Data in Biotech – Détails, épisodes et analyse

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.

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.

This week, we are pleased to welcome to the Data in Biotech podcast Brendan McCorkle, CEO of SciNote, a cloud-based ELN (Electronic Lab Notebook) with lab inventory, compliance, and team management tools.

In this episode, we discuss how the priorities of ‘Research’ and ‘Development’ differ when it comes to the data they expect and how they use it, and how ELNs can work to support both functions by balancing structure and flexibility. We explore the challenges of developing an ELN that serves the needs and workflows of all stakeholders, making the wider business case for ELNs, and why, in the lab, paper and Excel need to be a thing of the past.

Brendan is upfront about the data challenges faced by biotechs, which do not have one-vendor solutions. He emphasizes the importance of industry collaboration and software vendors’ role in following the principles of FAIR data. We also get his take on the future of ELNs and how they can leverage AI and ML.

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

Chapter Markers

[1:40] Brendan gives a whistlestop tour of his career and the path to setting up SciNote.

[4:20] Brendan discusses the principles of FAIR data and the challenges of adhering to them in the biotech industry.

[6:15] Brendan talks about the need to balance flexibility and structure when collecting R&D data.

[13:34] Brendan highlights the challenge of catering to diverse workflows, even within the same company.

[16:05] Brendan emphasizes the importance of metadata and how vendors, like SciNote, can help collect it with flexible tools for data entry and post-processing.

[18:59] Ross and Brendan discuss how to create an ELN that serves all stakeholders within the organization without imposing creativity constraints on research scientists.

[21:57] Brendan highlights how benefits like improving loss reduction and efficiency form part of the business case for a tool like SciNote.

[24:25] Brendan shares real-world examples of how companies integrate SciNote into their organizations and the need to work with other systems and software.

[34:01] Ross asks for his advice to biotech companies considering implementing ELNs, particularly into their workflows.

[39:10] Brendan gives his take on incorporating ML and AI within SciNote.

---

Download our latest white paper on “Using Machine Learning to Implement Mid-Manufacture Quality Control in the Biotech Sector.”

Visit this link: https://connect.corrdyn.com/biotech-ml

This week, we are pleased to be joined on the Data in Biotech Podcast by Pierre Salvy, who recently became the CTO at Cambrium, and his colleague Lucile Bonnin, Head of Research & Development at Cambrium. 

As part of the Cambrium team behind NovaColl™, the first micro-molecular and skin-identical vegan collagen to market, Pierre and Lucile share their practical experiences of using AI to support protein design.

We ask why Cambrium, as a molecular design organization, decided to focus on the cosmetics industry and dig into the factors that have driven its success. From developing a protein programming language to the challenges of collecting and utilizing lab data, Pierre and Lucile give a detailed look under the hood of a company using data and AI to accelerate its journey from start-up to scale-up.

They also talk to host Ross Katz about the benefits of working as a cloud-native company from day zero, de-risking the process of scaling, and opportunities for new biomaterials.   

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

Chapter Markers

[1:34] Pierre and Lucile make a quick introduction and give an overview of Cambrium’s work using AI to design proteins with the aim of developing sustainable materials.

[4:00] Lucile introduces NovaColl™, and Pierre elaborates on the process of bringing Cambrium’s first product to market.

[7:37] Ross asks Pierre and Lucile to give an overview of the considerations and challenges of protein design.

[11:01] Pierre and Lucile explain how Cambrium works with potential customers to design specific proteins that meet or exceed their expectations.

[12:49] Ross and Pierre discuss how Cambrium approached developing the data systems it needed to explore the protein landscape and how the team optimized the lab set-up.

[18:04] Pierre discusses the protein programming language developed at Cambrium.

[21:24] Lucile and Pierre talk through the development of the data platform at Cambrium as the company has scaled and the value of being cloud-native.

[24:12] Lucile and Pierre discuss how they approached designing the manufacturing process from scratch and how to reduce risk at every stage, especially while scaling up.  

[31:44] The conversation moves to look at how Cambrium will use the processes and data platform developed with NovaColl™ to explore opportunities for the development of new biomaterials. 

[34:42] Pierre gives advice on how start-ups can be smarter when selecting an area of focus.

[36:27] Lucile emphasizes the importance of getting cross-organizational buy-in to ensure successful data capture. 

[39:01] Pierre and Lucile recommend resources that may be of interest to listeners seeking more information on the topics covered. 

---

Download our latest white paper on “Using Machine Learning to Implement Mid-Manufacture Quality Control in the Biotech Sector.”

Visit this link: https://connect.corrdyn.com/biotech-ml

This week, we are pleased to welcome Jacob Oppenheim, Entrepreneur in Residence at Digitalis Ventures, a venture capital firm that invests in solutions to complex problems in human and animal health.

Jacob sat down with Ross to discuss the importance of establishing strong data foundations in biotech companies and how to approach the task. We explore the challenges biotech organisations face with existing tools. What are the limitations, and why are current data tools and systems not yet geared toward helping scientists themselves extract meaningful insights from the data?

We also get Jacob’s take on AI in the biotech space and what is needed for it to reach its full potential, plus some of the opportunities new modelling capabilities will allow scientists to explore.

Finally, we looked at the topic of building a team, how to approach this within a start-up, and the role consultancies play in providing expertise and guidance to early-stage biotech companies.

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

--

Chapter Markers:

[1:08] Jacob gives a quick overview of his career to date and explains how he landed in his current role at Digitalis Venture and what differentiates it as a venture fund.

[07:42] Ross asks Jacob about the biggest challenges and opportunities facing data scientists, data teams, and start-ups more broadly.

[9:56] Jacob talks about the limitations of existing data management tools within biotech companies. 

[13:55] Jacob discusses what is needed as a foundation for AI tools to reach their potential.  

[17:12] Jacob argues for the need for a unified data ecosystem and the benefits of a modular approach to tooling.

[23:42] Jacob explains that biology has become more engineering-focused and how this allows data to guide drug development.

[26:14] Ross and Jacob discuss the challenges of integrating data science and biotech teams, including cultural clashes and tooling conflicts. 

[32:52] Jacob emphasises the importance of consultancies in the biotech space, particularly for start-ups.

[36:21] Ross asks what the new modelling capabilities are that he is most excited about and how they will drive the industry forward.  

[38:45] Jacob shares his advice for scientists and entrepreneurs looking to start a biotech venture and recommends resources.

--

Download our latest white paper on “Using Machine Learning to Implement Mid-Manufacture Quality Control in the Biotech Sector.”

Visit this link: https://connect.corrdyn.com/biotech-ml

This week's guest is Joseph Pearson, Global Product Manager of OmicSoft at QIAGEN, a global provider of sample-to-insight solutions that enable customers to gain valuable molecular insights.  

During this episode, we dive into OmicSoft, a powerful NGS analysis suite that can quickly explore and compare 500,000 curated omics samples from disease-related studies. Joseph outlines the challenges of acquiring and analysing NGS data sets, how customers can interact with OmicSoft data, and what he thinks of the build versus buy debate when selecting new bioinformatics tools.

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

Chapter Markers:

[01:33] Joseph gives us a brief introduction to his career and how he got to the position that he has today. 

[03:39] Ross asks Joseph about QIAGEN and how OmicSoft complements the existing range of products the company already provides. 

[05:09] Joseph talks about the work that is going into their NGS datasets and how the company is extracting value from those datasets. 

[06:09] Ross asks Joseph about the types of customers that use this solution. 

[13:06] Joseph clarifies where the data underlying OmicSoft comes from.

[19:29] Ross asks Joseph how the company approaches educating the customer.

[22:44] Joseph explains the decision-making process that companies go through when deciding to either build or buy.

[27:15] Ross asks Joseph about the biggest challenges or criticisms people have about the platform. 

[31:07] Joseph explains how his biology background has shaped his view of the challenges he faces in his role in product management.

[34:11] Joseph tells us where we can find out more about OmicSoft and QIAGEN.

---

Download our latest white paper on “Using Machine Learning to Implement Mid-Manufacture Quality Control in the Biotech Sector.”

Visit this link: https://connect.corrdyn.com/biotech-ml

This week's guest is Wolfgang Halter, Head of Data Science and Bioinformatics at Merck Life Science, a leading global science and technology company. 

Ross sat down with Wolfgang to discuss the work on the BayBE project, an open-source library built for Bayesian optimization. Throughout the episode, we go on to learn how BayBE is used for both experimental design and as a means to accelerate innovation. The pair also discusses the benefits and challenges of Bayesian optimization and the need for standardised data models. Finally, Wolfgang shares some advice for those scientists and engineers who are keen to get ahead in the industry. 

You can access the GitHub repo mentioned in the episode by clicking here: github.com/emdgroup/BayBE

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

--

Chapter Markers:

[1:32] Wolfgang gives us a whistle-stop tour of his career to date and explains the motivation behind pursuing a career in Data Science. 

[2:35] Ross asks Wolfgang about Merck’s mission and the role the data science team is playing in helping the company achieve that mission. 

[5:28] Wolfgang explains the work that is going into the BayBE project. 

[13:23] Ross asks Wolfgang how Merck arranged their experimental campaigns in BayBE and how they garnered insights during the process. 

[17:45] Wolfgang explains why the team developed BayBE as an open-source library.

[19:25] Wolfgang shares some more details on how the data science team at Merck is using BayBE today.

[20:42] Wolfgang shares some examples of the kinds of applications that the team is currently developing. 

[21:54] Wolfgang provides us with information about the amount of time that is saved on average as a result of adopting this approach. 

[34:38] Ross asks Wolfgang how his engineering background informs his perspective on the problems facing biotech and R&D. 

[36:57] Wolfgang gives us his advice for young scientists and engineers who are looking to learn more about biotech. 

[38:24] Wolfgang provides us with a list of resources for those who want to find out more about Merck and the BayBE project. 

--

Download our latest white paper on “Using Machine Learning to Implement Mid-Manufacture Quality Control in the Biotech Sector.”

Visit this link: https://connect.corrdyn.com/biotech-ml

This week, we’re delighted to be joined by Annemie Ribbens, VP Science, Evidence and Trials at icometrix, a medical technology manufacturer that offers a portfolio of AI solutions to assist healthcare with various challenges in neurological disorders, such as brain trauma, strokes, dementia, and Alzheimer's disease.

During this episode, Annemie opens up on icometrix’s mission in analyzing and treating neurological disorders, the work that went into developing the data infrastructure and the challenges they face when dealing with such large data sets. Annemie also goes on to discuss how machine learning will influence the application of precision medicine in biotech over the next five years and the goals that the company is looking to achieve in the future. 

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

Chapter Markers:

[1:14] Annemie provides us with a brief introduction into her background and what led her to pursue a career in this field.

[4:17] Ross asks Annemie about icometrix’s portfolio and what differentiates it from the other tools in the market. 

[7:36] Annemie explains how icometrix are helping physicians improve both their understanding and treatment of particular disorders. 

[13:31] Annemie dives into the role that the public patient facing app plays and how the data that it gathers feeds the ecosystem. 

[22:03] Annemie reveals how their partnerships work. 

[28:11] Ross asks Annemie to provide some insights into how icometrix went about developing their data infrastructure.

[31:23] Annemie shares the channels involved when processing and analysing large data sets. 

[40:01] Annemie explains the methodology that enables icometrix to know what core areas to focus on.

[43:07] Annemie reveals one of the projects that she is most proud of. 

[45:00] Annemie gives us her thoughts on what the future holds for machine learning. 

[47:33] Annemie explains where listeners can go to find out more information on icometrix. 

---

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.

This week, we’re delighted to be joined by Lana Denysyk, Head of RWD Assets at Novo Nordisk.

During this conversation, Lana shares how real-world data is used in biotech, diving into how it can help clinicians understand patient experiences outside clinical trials. Lana also discusses the challenges in acquiring and utilising real-world data, the importance of having a centralised team to manage it, and emerging data types like patient-reported outcomes and health equity data. 

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

Discussed: 

[1:08] Lana talks about her career to date, from public health graduate to head of a real-world data department at Nova Nordisk. 

[3:55] Ross and Lana break down exactly what real-world data means and how biotech organisations use it. 

[7:03] Lana outlines that RWD is part of a diverse data ecosystem in organizations and why it's crucial to understand which data type best suits specific research questions to avoid silos and maximize data utilization. 

[8:40] Lana gives examples of the types of stakeholder groups that have research questions where RWD is helpful. 

[11:54] Lana walks through how she thinks about scoping a request for RWD and understanding the limitations and applicability of the data. 

[17:36] Ross and Lana discuss the role of RWD professionals in facilitating broader access to data through platforms and tools for non-data scientists. 

[19:33] Lana highlights why standardizing real-world data management processes, despite the diversity in data types, is crucial for efficiently integrating new data into an organization and what this process looks like. 

[21:31] Lana discusses the role of GDPR and HIPAA and its impact on RWD. 

[23:52] Lana discusses real-world data strategy in pharma, highlighting the importance of assessing data adequacy, employee training, and educating all staff on data capabilities and limitations for effective future use. 

[29:10] Lana shares her excitement about emerging real-world data sets beyond traditional claims and EMR sources in pharma,

[32:30] Lana lists some resources people can use to stay up-to-date on the application of RWD in biotech.

---

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.

This week, we’re delighted to be joined by Cody Schiffer, Associate Director, Machine Learning at SMPA - a biopharmaceutical company focused on delivering therapeutic and scientific breakthroughs in areas of critical patient need,

During this conversation, Cody and Ross discuss the construction, maintenance, and application of a knowledge graphic in biopharma, including how to integrate structured and unstructured data to support tasks like literature searches, competitive intelligence and drug discovery and the challenges in keeping a knowledge graph updated with new, real-time information. 

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

Discussed:

[1:09] Cody shares his background and career to date.

[2:43] Cody outlines how SMPA leverages data science to support its pipeline of investigational assets in healthcare.

[7:36] Cody explains how his team approaches helping scientists better understand scientific literature.

[12:44] Cody explains how the SMPA knowledge graph was constructed and how it is updated over time.

[18:13] Cody discusses how his team incorporates unstructured data in the knowledge graph.

[23:05] Cody explains how they apply weighting to the information that is gathered and ultimately fed into the knowledge graph.

[28:16] Cody shares the biggest lessons he has learned from building and maintaining the knowledge graph.

[34:48] Cody explains how he and SMPA view the build versus buy question when developing internal tools.

[38:47] Cody shares his thoughts on what the future holds for his team and the tools they are building internally.

---

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.