Machine Learning in Drug Discovery Symposium - Opening Remarks

Who speaks in this episode?

• Somaya (Host)
• Stacy Gabriel (Main speaker (opening remarks))

What is discussed, and when

1. 0:00 – 3:00: Broad Institute, Somaya, Chris Samson, Erica Cowwell
2. 3:00 – 6:00: Broad Institute, Somaya, Stacy Gabriel, Harvard
3. 6:00 – 9:00: Broad Institute, human genome project
4. 9:00 – 10:06: AI-driven drug discovery

Notable quotes from "Machine Learning in Drug Discovery Symposium - Opening Remarks"

• Broad institute machine learning for drug discovery symposium. I am your chair for the morning. My name is Somaya. I am a senior group leader at the broad institute for machine…

  about Somaya · at 0:12

• Stacy Gabriel is the executive vice president platforms and scientific execution at the Broad Institute of MIT and Harvard and has led platform development, execution and operations.

  about Stacy Gabriel · at 3:26

• Machine learning has the potential to transform every aspect of how we discover, develop, and deliver new medicines. From identifying new disease targets to designing molecules with.

  about AI-driven drug discovery · at 5:21

• Highquality reproducible and ethically sourced data. And as I hope you know the Broad Institute has long been committed to this kind of integrative science. Our mission is to…

  about Broad Institute · at 6:39

Who and what is mentioned in this episode?

People

• Somaya — Person · Host / session chair (morning chair; symposium organizer) · 3 mentions · first at 0:14
  Opens the event, provides acknowledgements, explains poster/lightning talk logistics, and introduces Stacy Gabriel; sets the tone and structure for the day.
• Stacy Gabriel — Person · Main speaker (opening remarks) · 2 mentions · first at 3:21
  Introduced to deliver opening remarks and frames the symposium’s goals around ML/AI and drug discovery, emphasizing Broad’s platforms and large-scale data generation.
• Chris Samson — Person · Operations lead (event operations) · 1 mention · first at 0:50
  Credited as an operations lead who made the symposium possible; acknowledged alongside Erica Cowwell.
  Organizing committee members. thank you all for your time and energy. and I would like to give a shout out and a round of applause for Erica Cowwell and Chris Samson who made this event possible who are our operation leads.
• Erica Cowwell — Person · Operations lead (event operations) · 1 mention · first at 0:50
  Credited as an operations lead who made the symposium possible; acknowledged by the chair during opening thanks.
  You all for your time and energy. and I would like to give a shout out and a round of applause for Erica Cowwell and Chris Samson who made this event possible who are our operation leads.

Companies & orgs

• Broad Institute — Company · Host organization · 5 mentions · first at 0:12
  Primary organizer of the symposium and a key player in AI-driven drug discovery research
• Harvard — Company · Affiliated institution · 1 mention · first at 3:30
  One of the founding institutions of the Broad Institute
  Stacy Gabriel is the executive vice president platforms and scientific execution at the Broad Institute of MIT and Harvard and has led platform development, execution and…
• MIT — Company · Affiliated institution · 1 mention · first at 3:30
  One of the founding institutions of the Broad Institute
  Stacy Gabriel is the executive vice president platforms and scientific execution at the Broad Institute of MIT and Harvard and has led platform development, execution and…

Concepts & topics

• AI-driven drug discovery — Concept · Core topic · 1 mention · first at 9:52
  Central theme of the symposium, focusing on the intersection of AI and drug discovery
• human genome project — Concept · Historical reference · 1 mention · first at 7:25
  Mentioned as a foundational project in genomics that Broad Institute contributed to
  Also thrive in the area of large-scale data production and producing data sets for the public good. as you know we have a long history that goes back to the human genome…
• TCGA — Concept · Reference project · 3 mentions
  Mentioned as one of the flagship projects Broad Institute has contributed to

Full transcript with timestamps

0:02 Good morning everyone. Um I'm delighted to see this house full of audience and um I welcome you to 2025 broad institute machine learning for drug discovery symposium. I am your chair for the morning. My name is Somaya. I am a senior group leader at the broad institute for uh machine learning and bionformatics team and it's an absolute pleasure to organize this symposium for the fourth time in a row and host you all. As I kick the day off, I have a couple of thank yous to give. Um as you can imagine, uh organizing a symposium like this takes a village and a lot of work. So, we couldn't even fit the entire organizing committee in one slide. So, we have two slides of organizing committee members. Um, thank you all for your time and energy. Uh, and I would like to give a shout out and a round of applause for Erica Cowwell and Chris Samson who made this event possible who are our operation leads.

1:04 Let's give them a round of applause. Thank you. Um and the same goes for our lovely um advisory committee who helped us in every um step uh to get this um event uh possible to make this event possible. Uh and next is our generous sponsors who uh supported us. So thanks to all our sponsors and finally the stars of the show, our speakers. We have a um separate um slide for our keynote. So the keynote is not here but all the other speakers many of them have um traveled long way to speak here. So uh welcome all the speakers and thank you very much for accepting our invite and speaking um in this symposium.

1:58 Next uh is our lightning talk winners and I'm very proud to announce these winners today. These winners were selected from the submitted abstracts. um we received way more abstracts that than what we could host today in the poster session. So it was a real competition. So congratulations to all of you for winning this award. And as you all probably know that we will also select four poster winners today. But I want to um say that do not feel obliged to stand by your poster. I mean if you want to do that feel free to do it. But also take this time to network um and take this opportunity to mingle with your peers um and academia and also industry folks that are present here today. And we will judge the posters by visuals and content anyway. So don't feel obliged to stand by.

2:57 Finally, we um have a QR code in the program that you might all have. If you want to read the abstracts more then you can scan that code and you'll be able to read the posters. And a final thank you to the broad institute um uh who allowed us to host uh all of you and make this symposium possible. So with that um it is my pleasure now to introduce Stacy Gabriel who will provide the opening remarks. Stacy Gabriel is the executive vice president platforms and scientific execution at the Broad Institute of MIT and Harvard and has led platform development, execution and operations since the institute's founding in 23 and she's also an institute scientist and serves on the institute's executive leadership team. She has been recognized by clarate analytics as one of the most highly cited scientists in molecular biology and genetics in the world for six years in a row. And now it is um my pleasure to say that that recently Stacy

4:08 has also been named on the best female scientist in the world ranking 22nd. So I welcome Stacy to deliver the opening remarks. Thank you Somaya. Hi everybody. Uh good morning. Welcome to the Broad Institute. So uh when Somaya um told me um when about this symposium and um how the organizing committee began um she said you know our goal is simple yet ambitious. I'm not surprised at that all at all by the way. Um, and the goal is to bring together innovative minds at the intersection of machine learning and artificial intelligence and drug discovery. And to highlight the remarkable progress that is being made when these fields work hand in hand, we envisioned a space where scientists from academia and industry could meet not just to present data and results, but to spark conversations, share challenges, and plant the seeds of new collaboration. Because as all of us know, the future of drug discovery will

5:15 not be driven just by one discipline alone, but really will be built at these intersections. Machine learning has the potential to transform every aspect of how we discover, develop, and deliver new medicines. From identifying new disease targets to designing molecules with desired properties to operating and iterating in R&D to optimizing clinical trial design and improving patient care. These advances aren't just about faster computation, as you all know, or better models. They're really about reimagining the scientific process itself. But that potential really is going to be done best through collaboration.

5:54 To make meaningful progress, computational biologists, uh, computational scientists need to work closely with experimental biologists and chemists, those who generate the data to fuel the machine learning systems. Experimentalists in turn will need to develop an understanding of how their data can be leveraged, reused, organized and then integrated into predictive frameworks. Each side brings a really important piece of the puzzle and neither can succeed on its own. We also need um the support of institutions both public and private to um invest in the infrastructure that makes this kind of research possible. And that's really important especially today. This means that not only the computational resources and data platforms but also the experimental systems that generate highquality reproducible and ethically sourced data. And as I hope you know the Broad Institute has long been committed

6:47 to this kind of integrative science. Our mission is to propel the understanding and treatment of human disease through interdisciplinary collaboration and this is perfectly aligned with the themes of this meeting today. We thrive at the intersection of computational biologists and AI researchers alongside medicinal chemists, structural biologists, genomicists, and clinical scientists. All united in a shared vision of how technology can accelerate discovery. We also thrive in the area of large-scale data production and producing data sets for the public good. Um as you know we have a long history that goes back to the human genome project and our commitment to those kind of flagship projects that drive fields has extended beyond that to other projects like TCGA GTE biioank programs and so on. And as we build capabilities for these projects we like to make them available to the world through our platforms. And you're

7:43 going to hear a little bit about that in a video that's going to be shown um during one of the breaks. And there's folks from our platforms here today who you can reach out to and find out more. I hope um on their horizon aside from the historical projects I've pointed to are some really exciting um new data gener generation opportunities in functional genomics and therapeutic development. for example, generating genomewide um crisper pertibbations or compound pertibbation um through large scale um drug scale drug treatments um are are generating data sets with massively parallel single cell RNA seek readout. These are happening right now at the scale of millions of cells per per project. Um, data sets like this will be used in biologically informed large AI models to build comprehensive cataloges of all cellular programs in health and disease. It'll be really exciting to me if next year we're

8:38 talking about some of those data sets in this conference. In therapeutics, we're excited about a new platform to screen nanobodies in a highly scalable and automated way. This is another area where you can see the data generated on the binders can be used with AI models to accelerate downstream downstream development. But of course there are many challenges ahead aside from the macro challenges I think that we all know about and and think a lot about these days. There's also the more proximal challenges to to our to our environment. The data we rely on can be noisy, incomplete or biased. Biological systems are kind of complex and messy in ways that might defy sort of easy modeling. And as the machine learning tools become more sophisticated, we must continue to to ask the important questions about interpretability, generalizability, and responsible use of data. But those challenges are precisely

9:33 what makes this this symposium happening at the right time and makes this feel so exciting. Um, we're at this moment of convergence, I believe, where advances in machine learning architectures, data generation technologies, and experimental systems are aligning to create opportunities we couldn't have imagined even 5 years ago. So, that's why today's symposium matters. That's why it's exciting. Um, I think in this room and around you are the people who will define what's next in this uh decade of AIdriven drug discovery.

Questions about this episode

Who speaks in "Machine Learning in Drug Discovery Symposium - Opening Remarks"?

Somaya (Host), Stacy Gabriel (Main speaker (opening remarks)).

What is discussed in "Machine Learning in Drug Discovery Symposium - Opening Remarks"?

In order: 0:00 Broad Institute, Somaya, Chris Samson, Erica Cowwell; 3:00 Broad Institute, Somaya, Stacy Gabriel, Harvard; 6:00 Broad Institute, human genome project; 9:00 AI-driven drug discovery.

What is mentioned in this Broad Institute episode?

10 people, works and ideas are mentioned, including Broad Institute, Somaya, Stacy Gabriel, AI-driven drug discovery, Harvard, MIT. Each one on this page links to its own page with every episode that mentions it.

How long is "Machine Learning in Drug Discovery Symposium - Opening Remarks"?

The episode runs 10 min; the transcript is about 1,540 words in 11 timestamped sections.

More from Broad Institute

• All analyzed episodes
• People mentioned on Broad Institute
• Topics mentioned on Broad Institute