by Stephen Turner
Bioinformatics, computational biology, and data science updates from the field. Occasional posts on programming. <br/><br/><a href="https://blog.stephenturner.us?utm_medium=podcast">blog.stephenturner.us</a>
Language
🇺🇲
Publishing Since
9/11/2024
Email Addresses
1 available
Phone Numbers
0 available
January 15, 2025
Data science educator and professor Stephen Turner examines the impact of AI on education, discussing the opportunities and challenges of using Large Language Models in data science teaching and learning.
December 23, 2024
<p><a target="_blank" href="https://blog.stephenturner.us/p/enlightenment-conservatory">https://blog.stephenturner.us/p/enlightenment-conservatory</a></p><p>I had good intentions to give <a target="_blank" href="https://en.wikipedia.org/wiki/National_Novel_Writing_Month">NaNoWriMo</a> a try this year but didn’t get very far. Instead I gave OpenAI’s <a target="_blank" href="https://chatgpt.com/g/g-lN1gKFnvL-creative-writing-coach">Creative Writing Coach GPT</a> a try for a (very) short story I had in mind, inspired by my frustration trying to access closed-access research articles for a review article I’m preparing. I found it to be an excellent writing coach with specific advice for refining the role of the curators, expanding the perspective of the cultivators, deepening the emotional stakes, clarifying the catalyst for change, polishing the resolution, adding complexity, making the revolt more dramatic, and fine-tuning the language.</p><p>Image created with <a target="_blank" href="https://chatgpt.com/g/g-2fkFE8rbu-dall-e">DALL-E</a>. Voiceover with <a target="_blank" href="https://elevenlabs.io/">ElevenLabs</a>.</p><p>In a world not so different from our own, there existed a fabled garden called the Enlightenment Conservatory. Here, ideas took root as seeds of thought, blooming into radiant flowers of discovery and wisdom. Each blossom held the promise of transformation - groundbreaking theories, profound insights, and untold wonders capable of reshaping the world. It was said that no other garden in existence could rival its beauty or its mystery.</p><p>The Conservatory was tended by a diverse group of dedicated cultivators. These scholars came from all corners of the world, driven by an insatiable curiosity and a passion for nurturing new ideas. They spent their days and nights planting seeds of thought, carefully tending to them, and watching in awe as their conceptual flowers blossomed into vibrant displays of intellectual beauty. Each bloom was unique, representing the culmination of the cultivators' hard work, creativity, and brilliance.</p><p>However, the Enlightenment Conservatory was not open to all. Surrounding it stood a tall, impenetrable wall, erected long ago by a powerful guild known as the Curators. Through a series of cunning maneuvers and ruthless acquisitions, the Curators had gained control over all the smaller intellectual gardens that once existed independently. Now, they ruled the Enlightenment Conservatory with an iron fist.</p><p>The Curators enforced one unyielding rule: entry to the Conservatory came at an outrageous price. Even the cultivators - those who had poured their hearts and minds into planting and nurturing each idea - were not spared. To gaze upon their own intellectual blooms, they too had to pay the Curators' steep toll. Many could only catch fleeting glimpses of their creations from outside the towering walls, denied the chance to savor the fruits of their labor. Their brilliance was trapped behind gates they could never afford to open.</p><p>The Enlightenment Conservatory was meant to be a place where people from all walks of life could come to marvel at the wonders of human thought and insight, where ideas could be shared freely and openly. But under the Curators' rule, it became a bastion of exclusivity. Only the wealthiest patrons and members of the most prestigious institutions could afford to enter and enjoy the intellectual bounty within. These privileged few would stroll through the Conservatory, plucking ideas at will, while the majority remained outside the walls, unable to access the knowledge and insights that had been so carefully cultivated.</p><p>The Curators defended their dominion by calling themselves the stewards of the Enlightenment Conservatory. They claimed their strict oversight was essential to protect the garden from mediocrity, ensuring only the most refined and worthy ideas took root. Without their watchful gaze, they warned, the Conservatory would drown in a sea of weeds, its beauty choked by chaos. But the cultivators saw through the façade. They knew the Curators tended nothing; they merely harvested the fruits of others’ labor while the true blooms of genius often went unnoticed, left to wither in the shadows.</p><p>They knew that the Curators did little to actually care for the Conservatory. The intellectual blooms within its walls were almost always unchanged from the moment they had been planted. The Curators did not prune, water, or tend to the flowers of thought; they simply collected fees and claimed ownership of every bloom. Worse still, they often overlooked some of the most extraordinary ideas, leaving them to wither and die, while promoting others simply because they had been paid to do so.</p><p>But for all the Curators' lofty claims, the Enlightenment Conservatory began to wither. Its once-thriving ecosystem of ideas grew barren, choked by exclusion. Young cultivators from distant lands - those with the boldest, freshest seeds of thought - were turned away, unable to pay the Curators' crushing fees. Some gave up entirely, their unplanted ideas fading like dreams forgotten at dawn. Others tried to nurture their seeds in secret, but without the support of the Conservatory, their efforts bore no fruit. The world would never know the brilliance that had been lost, and the cultivators could only watch as the garden they loved fell into quiet decline.</p><p>The cultivators' frustration grew into a quiet despair. They had poured their souls into planting seeds of thought, nurturing them with endless care, only to see their work imprisoned behind walls they could not afford to scale. What use was a garden of wisdom if it bloomed in the dark, unseen and unshared? They began to speak out, calling for change. They envisioned an Conservatory where all could enter freely, where the flowers of knowledge and insight could be shared by everyone, regardless of wealth or status. They dreamed of an intellectual paradise that truly reflected the diversity and richness of the world's ideas, unencumbered by the greed and control of the Curators.</p><p>As the cries for change swelled, a few bold cultivators decided they could wait no longer. They slipped beyond the Conservatory's walls and began planting their seeds of thought in the wild, in open fields where anyone - rich or poor, learned or curious - could come and marvel. These free gardens burst into dazzling bloom, spilling over with ideas as vibrant and diverse as the people who tended them. The movement spread like wildfire, and as more cultivators turned away from the Conservatory, the Curators panicked. They scrambled to suppress the rebellion, but it was too late. The walls that had stood for centuries began to crack.</p><p>In time, the Enlightenment Conservatory was no longer the sole sanctuary of wisdom. The walls that had once loomed so high crumbled to dust as people discovered they didn't need gates to access the beauty of knowledge. All around, new gardens flourished, each more diverse and vibrant than the last. The Conservatory itself, no longer shrouded in exclusivity, was reborn as a shared space for all. Its paths teemed with visitors, its flowers of insight blooming brighter than ever in the sunlight of collaboration and open exchange. At last, the cultivators' dream had come to life: a world where ideas could roam free, taking root wherever they were needed most.</p><p>And so, the Enlightenment Conservatory was transformed. No longer a place of exclusion, it became a symbol of what could be achieved when knowledge, discovery, and insight were shared freely and openly, for the benefit of all. The cultivators continued their work, more inspired than ever, knowing that their intellectual blooms would flourish in a world where everyone could enjoy them, without barriers, without walls.</p><p></p><p></p> <br/><br/>This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit <a href="https://blog.stephenturner.us?utm_medium=podcast&utm_campaign=CTA_1">blog.stephenturner.us</a>
December 20, 2024
<p><a target="_blank" href="https://blog.stephenturner.us/p/weekly-recap-dec-2024-part-3">https://blog.stephenturner.us/p/weekly-recap-dec-2024-part-3</a></p><p>This week’s recap highlights the Evo model for sequence modeling and design, biomedical discovery with AI agents, improving bioinformatics software quality through teamwork, a new tool from Brent Pedersen and Aaron Quinlan (vcfexpress) for filtering and formatting VCFs with Lua expressions, a new paper about the NHGRI-EBI GWAS Catalog, and a review paper on designing and engineering synthetic genomes.</p><p>Others that caught my attention include a new foundation model for scRNA-seq, a web-based platform for reference-based analysis of single-cell datasets, an AI system for learning how to run transcript assemblers, ATAC-seq QC and filtering, metagenome binning using bi-modal variational autoencoders, analyses of outbreak genomic data using split k-mer analysis, a review on Denisovan introgression events in modern humans, T2T assembly by preserving contained reads, and a commentary on AI readiness in biomedical data.</p><p>Audio generated with NotebookLM.</p><p></p><p>Subscribe to Paired Ends (free) to get summaries like this delivered to your e-mail.</p><p></p><p>Deep dive</p><p>Sequence modeling and design from molecular to genome scale with Evo</p><p><strong>Paper</strong>: Nguyen et al., "Sequence modeling and design from molecular to genome scale with Evo," Science, 2024. <a target="_blank" href="https://doi.org/10.1126/science.ado9336">https://doi.org/10.1126/science.ado9336</a>.</p><p>Before getting to this new paper from the Arc Institute, there’s also a Perspective paper published in the same issue, providing a very short introduction that’s also worth reading (“<a target="_blank" href="https://www.science.org/doi/10.1126/science.adt3007">Learning the language of DNA</a>”).</p><p><strong>TL;DR</strong>: This study introduces Evo, a groundbreaking genomic foundation model that learns complex biological interactions at single-nucleotide resolution across DNA, RNA, and protein levels. This model, trained on a massive set of prokaryotic and phage genomes, can predict how variations in DNA affect functions across regulatory, coding, and noncoding RNA regions. The paper and the Perspective paper above emphasize the innovative use of the StripedHyena architecture, which enables Evo to handle large-scale genomic contexts efficiently, setting a precedent for future advancements in genome-scale predictive modeling and synthetic biology.</p><p><strong>Summary</strong>: The authors present Evo, a 7-billion-parameter language model trained on prokaryotic and phage genomes, designed to capture information at nucleotide-level resolution over long genomic sequences. Evo surpasses previous models by excelling in zero-shot function prediction tasks across different biological modalities (DNA, RNA, protein) and can generate functional biological systems like CRISPR-Cas complexes and transposons. It leverages advanced deep signal processing with the StripedHyena architecture to address limitations faced by transformer-based models, allowing it to learn dependencies across vast genomic regions. Evo's training was validated through experimental testing, including the synthesis of novel functional proteins and genome-scale sequence design, underscoring its potential to transform genetic engineering and synthetic biology.</p><p><strong>Methodological highlights</strong>:</p><p>* <strong>Architecture</strong>: Utilized the StripedHyena, a hybrid attention-convolutional architecture, for efficient long-sequence processing at nucleotide-level resolution.</p><p>* <strong>Training</strong>: Conducted on 2.7 million genomes, with a maximum context length of 131 kilobases.</p><p>* <strong>Applications</strong>: Zero-shot predictions in mutation effects on fitness, and generation of operons, CRISPR systems, and large genomic sequences.</p><p>* <strong>Code and models</strong>: Open source (Apache license) and available at <a target="_blank" href="https://github.com/evo-design/evo">https://github.com/evo-design/evo</a>.</p><p>Empowering biomedical discovery with AI agents</p><p><strong>Paper</strong>: Gao et al., "Empowering biomedical discovery with AI agents," Cell, 2024. <a target="_blank" href="https://doi.org/10.1016/j.cell.2024.09.022">https://doi.org/10.1016/j.cell.2024.09.022</a>.</p><p>I’ve covered AI agents for bioinformatics in the highlights sections of previous weekly recaps (e.g., <a target="_blank" href="https://blog.stephenturner.us/i/149172883/biomania-simplifying-bioinformatics-data-analysis-through-conversation">BioMANIA</a> and <a target="_blank" href="https://blog.stephenturner.us/i/150024199/an-ai-agent-for-fully-automated-multi-omic-analyses">AutoBA</a>). This is an interesting, if speculative, look into the present and future of agentic AI in life sciences research.</p><p><strong>TL;DR</strong>: This perspective paper discusses the potential of AI agents to transform biomedical research by acting as "AI scientists," capable of hypothesis generation, planning, and iterative learning, thus bridging human expertise and machine capabilities.</p><p><strong>Summary</strong>: The authors outline a future in which AI agents, equipped with advanced reasoning, memory, and perception capabilities, assist in biomedical discovery by combining large language models (LLMs) with specialized machine learning tools and experimental platforms. Unlike traditional models, these AI agents could break down complex scientific problems, run experiments autonomously, and propose novel hypotheses, while incorporating feedback to improve over time. This vision extends AI's role from mere data analysis to active participation in hypothesis-driven research, promising advances in areas such as virtual cell simulation, genetic editing, and new drug development.</p><p><strong>Key ideas</strong>:</p><p>* <strong>Modular AI system</strong>: Integration of LLMs, ML tools, and experimental platforms to function as collaborative systems capable of reasoning and learning.</p><p>* <strong>Adaptive learning</strong>: Agents dynamically incorporate new biological data, enhancing their predictive and hypothesis-generating capabilities.</p><p>* <strong>Skeptical learning</strong>: AI agents analyze and identify gaps in their own knowledge to refine their approaches, mimicking human scientific inquiry.</p><p>Improving bioinformatics software quality through teamwork</p><p><strong>Paper</strong>: Ferenc et al., "Improving bioinformatics software quality through teamwork," Bioinformatics, 2024. <a target="_blank" href="https://doi.org/10.1093/bioinformatics/btae632">https://doi.org/10.1093/bioinformatics/btae632</a>.</p><p>One of the things this paper argues for is implementing code review. I used to work at a consulting firm, and I started a weekly code review session with me and my two teammates. In addition to improving code quality, it also increased the <a target="_blank" href="https://en.wikipedia.org/wiki/Bus_factor">bus factor</a> on a critical piece of software to n>1. I had a hard time scaling this. As my team grew from two to ~12, our weekly code review session turned into more of a regular standup-style what are you doing, what are you struggling with, etc., with less emphasis on code. I think the better approach would have been to make the larger meeting less frequent or async while holding smaller focused code review sessions with fewer people. On the other hand, <a target="_blank" href="https://blog.stephenturner.us/p/nextflow-summit-barcelona-2024">I recently attended the nf-core hackathon</a> in Barcelona where >140 developers came together to work on Nextflow pipelines, and I thought it was wildly successful.</p><p><strong>TL;DR</strong>: This paper argues that the quality of bioinformatics software can be greatly enhanced through collaborative efforts within research groups, proposing the adoption of software engineering practices such as regular code reviews, resource sharing, and seminars.</p><p><strong>Summary</strong>: This paper argues that bioinformatics software often suffers from inadequate quality standards due to individualistic development practices prevalent in academia. To bridge this gap, they recommend fostering teamwork and collective learning through structured activities such as code reviews and software quality seminars. The paper provides examples from the authors’ own experience at the Centre for Molecular Medicine Norway, where a community-driven approach led to improved coding skills, better code maintainability, and enhanced collaborative potential. This approach ensures researchers maintain ownership of their projects while leveraging the benefits of shared knowledge and collective feedback.</p><p><strong>Highlights</strong>:</p><p>* <strong>Structured teamwork</strong>: Adoption of collaborative practices like code review sessions and quality seminars to improve software development culture.</p><p>* <strong>Knowledge sharing</strong>: Emphasis on resource sharing to minimize redundant efforts and increase efficiency.</p><p>* <strong>Community building</strong>: Cultivating a supportive environment that allows for skill-building across the team.</p><p>* <strong>Resource website</strong>: The authors provide practical guidance and tools for fostering collaborative software development, accessible at <a target="_blank" href="https://ferenckata.github.io/ImprovingSoftwareTogether.github.io/">https://ferenckata.github.io/ImprovingSoftwareTogether.github.io/</a>.</p><p>Vcfexpress: flexible, rapid user-expressions to filter and format VCFs</p><p><strong>Paper</strong>: Brent Pedersen and Aaron Quinlan, "Vcfexpress: flexible, rapid user-expressions to filter and format VCFs," Bioinformatics, 2024. <a target="_blank" href="https://doi.org/10.1101/2024.11.05.622129">10.1101/2024.11.05.622129</a>.</p><p>On GitHub I “follow” both <a target="_blank" href="https://github.com/brentp">Brent</a> and <a target="_blank" href="https://github.com/arq5x">Aaron</a> so I get notifications whenever either of them publish a new repo. Brent has published many little utilities that improve a bioinformatician’s quality of life (<a target="_blank" href="https://github.com/brentp/mosdepth">mosdepth</a>, <a target="_blank" href="https://github.com/brentp/somalier">somalier</a>, <a target="_blank" href="https://github.com/brentp/vcfanno">vcfanno</a>, <a target="_blank" href="https://github.com/brentp/smoove">smoove</a>, to name a few).</p><p><strong>TL;DR</strong>: Vcfexpress is a new tool for filtering and formatting Variant Call Format (VCF) files that offers high performance and flexibility through user-defined expressions in the Lua programming language, rivaling BCFTools in speed but with extended functionality.</p><p><strong>Summary</strong>: The paper introduces <strong>vcfexpress</strong>, a powerful new tool designed to efficiently filter and format VCF and BCF files using Lua-based user expressions. Implemented in the Rust programming language, vcfexpress supports advanced customization that enables users to apply detailed filtering logic, add new annotations, and format output in various file types like BED and BEDGRAPH. It stands out by balancing speed and versatility, matching BCFTools in performance while surpassing it in analytical customization. Vcfexpress can handle complex tasks such as parsing fields from SnpEff and VEP annotations, providing significant utility for high-throughput genomic analysis.</p><p><strong>Methodological highlights</strong>:</p><p>* <strong>Lua integration</strong>: Unique support for Lua scripting enables precise filtering and flexible output formatting.</p><p>* <strong>High performance</strong>: Comparable in speed to BCFTools, yet offers additional, customizable logic.</p><p>* <strong>Template output</strong>: Allows specification of output formats beyond VCF/BCF, such as BED files.</p><p>* <strong>Code availability</strong>: On GitHub at <a target="_blank" href="https://github.com/brentp/vcfexpress">https://github.com/brentp/vcfexpress</a>. Permissively licensed (MIT).</p><p>The NHGRI-EBI GWAS Catalog: standards for reusability, sustainability and diversity</p><p><strong>Paper:</strong> Cerezo M et al., “The NHGRI-EBI GWAS Catalog: standards for reusability, sustainability and diversity”, bioRxiv 2024. <a target="_blank" href="https://doi.org/10.1101/2024.10.23.619767">https://doi.org/10.1101/2024.10.23.619767</a>.</p><p><strong>TL;DR:</strong> The NHGRI-EBI GWAS Catalog (<a target="_blank" href="https://www.ebi.ac.uk/gwas/">https://www.ebi.ac.uk/gwas/</a>) has implemented new standards and tools for GWAS summary statistics data submission and harmonization, improving data reusability and interoperability. The Catalog now contains over 625,000 curated SNP-trait associations and 85,000 full summary statistics datasets, with significant growth in molecular quantitative trait studies. The paper highlights important updates in data content, user interface improvements, and thoughtful handling of population descriptors.</p><p><strong>Summary:</strong> The GWAS Catalog serves as the largest public repository for FAIR GWAS data, containing over 625,000 curated SNP-trait associations from nearly 7,000 publications. The paper describes major improvements including implementation of the GWAS-SSF standard format for summary statistics, enhanced data harmonization pipelines, and improved handling of molecular quantitative trait studies. The authors address critical challenges in standardizing data submission and population descriptors while maintaining data interoperability. The Catalog has seen significant growth, particularly in molecular quantitative trait studies (82% of additions in 2023), and has implemented UI improvements to handle large-scale datasets efficiently. The work emphasizes the importance of careful population descriptor usage and the need for greater diversity in GWAS studies.</p><p><strong>Methodological highlights:</strong></p><p>* Developed and implemented GWAS-SSF standard format defining mandatory fields (chromosome, position, alleles, effect sizes, etc.) and recommended fields for summary statistics.</p><p>* Enhanced harmonization pipeline with 75% reduction in processing time through improved computational efficiency and workflow management. This pipeline is Nextflow-based (see figure S1, copied below).</p><p>* Implemented new trait mapping system using Ontology of Biological Attributes for molecular quantitative traits, enabling better integration with chemistry and protein databases.</p><p><strong>New tools, data, and resources:</strong></p><p>* GWAS Catalog web interface: <a target="_blank" href="https://www.ebi.ac.uk/gwas/">https://www.ebi.ac.uk/gwas/</a>.</p><p>* Project GitHub repository: <a target="_blank" href="https://github.com/EBISPOT/goci">https://github.com/EBISPOT/goci</a> (Apache 2.0 license).</p><p>* SSF-morph tool for format conversion: <a target="_blank" href="https://ebispot.github.io/gwas-sumstats-tools-ssf-morph/">https://ebispot.github.io/gwas-sumstats-tools-ssf-morph/</a>.</p><p>* Summary statistics API: <a target="_blank" href="http://www.ebi.ac.uk/gwas/summary-statistics/api/">http://www.ebi.ac.uk/gwas/summary-statistics/api/</a>.</p><p>* Data availability: All curated data available through web interface and programmatic access. Summary statistics submitted after March 2021 available under CC0 license.</p><p>Review: The design and engineering of synthetic genomes</p><p><strong>Paper:</strong> James, J. S., et al. "The design and engineering of synthetic genomes" in Nature Reviews Genetics, 2024. <a target="_blank" href="https://doi.org/10.1038/s41576-024-00786-y">https://doi.org/10.1038/s41576-024-00786-y</a>.</p><p>I spend a lot of time thinking about designing large synthetic DNA constructs — how the bioinformatics/design side informs the wet lab processes needed to create these. This was a great review on the history, applications, and practice of synthesizing genes and genomes.</p><p><strong>TL;DR:</strong> This comprehensive review examines how synthetic genomics has evolved from early viral genome synthesis to complex bacterial and eukaryotic genomes. The field is moving from proof-of-concept projects to practical applications in medicine, agriculture, and industry, driven by advances in DNA synthesis, assembly methods, and computational design tools.</p><p><strong>Summary:</strong> The review traces synthetic genomics from early milestones like poliovirus synthesis to recent achievements in building complete synthetic yeast chromosomes. While construction capabilities have grown impressively, our ability to predict how genome modifications will function lags behind. The authors highlight how computational tools, artificial intelligence, and improved DNA synthesis technologies are helping bridge this gap. They explore key applications including viral vaccines, engineered microorganisms for bioproduction, and synthetic chromosomes for various applications including xenotransplantation and enhanced crops. A major theme is the transition from demonstrating technical feasibility to practical real-world applications.</p><p><strong>Highlights:</strong></p><p>* Introduction of new approaches for genome design including template-guided design, genetic code alteration, and synthetic circuit-based design to build genomes with novel functions.</p><p>* Development of integrated computer-aided design and manufacturing platforms that combine sequence design, functional prediction, and automated assembly planning.</p><p>* Advances in hierarchical genome assembly methods that enable parallel construction and testing of multiple synthetic genome sections.</p><p>Other papers of note</p><p>* scLong: A Billion-Parameter Foundation Model for Capturing Long-Range Gene Context in Single-Cell Transcriptomics <a target="_blank" href="https://www.biorxiv.org/content/10.1101/2024.11.09.622759v1">https://www.biorxiv.org/content/10.1101/2024.11.09.622759v1</a></p><p>* <a target="_blank" href="https://www.archmap.bio">archmap.bio</a>: A web-based platform for reference-based analysis of single-cell datasets <a target="_blank" href="https://www.biorxiv.org/content/10.1101/2024.09.19.613883v1">https://www.biorxiv.org/content/10.1101/2024.09.19.613883v1</a></p><p>* Data-driven AI system for learning how to run transcript assemblers <a target="_blank" href="https://www.biorxiv.org/content/10.1101/2024.01.25.577290v2">https://www.biorxiv.org/content/10.1101/2024.01.25.577290v2</a></p><p>* Quaqc: Efficient and quick ATAC-seq quality control and filtering <a target="_blank" href="https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btae649/7852831">https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btae649/7852831</a></p><p>* Binning meets taxonomy: TaxVAMB improves metagenome binning using bi-modal variational autoencoder <a target="_blank" href="https://www.biorxiv.org/content/10.1101/2024.10.25.620172v1">https://www.biorxiv.org/content/10.1101/2024.10.25.620172v1</a></p><p>* Seamless, rapid, and accurate analyses of outbreak genomic data using split k-mer analysis <a target="_blank" href="https://genome.cshlp.org/content/34/10/1661.full">https://genome.cshlp.org/content/34/10/1661.full</a> </p><p>* Review: A history of multiple Denisovan introgression events in modern humans <a target="_blank" href="https://www.nature.com/articles/s41588-024-01960-y">https://www.nature.com/articles/s41588-024-01960-y</a> </p><p>* Telomere-to-telomere assembly by preserving contained reads <a target="_blank" href="https://genome.cshlp.org/content/early/2024/11/04/gr.279311.124.short">https://genome.cshlp.org/content/early/2024/11/04/gr.279311.124.short</a> </p><p>* AI-readiness for Biomedical Data: Bridge2AI Recommendations <a target="_blank" href="https://www.biorxiv.org/content/10.1101/2024.10.23.619844v2">https://www.biorxiv.org/content/10.1101/2024.10.23.619844v2</a> </p><p></p><p>Subscribe to Paired Ends (free) to get summaries like this delivered to your e-mail.</p><p></p><p></p> <br/><br/>This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit <a href="https://blog.stephenturner.us?utm_medium=podcast&utm_campaign=CTA_1">blog.stephenturner.us</a>
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at [email protected] for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.