ROCKET subsamples MSAs (inspired by https://t.co/4xUPb2qfFq) to generate diverse starting models, selects the best-fit conformation, then refines further with gradient descent. Note: we cannot use pLDDT alone to succeed! 9/14 https://t.co/rLFah2aWGy
Checkout these cited papers which analyzed these systems previously KaiB : [3] Wayment-Steele et al 2024: https://t.co/3sQnvRQFiB RR : [4] Malinverni et al 2019: https://t.co/UZhScWLStc
𝗛𝗲𝗿𝗲 𝗮𝗿𝗲 𝘁𝗵𝗲 𝗶𝗺𝗽𝗼𝗿𝘁𝗮𝗻𝘁 𝗿𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗹𝗶𝗻𝗸𝘀: Paper: https://t.co/Tt7J3KxVQI Code: https://t.co/opXFPoN2SW
@vitaliikl @MoAlQuraishi @deboramarks Been wondering this too. Haven't had the chance to dig deep into the paper, but this looks quite interesting: https://t.co/IGHQHj2nTc