| 1. |
- Herman, Stephanie
(författare)
-
Towards an Earlier Detection of Progressive Multiple Sclerosis using Metabolomics and Machine Learning
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Decision-making guided by advanced analytics is becoming increasingly common in many fields. Implementing computationally driven healthcare solutions does, however, pose ethical dilemmas as it involves human health. Therefore, augmenting clinical expertise with advanced analytical insights to support decision-making in healthcare is probably a more feasible strategy.Multiple sclerosis is a debilitating neurological disease with two subtypes; relapsing-remitting multiple sclerosis (RRMS) and the typically late-stage progressive subtype (PMS). Progressive multiple sclerosis is a neurodegenerative phenotype, with a vague functional definition, that currently is diagnosed retrospectively. The challenge of diagnosing PMS earlier is a great example where data-driven insights might prove useful.This thesis addresses the need for an earlier detection of patients developing the progressive and neurodegenerative subtype of multiple sclerosis, using primarily metabolomics and machine learning approaches. In Paper I, the biochemical differences in cerebrospinal fluid (CSF) from RRMS and PMS patients were characterised, leading to the conclusion that it is possible to distinguish PMS patients based on biochemical alterations. In addition, pathway analysis revealed several metabolic pathways that were affected in the transition to PMS, including tryptophan metabolism and pyrimidine metabolism. In Paper II and III, the possibility of generating a concise PMS signature based on solely low-molecular measurements (III) or in combination with radiological and protein measures (II) was explored. In both cases, it was concluded that it is plausible to generate a condensed set of highly informative markers that can distinguish PMS patients from RRMS patients. In Paper III, the classifier was complemented with conformal prediction that enabled an estimate of confidence in single patient predictions and a personalised evaluation of current disease state. Finally, in Paper IV, the extracted low-molecular marker candidates were characterised in isolation, revealing that several metabolites were distinctively altered in the CSF of PMS patients, including increased levels of 4-acetamidobutanoate, 4-hydroxybenzoate and thymine.Overall, the results from this work indicate that it is possible to detect PMS at an earlier stage and that advanced analytical algorithms can support healthcare.
|
|
| 2. |
- Capuccini, Marco
(författare)
-
Enabling Scalable Data Analysis on Cloud Resources with Applications in Life Science
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Over the past 20 years, the rise of high-throughput methods in life science has enabled research laboratories to produce massive datasets of biological interest. When dealing with this "data deluge" of modern biology researchers encounter two major challenges: first, there is a need for substantial technical skills for dealing with Big Data and; second, infrastructure procurement becomes difficult. In connection to this second challenge, the computing model and business trend that was originally popularized by Amazon under the name of cloud computing represents an interesting opportunity. Instead of buying computing infrastructure upfront, cloud providers enable the allocation and release of virtual resources on-demand. These resources are then billed with a pay-per-use pricing model and physical infrastructure management is delegated to the provider. In this thesis, we introduce a number of methods for running Big Data analyses of biological interest using cloud computing. Considerable efforts were made in enabling the application of trusted, bioinformatics software to Big Data scenarios as opposed to reimplementing the existing codebase. Further, we improve the accessibility of the technology with the aim of reducing the entry barrier for biologists. The thesis includes 5 papers. In Papers I and II, we explore the applicability of Apache Spark, one of the leading Big Data analytics platforms in cloud environments, to two drug-discovery use cases. In Paper III, we present a general method for running bioinformatics analyses on the cloud using the microservices-oriented architecture. In Paper IV, we introduce a method that combines microservices and Apache Spark with the aim of providing the best of both technologies. In Paper V, we discuss how to reduce the entry barrier for the allocation of cloud research environments. We show that all of the developed methods scale well and we provide high-level programming interfaces for improving accessibility. We have also made the developed software publicly available.
|
|
| 3. |
- Harrison, Philip John, 1977-
(författare)
-
Deep learning approaches for image cytometry: assessing cellular morphological responses to drug perturbations
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Image cytometry is the analysis of cell properties from microscopy image data and is used ubiquitously in basic cell biology, medical diagnosis and drug development. In recent years deep learning has shown impressive results for many image cytometry tasks, including image processing, segmentation, classification and detection. Deep learning enables a more data-driven and end-to-end approach than was previously possible with conventional methods. This thesis investigates deep learning-based approaches for assessing cellular morphological responses to drug perturbations. In paper I we demonstrated the benefit of combining convolutional neural networks and transfer learning for predicting mechanism of action and nucleus translocation. In paper II we showed, using convolutional and recurrent neural networks applied to time-lapse microscopy data, that it is possible to predict if mRNA delivery via nanoparticles has been effective based on cell morphology changes at time points prior to the protein production evidence of successful delivery. In paper III we used convolutional neural networks, adversarial training and privileged information to faithfully generate fluorescence imaging channels of adipocyte cells from their corresponding z-stack of brightfield images. Our models were both faithful at the fluorescence image level and at the level of the features extracted from these images, features that are commonly used for downstream analysis, including the design of effective drug therapies. In paper IV we showed that convolutional neural networks trained on brightfield image data provide similar, and in some cases superior, performance to models trained on fluorescence image data for predicting mechanism of action, due to the brightfield images possessing additional information not available in the fluorescence images. In paper V we applied deep learning models to brightfield time-lapse image data to explore the evolution of cellular morphological changes after drug administration for a diverse set of compounds, compounds that are often used as positive controls in image-based assays.
|
|
| 4. |
- Ahmed, Laeeq, et al.
(författare)
-
Predicting target profiles with confidence as a service using docking scores
- 2020
-
Ingår i: Journal of Cheminformatics. - : Springer Nature. - 1758-2946. ; 12:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Identifying and assessing ligand-target binding is a core component in early drug discovery as one or more unwanted interactions may be associated with safety issues. Contributions: We present an open-source, extendable web service for predicting target profiles with confidence using machine learning for a panel of 7 targets, where models are trained on molecular docking scores from a large virtual library. The method uses conformal prediction to produce valid measures of prediction efficiency for a particular confidence level. The service also offers the possibility to dock chemical structures to the panel of targets with QuickVina on individual compound basis. Results: The docking procedure and resulting models were validated by docking well-known inhibitors for each of the 7 targets using QuickVina. The model predictions showed comparable performance to molecular docking scores against an external validation set. The implementation as publicly available microservices on Kubernetes ensures resilience, scalability, and extensibility.
|
|
| 5. |
- Capuccini, Marco, et al.
(författare)
-
MaRe : Processing Big Data with application containers on Apache Spark
- 2020
-
Ingår i: GigaScience. - : Oxford University Press. - 2047-217X. ; 9:5
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Life science is increasingly driven by Big Data analytics, and the MapReduce programming model has been proven successful for data-intensive analyses. However, current MapReduce frameworks offer poor support for reusing existing processing tools in bioinformatics pipelines. Furthermore, these frameworks do not have native support for application containers, which are becoming popular in scientific data processing. Results: Here we present MaRe, an open source programming library that introduces support for Docker containers in Apache Spark. Apache Spark and Docker are the MapReduce framework and container engine that have collected the largest open source community; thus, MaRe provides interoperability with the cutting-edge software ecosystem. We demonstrate MaRe on 2 data-intensive applications in life science, showing ease of use and scalability. Conclusions: MaRe enables scalable data-intensive processing in life science with Apache Spark and application containers. When compared with current best practices, which involve the use of workflow systems, MaRe has the advantage of providing data locality, ingestion from heterogeneous storage systems, and interactive processing. MaRe is generally applicable and available as open source software.
|
|
| 6. |
|
|
| 7. |
- Gauraha, Niharika, et al.
(författare)
-
Robust Knowledge Transfer in Learning Under Privileged Information Framework
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Learning Under Privileged Information (LUPI) enables the inclusion of additional (privileged) information when training machine learning models; data that is not available when making predictions. The methodology has been successfully applied to a diverse set of problems from various fields. SVM+ was the first realization of the LUPI paradigm which showed fast convergence but did not scale well. To address the scalability issue, knowledge transfer approaches were proposed to estimate privileged information from standard features in order to construct improved decision rules.Most available knowledge transfer methods use regression techniques and the same data for approximating the privileged features as for learning the transfer function.Inspired by the cross-validation approach, we propose to partition the training data into K folds and use each fold for learning a transfer function and the remaining folds for approximations of privileged features - we refer to this a robust knowledge transfer. We conduct empirical evaluation considering four different experimental setups using one synthetic and three real datasets. These experiments demonstrate that our approach yields improved accuracy as compared to LUPI with standard knowledge transfer.
|
|
| 8. |
- Gauraha, Niharika, et al.
(författare)
-
Split knowledge transfer in learning under privileged information framework
- 2019
-
Ingår i: Proceedings of the Eighth Symposium on Conformal and Probabilistic Prediction and Applications. - : PMLR. ; , s. 43-52
-
Konferensbidrag (refereegranskat)abstract
- Learning Under Privileged Information (LUPI) enables the inclusion of additional (privileged) information when training machine learning models, data that is not available when making predictions. The methodology has been successfully applied to a diverse set of problems from various fields. SVM+ was the first realization of the LUPI paradigm which showed fast convergence but did not scale well. To address the scalability issue, knowledge transfer approaches were proposed to estimate privileged information from standard features in order to construct improved decision rules. Most available knowledge transfer methods use regression techniques and the same data for approximating the privileged features as for learning the transfer function. Inspired by the cross-validation approach, we propose to partition the training data into $K$ folds and use each fold for learning a transfer function and the remaining folds for approximations of privileged features—we refer to this as split knowledge transfer. We evaluate the method using four different experimental setups comprising one synthetic and three real datasets. The results indicate that our approach leads to improved accuracy as compared to LUPI with standard knowledge transfer.
|
|
| 9. |
- Gauraha, Niharika, et al.
(författare)
-
Synergy Conformal Prediction
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Conformal Prediction is a machine learning methodology that produces valid prediction regions under mild conditions. Ensembles of conformal predictors have been proposed to improve the informational efficiency of inductive conformal predictors by combining p-values, however, the validity of such methods has been an open problem. We introduce Synergy Conformal Prediction which is an ensemble method that combines monotonic conformity scores, and is capable of producing valid prediction intervals. We study the applicability in two scenarios; where data is partitioned in order to reduce the total model training time, and where an ensemble of different machine learning methods is used to improve the overall efficiency of predictions. We evaluate the method on 10 data sets and show that the synergy conformal predictor produces valid predictions and improves informational efficiency as compared to inductive conformal prediction and existing ensemble methods. The results indicate that synergy conformal prediction has advantageous properties compared to contemporary approaches, and we also envision that it will have an impact in Big Data and federated environments.
|
|
| 10. |
- Gauraha, Niharika, et al.
(författare)
-
Synergy Conformal Prediction for Regression
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Large and distributed data sets pose many challenges for machine learning, including requirements on computational resources and training time. One approach is to train multiple models in parallel on subsets of data and aggregate the resulting predictions. Large data sets can then be partitioned into smaller chunks, and for distributed data the need for pooling can be avoided. Combining results from conformal predictors using synergy rules has been shown to have advantageous properties for classification problems. In this paper we extend the methodology to regression problems, and we show that it produces valid and efficient predictors compared to inductive conformal predictors and cross-conformal predictors for 10 different data sets from the UCI machine learning repository using three different machine learning methods. The approach offers a straightforward and compelling alternative to pooling data, such as when working in distributed environments.
|
|
