owl
@owl_posting • 15,088 subscribers
cancer guy @noetik_ai || ex virus guy @dyno_tx || i write on bio ml at https://t.co/QPTHsR3fzm || podcast on https://t.co/JBM0K65IrO
Shorts
Videos
Today: a 1.5 hour interview with the co-founders of Coherence Neuro: Ben Woodington and Elise Jenkins They are, as far as i can tell, the only (neurotechnology x oncology) startup that exists today. 'Neurotechnology? For cancer?' you may ask. Yes! As it turns out, tumors interact with the nervous system a fair bit, and you can use the very same neuromodulation toolbox that exists for neuropsychiatric conditions, for monitoring and treating cancer. Coherence has built an invasive device to place at the site of a tumor to do exactly this. Their first indication is a form of brain cancer called glioblastoma; one of the most fatal subtypes of cancer to exist today. The standard of care (with one exception that we discuss) has not changed in 25 years. If Coherence works out, and there is a very real chance they will, that may change. Most interesting of all is that Coherence believes that the bioelectric properties of cancer are not just worth poking at for brain cancers, but for all cancers. And maybe even for diseases outside of it! This conversation covers how Coherence’s first neurotech device (SOMA) works, the molecular reasons behind why neuromodulation affects cancer at all, what the biomarker readouts look like, the obvious Michael Levin comparison, and a lot more. Also: shout to Nicole for setting up the connection here in the first place! Crazy to think that a meeting in mid-2025 ended up leading to this Youtube/Spotify/Apple Podcasts links in replies 0:00:00 - Introduction 0:01:42 - How is SOMA different from Novocure’s Optune? 0:08:57 - Why does neuromodulation affect cancer at all? 0:13:28 - How was cancer-nervous system crosstalk first discovered? 0:15:42 - Anti-epileptics and beta blockers as accidental cancer drugs 0:17:38 - What is molecularly happening when you block cancer-neuron crosstalk? 0:19:50 - What is SOMA actually reading out as a biomarker? 0:20:44 - What does it mean that cancer is “very electric”? 0:22:02 - Can you derive universal biomarkers across patients? 0:23:09 - How is the device placed? 0:24:45 - How does the blocking stimulation regime work? 0:26:43 - Is it fair to say this is closed loop? 0:29:05 - Why not just spam the tumor with constant stimulation? 0:32:31 - Why MRI safety is non-negotiable for oncology devices 0:33:35 - Walk us through the patient journey from diagnosis to implantation 0:36:13 - The Michael Levin question: can you reprogram cancer back to normal? 0:42:29 - Efficacy, hospice settings, and the utility of the neuromodulation literature 0:45:52 - Why start with glioblastoma instead of an easier cancer? 0:48:57 - Regulatory strategy and the reimbursement threat 0:55:37 - How well does mouse-to-human translation work for neuromodulation? 0:55:57 - What do in silico models of neuromodulation look like? 0:58:09 - Why didn’t this exist 10 years ago? 1:01:48 - The founding story 1:06:38 - Why build your own device instead of using off-the-shelf arrays? 1:08:35 - Speaking with glioblastoma patients 1:12:04 - What was it like to raise money for this? 1:13:56 - Beyond cancer: TBI, lung disease, and the pan-disease argument 1:17:40 - Hiring at Coherence + what is the hardest type of talent to find 1:23:17 - What would you do with $100M equity-free? 1:27:15 - Are you a neurotech company or a cancer company?
owl37,241 Aufrufe • vor 3 Monaten
![What could Alphafold 4 look like? (Sergey Ovchinnikov, Ep #3) 2 hours listening time (links below) To those in the (machine-learning for protein design) space, Dr. Sergey Ovchinnikov (Sergey Ovchinnikov) is a very, very well-recognized name. A recent MIT professor (circa early 2024), he has played a part in a staggering number of recent great papers in the field: ColabFold, RFDiffusion, Bindcraft, automated design of soluble proxies of membrane proteins, elucidating what protein language models are learning, conformational sampling via Alphafold2, and many more. Of course, all these papers were group efforts, but Sergey's name comes up astonishingly frequently! And even beyond the research that have come from his lab in the last few years, the co-evolution work he did during his PhD/fellowship also laid some of the groundwork for the original Alphafold paper, being cited twice in it. This is a two hour conversation with him, asking every question I could think of. We talk about his own journey into biology research, an issue he has with Alphafold3, what Alphafold4-and-beyond models may look like, what research he’d want to spend a hundred million dollars on, and lots more. Topics/institutions we discuss: Arc Institute's Evo models, Hannah Wayment-Steele's work, Isomorphic Labs's AF2/AF3, and EvolutionaryScale's ESM models Also, extremely grateful to Asimov Press (Asimov Press) for helping fund the travel + studio time required for this episode! They are a non-profit publisher dedicated to thoughtful writing on biology and metascience, such as articles over synthetic blood and interviews with plant geneticists. I myself have published within them twice! I highly recommend checking out their essays at or reaching out to editors@asimov.com if you’re interested in contributing. Timestamps: [00:00:00] Highlight clips [00:01:10] Introduction + Sergey's background and how he got into the field [00:18:14] Is conservation all you need? [00:23:26] Ambiguous vs non-ambiguous regions in proteins [00:24:59] What will AlphaFold 4/5/6 look like? [00:36:19] Diffusion vs. inversion for protein design [00:44:52] A problem with Alphafold3 [00:53:41] MSA vs. single sequence models [01:06:52] How Sergey picks research problems [01:21:06] What are DNA models like Evo learning? [01:29:11] The problem with train/test splits in biology [01:49:07] What Sergey would do with $100 million](https://image.24vids.com/tw-1915897678187372557/amplify_video_thumb/1915847249084456960/img/TnpQQQNlc88AcmQ2.jpg)
What could Alphafold 4 look like? (Sergey Ovchinnikov, Ep #3) 2 hours listening time (links below) To those in the (machine-learning for protein design) space, Dr. Sergey Ovchinnikov (Sergey Ovchinnikov) is a very, very well-recognized name. A recent MIT professor (circa early 2024), he has played a part in a staggering number of recent great papers in the field: ColabFold, RFDiffusion, Bindcraft, automated design of soluble proxies of membrane proteins, elucidating what protein language models are learning, conformational sampling via Alphafold2, and many more. Of course, all these papers were group efforts, but Sergey's name comes up astonishingly frequently! And even beyond the research that have come from his lab in the last few years, the co-evolution work he did during his PhD/fellowship also laid some of the groundwork for the original Alphafold paper, being cited twice in it. This is a two hour conversation with him, asking every question I could think of. We talk about his own journey into biology research, an issue he has with Alphafold3, what Alphafold4-and-beyond models may look like, what research he’d want to spend a hundred million dollars on, and lots more. Topics/institutions we discuss: Arc Institute's Evo models, Hannah Wayment-Steele's work, Isomorphic Labs's AF2/AF3, and EvolutionaryScale's ESM models Also, extremely grateful to Asimov Press (Asimov Press) for helping fund the travel + studio time required for this episode! They are a non-profit publisher dedicated to thoughtful writing on biology and metascience, such as articles over synthetic blood and interviews with plant geneticists. I myself have published within them twice! I highly recommend checking out their essays at or reaching out to [email protected] if you’re interested in contributing. Timestamps: [00:00:00] Highlight clips [00:01:10] Introduction + Sergey's background and how he got into the field [00:18:14] Is conservation all you need? [00:23:26] Ambiguous vs non-ambiguous regions in proteins [00:24:59] What will AlphaFold 4/5/6 look like? [00:36:19] Diffusion vs. inversion for protein design [00:44:52] A problem with Alphafold3 [00:53:41] MSA vs. single sequence models [01:06:52] How Sergey picks research problems [01:21:06] What are DNA models like Evo learning? [01:29:11] The problem with train/test splits in biology [01:49:07] What Sergey would do with $100 million
owl89,024 Aufrufe • vor 1 Jahr
We don't know what most microbial genes do. Can genomic language models help? there's only one way to find out! this is a 1 hour and 42 minute interview with an MIT professor (the famous Yunha Hwang) chatting about these questions, her work in solving them at Tatta Bio, and more. zoomer captions are back too Links in reply! Timestamps: 00:00:00 - Clips + sponsor roll from the wonderful LatchBio 00:02:07 – Introduction 00:02:23 – Why do microbial genomes matter 00:04:07 – Deep learning acceptance in metagenomics 00:05:25 – The case for genomic “context” over sequence matching 00:06:43 – OMG: the only ML-ready metagenomic dataset 00:09:27 – gLM2: A multimodal genomic language model 00:11:06 – What do you do with the output of genomic language models? 00:17:41 – How will OMG evolve? 00:20:26 – Why train on only microbial genomes, as opposed to all genomes? 00:22:58 – Do we need more sequences or more annotations? 00:23:54 – Is there a conserved microbial genome ‘language’? 00:28:11 – What non-obvious things can this genomic language model tell you? 00:33:08 – Semantic deduplication and evaluation 00:37:33 – How does benchmarking work for these types of models? 00:41:31 – Gaia: A genomic search engine 00:44:18 – Even ‘well-studied’ genomes are mostly unannotated 00:50:51 – Using agents on Gaia 00:54:53 – Will genomic language models reshape the tree of life? 00:59:18 – Current limitations of genomic language models 01:08:54 – Directed evolution as training data 01:12:35 – What is Tatta Bio? 01:19:02 – Building Google for genomic sequences (SeqHub) 01:25:46 – How to create communities around scientific OSS 01:29:06 – What’s the purpose in the centralization of the software? 01:35:37 – How will the way science is done change in 10 years?
owl44,253 Aufrufe • vor 6 Monaten
![Can machine learning enable 100-plex cryo-EM structure determination? (Ellen Zhong, Ep #5) (links in reply) this is a podcast filmed with Ellen Zhong, a computer science professor at Princeton, and one of the giants (if not outright creators) of the field of deep-learning applied to cryo-EM particle images i cannot emphasize how lopsided the ratio of (how important this field is) to (how interesting outside observers consider it) is. it's an area of research that i barely understood until last year. but now that i do grasp it, i increasingly believe that Ellen's work (especially in scaling up cryo-EM) will almost certainly end up being a weight-bearing pillar in the future of bio-ML here, we talk about the possibility of running cryo-EM at extremely high scales, what she did during her recent sabbatical at Generate:Biomedicines, her recent interest in areas beyond cryo-EM (cryo-ET and NMR specifically), and more (and thank you to Rush for sponsoring this! check out their preclinical computational tools at Timestamps: [00:00:00] Introduction [00:02:43] What does it mean to apply ML to cryo-EM? [00:04:28] Ab initio reconstruction and conformational heterogeneity [00:15:41] Can we do multiplex cryo-EM structure determination? [00:22:19] Datasets in cryo-EM [00:26:25] Why isn’t there a foundation model for cryo-EM particle analysis? [00:33:07] How much practical usage is there of these cryo-EM models amongst wet-lab cryo-EM researchers? [00:40:34] Where can things still improve? [00:46:57] Has deep learning done something in cryo-EM that was previously impossible? [00:48:22] Ellen’s experience in the cryo-EM field [00:53:40] Deep learning in cryo-EM outside of structure determination [00:57:32] 3D volume reconstruction versus residue assignment in cryo-EM [01:00:26] What did Ellen do during her sabbatical at Generate Biomedicines? [01:07:07] Ellen’s research in cryo-ET [01:13:54] Ellen’s research in NMR [01:21:05] How did Ellen get into the cryo-EM field? [01:26:57] Why did Ellen go back to graduate school? [01:32:17] What makes Ellen more confident about trusting an external cryo-EM paper?](https://image.24vids.com/tw-1987923818866721138/amplify_video_thumb/1987908501759287296/img/Au3741M4cUZX2m1N.jpg)
Can machine learning enable 100-plex cryo-EM structure determination? (Ellen Zhong, Ep #5) (links in reply) this is a podcast filmed with Ellen Zhong, a computer science professor at Princeton, and one of the giants (if not outright creators) of the field of deep-learning applied to cryo-EM particle images i cannot emphasize how lopsided the ratio of (how important this field is) to (how interesting outside observers consider it) is. it's an area of research that i barely understood until last year. but now that i do grasp it, i increasingly believe that Ellen's work (especially in scaling up cryo-EM) will almost certainly end up being a weight-bearing pillar in the future of bio-ML here, we talk about the possibility of running cryo-EM at extremely high scales, what she did during her recent sabbatical at Generate:Biomedicines, her recent interest in areas beyond cryo-EM (cryo-ET and NMR specifically), and more (and thank you to Rush for sponsoring this! check out their preclinical computational tools at Timestamps: [00:00:00] Introduction [00:02:43] What does it mean to apply ML to cryo-EM? [00:04:28] Ab initio reconstruction and conformational heterogeneity [00:15:41] Can we do multiplex cryo-EM structure determination? [00:22:19] Datasets in cryo-EM [00:26:25] Why isn’t there a foundation model for cryo-EM particle analysis? [00:33:07] How much practical usage is there of these cryo-EM models amongst wet-lab cryo-EM researchers? [00:40:34] Where can things still improve? [00:46:57] Has deep learning done something in cryo-EM that was previously impossible? [00:48:22] Ellen’s experience in the cryo-EM field [00:53:40] Deep learning in cryo-EM outside of structure determination [00:57:32] 3D volume reconstruction versus residue assignment in cryo-EM [01:00:26] What did Ellen do during her sabbatical at Generate Biomedicines? [01:07:07] Ellen’s research in cryo-ET [01:13:54] Ellen’s research in NMR [01:21:05] How did Ellen get into the cryo-EM field? [01:26:57] Why did Ellen go back to graduate school? [01:32:17] What makes Ellen more confident about trusting an external cryo-EM paper?
owl30,577 Aufrufe • vor 7 Monaten
How do you make a 250x better vaccine at 1/10 the cost? Develop it in India. (Soham Sankaran, Ep #2) There's a lot of discussion these days on how China's biotech market is on track to bypass the US's. I wondered: shouldn't we have observed the exact same phenomenon with India? It has seemingly all the same ingredients: low cost of labor, smart people, and a massive internal market. Yet, the Indian biotech research scene is nearly nonexistent. Why is that? To figure it out, I had a two-hour discussion with Soham Sankaran, the CEO of PopVax 🇮🇳, an mRNA vaccine development startup based in Hyderabad. Amongst those in the know, Soham Sankaran is well understood as one of the most talented biotech founders in India, and his company has had a genuinely incredible underdog success story. This story is still being written, but there's good reason to be bullish. We discuss so many things. Including policy prescriptions for Indian R&D, why PopVax's vaccines are so good, how machine-learning is changing vaccine development, and much more. Transcript below, and links in thread (including a jargon explanation). Timestamps: 01:31 Introduction 02:38 Why is there such little biotech research in India? 17:38 Advantages of building a company in India 26:03 Policy prescriptions for India 30:13 Questions on vaccine design 45:28 What does PopVax do? 56:20 The role of machine learning in vaccine design 01:06:29 The (conservative) culture of vaccinology 01:21:12 Hiring in India 01:40:44 How fundraising for an Indian vaccine design startup is coming along 01:55:15 How is PopVax so good at designing vaccines? 01:59:45 Pet theories on immune mechanisms 02:06:24 mRNA beyond infectious diseases 02:09:56 What would you do with $100 million dollars?
owl47,664 Aufrufe • vor 1 Jahr
Keine weiteren Inhalte verfügbar