Tagged articles

structural biology

4 articles · Page 1 of 1

Jun 28, 2026 · Artificial Intelligence

Why AlphaFold’s Success Refutes the ‘Bitter Lesson’ Myth – Insights from Nobel Laureate John Jumper

In a deep interview, AlphaFold’s core developer John Jumper explains how domain‑specific engineering, extensive ablation studies, and a hybrid Evoformer‑IPA architecture—not sheer compute—enabled protein‑folding breakthroughs, while distinguishing AI’s roles in prediction, control, and human‑in‑the‑loop understanding.

AlphaFoldEvoformerMachine learning

0 likes · 39 min read

Why AlphaFold’s Success Refutes the ‘Bitter Lesson’ Myth – Insights from Nobel Laureate John Jumper

HyperAI Super Neural

Mar 16, 2026 · Artificial Intelligence

AI‑Driven Quantum Refinement: AQuaRef Enables Full‑Atom Protein Model Optimization with Quantum Constraints

A collaborative team from Carnegie Mellon, Wrocław, and Florida universities introduced AQuaRef, an AI‑powered quantum refinement method that leverages the AIMNet2 machine‑learning potential to achieve near‑classical‑force‑field speed while closely approximating quantum‑mechanical results for full‑atom protein models, outperforming traditional restraints on low‑resolution structures.

AIAIMNet2Machine Learning Potentials

0 likes · 16 min read

AI‑Driven Quantum Refinement: AQuaRef Enables Full‑Atom Protein Model Optimization with Quantum Constraints

Data Party THU

Aug 21, 2025 · Artificial Intelligence

How AI Is Unlocking the Design of Proteins That Target Disordered Regions

This article reviews the AI‑driven Logos strategy for designing proteins that can bind intrinsically disordered protein regions, detailing scaffold generation, pocket specialization, RFdiffusion‑based assembly, threading, experimental validation, and its broader impact on drug discovery for diseases such as cancer and Alzheimer’s.

AIProteinMPNNRFdiffusion

0 likes · 14 min read

How AI Is Unlocking the Design of Proteins That Target Disordered Regions

Data Party THU

Aug 2, 2025 · Artificial Intelligence

How the All-Atom Protein Generative Model (APM) Redefines Multi‑Chain Design

The All‑Atom Protein Generative Model (APM) introduced by Hunan University, UCAS and ByteDance Seed combines full‑atom representation, multi‑chain native modeling, and novel flow‑matching techniques to outperform existing SOTA methods on folding, reverse‑folding, antibody and peptide design tasks, backed by a curated multi‑source dataset and extensive benchmarks.

Bioinformaticsall‑atom modelmulti‑chain design

0 likes · 13 min read

How the All-Atom Protein Generative Model (APM) Redefines Multi‑Chain Design