Release notes

General

This release introduces new GPU-enabled AWS G6e and G7 GPU instances. Please note that these instance types currently have limited availability on AWS, so tasks that use them may experience longer wait times before starting.

• • G7 instances use NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, with up to 8 GPUs per instance and 32 GB of memory on each GPU. They are designed for AI inference, graphics, and data analytics, and AWS reports up to 4.6x faster AI inference than the previous-generation G6 instances.

  • G6e instances use NVIDIA L40S Tensor Core GPUs, with up to 8 GPUs per instance and 48 GB of memory on each GPU, which is double the GPU memory of G6 instances. They are well suited to cost-efficient generative AI inference and to fine-tuning or training smaller models on a single node, and AWS reports up to 2.5x better performance than G5 instances.

Resources

To learn more about the newly introduces instance families, visit AWS pages for G6e instances and G7 instances. For the full list of AWS instances available on the platform, see Amazon Web Services.

If you have questions about instances,please contact your Velsera/Seven Bridges representative or reach out to the support team at support@velsera.com.

General

This release includes a change in the default behaviour for spot instance interruption handling.

Improvements

• By default, if a Spot instance is interrupted while a task is running, the task now retries once on a new Spot instance.

Resources
If you have questions about any of these changes, please contact your Velsera/Seven Bridges representative or reach out to the support team at support@velsera.com.

Recently published apps and resources

This release expanded the availability of key scientific workflows and upgraded QIIME2 workflows for microbiome research and STAR-based tools for RNA-seq analysis. These updates were designed to improve reproducibility, usability, and accessibility for researchers working across genomics, imaging, and multi-omics workflows.

Enhancements to the Nextflow import application

Several improvements were delivered to the sbpack_nf CWL App to streamline onboarding and deployment of Nextflow workflows on Seven Bridges platform, including:

• Support for importing Nextflow workflow packages directly from public GitHub repository URLs, reducing the need for manual archive uploads.
• Validation checks to prevent unsupported string output types during workflow packaging. Improved compatibility with EPI2ME and nf-core workflows

Together, these updates improve workflow portability, reduce deployment errors, and simplify the packaging process for Nextflow users on the platform.

Single-Cell Analysis Resources 

A standardized Monocle workflow has been developed to support scalable and reproducible single-cell RNA-seq trajectory analysis. This workflow enables researchers to: 

• Reconstruct developmental and cellular trajectories. 

• Perform pseudotime analyses. 

• Explore branching lineage relationships. 

• Investigate gene expression changes associated with cell state transitions. 

By providing a configurable and reusable workflow, this release simplifies advanced single-cell trajectory analysis for a broad range of biological applications.  

Microbiome Analysis Improvements 

The publicly available QIIME2 workflows for microbiome analysis have been reviewed, updated, and validated to align with current platform standards. Updated workflows include: 

• 16S rRNA Feature Classifier Training 

• 16S rRNA Metagenomic Profiling 

• QIIME2 Core Diversity Reporting 

Improvements include workflow validation, refreshed configurations, updated parameter guidance, enhanced documentation, and verification of referenced assets and metadata. These updates help ensure reliable execution and a more consistent user experience for microbiome researchers. 

RNA-seq Workflow Updates 

The STAR toolkit and associated RNA-seq alignment workflows available through the Public Apps Gallery have been updated to the latest supported version, improving consistency and maintaining alignment with current platform standards. The update includes the following components: STAR, STARsolo, STARsoloCellFiltering, STAR Genome Generate, and the RNA-seq Alignment STAR workflow. This release ensures that users performing bulk and single-cell RNA-seq analyses have access to the most up-to-date STAR-based tools while maintaining compatibility with existing analysis workflows. The refreshed toolkit supports reliable sequence alignment, genome indexing, and single-cell transcriptomic preprocessing across a variety of RNA-seq applications. 

 Resources 

If you have questions or need help with any of these new resources, please contact your Velsera Seven Bridges representative or email support@velsera.com. 

This release includes performance and reliability improvements across billing, Docker registry compatibility, and project administration, along with an updated CLI version

• Billing Reports: Billing Reports are exported and are shared over mail for easier access and download.

• Docker Registry: Support extended for Docker version 25 and above, including full visibility of the images in the Repository UI

• Task Logs (Nextflow): Actionable messages on Nextflow task execution failures for easier troubleshooting.

• Project Membership: Enabled deletion of disabled members from automation projects via the CLI, using the updated CLI version (0.25.3) included in this release.

If you have questions or experience issues, please contact your Velsera Seven Bridges representative or email support@velsera.com.

Recently published apps and resources

This release introduced a new set of applications, projects, and tool upgrades to the Public Apps Gallery on the Seven Bridges Platform. These additions expand support for clinical machine learning, multi-omics integration and biomedical imaging workflows, providing researchers with a broader portfolio of production-ready CWL applications for translational and bioinformatics research.

COMET Framework Applications 

Three new applications have been added to support machine learning workflows built around electronic health record (EHR) data and the COMET framework. Together, these tools provide an end-to-end workflow for representation learning, model training, evaluation, and clinical prediction.

COMET Train Word2Vec

Generates patient embeddings and recurrent neural network (RNN)-ready datasets from preprocessed EHR data. This application helps researchers transform longitudinal clinical records into structured representations suitable for downstream machine learning analyses.

COMET Run Experiments

Supports training and evaluation of GRU-based EHR models and enables zero-shot testing, fine-tuning, and integrated COMET experiments. The application simplifies model development and benchmarking across clinical machine learning studies.

COMET Prediction

Performs inference using trained COMET models on new patient datasets. Researchers can apply previously trained models to generate predictions and support downstream clinical and translational research applications.

 Expanded mixOmics Toolkit Portfolio 

A comprehensive set of mixOmics 6.32.0 applications for multivariate and integrative omics analyses. These tools strengthen support for biomarker discovery, dimensionality reduction, data integration, and predictive modeling across multiple omics datasets. 

MixOmicsPCA 

Supports exploratory data analysis and dimensionality reduction, helping users identify major sources of variation within complex biological datasets. 

MixOmicsPLS and sPLS 

Enables modeling relationships between datasets while incorporating variable selection capabilities, making it easier to identify the most informative molecular features. 

MixOmicsPLS-DA and sPLS-DA 

Provides supervised classification workflows for biomarker discovery and sample discrimination across biological conditions. 

MixOmicsrCCA 

Facilitates the exploration of correlations between datasets, supporting the identification of biologically relevant relationships across data modalities. 

MixOmicsMINT 

Enables integration of multiple independent studies measuring common variables, helping researchers identify robust and reproducible molecular signatures. 

DIABLO

Supports outcome-driven multi-omics integration and biomarker discovery by identifying correlated features across multiple data types associated with a phenotype or clinical outcome. 

These additions significantly enhance the platform’s capabilities for integrative omics analysis, biomarker identification, and advanced statistical learning workflows. 

New Public Projects 

Several new public projects have been published to provide reference implementations and reproducible examples across multi-omics and imaging domains. 

MixOmicsDIABLO Public Project 

Demonstrates outcome-driven multi-omics integration using DIABLO to identify correlated transcriptomic and proteomic signatures associated with COVID-19 severity, based on the Harriott et al. 2025 study. 

MixOmicsMINT Public Project 

Showcases multivariate integrative analysis using MAQC datasets to identify reproducible molecular signatures across independent microarray studies and platforms. 

nnU-Net Public Project

Provides an accessible implementation of the self-configuring nnU-Net v2 framework for biomedical image segmentation. The project supports automated preprocessing, model training, and inference for both 2D and 3D imaging datasets. 

MOFA2 Public Project

Brings together MOFA2, MEFISTO, and MOFACell workflows for unsupervised multi-omics factor analysis, temporal and spatial omics integration, and single-cell or multicellular program discovery. 

Resources 

If you have questions or need help  with any of these new resources, please contact your Velsera Seven Bridges representative or email support@velsera.com. 

Smarter Session Management for Data Studio Analysis

General

This release delivers improved session management for Data Studio, ensuring that interactive user activity (typing, running cells, UI interactions, mouse movement) is correctly recognized as active platform use. This prevents unintended logouts during active work while maintaining full FedRAMP compliance for truly inactive sessions. Together with redesigned session notifications and long-running session support, these changes provide a predictable, uninterrupted analysis experience.

New Features

• Interactive Data Studio activity- including typing, running cells, executing commands, UI clicks, navigation, and mouse movement – now counts as active platform use and resets the inactivity timer, preventing unintended session timeouts while users are actively working.

• A new “Session Expiring Warning” pop-up now appears before logout (at 10 minutes of inactivity on academic platforms; at 55 minutes on commercial platforms), giving users a 5-minute countdown warning with an “OK” button to dismiss and remain on the same page.

• A new “Session Expired” pop-up now appears at logout (at 15 minutes on academic; 60 minutes on commercial) with a “Log In Again” button that redirects to the login page.

• A new informational banner – “You are no longer inactive – your session is extended by [15/60] minutes” – now appears when a user returns during the session-expiring warning window. The banner fades after 10 seconds.

Improvements

• Session notification experience has been consolidated into a single pop-up system, replacing the previous banner + pop-up combination for a cleaner, less disruptive experience during active use.

• The countdown timer in the session-expiring warning pop-up now dynamically decrements to zero before transitioning to the session-expired pop-up.

• Long-running sessions now ensure that background work (computations, file writes, running jobs) continues independently even after the user is logged out due to inactivity. Background activity keeps the Data Studio instance alive but does not keep the user logged in – login sessions are governed exclusively by user-presence activity.

• Session management behavior is now consistent across all supported platforms.

Resources

If you have questions or experience issues with Data Studio session management, please contact your Velsera Seven Bridges representative or email [support@velsera.com].

Learn more about [Data Studio].

IAM Role Authentication for AWS S3 Volume Connections

General 

This release introduces IAM role authentication as a supported method for connecting AWS S3 buckets as volumes, alongside the existing IAM user method. 

 New Features 

A new feature that enables: 

• Authentication of AWS S3 volume connections using an IAM role in place of an IAM user access key 

• Temporary, automatically-renewed session credentials with no long-term keys to manage 

• Custom IAM policy support scoped to a bucket, or a sub-path within it, for read-only or read-write access 

• Optional External ID configuration for additional trust-policy protection against unauthorized role assumption 

• Volume creation and management via both the visual interface and dedicated API endpoints (create, get details, update) 

 Resources 

For questions or support related to IAM role volume connections, contact your Velsera Seven Bridges representative or email support@velsera.com. 

Learn more about IAM Roles. 

Spot instance controls for task execution

This release introduced configurable Spot instance execution controls for tasks, enabling explicit control over Spot interruption retries and On-Demand fallback behavior.

New Features

• Configurable Spot interruption retries. A new Spot Instance Interruption retry setting allows setting how many times a task retries on a new Spot instance if the cloud provider reclaims the running instance mid-execution. Retries remain bounded by the configured limit, after which the fallback setting determines whether the task moves to On-Demand or fails.

• Configurable On-Demand fallback. A new Fall back to On-Demand instance toggle is available under Task Execution Settings when Spot instances are enabled. The toggle is on by default, preserving the behavior of falling back to On-Demand when Spot capacity cannot be secured or the interruption retry limit is reached. Disabling fallback ensures a task runs Spot-only to avoid unexpected On-Demand charges; if Spot capacity cannot be secured, the task reports failure immediately instead of waiting for the next retry interval.

All Spot instance parameters (interruption retries, On-Demand fallback, and the existing initial Spot retry duration) can be configured via both the visual interface and the API. Configured fallback and retry settings are preserved when copying or rerunning a task or copying a project.

Note: These controls are configured at the task level and are not currently supported as execution hints within workflow definitions.

Resources

If you have questions about the new Spot instance execution controls, please contact your Seven Bridges representative or reach out to the support team at support@velsera.com.

Recently published apps and resources

This release introduced a new set of tool upgrades to the Public Apps Gallery on the Seven Bridges Platform, including VCFtools, GATK, and Regenie for variant processing, variant calling, and large-scale genetic association studies.

VCFtools Suite for Variant Processing and Comparison

A comprehensive collection of VCFtools-based applications has been upgraded to support routine variant-processing and quality-control workflows. These tools improve interoperability across genomic analysis pipelines while streamlining common data manipulation tasks.

The upgraded applications enable users to:

• Filter variants using quality, genotype, region, and variant-level criteria with VCFtools Filter.
• Separate SNPs and indels using VCFtools Keep SNPs and VCFtools Keep Indels.
• Merge, concatenate, sort, and subset variant datasets using VCFtools Merge, Concat, Sort, and Subset.
• Perform variant intersection analyses with VCFtools Isec, Venn2, and Venn3.
• Assess Hardy-Weinberg Equilibrium using VCFtools Hardy and VCFtools Hwe.
• Convert between VCF versions using VCFtools Convert to support downstream tool compatibility.

These enhancements simplify routine variant curation and analysis workflows for genomic researchers.

GATK Best-Practice Components

Several key Genome Analysis Toolkit (GATK) applications have been upgraded, enabling users to build variant-calling workflows aligned with widely adopted best-practice methodologies.

The upgraded applications include:

• BaseRecalibrator
• ApplyBQSR
• GatherBQSRReports
• HaplotypeCaller
• VariantFiltration
• GenomicsDBImport

Together, these tools support base-quality score recalibration, germline variant discovery, joint genotyping workflows, and downstream variant filtering to improve sequencing analysis quality and consistency.

Regenie

The Public Apps Gallery has also been upgraded with Regenie, a widely used tool for whole-genome regression and large-scale genetic association studies. Regenie is designed for efficient analysis of large cohorts and supports genome-wide association testing across quantitative and binary traits, making it a valuable addition for population-scale genomics and genetic epidemiology research.

Resources

If you have questions or need help  with any of these new resources, please contact your Velsera Seven Bridges representative or email support@velsera.com.