PulseAugur
LIVE 13:59:40
research · [5 sources] ·
0
research

AI models CodeFP and Proteo-R1 advance de novo protein design

Researchers have developed new AI models for de novo protein design, aiming to create functional proteins without relying on evolutionary templates. One approach, CodeFP, simultaneously decodes sequence and structure to improve both functionality and foldability, showing significant gains over existing methods. Another model, Proteo-R1, decouples molecular understanding from geometric generation by using a multimodal large language model to identify key residues, which then guide a diffusion-based generator. A third study explored high-entropy generative models, finding that maximum-entropy models like meDCA can represent a vastly larger functional sequence space while minimizing overfitting and better capturing evolutionary fitness landscapes. AI

Summary written by gemini-2.5-flash-lite from 5 sources. How we write summaries →

IMPACT Advances in AI-driven protein design could accelerate drug discovery and the development of novel biomaterials.

RANK_REASON Multiple arXiv papers present novel AI models and methods for protein design.

Read on arXiv cs.LG →

COVERAGE [5]

  1. arXiv cs.AI TIER_1 Deutsch(DE) · Xinrui Chen, Yizhen Luo, Siqi Fan, Zaiqing Nie ·

    Co-Generative De Novo Functional Protein Design

    arXiv:2605.00948v1 Announce Type: cross Abstract: De novo functional protein design aims to generate protein sequences that realize specified biochemical functions without relying on evolutionary templates, enabling broad applications in biotechnology and medicine. Existing appro…

  2. arXiv cs.LG TIER_1 · Fang Wu, Weihao Xuan, Heli Qi, Hanqun Cao, Heng-Jui Chang, Zeqi Zhou, Haokai Zhao, Ma Jian, Carl Ma, Yu-Chi Cheng, Kuan Pang, Xiangru Tang, Zehong Wang, Guanlue Li, Hanchen Wang, Kejun Ying, Pan Lu, Chiho Im, Seungju Han, Peng Xia, Tinson Xu, Yinxi Li, De ·

    Proteo-R1: Reasoning Foundation Models for De Novo Protein Design

    arXiv:2605.02937v1 Announce Type: new Abstract: Deep learning in \emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which resi…

  3. arXiv cs.LG TIER_1 · Roberto Netti, Emily Hinds, Francesco Calvanese, Rama Ranganathan, Martin Weigt, Francesco Zamponi ·

    Expanding functional protein sequence space using high entropy generative models

    arXiv:2605.03578v1 Announce Type: cross Abstract: Boltzmann Machines trained on evolutionary sequence data have emerged as a powerful paradigm for the data-driven design of artificial proteins. However, the relationship between model architecture, specifically parameter density, …

  4. arXiv cs.LG TIER_1 · Francesco Zamponi ·

    Expanding functional protein sequence space using high entropy generative models

    Boltzmann Machines trained on evolutionary sequence data have emerged as a powerful paradigm for the data-driven design of artificial proteins. However, the relationship between model architecture, specifically parameter density, and experimental performance remains poorly unders…

  5. Hugging Face Daily Papers TIER_1 ·

    Expanding functional protein sequence space using high entropy generative models

    Boltzmann Machines trained on evolutionary sequence data have emerged as a powerful paradigm for the data-driven design of artificial proteins. However, the relationship between model architecture, specifically parameter density, and experimental performance remains poorly unders…