Morning Overview on MSN

AlphaFold rewired science, and 5 years later it’s still evolving

AlphaFold arrived as a technical moonshot that suddenly made protein structures feel like software rather than secrets of ...
IEEE

HighMPNN: A Graph Neural Network Approach for Structure-Constrained Cyclic Peptide Sequence Design

Abstract: Cyclic peptides become attractive therapeutic candidates due to their diverse biological activities. However, existing deep learning-based sequence design models, such as ProteinMPNN, are ...
GitHub

PLAID (Protein Latent Induced Diffusion)

PLAID is a multimodal generative model that can generate protein sequence and all-atom structure based on conditional function and taxonomic prompts. Please see our ...
eLife

Interpretable protein-DNA interactions captured by structure-sequence optimization

This valuable work presents an interpretable protein-DNA Energy Associative (IDEA) model for predicting binding sites and affinities of DNA-binding proteins. While the method is convincing, it ...
Cal Alumni Association

How Do Social Structures Shape Your Well-Being?

Systemic, structural change has always been a part of the perspective of the Greater Good Science Center. In a 2022 essay, editor Jeremy Adam Smith defines structural forces in the context of our work ...
C&EN

HighPlay: Cyclic Peptide Sequence Design Based on Reinforcement Learning and Protein Structure Prediction

College of Pharmaceutical Sciences, Zhejiang University of Technology, Hangzhou 310014, China Centralab, Suzhou Kowloon Hospital, Shanghai Jiao Tong University School of Medicine, Suzhou 215028, China ...
Frontiers

Protein structure prediction via deep learning: an in-depth review

The application of deep learning algorithms in protein structure prediction has greatly influenced drug discovery and development. Accurate protein structures are crucial for understanding biological ...
GitHub

MULAN: Multimodal Protein Language Model for Sequence and Structure Encoding

31/03/2025 Added MULAN-ESM2 checkpoints for medium and large models, updated MULAN-small. Code update: MULAN now uses rotary positional embeddings and has improved quality. 20/05/2025 MULAN is ...
Snopes.com

No credible evidence supports claims of vast underground structures found beneath Egyptian pyramids

Researchers of ancient Egypt discovered “five identical structures near the Khafre Pyramid’s base, linked by pathways, and eight deep vertical wells descending 648 meters underground.” Claims that ...
Microsoft

Toward deep learning sequence–structure co-generation for protein design

Deep generative models that learn from the distribution of natural protein sequences and structures may enable the design of new proteins with valuable functions. While the majority of today’s models ...
Science Daily

With generative AI, chemists quickly calculate 3D genomic structures

Chemists have found a new way to determine 3D genome structures, using generative AI, that can predict thousands of genome structures in minutes, making it much speedier than existing methods for ...