Protein Data Bank, every mention
14 scenes · ← back to Protein Data Bank
tap a year for its mentions
every year anyone Gabriele Corso 5Evan Feinberg 3Sergei Yudinov 1Joseph Krause 1Ci Chu 1Bo Wang 1Andy Beam 1
Verbatim, from the transcripts: the passages where Protein Data Bank comes up
🔬Causal Models Need Causal Data - Xaira’s X-Cell model (Bo Wang & Ci Chu)
- ▶ 9:23 Ci Chu People deposit protein structures into a database, right, called PDB.
- ▶ 27:24 unnamed speaker So we generate these two-D rich dataset, not that different than the size, the type of PDB data,
- ▶ 1:20:33 Bo Wang Because of the availability of open source data sets in PDBs, therefore we have models such as AlphaFold, RosettaFold.
🔬 RL with Verifiable Rewards, but the Verifier is a Lab — Lila Sciences
🔬 "The Most Innovative Diffusion Research Is Happening in Drug Discovery, Not Image Generation"
- ▶ 15:23 Sergei Yudinov So a lot of training data that people are used is so-called PDB, uh, which is a public database of like all of the historical
- ▶ 22:28 Evan Feinberg The closest equivalent, as Sergey mentioned, is the RCSB Protein Data Bank, which has more like a couple 100,000 crystal structures.
- ▶ 49:41 Evan Feinberg And if you don't believe me, you can open up the electron density diagram in the PDB.
- ▶ 1:41:59 Evan Feinberg The objective of the company is creating value for biotechs and pharma companies that are usually working on hard drug targets that are different from what's in the PDB, and so we've had to build the models in a way that are able to…
🔬 The Limits of AI in Science - Why We Need Self-Driving Labs — Joseph Krause, Radical AI
- ▶ 46:07 Joseph Krause The protein data bank, uh, for, for, for materials, and it's much more complicated than, than just crystallography structures or, or whatever else was in there.
🔬 The Bitter Lesson is Coming for Proteins - Alex Rives, BioHub
- ▶ 50:25 unnamed speaker We have many of these resolved in the PDB. 3 times in the scene
🔬 Training Transformers to solve 95% failure rate of Cancer Trials — Ron Alfa & Daniel Bear, Noetik
🔬Generating Molecules, Not Just Models
- ▶ 45:12 Gabriele Corso Basically, the way that you can evaluate them is that, you know, you train the model on a structure that was, you know, released across the field up until a certain time, and, you know, one of the things that we didn't talk about that was… 3 times in the scene
- ▶ 1:20:19 Gabriele Corso And so one of the experiments that we did was to, uh, take nine targets from, um, the PDB filtering to things where there is no known interaction, uh, in, in the PDB. 2 times in the scene