Estimating diagnostic uncertainty in artificial intelligence assisted pathology using conformal prediction.

Unreliable predictions can occur when an artificial intelligence (AI) system is presented with data it has not been exposed to during training. We demonstrate the use of conformal prediction to detect unreliable predictions, using histopathological diagnosis and grading of prostate biopsies as example. We digitized 7788 prostate biopsies from 1192 men in the STHLM3 diagnostic study, used for training, and 3059 biopsies from 676 men used for testing. With conformal prediction, 1 in 794 (0.1%) predictions is incorrect for cancer diagnosis (compared to 14 errors [2%] without conformal prediction) while 175 (22%) of the predictions are flagged as unreliable when the AI-system is presented with new data from the same lab and scanner that it was trained on. Conformal prediction could with small samples (N = 49 for external scanner, N = 10 for external lab and scanner, and N = 12 for external lab, scanner and pathology assessment) detect systematic differences in external data leading to worse predictive performance. The AI-system with conformal prediction commits 3 (2%) errors for cancer detection in cases of atypical prostate tissue compared to 44 (25%) without conformal prediction, while the system flags 143 (80%) unreliable predictions. We conclude that conformal prediction can increase patient safety of AI-systems.

MaRe: Processing Big Data with application containers on Apache Spark.

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.

Interoperable and scalable data analysis with microservices: applications in metabolomics.

MOTIVATION: Developing a robust and performant data analysis workflow that integrates all necessary components whilst still being able to scale over multiple compute nodes is a challenging task. We introduce a generic method based on the microservice architecture, where software tools are encapsulated as Docker containers that can be connected into scientific workflows and executed using the Kubernetes container orchestrator. RESULTS: We developed a Virtual Research Environment (VRE) which facilitates rapid integration of new tools and developing scalable and interoperable workflows for performing metabolomics data analysis. The environment can be launched on-demand on cloud resources and desktop computers. IT-expertise requirements on the user side are kept to a minimum, and workflows can be re-used effortlessly by any novice user. We validate our method in the field of metabolomics on two mass spectrometry, one nuclear magnetic resonance spectroscopy and one fluxomics study. We showed that the method scales dynamically with increasing availability of computational resources. We demonstrated that the method facilitates interoperability using integration of the major software suites resulting in a turn-key workflow encompassing all steps for mass-spectrometry-based metabolomics including preprocessing, statistics and identification. Microservices is a generic methodology that can serve any scientific discipline and opens up for new types of large-scale integrative science. AVAILABILITY AND IMPLEMENTATION: The PhenoMeNal consortium maintains a web portal (https://portal.phenomenal-h2020.eu) providing a GUI for launching the Virtual Research Environment. The GitHub repository https://github.com/phnmnl/ hosts the source code of all projects. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

On-demand virtual research environments using microservices.

The computational demands for scientific applications are continuously increasing. The emergence of cloud computing has enabled on-demand resource allocation. However, relying solely on infrastructure as a service does not achieve the degree of flexibility required by the scientific community. Here we present a microservice-oriented methodology, where scientific applications run in a distributed orchestration platform as software containers, referred to as on-demand, virtual research environments. The methodology is vendor agnostic and we provide an open source implementation that supports the major cloud providers, offering scalable management of scientific pipelines. We demonstrate applicability and scalability of our methodology in life science applications, but the methodology is general and can be applied to other scientific domains.

Container-based bioinformatics with Pachyderm.

MOTIVATION: Computational biologists face many challenges related to data size, and they need to manage complicated analyses often including multiple stages and multiple tools, all of which must be deployed to modern infrastructures. To address these challenges and maintain reproducibility of results, researchers need (i) a reliable way to run processing stages in any computational environment, (ii) a well-defined way to orchestrate those processing stages and (iii) a data management layer that tracks data as it moves through the processing pipeline. RESULTS: Pachyderm is an open-source workflow system and data management framework that fulfils these needs by creating a data pipelining and data versioning layer on top of projects from the container ecosystem, having Kubernetes as the backbone for container orchestration. We adapted Pachyderm and demonstrated its attractive properties in bioinformatics. A Helm Chart was created so that researchers can use Pachyderm in multiple scenarios. The Pachyderm File System was extended to support block storage. A wrapper for initiating Pachyderm on cloud-agnostic virtual infrastructures was created. The benefits of Pachyderm are illustrated via a large metabolomics workflow, demonstrating that Pachyderm enables efficient and sustainable data science workflows while maintaining reproducibility and scalability. AVAILABILITY AND IMPLEMENTATION: Pachyderm is available from https://github.com/pachyderm/pachyderm. The Pachyderm Helm Chart is available from https://github.com/kubernetes/charts/tree/master/stable/pachyderm. Pachyderm is available out-of-the-box from the PhenoMeNal VRE (https://github.com/phnmnl/KubeNow-plugin) and general Kubernetes environments instantiated via KubeNow. The code of the workflow used for the analysis is available on GitHub (https://github.com/pharmbio/LC-MS-Pachyderm). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PhenoMeNal: processing and analysis of metabolomics data in the cloud.

BACKGROUND: Metabolomics is the comprehensive study of a multitude of small molecules to gain insight into an organism's metabolism. The research field is dynamic and expanding with applications across biomedical, biotechnological, and many other applied biological domains. Its computationally intensive nature has driven requirements for open data formats, data repositories, and data analysis tools. However, the rapid progress has resulted in a mosaic of independent, and sometimes incompatible, analysis methods that are difficult to connect into a useful and complete data analysis solution. FINDINGS: PhenoMeNal (Phenome and Metabolome aNalysis) is an advanced and complete solution to set up Infrastructure-as-a-Service (IaaS) that brings workflow-oriented, interoperable metabolomics data analysis platforms into the cloud. PhenoMeNal seamlessly integrates a wide array of existing open-source tools that are tested and packaged as Docker containers through the project's continuous integration process and deployed based on a kubernetes orchestration framework. It also provides a number of standardized, automated, and published analysis workflows in the user interfaces Galaxy, Jupyter, Luigi, and Pachyderm. CONCLUSIONS: PhenoMeNal constitutes a keystone solution in cloud e-infrastructures available for metabolomics. PhenoMeNal is a unique and complete solution for setting up cloud e-infrastructures through easy-to-use web interfaces that can be scaled to any custom public and private cloud environment. By harmonizing and automating software installation and configuration and through ready-to-use scientific workflow user interfaces, PhenoMeNal has succeeded in providing scientists with workflow-driven, reproducible, and shareable metabolomics data analysis platforms that are interfaced through standard data formats, representative datasets, versioned, and have been tested for reproducibility and interoperability. The elastic implementation of PhenoMeNal further allows easy adaptation of the infrastructure to other application areas and 'omics research domains.

Efficient iterative virtual screening with Apache Spark and conformal prediction.

BACKGROUND: Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening. The problem is trivially parallelizable, and calculations are generally carried out on computer clusters or on large workstations in a brute force manner, by docking and scoring all available ligands. CONTRIBUTION: In this study we propose a strategy that is based on iteratively docking a set of ligands to form a training set, training a ligand-based model on this set, and predicting the remainder of the ligands to exclude those predicted as 'low-scoring' ligands. Then, another set of ligands are docked, the model is retrained and the process is repeated until a certain model efficiency level is reached. Thereafter, the remaining ligands are docked or excluded based on this model. We use SVM and conformal prediction to deliver valid prediction intervals for ranking the predicted ligands, and Apache Spark to parallelize both the docking and the modeling. RESULTS: We show on 4 different targets that conformal prediction based virtual screening (CPVS) is able to reduce the number of docked molecules by 62.61% while retaining an accuracy for the top 30 hits of 94% on average and a speedup of 3.7. The implementation is available as open source via GitHub ( https://github.com/laeeq80/spark-cpvs ) and can be run on high-performance computers as well as on cloud resources.

Large-scale virtual screening on public cloud resources with Apache Spark.

BACKGROUND: Structure-based virtual screening is an in-silico method to screen a target receptor against a virtual molecular library. Applying docking-based screening to large molecular libraries can be computationally expensive, however it constitutes a trivially parallelizable task. Most of the available parallel implementations are based on message passing interface, relying on low failure rate hardware and fast network connection. Google's MapReduce revolutionized large-scale analysis, enabling the processing of massive datasets on commodity hardware and cloud resources, providing transparent scalability and fault tolerance at the software level. Open source implementations of MapReduce include Apache Hadoop and the more recent Apache Spark. RESULTS: We developed a method to run existing docking-based screening software on distributed cloud resources, utilizing the MapReduce approach. We benchmarked our method, which is implemented in Apache Spark, docking a publicly available target receptor against [Formula: see text]2.2 M compounds. The performance experiments show a good parallel efficiency (87%) when running in a public cloud environment. CONCLUSION: Our method enables parallel Structure-based virtual screening on public cloud resources or commodity computer clusters. The degree of scalability that we achieve allows for trying out our method on relatively small libraries first and then to scale to larger libraries. Our implementation is named Spark-VS and it is freely available as open source from GitHub (https://github.com/mcapuccini/spark-vs).Graphical abstract.