29 November 2017 in Nucleic Acids Research
MicroRNAs are important regulators of gene expression, achieved by binding to the gene to be regulated. Even with modern high-throughput technologies, it is laborious and expensive to detect all possible microRNA targets. For this reason, several computational microRNA–target prediction tools have been developed, each with its own strengths and limitations. Integration of different tools has been a successful approach to minimize the shortcomings of individual databases. Here, we present mirDIP v4.1, providing nearly 152 million human microRNA–target predictions, which were collected across 30 different resources. We also introduce an integrative score, which was statistically inferred from the obtained predictions, and was assigned to each unique microRNA–target interaction to provide a unified measure of confidence. We demonstrate that integrating predictions across multiple resources does not cumulate prediction bias toward biological processes or pathways. mirDIP v4.1 is freely available at http://ophid.utoronto.ca/mirDIP/.
8 April 2014 in Journal of Breath Research
We define breathomics as the metabolomics study of exhaled air. It is a strongly emerging metabolomics research field that mainly focuses on health-related volatile organic compounds (VOCs). Since the amount of these compounds varies with health status, breathomics holds great promise to deliver non-invasive diagnostic tools. Thus, the main aim of breathomics is to find patterns of VOCs related to abnormal (for instance inflammatory) metabolic processes occurring in the human body. Recently, analytical methods for measuring VOCs in exhaled air with high resolution and high throughput have been extensively developed. Yet, the application of machine learning methods for fingerprinting VOC profiles in the breathomics is still in its infancy. Therefore, in this paper, we describe the current state of the art in data pre-processing and multivariate analysis of breathomics data. We start with the detailed pre-processing pipelines for breathomics data obtained from gas-chromatography mass spectrometry and an ion-mobility spectrometer coupled to multi-capillary columns. The outcome of data pre-processing is a matrix containing the relative abundances of a set of VOCs for a group of patients under different conditions (e.g. disease stage, treatment). Independently of the utilized analytical method, the most important question, 'which VOCs are discriminatory?', remains the same. Answers can be given by several modern machine learning techniques (multivariate statistics) and, therefore, are the focus of this paper. We demonstrate the advantages as well the drawbacks of such techniques. We aim to help the community to understand how to profit from a particular method. In parallel, we hope to make the community aware of the existing data fusion methods, as yet unresearched in breathomics.
9 February 2022 in Bioinformatics
Limited data access has hindered the field of precision medicine from exploring its full potential, e.g. concerning machine learning and privacy and data protection rules. Our study evaluates the efficacy of federated Random Forests (FRF) models, focusing particularly on the heterogeneity within and between datasets. We addressed three common challenges: (i) number of parties, (ii) sizes of datasets and (iii) imbalanced phenotypes, evaluated on five biomedical datasets. The FRF outperformed the average local models and performed comparably to the data-centralized models trained on the entire data. With an increasing number of models and decreasing dataset size, the performance of local models decreases drastically. The FRF, however, do not decrease significantly. When combining datasets of different sizes, the FRF vastly improve compared to the average local models. We demonstrate that the FRF remain more robust and outperform the local models by analyzing different class-imbalances. Our results support that FRF overcome boundaries of clinical research and enables collaborations across institutes without violating privacy or legal regulations. Clinicians benefit from a vast collection of unbiased data aggregated from different geographic locations, demographics and other varying factors. They can build more generalizable models to make better clinical decisions, which will have relevance, especially for patients in rural areas and rare or geographically uncommon diseases, enabling personalized treatment. In combination with secure multi-party computation, federated learning has the power to revolutionize clinical practice by increasing the accuracy and robustness of healthcare AI and thus paving the way for precision medicine. The implementation of the federated random forests can be found at https://featurecloud.ai/. Supplementary data are available at Bioinformatics online.
1 April 2018 in Journal of Psychiatric Research
MMMalgorzata Maciukiewicz
+3
30 January 2024 in Journal of Biomedical Informatics
Lack of trust in artificial intelligence (AI) models in medicine is still the key blockage for the use of AI in clinical decision support systems (CDSS). Although AI models are already performing excellently in systems medicine, their black-box nature entails that patient-specific decisions are incomprehensible for the physician. Explainable AI (XAI) algorithms aim to "explain" to a human domain expert, which input features influenced a specific recommendation. However, in the clinical domain, these explanations must lead to some degree of causal understanding by a clinician. We developed the CLARUS platform, aiming to promote human understanding of graph neural network (GNN) predictions. CLARUS enables the visualisation of patient-specific networks, as well as, relevance values for genes and interactions, computed by XAI methods, such as GNNExplainer. This enables domain experts to gain deeper insights into the network and more importantly, the expert can interactively alter the patient-specific network based on the acquired understanding and initiate re-prediction or retraining. This interactivity allows us to ask manual counterfactual questions and analyse the effects on the GNN prediction. We present the first interactive XAI platform prototype, CLARUS, that allows not only the evaluation of specific human counterfactual questions based on user-defined alterations of patient networks and a re-prediction of the clinical outcome but also a retraining of the entire GNN after changing the underlying graph structures. The platform is currently hosted by the GWDG on https://rshiny.gwdg.de/apps/clarus/.
1 May 2023 in IEEE Journal of Biomedical and Health Informatics
Despite their remarkable performance, deep neural networks remain unadopted in clinical practice, which is considered to be partially due to their lack of explainability. In this work, we apply explainable attribution methods to a pre-trained deep neural network for abnormality classification in 12-lead electrocardiography to open this “black box” and understand the relationship between model prediction and learned features. We classify data from two public databases (CPSC 2018, PTB-XL) and the attribution methods assign a “relevance score” to each sample of the classified signals. This allows analyzing what the network learned during training, for which we propose quantitative methods: average relevance scores over a) classes, b) leads, and c) average beats. The analyses of relevance scores for atrial fibrillation and left bundle branch block compared to healthy controls show that their mean values a) increase with higher classification probability and correspond to false classifications when around zero, and b) correspond to clinical recommendations regarding which lead to consider. Furthermore, c) visible P-waves and concordant T-waves result in clearly negative relevance scores in atrial fibrillation and left bundle branch block classification, respectively. Results are similar across both databases despite differences in study population and hardware. In summary, our analysis suggests that the DNN learned features similar to cardiology textbook knowledge.