Data in Biotech

Four rival pharma companies build AI startups together. The science is rarely what decides which ones succeed.

You've built a model that works on public data. Now pharma wants a security review, a test you can't design yourself, and proof your tool fits a program they already run.

Yair Benita is CTO of AION Labs, a venture studio owned by Teva, Merck, Pfizer, AstraZeneca and AWS that builds AI drug discovery companies from scratch. His career runs from immuno-oncology at Merck in the early Keytruda days to immune checkpoint discovery at Compugen and patient data work at CytoReason.

Ross Katz and Yair break down the barriers between good technology and a pharma team willing to use it. You'll hear how blind validation won over skeptical chemists, why a design tool sells where a prediction stalls, and how a year of compliance work became a one-click AWS deployment.

Key Takeaways

• A startup's model ranked a pharma compound library it had never seen, against targets it didn't know. The chemists hoped for two binders in the top 100. The results kept them testing for ten targets.
• Telling a team its CRISPR guide is toxic after months and $1 million of work sends them back to the start. Yair's rule: if you can predict it, you can design it.
• Splitting antibody discovery and optimization into two companies made scientific sense. Commercially, pharma wanted the whole step.
• If pharma partners can't agree on a nonclinical test for success, don't start the company. That's why AION Labs never entered drug combination.

Chapter Markers

00:00 Introduction: Rival pharma companies building AI companies together

01:30 From pharmacology to computational biology

03:13 Merck and Compugen: discovering novel immune checkpoints from genome structure

07:00 Go it alone or reveal early? Lessons on proving a computational discovery

11:14 Cytoreason: deconvolving cell composition to solve pharma problems

15:18 Start with low-hanging fruit: indication selection vs. target discovery

17:30 Business models: why tech-for-pharma is hard, and why that is changing

19:58 What AION Labs is and how four pharma companies and AWS built it

23:10 Limitations of the model: shared challenges and the data-for-training problem

27:13 Blind validation: the small molecule ranking story

32:30 Baby steps, blinded competitions and building pharma trust

35:39 How seed-stage startups innovate on limited data and funding

41:54 Lesson: predictions are useless without a fix (Cassidy Bio)

44:00 Lesson: pharma wants the full process, not a piece (antibody discovery and optimization)

46:29 Defining the problem and the test: why no drug combination company was started

51:00 Eon’s evolving model: access to pharma, co-development and funding partners

54:40 The compliance bottleneck: ISO 27001 and one-click compliant AWS

58:07 Vision: an end-to-end ecosystem of specialized AI companies

01:00:27 Who should reach out to AION Labs

01:01:24 Four barriers of data, product, proof and access

Useful Links & Resources

• AION Labs: https://www.aionlabs.com
• CASP (Critical Assessment of Structure Prediction): https://predictioncenter.org
• ISO/IEC 27001 information security standard: https://www.iso.org/standard/27001
• AlphaFold Protein Structure Database: https://alphafold.ebi.ac.uk
• Yair Benita on LinkedIn: https://www.linkedin.com/in/ybenita/

Connect With the Show

• Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/
• CorrDyn on LinkedIn: https://www.linkedin.com/company/corrdyn/
• CorrDyn website: https://www.corrdyn.com

Which barrier has slowed your team most: data access, proof, product fit, or security review? Tell us in the comments. If you've run a blind validation with a pharma partner, we'd like to hear how you set it up.

Visit corrdyn.com to see how CorrDyn can help your organization extract value from data.

#DataInBiotech #DrugDiscovery #BiotechDataScience #MachineLearning #LifeSciences

AI can design a molecule in seconds, however someone still has to build it and test it before it means anything.

You're pouring resources into AI-driven molecule design, but nobody on your team has answered the harder question: can you actually make what the model just designed?

Patrick Finn is President and Chief Operating Officer of Twist Bioscience, a company writing DNA on silicon chips at a scale of roughly 32 million distinct oligonucleotides a day. Under his leadership, Twist has become the manufacturing layer behind antibody discovery, liquid biopsy, and molecular residual disease testing programs across biotech.

You'll get a clear picture of what happens after an AI model produces a candidate molecule, and why the synthesis step decides whether that design ever becomes usable data. Paddy breaks down how pooled DNA synthesis and display selection turn hundreds of thousands of candidates into model feedback in weeks instead of months, and where the manufacturability gap bites hardest as AI pushes sequences into territory nature never explored.

This episode covers high-throughput DNA synthesis, target enrichment for liquid biopsy, tumor-informed molecular residual disease testing, and the economics of scaling antibody discovery. It's built for data and R&D leaders investing in AI-driven drug discovery who haven't stress-tested the physical layer underneath their models, plus anyone in biotech data science curious how life sciences data pipelines actually generate their evidence.

Key Takeaways

• Twist's silicon chip platform pushes roughly 32 million oligonucleotides through synthesis every day, and that scale is what turns a single AI-designed antibody into a dataset instead of a guess.
• Liquid biopsy tests need sequencing depth around 50,000x coverage to catch a signal in the noise, and target enrichment panels can cut total sequencing costs by roughly half.
• AI models are pushing sequence designs into territory that's genuinely hard to manufacture: homopolymers, long repeats, extreme GC content. Twist's acceptance rate on submitted sequences climbed from 96% to 99.5%, and that gap matters more than it sounds.
• Memorial Sloan Kettering sent Twist 100,000 antibody designs and had the entire set synthesized as a single pooled library, tested through phage or yeast display, instead of one sequence at a time.

Chapter Markers

00:00 Introduction to Twist Bioscience and Paddy Finn

01:12 Overview of Twist's silicon DNA synthesis platform

04:13 How miniaturized chips drive 32 million oligos daily

05:35 Killer applications built on Twist's infrastructure

07:44 Liquid biopsy and the cost of sequencing depth

12:02 How target enrichment lowers diagnostic costs

13:15 Tumor-informed molecular residual disease testing

16:30 What "disease-free" really means in MRD testing

18:02 Producing and characterizing antibodies at scale

22:25 The assay menu behind antibody developability

24:04 Why AI-designed sequences are hard to manufacture

27:36 Predicting manufacturability before synthesis begins

31:16 Going from 96% to 99.5% sequence acceptance

33:16 Wet lab partnership with Amazon and Memorial Sloan Kettering

36:10 Why Twist stays an enabler, not a model builder

38:20 Is AI-driven biology durable, or a short cycle

41:53 What R&D leaders should ask before scaling AI design

43:00 Ross's takeaways: bottlenecks move, they don't disappear

Useful Links & Resources

• Twist Bioscience: https://www.twistbioscience.com
• Patrick Finn on LinkedIn: https://www.linkedin.com/in/patrickjfinn/
• CorrDyn: https://www.corrdyn.com
• Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/

#DataInBiotech #BiotechDataScience #DrugDiscovery #LifeSciences #AIinBiotech

Flow cytometry can find a cell population in seconds, but naming it consistently across labs is a problem still unsolved.

If you've ever tried to compare cytometry data across studies, CROs, or even two scientists in the same lab, you know the frustration: everyone gates their own way, and the same cell population ends up with three different definitions. That inconsistency is quietly limiting what AI can do with biotech data.

Ryan Brinkman is VP Research Director of Flow Cytometry Bioinformatics at Dotmatics and Founding Director of SOULCAP, the Standard Ontology for Unambiguous Labeling in Cytometry and Phenotyping, built after years as an academic developing automated gating tools that kept running into the same naming problem. He's joined by Brian Wile, who is the General Manager of Flow Cytometry at KCAS Bio, a CRO that feels the cost of inconsistent labeling in client projects every day.

You'll get a clear picture of how flow cytometry data moves from raw signal to labeled cell population, why that last step has resisted automation, and what a shared standard could unlock for machine learning models trained on this data. Ryan and Brian break down the gap between automated gating and consistent labeling, and why agreement, not just data volume, is what AI in biotech actually needs.

This episode covers the mechanics of flow cytometry, an EVE Online citizen science project that trained a gating algorithm on hundreds of millions of human-labeled plots, and why cell population names like "Treg" or "natural killer cell" don't map to one agreed set of markers.

Key Takeaways

• Gating automation solved half the problem: computers can now draw boundaries around cell populations, but nothing proves which name belongs on the result.
• A citizen science project turned hundreds of thousands of EVE Online players into an unlikely training set, collecting roughly half a billion labeled plots from people with zero biology background.
• The same cell type, like a regulatory T cell, gets defined by entirely different marker combinations depending on the lab or CRO, and those datasets can't simply be merged later.
• SOULCAP is running a Delphi-style consensus process among scientists worldwide to tie every cell population name to a specific, reproducible set of markers and experiments.

Chapter Markers

00:00 Why naming cells is harder than naming genes

02:13 What flow cytometry measures, from cell to signal

06:21 The scale and complexity of high-dimensional cytometry data

09:20 How raw data becomes a gated cell population

12:02 Why gating has stayed manual for decades

16:19 Clusters of differentiation and the marker explosion

18:11 Training an algorithm with EVE Online players

25:31 Evaluating accuracy without a gold standard

31:34 Why solving gating doesn't solve labeling

36:32 What genomics got right that cytometry hasn't

38:09 Two definitions of a regulatory T cell, one label

44:28 The cost of inconsistent labeling for CROs and pharma

47:43 Introducing SoCAP and the Delphi consensus process

57:18 What automated labeling could make possible

65:38 How to get involved in SOULCAP

Useful Links & Resources

• Ryan Brinkman on LinkedIn: https://www.linkedin.com/in/ryan-brinkman-9bb1103/
• Brian Wile on LinkedIn: https://www.linkedin.com/in/brianwile/
• KCAS Bio: https://www.kcasbio.com
• CorrDyn: https://www.corrdyn.com

Connect With the Show

• Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/
• CorrDyn LinkedIn: https://www.linkedin.com/company/corrdyn/

Where do you land on the naming problem? Have you had to merge cytometry datasets that turned out to use different definitions for the same cell type? Tell us about it in the comments.

Visit corrdyn.com to learn how CorrDyn can help your organization extract value from data.

#DataInBiotech #FlowCytometry #BiotechDataScience #Bioinformatics #LifeSciences

Ask a general AI model how many approved drugs hit a target, and it might tell you three when the real answer is six, sounding just as confident either way.

If your team is grounding drug discovery decisions in AI output with no way to trace where the answer came from, you're one regulator's question away from a very expensive problem.

Lisa Downey is CEO of DrugBank, a structured biomedical intelligence platform cited in more than 60,000 papers and used by nine of the top 20 global pharma companies. She previously built Clarivate's genomic and rare disease data business from the ground up and held leadership roles at GlobalData, giving her almost 20 years across healthcare and life sciences data.

Lisa breaks down why the bottleneck in AI-driven drug discovery has shifted from data scarcity to trustworthy grounding, and what that means for teams making target identification and go/no-go calls. You'll hear how DrugBank's knowledge graph separates causation from correlation, why reproducibility matters more than speed, and what questions to ask before building a reference data layer in-house.

This episode covers deterministic versus probabilistic data, human-in-the-loop versus human-over-the-loop curation, and how biopharma teams connect grounding layers to their AI agents through MCP. It's built for data and analytics leaders, R&D teams, and anyone deciding whether to build or buy their biomedical data infrastructure.

Key Takeaways

- A general model asked how many approved drugs hit PD-L1 will answer with total confidence, and total inaccuracy, missing half the real number without any signal that it's wrong.

- Anthropic's own benchmarks found frontier models pulling public genomic data got it right as little as 17% of the time, until a deterministic tool pushed accuracy past 99%.

- DrugBank moved from human-in-the-loop curation to human-over-the-loop oversight once its data was connected enough that one expert validating one relationship could cascade trust across dozens of related facts.

- Before building or buying a reference data layer, Lisa lays out four questions that separate real infrastructure from marketing, starting with whether every fact traces back to a source and a date.

Chapter Markers

00:00 Why data scarcity isn't the real bottleneck anymore

01:22 What drew Lisa to DrugBank's mission

03:04 What DrugBank is and who relies on it

05:03 The grounding layer: completeness and reproducibility

07:28 Anthropic's benchmark on data infrastructure

09:21 The high-stakes decisions DrugBank data informs

12:23 Where lost cycle time actually comes from

14:13 DrugBank versus homegrown knowledge graphs

19:43 Human-in-the-loop versus human-over-the-loop curation

24:12 How DrugBank checks its own data quality

25:37 Deterministic versus probabilistic data explained

28:52 The J&J case: separating causation from correlation

33:06 Connecting DrugBank to your AI stack via MCP

37:28 Four questions to ask before you build or buy

42:15 Where DrugBank fits, and where it doesn't

44:44 AI as an amplifier of both good and bad decisions

Useful Links & Resources

- Connect with Lisa Downey on LinkedIn (https://www.linkedin.com/in/lisaldowney/)

Connect With the Show

- Ross Katz on LinkedIn (https://www.linkedin.com/in/b-ross-katz/)

- CorrDyn on LinkedIn (https://www.linkedin.com/company/corrdyn/)

Have you run into an AI model giving you a confident, wrong answer in your own R&D work? Tell us about it in the comments, we're always looking for real examples for future episodes.

Visit corrdyn.com to learn how CorrDyn can help your organization extract value from data.

#DataInBiotech #BiotechAI #DrugDiscovery #DataScience #LifeSciences

Most drug discovery genomic data comes from a thin slice of the world, and that bias follows every decision downstream.

Your team can run a Mendelian randomization study on 35,000 patients and still walk away with a single signal that doesn't even apply to the population you care about. If your phenotype definitions are fuzzy, more data won't save you.

Erika Kvikstad is a computational biologist who led precision medicine for cardiovascular disease at Bristol-Myers Squibb, working on therapies including Camzyos for hypertrophic cardiomyopathy. She now works independently on genomic data equity, focused on how reference populations shape everything from target discovery to clinical trial recruitment.

You'll get a practical look at how to evaluate real-world data vendors, why heart failure is nearly impossible to define cleanly from billing codes, and where statistical power breaks down even with tens of thousands of patients. Erika also explains how her team used AI to reconstruct missing imaging data and validate cardiomyopathy diagnoses at scale.

This episode covers GWAS studies, Mendelian randomization, UK Biobank, proteome-wide analysis, and the practical gap between biobank-scale data and disease-specific cohorts. It's built for data and analytics leaders working in life sciences who need to understand where genomic bias enters their pipeline, not just that it exists.

Clarification

Around 57:58–58:24, in discussing the proteome-wide Mendelian randomization study, Erika moved quickly between two related findings. BTN3A2 was identified as a candidate associated with ischemic stroke and potential immune-modulatory biology. Separately, single-cell expression data helped contextualize other candidate signals, including some with enriched expression in cardiomyocyte populations. Cardiomyocyte-enriched expression was not a specific finding for BTN3A2.

Chapter Markers

00:00 Whose genome are we designing drugs for

01:34 Erika's path from academic genomics to BMS

03:48 Building the precision medicine strategy at BMS

06:37 Ross shares his own HCM diagnosis

07:09 Why heart failure resists clean definition

11:11 How medication use reclassifies patients

14:35 Imaging as a biomarker, and its data gaps

20:23 Data infrastructure gaps across regions

22:44 What to look for when evaluating a data vendor

27:35 Consortia and biobanked specimens for rare mutations

29:52 Cardiovascular data infrastructure versus oncology

32:29 Where statistical power breaks down

37:07 UK Biobank's strengths and its limits

40:01 Bridging broad biobanks with disease-specific cohorts

44:32 How reference population bias propagates downstream

48:53 Where genomic bias hits hardest in the pipeline

53:18 Inside a proteome-wide Mendelian randomization study

59:42 Choosing the right computational tool for the question

1:06:38 Building globally representative genomic infrastructure

1:08:04 Ross's takeaways on bias and statistical power

Useful Links & Resources

- Erika on LinkedIn: https://www.linkedin.com/in/erikakvikstad

- UK Biobank: https://www.ukbiobank.ac.uk

- Alliance for Genomic Discovery: https://alliancegenomicdiscovery.org

- SHaRe Registry (DCM Foundation): https://dcmfoundation.org

Connect With the Show

- Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/

- (Ross Katz on X: https://x.com/brosskatz

- CorrDyn LinkedIn: https://www.linkedin.com/company/corrdyn/

Have you run into genomic reference bias in your own work? Tell us what it looked like and how your team caught it.

Visit corrdyn.com to learn how CorrDyn can help your organization extract value from data.

Subscribe to Data in Biotech so you don't miss the next conversation.

Why treating the cell, not the protein, could turn chronic disease treatment into something closer to a cure.

You've built single-cell pipelines that spit out clusters, p-values and target lists, but nothing that survives contact with the clinic. What if the clustering method itself is quietly leading you astray?

Adam Freund is Founder and CEO of Arda Therapeutics, a biotech using single-cell sequencing to find the pathogenic cells driving chronic disease. He spent seven years as a Principal Investigator at Calico Life Sciences, building a research lab on the biology of ageing and helping grow the company from 15 to more than 200 people, and holds a PhD in Molecular and Cell Biology from UC Berkeley.

You'll get a working model for how Arda's discovery engine turns single-cell and spatial transcriptomic data into causal cell targets. Adam explains why a common statistical shortcut in single-cell analysis produces disease signals that don't hold up and how cell depletion could replace daily dosing with a handful of treatments that reset the immune system.

Ross and Adam cover how Arda finds pathogenic cell populations across hundreds of donors, why chi-squared tests on cell clusters can substitute cell count for donor count without anyone noticing, and how B-cell depletion therapies proved that removing a cell can beat blocking its pathway. This one is for data science leaders and computational biologists building single-cell pipelines, not listeners after a general intro to drug discovery.

Key Takeaways

- Chi-squared tests on cell clusters draw their statistical power from the number of cells, not the number of donors, so a single oversampled patient can produce the same p-value as a hundred-donor study.

- Rituximab clears 100% of B cells from circulation yet does nothing for lupus because the disease-driving cells live in tissue, not blood, a lesson now shaping where Arda tests its own molecules.

- Neighborhood analysis scores each cell by the donor identity of its nearest neighbours rather than forcing cells into predefined clusters, producing a continuous disease-enrichment map with no cluster boundaries.

- When depleted cells regrow, they often come back without the trait that made them harmful in the first place, which means a handful of doses can hold a chronic disease in remission for months.

Chapter Markers

00:00 Why cell depletion beats pathway blocking

01:05 Welcome Adam Freund to the show

01:30 From Calico Life Sciences to founding Arda

03:29 Why blocking one pathway rarely works

05:32 B-cell depletion as the proof of concept

08:14 Building a modular library of depletion tools

10:46 Single-cell sequencing removes the need for a hypothesis

11:43 Why clustering is a dial, not ground truth

15:24 The chi-squared trap in single-cell analysis

20:40 Neighbourhood analysis and donor-weighted scoring

23:44 Moving from enrichment to causality

26:32 Inside Arda's lead fibrosis program

30:33 Why solid tissue testing beats blood samples

34:25 Simulating depletion in spatial transcriptomic data

38:49 The case for intermittent dosing over daily pills

43:58 The data infrastructure behind Arda's platform

48:46 Where spatial and protein data are heading

Useful Links & Resources

- Adam Freund on LinkedIn: https://www.linkedin.com/in/adam-freund-0657654

- CorrDyn: https://corrdyn.com

Connect With the Show

- Host Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/

- Host Ross Katz on X: https://x.com/brosskatz

- CorrDyn on LinkedIn: https://www.linkedin.com/company/corrdyn/

If your team runs single-cell pipelines, how do you currently decide on the number of clusters, and have you ever checked whether your significance scales with donor count rather than cell count? Tell us in the comments; we're building a running list of data QA checks for biotech data science teams.

Visit corrdyn.com to learn how CorrDyn can help your organization extract value from data.

Everyone in biotech agrees AI needs more data. Almost no one is willing to pay for it.

If you're trying to build or buy a biotech AI model, you've hit the same wall: predictive performance depends on data your budget doesn't cover, and nobody in the field seems willing to close that gap.

John Androsavich runs Ginkgo Datapoints, the bio AI data arm of Ginkgo Bioworks. He trained as an RNA scientist, spent years on the pharma side deciding which technologies were worth buying, and now sells the raw biological data everyone claims to want.

Ross and John get into why biotech spends a fraction of what tech spends on data, how automation dropped ADME testing to $199 a compound, and what that unlocks for drug discovery pipelines and data science in biotech more broadly. You'll hear why single-cell foundation models don't scale the way the field expected, and how GPT-5 designed its own lab experiments inside an autonomous facility.

This one's for data and analytics leaders in biotech who need a clearer read on where to spend on data generation, and where the field is still guessing. It's less useful if you're after a general AI overview with no biotech specifics.

Key Takeaways

- One Meta investment in a data-labelling vendor outweighs a full year of AI drug discovery venture funding combined, and dwarfs the entire single-cell data market. Biotech's data spend looks nothing like tech's.

- Ginkgo's ADME-1 offering runs at roughly a tenth of standard pricing, which is changing when and how much companies test. Teams are now running full tier-one panels earlier instead of triaging molecules before they've generated the negative data models need.

- A recent Microsoft Research paper found single-cell foundation model learning saturates at 200,000 to 2 million cells, out of a possible 20 million. Volume alone isn't the lever people assumed it was.

- GPT-5 wrote its own experimental protocols for optimising cell-free protein expression, ran them through Ginkgo's autonomous Nebula lab, and hit the lowest price-per-titer ever recorded in the field.

Chapter Markers

00:00 Introducing John Androsavich and Ginkgo Datapoints

01:12 Why Ginkgo launched a bio AI data business

05:03 Which companies benefit most from Datapoints

06:31 The paradox: everyone wants data, no one pays

09:00 How automation drives ADME-1's $199 price point

12:59 Testing the Jevons paradox in biotech data buying

16:05 Do we actually know biotech AI's scaling laws?

20:54 Why foundation model builders resist more data

24:59 What an empirical bake-off for bio AI could look like

29:32 The case against sitting on the sidelines

33:26 Inside the Virtual Cell Pharmacology Initiative

41:57 Where VCP fits among other virtual cell projects

44:50 The Antibody Developability Consortium with Apheris

53:57 Autonomous labs and GPT-5 designing its own experiments

59:38 Advice for mid-stage biotech data strategy

01:01:31 Final thoughts on where bio AI investment is heading

Useful Links & Resources

- Ginkgo Bioworks: [ginkgobioworks.com](https://www.ginkgobioworks.com)

- Related episode: Apheris CEO Robin Rohm on federated co-folding (Data in Biotech)

- Related episode: Eliza Appel on Lilly's TuneLab and federated learning (Data in Biotech)

- CorrDyn: [corrdyn.com](https://www.corrdyn.com)

Connect With the Show

- Host LinkedIn (Ross Katz): [linkedin.com/in/b-ross-katz](https://www.linkedin.com/in/b-ross-katz/)

- Host X: [x.com/brosskatz](https://x.com/brosskatz)

- CorrDyn LinkedIn: [linkedin.com/company/corrdyn](https://www.linkedin.com/company/corrdyn/)

Where does your organisation sit on the data investment paralysis John describes? Are you waiting for someone else to prove the scaling laws first, or are you buying the data now? Drop your take in the comments.

Visit corrdyn.com to learn how CorrDyn can help your organisation extract value from data.

#DataInBiotech #BiotechAI #DrugDiscovery #DataScience #GinkgoBioworks

In this episode of Data in Biotech, host Ross Katz sits down with Woody Sherman, Founder and Chief Innovation Officer at PsiThera, for a conversation on why AI can transform drug discovery's paperwork and code while barely touching the hardest part of the problem: the molecules themselves. Woody's career runs through physical chemistry at MIT; over a decade at Schrödinger building tools the industry still relies on; founding Silicon Therapeutics (where his team took a small molecule STING agonist from concept to clinic in roughly three years); scaling that platform after Roivant's acquisition; and now leading PsiThera's effort to build oral small molecules for immunology targets that today are only reachable with injectable biologics.

The conversation digs into why large language models excel at automation, coding, and regulatory writing but hit a wall when the task is predicting how a molecule behaves, what "physical AI" actually means as a category distinct from both LLMs and traditional physics-based simulation, and why representing molecules as quantum mechanical objects rather than text strings or 2D graphs changes what's predictable. 

Woody also walks through the STING program in detail, why the field's excitement over fast co-folding models like Boltz needs a strong dose of skepticism, and what it takes to build a database and team culture where chemists, biologists, and data scientists can actually understand each other.

What you'll learn in this episode:

>> Why the contradiction of "AI is transforming drug discovery" and "drugs still take a decade and billions of dollars" can both be true at once.

>> How Silicon Therapeutics engineered a small molecule STING agonist to dimerize itself through a quantum mechanical interaction that had never been designed for before.

>> What "physical AI" means as a new category built on embeddings from orbital-level, quantum mechanical representations of molecules, rather than language tokens or force-field simulations.

>> Why molecular representation is the whole game: the limitations of SMILES strings and 2D graphs versus true 3D, quantum mechanical embeddings like PsiThera's Psiformer model

>> Why a widely publicized claim of near-FEP-quality binding affinity at 1,000x the speed didn't hold up under scrutiny.

>> How PsiThera captures not just simulation and wet lab data but human chemist judgment and reasoning as structured data, and why building a shared vocabulary across computational and experimental teams is as important as any model.

Meet our guest:

Woody Sherman, PhD, is Founder and Chief Innovation Officer at PsiThera, a biotechnology company designing oral small molecule drugs for immunology and inflammatory diseases, starting with the TNF superfamily. His career spans physical chemistry research at MIT, more than a decade at Schrödinger developing computational drug discovery tools, founding Silicon Therapeutics (acquired by Roivant), and leading the platform's evolution through PsiThera today. He has published more than 100 peer-reviewed papers spanning molecular dynamics, quantum mechanics, free energy simulations, and machine learning for drug design.

• Connect with Woody Sherman on LinkedIn: https://www.linkedin.com/in/woodysherman/

About the host:

Ross Katz is Principal and Data Science Lead at CorrDyn. Ross specializes in building intelligent data systems that empower biotech and healthcare organizations to extract insights and drive innovation.

• Connect with Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/

Sponsored by…

This episode is brought to you by CorrDyn, the leader in data-driven solutions for biotech and healthcare. Discover how CorrDyn is helping organizations turn data into breakthroughs at CorrDyn. https://www.linkedin.com/company/corrdyn/

In this episode of Data in Biotech, host Ross Katz sits down with Paul Finn, Chief Scientific Officer at Oxford Drug Design, for a conversation on what it actually takes to find a drug molecule that works not just on paper but also in the lab, in the cell, and, ultimately, in the clinic. Paul brings four decades of experience across what became GSK, Pfizer, and a series of Oxford-area spinouts and has shepherded a compound all the way to a marketed drug. That perspective gives him a particular kind of skepticism toward AI results that look too good to be true because he's done the work of checking whether they are.

The conversation moves through synthesizability as a first-class constraint, why chemistry has proven so much harder for AI than biology, how 3D molecular representation gets closer to the physics that actually matters, and what rigorous multi-parameter optimization looks like when you're trying to kill cancer cells and drug-resistant bacteria at the same time.

What you'll learn in this episode:

>> Why synthesizability is chronically underestimated and why changing a single atom in a structure can take a molecule from trivially easy to make to practically impossible

>> How Oxford Drug Design constrains the generative search to reaction schemes and purchasable building blocks, and why that chemical space is still so vast that novelty is not meaningfully sacrificed

>> Why most generative AI models learn from a 2D string representation of a molecule; two steps removed from the 3D physics that govern how a drug actually binds to its target

>> How Bayesian optimization over reagent space, rather than molecular space, allows an active learning loop to focus on the structural patterns associated with activity

>> Why benchmarking complex models against simple ones is the discipline that exposes false correlations and why Paul and his co-authors were able to recover the Halicin result using methods decades older than deep learning

>> What a pharma company should actually ask an AI drug discovery vendor before buying what they're selling

Meet our guest:

Paul Finn is Chief Scientific Officer at Oxford Drug Design, a computational drug discovery company with roots in Oxford's chemistry department. His career spans over 40 years of computational drug discovery, from early structure-activity modeling in the 1980s through to modern generative AI methods, with deep experience at what became GSK and Pfizer before moving into the Oxford spinout ecosystem. At Oxford Drug Design, Paul leads internal programs in oncology and antibacterial resistance, combining novel computational methods with a rigorous, synthesizability-first approach to multi-parameter optimization.

• Connect with Paul Finn on LinkedIn: https://uk.linkedin.com/in/paul-finn-2250616

About the host:

Ross Katz is Principal and Data Science Lead at CorrDyn. Ross specializes in building intelligent data systems that empower biotech and healthcare organizations to extract insights and drive innovation.

• Connect with Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/

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!

Sponsored by…

This episode is brought to you by CorrDyn, the leader in data-driven solutions for biotech and healthcare. Discover how CorrDyn is helping organizations turn data into breakthroughs at CorrDyn. https://www.linkedin.com/company/corrdyn/

In this episode of Data in Biotech, host Ross Katz sits down with Arvind Rao, Professor of Computational Medicine and Bioinformatics at the University of Michigan, for a discussion on the gap between what biomedical AI can do and what it can reliably be trusted to do in clinical practice. Arvind's research sits at the intersection of computational oncology and AI governance and his lab works across H&E histopathology, multiplex immunofluorescence, spatial transcriptomics, and single-cell RNA sequencing, not just to build predictive models, but to understand the full lifecycle from data to model to inference, and to ask where that lifecycle can be trusted and where it can't. 

The conversation moves through two of his recent papers on SPIFEE, a graph-based framework that replaces scalar interaction scores in the tumor microenvironment with spatially resolved functional representations, and a multimodal framework that traces a path from stained tissue slides to nominated drug targets via morphological pattern discovery and spatial transcriptomic mapping. 

What you’ll learn in this episode: 

>> Why the field's central failure is not algorithmic but translational and the gap between a model that performs well on a benchmark and one that can be consistently trusted in a high-stakes clinical setting 

>> How SPIFEE replaces the conventional scalar edge representation of cell-cell interactions in the tumor microenvironment with spatially resolved functional edges

>> How Arvind's multimodal framework moves from H&E pathology slides labeled with clinical outcomes, through morphological pattern discovery via multiple instance learning, to spatial transcriptomic mapping, to the nomination of molecular mechanisms and actionable drug targets

>> Why Goodhart's Law applies directly to foundation model evaluation in biology 

>> What the AI literacy gap costs when it goes unaddressed in healthcare and pharma organizations 

Meet our guest:

Arvind Rao is a Professor of Computational Medicine and Bioinformatics, with a joint appointment in Radiation Oncology, at the University of Michigan. His research focuses on establishing trust in biomedical AI predictions across the full data-to-decision pipeline, integrating H&E histopathology, spatial transcriptomics, multiplex immunofluorescence, and single-cell RNA sequencing to build models that are predictive, interpretable, and biologically credible. Alongside his research, Arvind develops AI literacy programs for healthcare and pharma professionals, helping clinical and procurement teams evaluate and govern AI systems with the rigor those decisions demand.

• Connect with Arvind Rao on LinkedIn: https://www.linkedin.com/in/arvind-rao-3301301ba/

About the host:

Ross Katz is Principal and Data Science Lead at CorrDyn. Ross specializes in building intelligent data systems that empower biotech and healthcare organizations to extract insights and drive innovation.

• Connect with Ross Katz on LinkedIn: https://www.linkedin.com/in/b-ross-katz/

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!

Sponsored by…

This episode is brought to you by CorrDyn, the leader in data-driven solutions for biotech and healthcare. Discover how CorrDyn is helping organizations turn data into breakthroughs at CorrDyn. https://www.linkedin.com/company/corrdyn/