Here, we introduce the ChemicalToolbox, a publicly available web server for performing cheminformatics analysis. The ChemicalToolbox provides an intuitive, graphical interface for common tools for downloading, filtering, visualizing and simulating small molecules and proteins. The ChemicalToolbox is based on Galaxy, an open-source web-based platform which enables accessible and reproducible data analysis. There is already an active Galaxy cheminformatics community using and developing tools. Based on their work, we provide four example workflows which illustrate the capabilities of the ChemicalToolbox, covering assembly of a compound library, hole filling, protein-ligand docking, and construction of a quantitative structure-activity relationship (QSAR) model. These workflows may be modified and combined flexibly, together with the many other tools available, to fit the needs of a particular project. The ChemicalToolbox is hosted on the European Galaxy server and may be accessed viahttps://cheminformatics.usegalaxy.eu.
Background: Galaxy is a web-based and open-source scientific data-processing platform. Researchers compose pipelines in Galaxy to analyse scientific data. These pipelines, also known as workflows, can be complex and difficult to create from thousands of tools, especially for researchers new to Galaxy. To help researchers with creating workflows, a system is developed to recommend tools that can facilitate further data analysis. Findings: A model is developed to recommend tools using a deep learning approach by analysing workflows composed by researchers on the European Galaxy server. The higher-order dependencies in workflows, represented as directed acyclic graphs, are learned by training a gated recurrent units neural network, a variant of a recurrent neural network. In the neural network training, the weights of tools used are derived from their usage frequencies over time and the sequences of tools are uniformly sampled from training data. Hyperparameters of the neural network are optimized using Bayesian optimization. Mean accuracy of 98% in recommending tools is achieved for the top-1 metric. Conclusions: The model is accessed by a Galaxy API to provide researchers with recommended tools in an interactive manner using multiple user interface integrations on the European Galaxy server. High-quality and highly used tools are shown at the top of the recommendations. The scripts and data to create the recommendation system are available under MIT license at https://github.com/anuprulez/galaxy_tool_recommendation.
Supervised machine learning is an essential but difficult to use approach in biomedical data analysis. The Galaxy-ML toolkit (https://galaxyproject.org/community/machine-learning/) makes supervised machine learning more accessible to biomedical scientists by enabling them to perform end-to-end reproducible machine learning analyses at large scale using only a web browser. Galaxy-ML extends Galaxy (https://galaxyproject.org), a biomedical computational workbench used by tens of thousands of scientists across the world, with a suite of tools for all aspects of supervised machine learning.
Background: With the advances in next-generation sequencing technologies, it is possible to determine RNA-RNA interaction and RNA structure predictions on a genome-wide level. The reads from these experiments usually are chimeric, with each arm generated from one of the interaction partners. Owing to short read lengths, often these sequenced arms ambiguously map to multiple locations. Thus, inferring the origin of these can be quite complicated. Here we present ChiRA, a generic framework for sensitive annotation of these chimeric reads, which in turn can be used to predict the sequenced hybrids. Results: Grouping reference loci on the basis of aligned common reads and quantification improved the handling of the multi-mapped reads in contrast to common strategies such as the selection of the longest hit or a random choice among all hits. On benchmark data ChiRA improved the number of correct alignments to the reference up to 3-fold. It is shown that the genes that belong to the common read loci share the same protein families or similar pathways. In published data, ChiRA could detect 3 times more new interactions compared to existing approaches. In addition, ChiRAViz can be used to visualize and filter large chimeric datasets intuitively. Conclusion: ChiRA tool suite provides a complete analysis and visualization framework along with ready-to-use Galaxy workflows and tutorials for RNA-RNA interactome and structurome datasets. Common read loci built by ChiRA can rescue multi-mapped reads on paralogous genes without requiring any information on gene relations. We showed that ChiRA is sensitive in detecting new RNA-RNA interactions from published RNA-RNA interactome datasets.
Background: Galaxy is a web-based open-source platform for scientific analyses. Researchers use thousands of high-quality tools and workflows for their respective analyses in Galaxy. Tool recommender system predicts a collection of tools that can be used to extend an analysis. In this work, a tool recommender system is developed by training a transformer on workflows available on Galaxy Europe and its performance is compared to other neural networks such as recurrent, convolutional and dense neural networks. Results: The transformer neural network achieves two times faster convergence, has significantly lower model usage (model reconstruction and prediction) time and shows a better generalisation that goes beyond training workflows than the older tool recommender system created using RNN in Galaxy. In addition, the transformer also outperforms CNN and DNN on several key indicators. It achieves a faster convergence time, lower model usage time, and higher quality tool recommendations than CNN. Compared to DNN, it converges faster to a higher precision@k metric (approximately 0.98 by transformer compared to approximately 0.9 by DNN) and shows higher quality tool recommendations. Conclusion: Our work shows a novel usage of transformers to recommend tools for extending scientific workflows. A more robust tool recommendation model, created using a transformer, having significantly lower usage time than RNN and CNN, higher precision@k than DNN, and higher quality tool recommendations than all three neural networks, will benefit researchers in creating scientifically significant workflows and exploratory data analysis in Galaxy. Additionally, the ability to train faster than all three neural networks imparts more scalability for training on larger datasets consisting of millions of tool sequences. Open-source scripts to create the recommendation model are available under MIT licence at https://github.com/anuprulez/galaxy_tool_recommendation_transformers
Background: Artificial intelligence (AI) programs that train on large datasets require powerful compute infrastructure consisting of several CPU cores and GPUs. JupyterLab provides an excellent framework for developing AI programs, but it needs to be hosted on such an infrastructure to enable faster training of AI programs using parallel computing. Findings: An open-source, docker-based, and GPU-enabled JupyterLab infrastructure is developed that runs on the public compute infrastructure of Galaxy Europe consisting of thousands of CPU cores, many GPUs, and several petabytes of storage to rapidly prototype and develop end-to-end AI projects. Using a JupyterLab notebook, long-running AI model training programs can also be executed remotely to create trained models, represented in open neural network exchange (ONNX) format, and other output datasets in Galaxy. Other features include Git integration for version control, the option of creating and executing pipelines of notebooks, and multiple dashboards and packages for monitoring compute resources and visualization, respectively. Conclusions: These features make JupyterLab in Galaxy Europe highly suitable for creating and managing AI projects. A recent scientific publication that predicts infected regions in COVID-19 computed tomography scan images is reproduced using various features of JupyterLab on Galaxy Europe. In addition, ColabFold, a faster implementation of AlphaFold2, is accessed in JupyterLab to predict the 3-dimensional structure of protein sequences. JupyterLab is accessible in 2 ways—one as an interactive Galaxy tool and the other by running the underlying Docker container. In both ways, long-running training can be executed on Galaxy’s compute infrastructure. Scripts to create the Docker container are available under MIT license at https://github.com/usegalaxy-eu/gpu-jupyterlab-docker.