Here's a quick summary: Molecular simulation is in a tough situation. Fast simulations give the wrong answers, but accurate simulations are too slow for anything useful. But, instead of relying on physical equations for our simulation, perhaps we can approximate them using black-box models? As it turns out, there's an entire research field devoted to this question, and these models are often referred to as neural network potentials, or NNP's. Here, I interview two scientists (Corin and Ari) building neural network potentials (NNP’s). We talk about whether molecular dynamics are useful at all, the role of computational chemistry in drug design, what the future of the field looks like for molecular simulation, and a lot more.
And timestamps, just so you know whats in the podcast: 00:00 Introduction 01:19 Divide between classical and quantum simulation 03:48 What are NNP's actually learning? 06:02 What will NNP's fail on? 08:08 Short range and long range interactions in NNP's 10:23 Emergent behavior in NNP's 16:58 Enhanced sampling 18:16 Cultural distinctions in NNP's for life-sciences and material sciences 21:13 Gap between simulation and real-life 36:18 Benchmarking in NNP's 41:49 Is molecular dynamics actually useful? 53:14 Solvent effects 55:17 Quantum effects in large biomolecules 57:03 The legacy of DESRES and Anton 01:02:27 Unique value add of simulation data 01:06:34 NNP's in material science 01:13:57 The road to building NNP's 01:21:13 Building the SolidWorks of molecular simulation 01:30:05 Simulation workflows 01:41:06 The role of computational chemistry 01:44:06 The future of NNP's 01:51:23 Selling to scientists 02:01:41 What would you spend 200 million on?
Hey LW! I recently filmed a two-hour long scientific podcast. It's niche, but may be of interest to some people here.
Here's a quick summary: Molecular simulation is in a tough situation. Fast simulations give the wrong answers, but accurate simulations are too slow for anything useful. But, instead of relying on physical equations for our simulation, perhaps we can approximate them using black-box models? As it turns out, there's an entire research field devoted to this question, and these models are often referred to as neural network potentials, or NNP's. Here, I interview two scientists (Corin and Ari) building neural network potentials (NNP’s). We talk about whether molecular dynamics are useful at all, the role of computational chemistry in drug design, what the future of the field looks like for molecular simulation, and a lot more.
If you're confused by this episode, I have a 'Jargon Explanation' section.
Here is a transcript of this episode (contains links to all referenced organizations and papers).
And a Youtube link, in case that's easier.
And timestamps, just so you know whats in the podcast:
00:00 Introduction
01:19 Divide between classical and quantum simulation
03:48 What are NNP's actually learning?
06:02 What will NNP's fail on?
08:08 Short range and long range interactions in NNP's
10:23 Emergent behavior in NNP's
16:58 Enhanced sampling
18:16 Cultural distinctions in NNP's for life-sciences and material sciences
21:13 Gap between simulation and real-life
36:18 Benchmarking in NNP's
41:49 Is molecular dynamics actually useful?
53:14 Solvent effects
55:17 Quantum effects in large biomolecules
57:03 The legacy of DESRES and Anton
01:02:27 Unique value add of simulation data
01:06:34 NNP's in material science
01:13:57 The road to building NNP's
01:21:13 Building the SolidWorks of molecular simulation
01:30:05 Simulation workflows
01:41:06 The role of computational chemistry
01:44:06 The future of NNP's
01:51:23 Selling to scientists
02:01:41 What would you spend 200 million on?