Seqera has run Nextflow protein-design and structure-prediction pipelines on Nebius AI Cloud. Its team describes testing a pipeline on an H100 GPU virtual machine and running a protein-binder design project on managed Kubernetes. The company also publishes cluster and workflow configuration for the joint work. For the January 2026 Nipah binder project, the production run scaled to 16 H100 GPUs for parallel Boltz2 validation. CPU stages handled ranking, ProteinMPNN sequence redesign and analysis. Seqera reports completing the workflow of 2,000 initial designs and 200 final candidates in a few hours.
In an earlier Chai-1 demonstration, Seqera predicted structures for 84 sequences using 24 H100 GPUs through Slurm and Soperator. Seqera identifies the example as nf-chai predictions for CASP15. The demonstration used single-sequence mode without multiple-sequence alignment and produced 420 structure predictions. Seqera used Apptainer to share container images between nodes and pre-downloaded Chai-1 reference weights for reuse across workflow tasks. A separate presentation describes moving Nextflow jobs to Nebius and reports a fourfold improvement for the deployment shown. In August 2026, Nebius reported a fourfold speedup for Seqera’s protein structure prediction through NVIDIA NIM compared with launching containers natively. These figures refer to particular demonstrations. Seqera also works with Nebius as a technology partner.
For its Kubernetes deployment, Seqera used Terraform to configure an autoscaling cluster and Nebius-managed GPU drivers, device plugins and Grafana dashboards. Nebius describes a jointly engineered Seqera integration supporting Nextflow and nf-core pipelines on its GPU clusters with one-click Terraform deployment. In March 2026, CEO Evan Floden reported success running Nextflow with Nebius and praised its GPU availability and interface.
Seqera describes running nf-chai on Nebius through Slurm and Soperator with 24 H100 GPUs. Its demonstration predicted structures for 84 protein sequences and produced 420 predictions in single-sequence mode without multiple-sequence alignment. Seqera used Apptainer to share container images between nodes and pre-downloaded Chai-1 reference weights for reuse across tasks.
Nextflow with Slurm and Soperator19 Feb 2025 · Seqera · Web pageSeqera describes running nf-chai on Nebius through Slurm and Soperator with 24 H100 GPUs. Its demonstration predicted structures for 84 protein sequences and produced 420 predictions in single-sequence mode without multiple-sequence alignment. Seqera used Apptainer to share container images between nodes and pre-downloaded Chai-1 reference weights for reuse across tasks.
Co-Scientist project retrospective
11 Jun 2026 · Seqera · Web page
Seqera dates its Nipah binder competition project to January 2026 and describes running nf-proteindesign on Nebius GPU Kubernetes infrastructure. The team tested pipeline branches on Nebius GPU virtual machines and manually corrected configuration and container issues.
Co-Scientist project retrospective11 Jun 2026 · Seqera · Web pageSeqera dates its Nipah binder competition project to January 2026 and describes running nf-proteindesign on Nebius GPU Kubernetes infrastructure. The team tested pipeline branches on Nebius GPU virtual machines and manually corrected configuration and container issues.
GPU Nextflow production cluster
25 Mar 2026 · Seqera · Web page
Seqera describes its protein-design production run on Nebius managed Kubernetes. Boltz2 validation used 16 H100 GPUs across two nodes, while CPU stages handled ranking, ProteinMPNN sequence redesign and analysis. The workflow processed 2,000 initial designs and 200 final candidates in a few hours.
GPU Nextflow production cluster25 Mar 2026 · Seqera · Web pageSeqera describes its protein-design production run on Nebius managed Kubernetes. Boltz2 validation used 16 H100 GPUs across two nodes, while CPU stages handled ranking, ProteinMPNN sequence redesign and analysis. The workflow processed 2,000 initial designs and 200 final candidates in a few hours.
Nipah binder pipeline run
8 Jan 2026 · Seqera · Web page
Seqera describes testing its protein-design pipeline on a Nebius virtual machine with one H100 GPU before scaling through Nebius managed Kubernetes. During testing, Nextflow’s resume feature let the team fix individual processes without rerunning the entire pipeline.
Nipah binder pipeline run8 Jan 2026 · Seqera · Web pageSeqera describes testing its protein-design pipeline on a Nebius virtual machine with one H100 GPU before scaling through Nebius managed Kubernetes. During testing, Nextflow’s resume feature let the team fix individual processes without rerunning the entire pipeline.
Seqera Nebius deployment repository
27 Sept 2026 · Seqera · Web page
Original company repository supplies cluster and workflow configuration.
Seqera develops software for bioinformatics and scientific data analysis, used by researchers, bioinformaticians, and data scientists in pharmaceutical, biotechnology, healthcare, and research organizations. Its Nextflow workflow engine runs reproducible analysis pipelines across cloud and on-premises computing environments. Seqera Platform adds tools for launching and monitoring pipelines, managing data and compute, and collaborating on interactive analyses. Other products include MultiQC for combining analysis quality reports, Wave for provisioning software containers, and Fusion for accessing cloud storage within computational workflows.
Seqera opens early access to Nextflow Global Cache
Nextflow Global Cache reuses identical task outputs across runs, pipelines and projects within a workspace. Seqera opened early access ahead of availability in Seqera Cloud and Enterprise 26.2, with support for AWS, Azure and Google Cloud.
Seqera announces Platform 26.2 automation and data governance features
Seqera Platform 26.2 adds event-driven pipeline and agent automation, identity-based data permissions and service accounts. It also introduces cross-workspace lineage search and expands GxP support to interactive Studios.
The release adds stable static typing, reusable workflow modules and direct pipeline composition. An experimental agent primitive brings AI tasks into Nextflow pipelines.
Scientific workflow orchestration and Nextflow · Health
How they use Nebius AI Cloud
Seqera has run Nextflow protein-design and structure-prediction pipelines on Nebius AI Cloud. Its team describes testing a pipeline on an H100 GPU virtual machine and running a protein-binder design project on managed Kubernetes. The company also publishes cluster and workflow configuration for the joint work. For the January 2026 Nipah binder project, the production run scaled to 16 H100 GPUs for parallel Boltz2 validation. CPU stages handled ranking, ProteinMPNN sequence redesign and analysis. Seqera reports completing the workflow of 2,000 initial designs and 200 final candidates in a few hours.
In an earlier Chai-1 demonstration, Seqera predicted structures for 84 sequences using 24 H100 GPUs through Slurm and Soperator. Seqera identifies the example as nf-chai predictions for CASP15. The demonstration used single-sequence mode without multiple-sequence alignment and produced 420 structure predictions. Seqera used Apptainer to share container images between nodes and pre-downloaded Chai-1 reference weights for reuse across workflow tasks. A separate presentation describes moving Nextflow jobs to Nebius and reports a fourfold improvement for the deployment shown. In August 2026, Nebius reported a fourfold speedup for Seqera’s protein structure prediction through NVIDIA NIM compared with launching containers natively. These figures refer to particular demonstrations. Seqera also works with Nebius as a technology partner.
For its Kubernetes deployment, Seqera used Terraform to configure an autoscaling cluster and Nebius-managed GPU drivers, device plugins and Grafana dashboards. Nebius describes a jointly engineered Seqera integration supporting Nextflow and nf-core pipelines on its GPU clusters with one-click Terraform deployment. In March 2026, CEO Evan Floden reported success running Nextflow with Nebius and praised its GPU availability and interface.
Seqera describes running nf-chai on Nebius through Slurm and Soperator with 24 H100 GPUs. Its demonstration predicted structures for 84 protein sequences and produced 420 predictions in single-sequence mode without multiple-sequence alignment. Seqera used Apptainer to share container images between nodes and pre-downloaded Chai-1 reference weights for reuse across tasks.
Nextflow with Slurm and Soperator19 Feb 2025 · Seqera · Web pageSeqera describes running nf-chai on Nebius through Slurm and Soperator with 24 H100 GPUs. Its demonstration predicted structures for 84 protein sequences and produced 420 predictions in single-sequence mode without multiple-sequence alignment. Seqera used Apptainer to share container images between nodes and pre-downloaded Chai-1 reference weights for reuse across tasks.
Co-Scientist project retrospective
11 Jun 2026 · Seqera · Web page
Seqera dates its Nipah binder competition project to January 2026 and describes running nf-proteindesign on Nebius GPU Kubernetes infrastructure. The team tested pipeline branches on Nebius GPU virtual machines and manually corrected configuration and container issues.
Co-Scientist project retrospective11 Jun 2026 · Seqera · Web pageSeqera dates its Nipah binder competition project to January 2026 and describes running nf-proteindesign on Nebius GPU Kubernetes infrastructure. The team tested pipeline branches on Nebius GPU virtual machines and manually corrected configuration and container issues.
GPU Nextflow production cluster
25 Mar 2026 · Seqera · Web page
Seqera describes its protein-design production run on Nebius managed Kubernetes. Boltz2 validation used 16 H100 GPUs across two nodes, while CPU stages handled ranking, ProteinMPNN sequence redesign and analysis. The workflow processed 2,000 initial designs and 200 final candidates in a few hours.
GPU Nextflow production cluster25 Mar 2026 · Seqera · Web pageSeqera describes its protein-design production run on Nebius managed Kubernetes. Boltz2 validation used 16 H100 GPUs across two nodes, while CPU stages handled ranking, ProteinMPNN sequence redesign and analysis. The workflow processed 2,000 initial designs and 200 final candidates in a few hours.
Nipah binder pipeline run
8 Jan 2026 · Seqera · Web page
Seqera describes testing its protein-design pipeline on a Nebius virtual machine with one H100 GPU before scaling through Nebius managed Kubernetes. During testing, Nextflow’s resume feature let the team fix individual processes without rerunning the entire pipeline.
Nipah binder pipeline run8 Jan 2026 · Seqera · Web pageSeqera describes testing its protein-design pipeline on a Nebius virtual machine with one H100 GPU before scaling through Nebius managed Kubernetes. During testing, Nextflow’s resume feature let the team fix individual processes without rerunning the entire pipeline.
Seqera Nebius deployment repository
27 Sept 2026 · Seqera · Web page
Original company repository supplies cluster and workflow configuration.
Seqera develops software for bioinformatics and scientific data analysis, used by researchers, bioinformaticians, and data scientists in pharmaceutical, biotechnology, healthcare, and research organizations. Its Nextflow workflow engine runs reproducible analysis pipelines across cloud and on-premises computing environments. Seqera Platform adds tools for launching and monitoring pipelines, managing data and compute, and collaborating on interactive analyses. Other products include MultiQC for combining analysis quality reports, Wave for provisioning software containers, and Fusion for accessing cloud storage within computational workflows.
Seqera opens early access to Nextflow Global Cache
Nextflow Global Cache reuses identical task outputs across runs, pipelines and projects within a workspace. Seqera opened early access ahead of availability in Seqera Cloud and Enterprise 26.2, with support for AWS, Azure and Google Cloud.
Seqera announces Platform 26.2 automation and data governance features
Seqera Platform 26.2 adds event-driven pipeline and agent automation, identity-based data permissions and service accounts. It also introduces cross-workspace lineage search and expands GxP support to interactive Studios.
The release adds stable static typing, reusable workflow modules and direct pipeline composition. An experimental agent primitive brings AI tasks into Nextflow pipelines.
