Frequently Asked Questions

What type of bioinformatics service does Lifebit provide?

Lifebit provides end-to-end bioinformatics support. The Lifebit Platform comes with pre-built pipelines for researchers to run analyses to answer different research questions. As part of our standard onboarding process, our delivery team includes bioinformaticians who work alongside your users to ensure they are fully enabled to begin using the platform seamlessly.

What cloud providers can Lifebit work with?

Lifebit’s Platform is cloud-agnostic. We can work with any cloud provider and can even support hybrid or on-site infrastructure.

How does Lifebit's solution conform to local, national, or international data regulations/governance?

Lifebit utilises its proprietary, patented, federated technology so that data can be analysed within the client's secure environment. For example, Lifebit works with several biobanks in Europe and Asia, where data must remain in the country. Because the data is never copied or downloaded, conforming with local data regulations and governance is much simpler.

Where is the data stored when working with Lifebit?

All biomedical data, both clinical and genomic, is stored within the client's own environment. When clients utilise a cloud-based configuration, raw data is, for example, stored in their AWS HCC account, and then ingested data is hosted in EC2 machines. When clients utilise a hybrid set-up, raw data may be stored on-premise, while ingested data could be stored in the cloud. Finally, all the data is stored on-site when clients require an on-premise configuration.

Can the Lifebit Platform encrypt data for security purposes?

Within Lifebit’s Platform, data is encrypted at rest (e.g., when data is in storage) and in transit (e.g., when data moves between storage buckets and compute machines). Data can only be de-encrypted by authenticated staff, and the security network imposes additional constraints on which specific users can access, view, or edit encrypted files. Lifebit works proactively with clients to comply with sensitive data requirements, ensuring that organisations can meet and exceed industry standards amidst the changing regulatory and regional landscape. Lifebit's Platform empowers our clients to meet their data security and privacy compliance goals whilst enabling valuable research at scale.

Can the Lifebit Platform anonymise data?

Yes, Lifebit's ETL (Extraction Transfer Loading) ingestion pipelines can anonymise patient data. The ETL pipelines generate anonymised IDs that researchers can view in place of identifiable information.

How does data flow in the Lifebit Platform?

Data from a client's environment flows into the Lifebit Platform in the following way: First, data within the client environment needs to be made analysis-ready before ingestion into the databases within the Lifebit Platform. Any raw data (e.g. real-world and omics data) will go through Lifebit’s data transformation (ETL) pipelines, which clean and harmonise data to a common data model, ensuring it is ready for analysis. All data harmonisation and processing occurs within the client's infrastructure, which RESTful APIs trigger to the Lifebit Platform. The Lifebit Platform can then orchestrate the execution of data harmonisation pipelines. Second, the analysis-ready data is ingested into an aggregation layer (Phenotypic & Variant Databases, within the client's environment), ready to be used for downstream analyses with the Platform’s built-for-purpose applications. Users can build cohorts, identify phenotypes and genotypes of interest, explore variant information, and perform downstream analysis. All downstream analyses are run within the Downstream Compute Environment (also within the client environment). In summary, data processing takes place in the backend, with the data and analysis all remaining within the client environment, keeping data safe and secure at all times.

Our system is offline - how can we import custom pipelines into the Lifebit Platform?

The Lifebit Platform can accommodate configurations that do not have internet access - the client can import pipelines from Gitlab or any other local repositories.

How do we incorporate datasets into the Lifebit Platform?

Lifebit’s Platform has the ability to add and connect to different external or in-house databases. There are two ways of easily linking data to the Lifebit Platform: 1) AWS HCC S3 buckets can easily be linked via federation and 2) the Lifebit Connect Engine can link the Client to disparate datasets, also via federation.

What data types does the Lifebit Platform support?

Lifebit has extensive experience with large, complex health data sets containing real-world and clinical information (i.e. demographics, disease diagnosis, treatment, etc.) as well as molecular data, including WGS (germline and for cancer patients also somatic), RNA seq and CNV (copy number variants), and others.

How does Lifebit transform clinical data to ensure datasets from disparate sources are interoperable?

Lifebit has a team of specialised data scientists and an array of upstream ingestion ETL pipelines that can transform both clinical, phenotypic and genomic data to make it ready for ingestion into the platform for subsequent downstream analysis. Specifically, Lifebit is OMOP-certified; we have deep experience in harmonising disparate data sources by transforming them to a common data format using a standard set of vocabularies so they can be analysed with standard analytical pipelines. In addition, Lifebit supports FHIR and HL-7 industry standards to exchange healthcare data in a standardised and secure manner.

Can the Lifebit Platform support clinical trial data?

Lifebit has worked with clients, including top pharmaceutical companies, to transform their clinical trial data to be analysis-ready. Lifebit's ETL pipelines can standardise clinical trial data into the OMOP common data model, making the data usable and interoperable with other global datasets. Our team contains OMOP experts and is at the cutting edge of complex data standardisation. Further, regarding clinical trial data, Lifebit also has experience with CDISC (SDTM and ADAM) and custom data formats.

Can users import tools/pipelines into the Lifebit Platform?

Yes, users can import tools and pipelines into the Lifebit Platform. For tools to be imported as a pipeline/tool into the Platform's Analytics Engine, they must be containerised (eg Nextflow, Docker, WDL). Scripts can be run within a Jupyter Notebook session in the Analytics Engine of the Lifebit Platform - this means any analytical tool of the client can be used in the Lifebit Platform, out-of-the-box. Given the broad range of users, including those without computational backgrounds, our expert bioinformaticians will be ready to ensure users can perform their analysis through our dedicated training/onboarding and ongoing support.

How does the Lifebit Connect Engine work?

Within Lifebit Connect, users can run joint queries on cohorts across distributed research environments and filter across these separate datasets. The analysis on each dataset is conducted separately but run in parallel, and the results are aggregated in a Safe Haven before being exported to the authorised user. The datasets are never moved into a centralised environment as this would comprise security.

Does the Lifebit Platform have the ability to track costs?

Yes, the Lifebit Platform does indeed have the ability to track billing. There is an existing functionality within the Lifebit Platform to track costs associated with a project/user/workspace.