Overcoming Data Fragmentation in Healthcare with Vera Mucaj

Data in Biotech

#Science #Tech #Biology #CorrDyn

33:58

In this episode, we delve into the concept of being "qualified" in the workplace, examining who gets labeled as such, who doesn't, and the underlying reasons. We explore "competency checking"—the practice of scrutinizing individuals' abilities—and how it disproportionately affects underrepresented groups, often going unnoticed or unchallenged. Our discussion aims to redefine qualifications in a fair, equitable, and actionable manner. Our guest, Shari Dunn , is an accomplished journalist, former attorney, news anchor, CEO, university professor, and sought-after speaker. She has been recognized as Executive of the Year and a Woman of Influence, with her work appearing in Fortune Magazine, The Wall Street Journal, Ad Age, and more. Her new book, Qualified: How Competency Checking and Race Collide at Work , unpacks what it truly means to be deserving and capable—and why systemic barriers, not personal deficits, are often the real problem. Her insights challenge the narratives that hold so many of us back and offer practical solutions for building a more equitable future. Together, we can build workplaces and communities that don’t just reflect the world we live in, but the one we want to create. A world where being qualified is about recognizing the talent and potential that’s been overlooked for far too long. It’s not just about getting a seat at the table—it’s about building an entirely new table, one designed with space for all of us. Connect with Our Guest Shari Dunn Website& Book - Qualified: https://thesharidunn.com LI: https://www.linkedin.com/today/author/sharidunn TikTok: https://www.tiktok.com/@thesharidunn Related Podcast Episodes: How To Build Emotionally Mature Leaders with Dr. Christie Smith | 272 Holding It Together: Women As America's Safety Net with Jessica Calarco | 215 How To Defy Expectations with Dr. Sunita Sah | 271 Share the Love: If you found this episode insightful, please share it with a friend, tag us on social media, and leave a review on your favorite podcast platform! 🔗 Subscribe & Review: Apple Podcasts | Spotify | Amazon Music…

about a year ago 45:54

MP3•Episode home

This week, we’re delighted to be joined by Vera Mucaj, Chief Scientific Officer at Datavant, a data logistics company for healthcare.

During the interview, Vera shares how the organization helps companies overcome issues of data fragmentation and availability, which ultimately leads to better decision-making in healthcare, the importance of connecting clinical trial data with real-world data to improve research outcomes and the challenges of semantic interoperability in data sets.

Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in life sciences.

Discussed:

[1:06] Vera introduces herself, explains her role, and explains what drove her to join the scientific field.

[4:00] Vera outlines the challenges that Datavant customers face in the acquisition and sharing of medical data.

[8:49] Vera unpacks the role Datavant plays in enabling healthcare organizations to produce and consume data to answer important scientific questions.

[12:21] Vera addresses the problem of security around data assets and how the company helps producers tackle the risk of the potential de-identification of sensitive patient data.

[15:27] Vera explains the most common use cases of the Datavant platform and the value that can be unlocked by consumers of the platform.

[22:10] Vera outlines Datavant's business model.

[27:06] Vera talks about how Datavant is leveraging AI to generate, analyze and create imputations of data sets.

[31:09] Vera discusses the regulatory and cultural barriers to making data available in healthcare.

[38:53] Vera shares her thoughts on semantic interoperability between data sets.

[44:31] Vera shares the resources that she follows to better understand the work of Datavant.

---

If you’re a biotech company struggling to unlock a data challenge, CorrDyn can help.

Whether you need to supplement existing technology teams with specialist expertise or launch a data program that lays the groundwork for future internal hires, you can partner with Corrdyn to unlock the potential of your business data - today.

Visit connect.corrdyn.com/biotech to learn more.

39 episodes

Data in Biotech

Overcoming Data Fragmentation in Healthcare with Vera Mucaj

Data in Biotech

published about a year ago

MP3•Episode home

This week, we’re delighted to be joined by Vera Mucaj, Chief Scientific Officer at Datavant, a data logistics company for healthcare.

Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in life sciences.

Discussed:

[1:06] Vera introduces herself, explains her role, and explains what drove her to join the scientific field.

[4:00] Vera outlines the challenges that Datavant customers face in the acquisition and sharing of medical data.

[8:49] Vera unpacks the role Datavant plays in enabling healthcare organizations to produce and consume data to answer important scientific questions.

[12:21] Vera addresses the problem of security around data assets and how the company helps producers tackle the risk of the potential de-identification of sensitive patient data.

[15:27] Vera explains the most common use cases of the Datavant platform and the value that can be unlocked by consumers of the platform.

[22:10] Vera outlines Datavant's business model.

[27:06] Vera talks about how Datavant is leveraging AI to generate, analyze and create imputations of data sets.

[31:09] Vera discusses the regulatory and cultural barriers to making data available in healthcare.

[38:53] Vera shares her thoughts on semantic interoperability between data sets.

[44:31] Vera shares the resources that she follows to better understand the work of Datavant.

---

If you’re a biotech company struggling to unlock a data challenge, CorrDyn can help.

Visit connect.corrdyn.com/biotech to learn more.

39 episodes

#Science #Tech #Biology #CorrDyn

All episodes

Data in Biotech

1
Organoids and Active Learning for Chronic Disease with Naren Tallapragada 50:25

7 days ago50:25

50:25

In this episode of Data In Biotech, Ross Katz interviews Naren Tallapragada, CEO and Co-founder of Tessel Bio, about his background in electrical engineering and physics and how personal circumstances led to him pivoting his focus to enter biotech and start Tessel Bio. Naren breaks down Tessel Bio’s unique approach to drug discovery, which involves "reverse engineering" chronic diseases. Instead of starting with a potential drug and testing its effects, they begin with a clear picture of the disease itself—specifically, how it appears and behaves in the body. A key part of their method is using human organoids—tiny, lab-grown versions of human tissues—to closely replicate real diseases and see how different treatments interact with them. This “small data” approach is made substantially more efficient with the addition of active learning. Join us for a fascinating conversation about Tessel Bio’s approach to finding cures for chronic diseases that impact hundreds of thousands of people every day. What You'll Learn in This Episode: Naren’s journey into biotech and personal motivation Understanding Tessel Bio's approach to drug discovery The role of organoids in disease modeling Data gathering and target identification strategies Active learning in drug discovery at Tessel Bio Connect with Our Guest: Sponsor: CorrDyn, a data consultancy Find out more about Tessel Bio Connect with Naren on LinkedIn Connect with Us: Follow the podcast for more insightful discussions on the latest in biotech and data science. Subscribe and leave a review if you enjoyed this episode!…

Data in Biotech

1
How Alex Junge from amass is Speeding Up Scientific Breakthroughs with AI 52:25

21 days ago52:25

52:25

In this episode of the Data and Biotech Podcast , host Ross Katz sits down with Alexander Junge, Co-Founder and CTO of amass , to break down how AI is reshaping scientific research in life sciences. Alex walks us through how his platform is creating professional tools for researchers, biotech companies, and venture firms to navigate the (rapidly!) growing breadth and depth of scientific knowledge by leveraging artificial intelligence - and what this will look like in the future. Alex also shares insights into his company’s work with Nordic Bio Ventures and how amass delivers reliability and builds trust in its platform. What You'll Learn in This Episode: What challenges researchers face in formulating questions and retrieving relevant answers from the breadth of scientific knowledge. The importance of design and user experience in life sciences, and how the company adopts a rigorous approach to information retrieval. How amass helps life sciences professionals navigate complex scientific domains by building trust in answers generated by AI. A real-world case study of how amass is assisting Nordic BioVentures a venture firm to build a biotech company. Alex’s predictions for AI's impact on scientific discovery over the next decade. Connect with Our Guest: Sponsor: CorrDyn, a data consultancy Find out more about amass Connect with Alex on LinkedIn Connect with Us: Follow the podcast for more insightful discussions on the latest in biotech and data science. Subscribe and leave a review if you enjoyed this episode!…

Data in Biotech

1
Advancing Therapeutic Design in Gene and Cell Therapy with Dipen Sangurdekar 40:34

30 days ago40:34

40:34

In this episode of Data in Biotech, Ross sits down with Dipen Sangurdekar, VP of Data Sciences at KSQ Therapeutics, to discuss the role of data-driven approaches in therapeutic design and development. The conversation explores the intersection of computational biology, machine learning, and bioinformatics in advancing personalized medicine and improving patient outcomes. Dipen shares his journey in the industry, emphasizing the importance of integrating data science with biological research and the challenges associated with working in the rapidly evolving field of cell therapies. From hypothesis-driven research to leveraging multimodal data for actionable insights, this episode explores the nuances of using statistical methods and AI to enhance drug development. Key Takeaways: Successful data science in therapeutics requires a deep understanding of both statistical methods and biological processes. High-dimensional but low-sample-size data demands a guided hypothesis-driven approach to avoid false positives. Data integration and collaboration between computational and biological teams are critical for generating meaningful insights. Emerging AI and machine learning tools are enhancing productivity but must be carefully applied in therapeutic research. Picking a problem you’re passionate about and going deep into it is crucial for long-term success in the field. Connect with Our Guest: Sponsor: CorrDyn, a data consultancy Find out more about KSQ Therapeutics Connect with Dipen on LinkedIn Connect with Us: Follow the podcast for more insightful discussions on the latest in biotech and data science. Subscribe and leave a review if you enjoyed this episode!…

Data in Biotech

1
Democratizing Therapeutic Discovery for Neglected Diseases using AI with Timothy Jenkins of DTU Bioengineering 50:39

7 weeks ago50:39

50:39

This week on Data in Biotech, we welcome Timothy Jenkins, the Head of Data Science and Associate Professor at DTU Bioengineering, a leading scientific community dedicated to advancing areas of biotechnology, food technology, and health through innovative teaching and research. Timothy starts the conversation by walking us through his background and early career beginnings, from the first time he expressed interest in zoology and venomous snakes to now leading a research group focused on AI-guided drug discovery for snake antivenom. He and our host, Ross Katz, dive into one of DTU’s most exciting recent publications about "de novo" designed proteins to neutralize lethal snake venom toxins. Inspired by Nobel Prize winner David Baker’s groundbreaking paper and in collaboration with the Baker Lab on computational design methodology, this project holds great promise in therapeutic discovery and drug development. Tim explains how computational protein design and protein structure prediction are revolutionizing his field, highlighting compelling examples and milestones from his research on antivenom. He also provides an overview of the process used to discover new antivenoms, including the sourcing of biological data, model training, and integration of experimental feedback. Finally, we get Tim’s perspective on the future of AI-powered therapeutic discovery, and his take on the integration of quantum computing into protein design. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Useful Links Nature - De novo designed proteins neutralize lethal snake venom toxins Timothy’s LinkedIn DTU Bioengineering Website UW Institute for Protein Design “ de novo” designed proteins project Information on Nobel Prize winner David Baker…

Data in Biotech

1
Revolutionizing Drug Discovery with AI: Fred Manby of Iambic Therapeutics 38:19

9 weeks ago38:19

38:19

In this episode, Ross Katz sits down with Fred Manby, Co-Founder and Chief Technology Officer of Iambic Therapeutics, to explore how cutting-edge AI technologies are reshaping the landscape of drug discovery. From building advanced machine learning platforms to designing user-friendly interfaces for scientists, Fred shares insights into the company’s approach to tackling some of the biggest challenges in biotech. Fred dives into the unique capabilities of Iambic’s Enchant multi-modal transformer model, its differentiation from other biological foundation models, and the importance of aligning model architecture with data creation and acquisition in modern drug discovery. We also discuss Iambic’s data-driven approach to developing oncology drugs, the exciting possibilities of incorporating new modalities like imaging, and the recent breakthroughs in protein-ligand structure prediction with NeuralPLexer3. Highlights: Enchant Multi-Modal Transformer Model : How it systematically surpasses state-of-the-art molecular AI technologies. Uncertainty Quantification : The role of probabilities and predictions in streamlining drug discovery. Interface Design for Scientists : Iambic’s approach to integration between AI platforms and experimental workflows. Connect with Our Guest: Sponsor: CorrDyn, a data consultancy Find out more about Iambic’s work on their website Connect with Fred Manby on LinkedIn…

Data in Biotech

1
Unlocking the Power of AI in Microscopy with Ilya Goldberg and Reese Findley 47:32

13 weeks ago47:32

47:32

In this episode of Data in Biotech, Ross Katz explores the transformative role of AI in microscopic imaging and life sciences with Ilya Goldberg, Chief Science Officer, and Reese Findley, an AI Data Scientist at ViQi. They discuss the cutting-edge applications of AI in automating high-content screening (HCS), enabling more efficient drug discovery, and unraveling complex biological processes. From streamlining time-course analysis to detecting off-target effects in drug compounds, ViQi’s tools are revolutionizing how scientists approach image-based data. Key Highlights: How AI-powered "eyes" analyze thousands of microscopy images to identify phenotypic changes. The benefits of using brightfield imaging and live-cell dyes to capture time-course data efficiently. Real-world applications of AutoHCS for high-content screening, including drug efficacy studies, stem cell differentiation tracking, and phenotypic clustering for toxicity detection. Insights into how automation empowers researchers by reducing repetitive tasks and enhancing focus on innovation. The broader implications of AI in medicine, from radiology to pathology, and how it's redefining workflows for specialists. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Learn more about who was featured on the podcast: CorrDyn, an enterprise data specialist that enables excellent companies to make smarter strategic decisions, at www.corrdyn.com ViQi – helping virologists accelerate, automate and simplify infectivity assays: www.viqiai.com Connect with Reese and Ilya on LinkedIn…

Data in Biotech

1
Reflections & Predictions: One Year of Data in Biotech with Ross Katz 39:42

15 weeks ago39:42

39:42

In this episode of Data in Biotech, Ross Katz reflects on what he’s learned from one year of hosting the podcast. Diving deep into the intersection of data science and biotechnology, this episode covers topics like: The need for predictive models in biotech that are grounded in real-world experimentation. The challenges of biases in model evaluation and designing experiments that maximize collecting information for iterative improvements. The balance between leveraging computational methods and validating insights through experimental data. As we look to 2025, Ross shares his vision of the emerging democratization of the biotech data ecosystem by making domain knowledge, datasets and tools more accessible. He discusses the possibility of a future where decentralized collaboration, akin to open-source software projects, can tackle specific diseases through computational pipelines and cloud labs, enabling experiments without the need for costly infrastructure. Or where emerging trends like foundation models and ensemble modeling in drug discovery, cell and gene therapy, and the role of new data from advanced imaging and assay technologies can be unlocked to create novel insights. Finally, he invites regular listeners to contribute ideas, guest suggestions and resources as we build community and embrace more curiosity and openness. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences.…

Data in Biotech

1
From Moderna to Dash Bio - Revolutionizing Drug Development with Dave Johnson 32:54

19 weeks ago32:54

32:54

In this episode of Data in Biotech, Ross Katz sits down with Dave Johnson, CEO and co-founder of Dash Bio, a next-gen drug development services company with a mission to revolutionize clinical bioanalysis and streamline drug development. Dave begins the episode by taking us back to the early research days in Moderna, where he helped lay the groundwork for mRNA technology, which later enabled the development of a vaccine for COVID-19 at unprecedented speed. As he explains, this automated work and pre-built systems ultimately played a central role in responding to urgent health challenges. He also shares his firsthand experience of working in a rapidly scaling pharma company, discussing the potential challenges that arose along the way and the lessons he learned to overcome them. Dave then proceeds to highlight the most significant insufficiencies in drug development—particularly the lack of industrialization and standardization. He explains how Dash Bio aims to address these issues, focusing on clinical bioanalysis now and expanding to broader standardization later. The goal is ultimately to develop a more efficient, high-quality end-to-end system and improve the overall efficacy of the drug development process. Finally, Dave and Ross discuss the misconceptions surrounding lab automation and emphasize the need for a shift of perspective within the drug development space. They also touch upon Dave’s vision for the future of Dash Bio, plus his advice for aspiring biotech data leaders eager to contribute to industry transformation. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers: [1:38] Introduction to Dave Johnson and his career journey from Moderna to founding a next-gen drug development company [2:57] Establishing mRNA technology groundwork in Moderna [4:36] The challenges of scaling up COVID-19 vaccine development [7:55] How rapid company growth impacts the organizational structure and engaging models [11:03] The role of AI, automation, and machine learning in drug development [12:45] Addressing the most significant insufficiencies in drug development and potential solutions [16:31] The need for standardization and automation in drug development [18:04] Current focus of Dash Bio on clinical bioanalysis [19:37] The misconceptions surrounding lab automation and the need for a shift of perspective within the drug development space [22:33] Dave’s vision for the future of Dash Bio and streamlining drug development [25:16] The current state of lab automation [27:41] The role of experimentation in Dash Bio's approach [29:47] Advice for aspiring data scientists and leaders in the biotech sector Useful Links Dave Johnson LinkedIn Dash Bio Website…

Data in Biotech

1
Chitrang Dave on Harnessing Real-Time Data to Transform MedTech and Healthcare 29:10

21 weeks ago29:10

29:10

This week, Chitrang Dave, Global Head of Enterprise Data & Analytics at Edwards Lifesciences, joins us to discuss the transformative power of real-time data, AI, and collaboration in medical device manufacturing and support. He and host, Ross Katz, dive into how real-time data from IoT devices is reshaping quality assurance in medtech and what the future holds for medtech as big tech players like Apple and Meta enter the healthcare arena. Together, they discuss everything from AI-powered patient identification to the integration of consumer wearables with FDA-approved medical devices. Tune in to hear how collaboration, innovation, and cutting-edge technology are improving patient outcomes and revolutionizing healthcare. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers [01:36] Chitrang shares the experience that led him to work at leading data and analytics organizations and what work there is to be done [04:09] Chitrang highlights the role of IoT devices in medical device manufacturing, where real-time data can drive automation and improve quality assurance [06:25] What is driving innovation right now in research and development, and how companies like Apple are disrupting the medical device space [09:23] Chitrang talks about how connectivity in devices and the expectation of the user to be able to use an intuitive interface are evolving into more real-time medical device technology [11:47] The importance of keeping patient data private between the patient and the practitioner while using anonymized data to create solutions and identify patterns in health [13:25] Using data to create a complete picture of the patient in order to make their life easier [14:20] Chitrang discusses the challenge of manufacturing medical devices when there are issues with raw materials [16:30] Chitrang discusses the potential for automation for real-time data in manufacturing [19:17] Ross and Chitrang discuss the value of having comprehensive data to personalize treatments and ensure timely responses, especially for scenarios where early detection of Alzheimer’s can save trillions of dollars [21:27] Chitrang mentions significant collaborations, such as the Cancer AI Alliance, where tech giants like AWS, Microsoft, NVIDIA, and Deloitte are working together to address critical problems in healthcare [27:10] How real-time data from medical devices could improve patient outcomes, stakeholder coordination and future trends [28:29] Closing thoughts and where to find Chitrang Dave online Download CorrDyn’s latest white paper on “Using Machine Learning to Implement Mid-Manufacture Quality Control in the Biotech Sector.” Find the white paper online at: https://connect.corrdyn.com/biotech-ml…

Data in Biotech

1
Automating Bioprocessing to Speed up Workflows with Invert 36:41

23 weeks ago36:41

36:41

This week on Data in Biotech, we’re joined by Martin Permin, the co-founder of Invert, a company that builds software that automates bioprocessing. Martin talks us through his own unique journey into biotech - starting from a role at Airbnb - through to co-founding Invert. Invert helps users grab data from their instruments, map out their individual processes, clean up the data for analysis, and look for ways to speed up the “mundane” data cleaning tasks that often take up the majority of one’s time. With our host, Ross Katz, Martin tells us the statistical problems Invert works to solve for their different types of clients: biologic development labs, full-scale manufacturers, and CDMOs. While they all approach data cleaning and analysis from different directions, Invert can see how clients use the system and look for ways to automate repeated processes to help them save time. They discuss implementing Invert into the Design, Build, Test, Learn Loop and why Invert is invested in reducing how many times one has to go around that loop. Martin explains how his company looks to reduce the risk in tech transfer in both directions, in terms of time and labor. Then, the conversation moves to ML/AI, where Martin tells us how a lot of his customers are finding that the bottlenecks in their processes aren’t where they thought they were, thanks to using Invert for process automation. Finally, Martin gives us his opinions on the future trends around the corner for the biotech industry - and how Invert is preparing themselves and their customers. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers [1:29] Introduction to Martin and his journey into biotech [4:10] Introduction to Invert - the what and why [6:47] How Invert is implemented into a customer’s workflow [11:36] The problems Invert can solve [16:16] Design > build > test > learn… and how Invert facilitates that [20:00] CDMOs and contractors - how Invert works with their different customers [22:15] The use of ML/AI in bio-processing [33:40] Trends in Biotech that will influence Invert over the long-term…

Data in Biotech

1
The Evolution of Genomic Analysis with Sapient 43:15

25 weeks ago43:15

43:15

This week on Data in Biotech, we’re joined by Mo Jain, the Founder and CEO of Sapient, a biomarker discovery organization that enables biopharma sponsors to go beyond the genome to accelerate precision drug development. Mo talks us through his personal journey into the world of science, from school to working in academia to founding his business, Sapient. He explains how and why Sapient first started and the evolution of the high-throughput mass-spectrometry service it provides to the biopharmaceutical sector. Together with our host Ross, they explore the technology that’s allowed scientists to explore one's medical history like never before via metabolome, lipidome, and proteome analysis. They look at how the technology developed to allow data testing to go from running twenty tests per blood sample to twenty thousand . How have Sapient built themselves up to such a renowned status in biopharmaceuticals for large-scale data projects? They discuss Sapient’s process when working with clients on genome projects. We learn about Sapient’s relationship with their clients, how they understand the targets and aims of each project, why they put so much importance on proprietary database management and quality control, and Sapient’s three pillars for high quality data discovery. Finally, Mo takes the opportunity to give us his insights on the future of biomarker discovery and mass-spectrometry technology - and how AI and Machine Learning are leading to enhanced data quality and quantity. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers [1:33] Introduction to Mo Jain, his journey, Genomics, and Sapient’s use of Genomics data to accelerate Medicine and Drug Development [6:50] The types of data generated at Sapient via metabolome, lipidome & proteome, and why that data is generated [12:30] How Sapient generates this data at scale, via specialist mass-spectrometry technology [14:48] The problems Sapient can solve for pharma and biotech companies with this data [21:03] Sapient as a service company: the questions they’re asked by pharmaceutical businesses, why they come to Sapient, and Sapient’s process for answering those questions. [26:23] computational frameworks and data handling side of things, and how the team interact with the client [29:59] Proprietary database development and quality control [35:27] The future of biomarker discovery and mass-spectrometry technology, and how AI and Machine Learning are leading the way at Sapient…

Data in Biotech

1
Transforming Drug Discovery through AI and Single-Cell Multiomics with Cellarity 39:55

28 weeks ago39:55

39:55

This week on Data in Biotech, we are joined by Parul Bordia Doshi, Chief Data Officer at Cellarity, a company that is leveraging data science to challenge traditional approaches to drug discovery. Parul kicks off the conversation by explaining Cellarity’s mission and how it is using generative AI and single-cell multiomics to design therapies that target the entire cellular system, rather than focusing on single molecular targets. She gives insight into the functionality of Cellarity Maps, the company’s cutting-edge visualization tool that maps the progression of disease states and bridges the gap between biologists and computational scientists. Along with host Ross Katz, Parul walks through some of the big challenges facing Chief Data Officers, particularly for biotech organizations with data-centric propositions. She emphasizes the importance of robust data frameworks for validating and standardizing complex data sets, and looks at some of the practical approaches that ensure data scientists can derive the maximum amount of value from all available data. They discuss what data science teams look like within Cellarity, including the unique way the company incorporates human intervention into its processes. Parul also emphasizes the benefits that come through hiring multilingual, multidisciplinary teams and putting a strong focus on collaboration. Finally, we get Parul’s take on the future of data science for drug discovery, plus a look at Cellarity’s ongoing collaboration with Novo Nordisk on the development of novel therapeutics. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers [1:45] Introduction to Parul, her career journey, and Cellarity’s approach to drug discovery. [5:47] The life cycle of data at Cellarity from collection to how it is used by the organization. [7:45] How the Cellarity Maps visualization tool is used to show the progression of disease states [9:05] The role of a Chief Data Officer in aligning an organization’s data strategy with its company mission. [11:46] The benefits of collaboration and multidisciplinary, cross-functional teams to drive innovation. [14:53] Cellarity's end-to-end discovery process; including how it uses generative AI, contrastive learning techniques, and visualization tools. [19:42] The role of humans vs the role of machines in scientific processes. [23:05] Developing and validating models, including goal setting, benchmarking, and the need for collaboration between data teams and ML scientists. [30:58] Generating and managing massive amounts of data, ensuring quality, and maximizing the value extracted. [37:08] The future of data science for drug discovery, including Cellarity’s collaboration with Novo Nordisk to discover and develop a novel treatment for MASH.…

Data in Biotech

1
Using Generative AI to Design New Therapeutic Proteins with Evozyne 40:23

30 weeks ago40:23

40:23

This week on Data in Biotech, Ryan Mork, Director of Data Science at Evozyne, joins host Ross Katz to discuss how data science and machine learning are being used in protein engineering and drug discovery. Ryan explains how Evozyne is utilizing large language models (LLMs) and generative AI (GenAI) to design new biomolecules, training the models with huge volumes of protein and biology data. He walks through the organization’s evolution-based design approach and how it leverages the evolutionary history of protein families. Ross and Ryan dig into the different models being used by Evozyne, including latent variable models and embeddings. They also discuss some of the challenges around testing the functionality of models and the approaches that can be used for evaluation. Alongside the deep dive into data and modeling topics, Ryan also discusses the importance of relationships between the wet lab and data science teams. He emphasizes the need for mutual understanding of each role to ensure the entire organization pulls together towards the same goals. Finally, Ross asks Ryan to opine on the future of GenAI and LLMs for biotechnology and how this area will develop over the next five years. He also finds out more about the R&D roadmap at Evozyne and its plans to play a part in moving GenAI for protein engineering forward. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers [1:24] Introduction to Ryan, his career to date, and the focus of Evozyne. [2:59] How the Evozyne data science team operates and the data sources it utilizes. [4:22] Building models to develop synthetic proteins for therapeutic uses. [9:10] Deciding which proteins to take into the lab for experimental validation. [10:49] Taking an evolution-based design approach to protein engineering. [14:34] Using latent variable models and embeddings to capture evolutionary relationships. [18:01] Evaluating the functionality of generative models and the role of auxiliary models. [24:24] The value of tight coupling and mutual understanding between wet lab and data science teams. [28:07] Evozyne’s approach to developing and testing new data science tools, models, and technologies. [31:35] Predictions for future developments in Generative AI for biotechnology. [33:41] Evozyne’s goal to increase throughput and its planned approach. [39:09] Where to connect with Ryan and keep up to date with news from Evozyne.…

Data in Biotech

1
Balancing Software-Driven Processes and Human Curation to Unlock Genomics Intelligence with Genomenon 40:59

32 weeks ago40:59

40:59

This week on Data in Biotech, Ross is joined by Jonathan Eads, VP of Engineering at genomics intelligence company Genomenon , to discuss how his work supports the company’s mission to make genomic evidence actionable. Jonathan explains his current role leading the teams focused on clinical engineering, curation engineering, platform development and overseeing Genomenon’s data science and AI efforts. He gives insight into how Genomenon’s software works to scan genomics literature and index genetic variants, providing critical evidence-based guidance for those working across biotech, pharmaceutical, and medical disciplines. Jonathan outlines the issues with inconsistent genetic data, variant nomenclature and extracting genetic variants from unstructured text, before explaining how human curators are essential to ensure accuracy of output. Jonathan and Ross discuss the opportunities and limitations that come with using AI and natural language processing (NLP) techniques for genetic variant analysis. Jonathan lays out the process of developing robust validation datasets and fine-tuning AI models to handle issues like syntax anomalies and outlines the need to balance the short-term need for data quality with the long-term goal of advancing the platform’s AI and automation capabilities. We hear notable success stories of how Genomenon’s platform is being used to accelerate variant interpretation, disease diagnosis, and precision medicine development. Finally, Ross gets Jonathan’s take on the future of genomics intelligence, including the potential of end-to-end linkage of information from variants all the way out to patient populations. Data in Biotech is a fortnightly podcast exploring how companies leverage data innovation in the life sciences. Chapter Markers [1:50] Introduction to Jonathan and his academic and career background. [5:14] What Genomenon’s mission to ‘make genomic evidence actionable’ looks like in practice. [14:48] The limitations of how scientists and doctors have historically been able to use literature to understand genetic variants. [16:08] Challenges with nomenclature and indexing and how this impacts on access to information. [18:11] Extracting genetic variants from scientific publications into a structured, searchable index. [22:04] Using a combination of software processes and human curation for accurate research outputs. [24:57] Building high functionality, complex, and accurate software processes to analyze genomic literature. [29:45] Dealing with the challenges of AI and the role of human curators for the accuracy of genetic variant classification. [34:37] Managing the trade-off between short-term needs for improved data and long-term goals for automation and AI development. [38:39] Success stories using the Genomenon platform including making an FDA case and diagnosing rare disease. [41:55] Predictions for future advancements in literature search for genetic variant analysis. [43:21] The potential impact of Genomenon’s acquisition of Jack's Clinical Knowledge Base.…

Data in Biotech

1
Optimizing Allogeneic Cell Therapy Manufacturing with Atara Biotherapeutics 40:00

34 weeks ago40:00