay platform that provides high-throughput, high-content data for biological readouts. In November 2022, the JUMP-Cell Painting Consortium released the largest publicly available Cell Painting dataset with CellProfiler features, comprising more than 2 billion cell images. This dataset is designed for predicting the activity and toxicity of 115k drug compounds, with the aim to make cell images as computable as genomes and transcriptomes. In this context, our paper introduces a scalable and computationally efficient data analytics workflow created to meet the needs of researchers. This data-driven workflow facilitates the comparison of drug treatment effects through significant and biologically relevant insights. The workflow consists of two parts: first, the Equivalence score (Eq. score), a straightforward yet sophisticated metric highlighting relevant deviations from negative controls based on cell image morphology; second, the scalability of the workflow, by utilizing the Eq. scores on a large scale to predict and classify the subtle morphological changes in cell image profiles. By doing so, we show classification improvements compared to using the raw CellProfiler features on the CPJUMP1-pilot dataset on three types of perturbations. We hope that our workflow's contributions will enhance drug screening efficiency and streamline the drug development process. As this process is resource-intensive, every incremental improvement is valuable. Through our collective efforts in advancing the understanding of high-throughput image-based data, we aim to reduce both the time and cost of developing new, life-saving treatments.