The Genetics Podcast

This week on The Genetics Podcast, Patrick is joined by Dr. James Zou, Associate Professor of Biomedical Data Science at Stanford University. They discuss the concept of virtual biotechs and how AI agents link single cell data to clinical trial success, Paper to Agent and turning papers into living virtual authors, clinical AI from EchoNet to SleepFM, and the role of academia alongside big AI labs.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to James 

01:55 An overview of James’s virtual biotech and its AI scientist agents

04:11 How single cell evidence behind drug targets predicts clinical trial success

06:33 Behind the scenes of how autonomous the virtual biotech agents are

08:06 Missing proprietary trial data as the next gap for the virtual biotech

09:44 Scaling the number of collaborating AI agents as a new frontier for drug discovery

12:29 How teamwork and structure evolved among the agents 

15:53 Behind the idea of Paper to Agent and virtual authors

19:01 What converting over 100 papers into agents revealed about reproducibility

23:14 The story behind EchoNet, an FDA-cleared AI tool for cardiac ultrasound

26:28 Predicting risk for over 100 future diseases from one night of sleep

27:40 Transferring SleepFM from sleep labs to consumer wearables

28:43 Combining multimodal health data to predict disease

30:10 Longitudinal blood proteomics as the biggest data gap for health AI

31:18 The role of academia as an open, neutral counterweight to big AI labs

32:51 How James’s path from Cambridge math and Harvard machine learning led to biology

34:41 Closing remarks

Find out more

• Virtual biotech paper (https://www.science.org/doi/10.1126/science.aeg6779)

• Paper2Agent paper (https://www.nature.com/articles/s41586-026-11044-y)

This week on The Genetics Podcast, Patrick is joined by Dr. Jeffrey Barrett, Group Leader at the Ellis Institute Finland and the University of Helsinki. They discuss using AI and federated biobank data to stratify common chronic diseases, how LLMs reading clinical notes in Finland's health registries can reveal treatment response, how AI is changing the way scientists research and train, and what the UK's COVID genome sequencing effort means for biosecurity.

Show Notes

0:00 Intro to The Genetics Podcast

01:00 Welcome to Jeff 

02:08 Jeff's research focus for his new lab, including molecular subtyping of common chronic diseases with AI

06:18 Barriers to pooling biobank data across research environments for federated AI models

11:00 Why Jeff expects larger datasets to make complex models better at predicting disease

13:34 The three disease areas Jeff's lab will target first: cardiometabolic, inflammatory and neuropsychiatric

19:41 Using LLMs to read clinician notes in Finland's health registries for treatment response

24:50 How Jeff uses AI in his research and where humans still need to read and review

31:08 Using Claude to understand papers and the gaps in its literature searches

32:14 Jeff on AI solving open problems in mathematics and biology, and where researchers fit

35:48 Simultaneous discoveries and why lab data generation still needs experts

39:01 Jeff's COVID genome sequencing at Sanger and what it means for AI and biosecurity

43:16  Closing remarks

Summary

This week on The Genetics Podcast, Patrick is joined by Jenny Hsieh, Co-Founder and President of the Danon Foundation. They discuss how Danon disease affects males and females, why it is so often misdiagnosed, the current therapy landscape and research priorities, and how families can make informed decisions about gene therapy trials.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to Jenny 

01:28 An overview of Danon disease

02:34 Sex differences in Danon disease and severe disease in females

05:15 Why Danon disease is misdiagnosed and how it may be spotted earlier

08:50 Therapy pipeline for Danon and the Foundation's global patient coordination

13:46 Origin story of the Danon Foundation

18:10 Research priorities and the burden of Danon disease beyond the heart

22:39 Raising genetic testing awareness among ophthalmologists and cardiologists for Danon disease

25:20 Recognizing broader Danon symptoms and launching the first Danon Awareness Day

29:37 Informed consent and trial literacy for families weighing gene therapy

33:14 Patient-friendly trial experiences

36:19 Ways to support Danon research

37:37 Closing remarks

Find out more

• Danon Foundation

This week on The Genetics Podcast, Patrick is joined by Dr. Inigo Martincorena, Group Leader at the Wellcome Sanger Institute. They discuss the discovery of widespread cancer-driver mutations in normal tissue, the role of somatic mutations in autoimmune disease, new sequencing technologies transforming the field, and the therapeutic potential of targeting these mutations.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to Inigo 

01:46 How Inigo's eyelid skin study revealed widespread cancer-driver mutations

07:14 Findings from a follow-up study on esophageal tissue

10:02 How NanoSeq technology scaled somatic mutation research across tissues

12:34 The thyroid study linking somatic mutations to autoimmune disease

17:07 How escaped B cell clones evolve into polyclonal autoimmune disease

20:21 Immune gene mutations occurring in healthy aging lymphocytes

21:21 Why driver mutation clones in normal tissue rarely become cancer

24:16 Two therapeutic paradigms for targeting somatic mutations in disease

28:13 Examples of somatic rescue mutations in the colon, liver, and blood

29:20 Why clonal selection only occurs in dividing cell types

31:20 The field's remaining blind spots in mobile immune cells and rare samples

33:46 How new single-cell sequencing will link genotype to phenotype

36:03 What Inigo has learned from collaborating across Sanger's expertise

38:09 Closing remarks

Find out more

• Eyelid study

• Esophagus study

This week on The Genetics Podcast, Patrick is joined by Dr. Marleah Dean Kruzel, Professor of Communication at the University of South Florida. They discuss her personal path from watching breast cancer move through her family to testing positive for a hereditary mutation herself, the ART framework she developed for managing uncertainty, and the complexities of communicating genetic risk within families.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to Marleah

01:35 Marleah's family history of breast cancer across four generations

02:48 Marleah's childhood living through her mother's five-year cancer battle

04:26 Marleah's experience with genetic testing

07:19 How a positive test result reshaped Marleah’s PhD research focus

08:40 The central challenges of living with a positive test result 

10:50 The ART framework for managing hereditary cancer uncertainty

15:06 Applying the ART framework to Patrick’s experience with uncertainty and the importance of having a support system 

19:53 Common misconceptions in how families communicate genetic risk

23:54 The previvor identity and the chronic uncertainty it brings

25:40 How Marleah has learned to accept and embrace uncertainty

27:57 Balancing logic and emotion in hereditary cancer family planning

31:28 How Marleah grounds her research tools in patients' lived experience

33:21 How AI is eroding our capacity to sit with uncertainty

35:57 Redesigning healthcare for a lifespan of genetic risk information

38:10 Closing remarks

This week on The Genetics Podcast, Patrick is joined by Dr. David Hallett, Chief Scientific Officer at Recursion. They discuss the biggest shifts in drug discovery over Dave's three-decade career, where AI is genuinely transforming the field today versus where the hype outruns the reality, and how Recursion's perturbational maps have uncovered and validated a novel neurodegeneration target.

Show Notes

0:00 Intro to The Genetics Podcast

01:00 Welcome to Dave

01:57 The biggest shifts in drug discovery over three decades

06:39 Where AI is delivering real wins across drug discovery today

12:19 How AI-assisted trial simulation reveals which eligibility criteria to relax

14:46 The three biggest reasons drug programs fail in the clinic 

18:20 How Recursion's perturbational maps uncover new drug targets

24:58 A four-step framework for validating a novel drug target

28:44 How Recursion balances deep therapeutic focus with partnership breadth

30:52 Why AI can't shortcut clinical trials, and what proof of real impact looks like

34:57 The skills scientists need most in the AI era, and why trusting AI outputs starts with trusting the data

39:52 Closing remarks

Find out more:

• Recursion (https://www.recursion.com/)

This week on The Genetics Podcast, Patrick is joined by Dr. Danny Miller, Assistant Professor of Pediatrics and of Laboratory Medicine and Pathology at the University of Washington and Attending Physician at Seattle Children's Hospital. They discuss the case for making long-read sequencing the first genetic test every patient receives, the reference dataset his lab is building from the 1000 Genomes Project to resolve structural variants, publicly available methylation signatures as biomarkers for diagnosis and treatment response, and his vision for genome-informed care from newborn screening through the NICU.

Show Notes

0:00 Intro to The Genetics Podcast

01:00 Welcome to Danny

01:41 The case for long-read sequencing as first-line genetic testing

02:52 Current barriers to wider use of long-read sequencing 

04:14 Building a long-read reference dataset from 1000 Genomes for variant filtering

06:47 How long-read sequencing can solve a missed diagnosis 

08:12 The clinical case for complete telomere-to-telomere genomes

10:39 What it will take to shift the clinical genetics status quo

12:06 Making methylation signatures public to diagnose disease and track therapy

15:58 Danny's path from programming and finance into clinical genetics

18:19 Danny's lived experience with deafness and achondroplasia, and how it shapes his approach to genetic counseling

21:46 Danny's optimism about AI in genomics and worry about AI in education

27:15 The path to making genomes a routine part of the medical record

29:47 The vision of same-day newborn genomic data guiding NICU treatment decisions

34:31 Closing remarks

Find out more:

• Miller Lab (https://millerlaboratory.com/)

This week on The Genetics Podcast, Patrick is joined by Dr. Brent Richards, CEO and Founder of 5 Prime Sciences and Professor of Human Genetics, Epidemiology, and Medicine at McGill University. They discuss how to triangulate different types of genetic evidence to validate a drug target, why herd psychology often drives which targets get funded, why strong genetic support didn't save the Zeus IL-6 trial, and how collider bias can distort genetically stratified clinical trials.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to Brent

01:43 How company size shapes access to genetic drug discovery tools

04:10 Brent's framework for triangulating different types of genetic evidence

06:50 The herd psychology behind which drug targets get funded

10:01 Potential reasons the Zeus IL-6 trial failed despite strong genetic evidence

12:49 What a gold standard genetic evidence package actually looks like 

17:13 Closing the data gap with diverse genomes and systematic pipelines

19:03 The diabetes patient story that drove Brent into drug development and balancing academia with industry

25:39 Why obesity went from a drug development graveyard to its biggest frontier

29:13 How collider bias can distort genetic risk trial results

38:20 Where to go deeper on advanced genetic drug discovery concepts

40:11 Closing remarks

Find out more:

• 5PrimeSciences’ symposium on human genetics at ASHG2026 in October

This week on The Genetics Podcast, Patrick is joined by Dr. Andrew Jackson, Programme Leader at the MRC Human Genetics Unit at the University of Edinburgh. They discuss how his lab discovered that gain-of-function DNMT3A mutations cause both microcephalic dwarfism and an accelerated aging syndrome, and what that reveals about the shared biology of growth and aging.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to Andrew

01:34 The origins of Andrew's work linking brain size and aging

02:54 The genetics of mammalian size range and epigenetic factors regulating growth

05:02 How DNMT3A mutations causing dwarfism led to discovering an accelerated aging syndrome

09:46 Cell number rather than cell size as the shared driver of growth and aging

13:07 Whether brain size within humans actually predicts cognitive ability

15:20 Why intellectual disability has far more known genes than dwarfism

19:26 Discovering ribonuclease H2's role in DNA repair, and its unexpected link to cancer 

23:35 Why studying rare monogenic diseases reveals broader biology

26:59 Andrew's next research questions on aging, cancer, and mutation biology

28:42 Why humans, model organisms, and cell assays each have a role

31:00 Somatic mosaicism's growing role in aging and disease beyond cancer

36:11 Closing remarks

Find out more:

Mentioned studies from Andrew’s lab: 

• https://www.nature.com/articles/s41588-026-02633-8

• https://www.nature.com/articles/s41588-018-0274-x
  

This week on The Genetics Podcast, Patrick is joined by Stevie Ringel, co-founder of Nome and founder of the Kizuna Foundation. They discuss Stevie's own ultra-rare disease diagnosis and shaped his path to founding Kizuna Foundation and Nome, how Nome's AI agents help scientists navigate the operational complexity of small-batch drug development, the technical and business model advantages underpinning Nome's accuracy, and what it will take to build a sustainable funding model for ultra-rare disease.

Show Notes

0:00 Intro to The Genetics Podcast

00:59 Welcome to Stevie

01:37 Stevie's inherited retinal disease (IRD) diagnosis and subsequent path into genomics

03:16 Why Stevie founded Kizuna Foundation and why ultra-rare drug development is so operationally complex

06:27 The origin story of Nome and using AI to automate the operational work 

10:09 The inspiration for the name “Nome” and who the company is built to serve

12:44 The biggest blockers to program speed

15:07 How AI and scale can bring down the cost of gene therapy manufacturing

18:01 FDA signals and global regulatory competition 

19:33 Priority review vouchers and why Nome stays out of molecule IP

20:33 Nome's AI and review process for patient reports and its expansion to health systems

25:04 Nome's agent architecture and the data behind its accuracy

28:17 Why delivery remains gene therapy's biggest bottleneck and approaches for solving it

31:34 The case for a new capital model in rare disease drug development 

33:25 What’s next for Nome as they advance preclinical programs

34:25 Nome’s focus on process excellence across therapeutic modalities

36:34 Closing remarks

Find out more: Nome