Episode 45: tinybio - Nextflow x AI

In this episode of Channels, the Nextflow podcast, host Geraldine from Seqera and her colleague Ben Sherman dive into the differences and similarities between Nextflow and the Workflow Description Language (WDL). They discuss the origins and development of WDL at the Broad Institute, the challenges of working with different workflow languages, and how Nextflow's channel-based data flow model compares to WDL's approach. The conversation covers key features, type systems, and runtime specifications, highlighting the strengths and limitations of both languages. Ben hints at upcoming improvements and enhancements for Nextflow, aimed at making the language more robust and user-friendly. The episode offers valuable insights for bioinformaticians and developers navigating the complexities of workflow management.

In this episode of Channels, the Nextflow podcast, join us as we explore Nextflow and AI. Our special guest, Sasha from Seqera, shares his remarkable journey from the consumer tech industry to bioinformatics. Learn about the birth of TinyBio, its innovations in bioinformatics AI applications, and its recent acquisition by Seqera. We delve into AI concepts, the challenges faced, and the future of integrating AI with Nextflow. Tune in to discover how advancements in AI are reshaping the bioinformatics landscape. 00:00 Podcast 45: Tinybio : Nextflow x AI 00:09 Introduction 00:34 Sasha's background 03:17 How tinybio started 05:57 Tinybio co-founder: Vishal Patel 06:35 tinybio chat public launch 09:20 Failed feature launches 10:39 Running the code too 12:46 User trust 14:11 Accessing files via chat 15:08 Experiment idea generator 17:16 Pipeline generator 20:25 AI concepts: Foundational models 22:36 AI concepts: RAG 24:53 AI concepts: Langchain 26:37 AI concepts: Fine tuning 29:14 Challenges in bioinformatics AI 31:53 AI concepts: Q&A training 33:09 Motivation for joining Seqera 34:43 What happens to tinybio now? 35:36 Future plans 38:20 AI and open-source 40:50 Find more updates 41:37 Wrap up

In episode 44 of the Nextflow Channels podcast, Phil Ewels welcomes Alex Pelzer— a key figure in the Nextflow and nf-core community. Alex shares his journey from academia to the pharmaceutical industry, highlighting the critical role of regulatory frameworks in bioinformatics. 🌟 Key Highlights: The transition from working at QBiC to Boehringer Ingelheim. The importance of maintaining high-quality, reproducible pipelines in bioinformatics. Understanding regulatory requirements and their impact on clinical trials. How regulatory standards and open-source initiatives like @nf-core are shaping the future of bioinformatics. Alex also discusses the formation of the @nf-core Regulatory Special Interest Group, which aims to bring together experts in the field to establish and promote best practices for ensuring pipeline quality and compliance with regulatory standards. Looking forward to seeing many of you at the upcoming #NextflowSummit in Barcelona this October! We’ll be working with this #regulatory group during the nf-core hackathon. 00:00 Episode 44: Regulatory revolution 00:06 Introductions 00:33 Upcoming Nextflow Summit Announcement 01:34 Alex’s Background and Early Days with Nextflow 04:41 Formation and Growth of nf-core 06:18 Transition to Pharma and Regulatory Work 08:56 Regulatory Challenges and Practices in Bioinformatics 13:30 Tool Selection and Quality Assurance 15:23 Evaluating Software Trustworthiness 17:08 Overhead in Academia vs. Industry 18:11 Downstream analysis 20:57 Regulatory Special Interest Group 25:28 Special Interest Groups in nf-core 28:59 Future Directions and Community Involvement 30:15 Open source contributions in pharma 33:27 Conclusion and Upcoming Events

In this episode we explore the new features of Seqera's Data Studios and Data Explorer, with Phil Ewels, Rob Newman and Rob Syme from Seqera. Discover how to use these tools for troubleshooting Nextflow pipelines, tertiary analysis and Nextflow development. We discuss the pain points that led to the creation of Data Studios and how it's designed to allow scientists to interactively and collaboratively work with data and complex workflows, without having to move large datasets around. Rob Syme wows us with another fantastic practical demonstration, setting up and using Data Studios to write and test a Nextflow pipeline in VSCode running on the cloud in a Data Studio environment, including running the Nextflow CLI with task submission to AWS Batch. We cover features like session persistence to save work states, and upcoming custom container support for your own specialized applications. Learn how these tools can enhance your computational biology projects and make seamless cloud integration a reality. 00:00 Channels Podcast 43: Data Studios 00:26 Introductions 01:54 Data Studios 04:51 Move the compute to the data 06:13 Real-time collaboration 06:47 Data Explorer 09:41 Access to public data 10:45 Data Explorer demo 13:56 Data Studios setup 20:17 Session persistance 22:52 Data Studios RStudio demo 28:24 Nextflow development in Data Studios 36:17 Future development 37:01 Custom containers 40:01 Boston Summit demo 44:01 Lifetime management 47:14 Wrap up

A small but intrepid team of Seqerans recently attended the ISMB 2024 conference in Montreal, a great mix of computational biology and bioinformatics with a largely academic / research-focused audience. Join Geraldine Van der Auwera, Rob Syme and Florian Wuennemann for a lively discussion about the scientific themes of the conference, their experience running the booth, meeting with the ISMB and BOSC community, and resources for job seekers.

Join us in exploring the latest Nextflow release, 24.04. Phil Ewels and Ben Sherman dive deep into the new updates in Nextflow’s most recent version. We discuss advanced retry strategies, job arrays, resourceLimits, Singularity’s OCI mode, and the game-changing Workflow Output Definition. We’re actively seeking feedback from the community on these new features. We would love for you to experiment with the new syntax and let us know your thoughts. Please let us know what you think either via Nextflow GitHub issues or via the community forum. In this episode we refer to a the recent blog post about the release, which you can find here: Nextflow 24.04 - Release highlights. Intro - tweaks, fixes and new support in 24.04 Performance and Stability Improvements Ben kicks off the discussion with key performance and stability improvements. The latest stable release, 24.04, includes numerous bug fixes and performance enhancements. There’s a significant focus on closing gaps and adding retry strategies for better stability, especially concerning cloud providers. Notably, if Nextflow’s API calls against cloud providers fail for any server-side reason, it will retry automatically, avoiding pipeline failures caused by temporary server issues. Publishing Changes Previously, if a file failed to publish, Nextflow would only issue a warning. It was possible for a pipeline to complete successfully without noticing missing output files. Now, by default, Nextflow will fail the pipeline if the publishing fails, though there’s an option to revert to the old behavior. Additionally, retry strategies for publishing have been introduced to ensure retry attempts if an issue arises. Job Arrays One highly requested feature is the introduction of job arrays. This allows users to submit many jobs as a single submission, alleviating strain on schedulers. The submission happens in a batch, and then the scheduler can process and plan effectively. Once a job is submitted as part of a job array, the jobs run independently. If any child job fails, it is resubmitted without affecting the rest of the array. Singularity OCI mode and GA4GH TES In the past, Singularity supported Docker images by converting them into SIF files, consuming storage and time. Now, both Singularity and Apptainer can run OCI images directly, saving valuable resources. Additionally, the TES executor has seen significant improvements, now supporting TES 1.1, which brings broader compatibility and integration with existing workflows. Major new syntax features Topic Channels A new feature called topic channels offers a more straightforward approach to collecting channel outputs across pipelines. Channels can emit data to a named topic, simplifying the collection and use of version information from various processes within Nextflow pipelines. Eval Outputs Eval outputs simplify the addition of shell commands to tasks. With eval outputs, necessary post-task commands can be defined neatly, avoiding repetitive code within process definitions. Workflow Output Definition The concept of workflow output definitions has been introduced. This new syntax streamlines the publication of files by defining publish targets within workflows. Instead of defining publication behaviors within process definitions, users can now manage them at the workflow level, ensuring better clarity and fewer repetitions in the code.

Join us to hear Phil Ewels chat with Maxime Garcia and Franziska Bonath about how nf-core started at the National Genomics Infrastructure (NGI) at SciLifeLab in Sweden.We chat about how the nf-core/sarek pipeline grew alongside and eventually joined nf-core,as well as the early days of nf-core bytesize talks and outreach organisation. Links: - SciLifeLab - National Genomics Infrastructure - Maxime's Nextflow Summit Boston 2023 presentation about Sarek - nf-core bytesize talks

Tune in to hear all about Pixelgen Technologies - creators of a novel technology for doing single-cell spatial proteomics. We chat about how this fascinating technology works, what you can do with the data and why they chose to develop their analysis suite as an open-source nf-core pipeline. Links: Software: nf-core/pixelator pipeline Pixelator Python package Science: Nature Methods publication: “Molecular pixelation: spatial proteomics of single cells by sequencing” Presentations: Nextflow Summit 2022 talk: “Pixelgen Technologies ❤︎ Nextflow” Nextflow Summit 2024 Boston talk: “Nextflow allows Pixelgen innovation engine to reach the market quicker” Nextflow Summit 2024 Barcelona Pixelgen: Pixelgen Technologies homepage @PixelgenTech on twitter / X and LinkedIn BioLizard: BioLizard homepage @BioLizard_nv on twitter / X and LinkedIn Chapters: Start (00:00) Welcome (00:09) Introductions (00:50) Intro to Pixelgen Technologies (01:41) Lab methods (03:08) Nature Methods publication (06:15) Data visualisation (09:35) Working with single cell data (12:29) Cell interactions (15:06) Why Pixelgen chose open source (16:05) Pixelator Python package (20:10) Building within nf-core (21:40) Florian - Biolizard (23:01) Pipeline overview (25:19) Using nf-core from a commercial setting (26:50) Coming out of stealth (28:53) Extending Pixelator (32:24) Dealing with customers (34:58) Looking to the future (39:38) Interactive analysis (41:32) Advice for others (43:12) Pixelgen at the Nextflow Summit (45:16)

Evan Floden (CEO and co-founder of Seqera) joins Phil Ewels (Product Manager for OSS at Seqera) to talk about two of the big announcements at the recent Nextflow Summit Boston 2024 - Seqera Pipelines and Seqera Containers. We dive into what these two new community offerings are, why we built them and how they work. Links: https://seqera.io/pipelines/ https://seqera.io/containers/ Announcement blog post Nextflow Summit Boston 2024 agenda Summit YouTube playlist Nextflow 24.04 blog post Timeline: 00:00 - Introduction 00:37 - Nextflow Summit Boston 2024 01:14 - Summit talks available online 01:57 - Summit announcements 04:32 - Seqera Pipelines - motivations 05:59 - Seqera Pipelines - first look 06:48 - Testing requirements for community pipelines 10:05 - How we tested pipelines 11:53 - SRA-Explorer tangent 12:34 - Seqera Pipelines - live demo 16:14 - Getting Nextflow launch commands 19:12 - Seqera Containers - intro 24:03 - Seqera Containers - live demo 27:13 - Containers - ARM cpu arch builds 28:33 - Singularity containers 29:09 - Wave CLI 31:19 - Nextflow with Seqera Containers 33:22 - Seqera Containers - future usage 35:09 - Where to read more 36:53 - Thank you to the community

Join us as we discuss the brand new @nf-core / EuroFaang pre-print! 🔥 We chat to some of the key authors, covering the background to the paper, the main messages and how EuroFAANG and nf-core have collaborated. 🧬 👩🏻‍🔬