CCAOM
SIGNAL FEED / EXTERNAL SOURCES

行业资讯

持续收集实验室、模型团队、产业媒体与开源项目的新信号。每条记录保留来源并直达原文。

124 SIGNALSDAILY FILTERED

研究机构

10 SIGNALS
02
Institute for Protein Design

Custom computing for the next generation of protein design

The IPD is collaborating with NVIDIA to deliver the accelerations necessary for protein design pipelines to meet global grand challenges The post Custom computing for the next generation of protein design first appeared on Institute for Pr…

↗
03
Institute for Protein Design

A New Era for Protein Design in Oncology: Dr. Ahn Joins the IPD

Dr. Green Ahn joins the University of Washington Department of Biochemistry and the Institute for Protein Design as an Assistant Professor. The post A New Era for Protein Design in Oncology: Dr. Ahn Joins the IPD first appeared on Institut…

↗
04
Institute for Protein Design

First vaccine targeting SARS virus family enters human trials

The computer-designed vaccine aims to protect against coronaviruses that haven't yet emerged, including pandemic threats The post First vaccine targeting SARS virus family enters human trials first appeared on Institute for Protein Design .

↗
05
Institute for Protein Design

RFdiffusion3 now available

This foundation model for biodesign can generate proteins that interact with any type of molecule commonly found inside cells. The post RFdiffusion3 now available first appeared on Institute for Protein Design .

↗
06
Institute for Protein Design

RFdiffusion2: efficient enzymes from prompts

AI model that creates catalysts in weeks instead of years opens the door to degrading pollutants and building new medicines. The post RFdiffusion2: efficient enzymes from prompts first appeared on Institute for Protein Design .

↗
07
Institute for Protein Design

Teaching AI to build antibodies from scratch

Generating antibodies entirely on computers — no animal immunizations required — could unlock treatments for countless diseases. The post Teaching AI to build antibodies from scratch first appeared on Institute for Protein Design .

↗
08
Institute for Protein Design

Delivering protein nanoparticle vaccines via mRNA

Combining the speed of mRNA and potency of design proteins yielded up to 28-fold more antibodies — and a platform technology that could transform how we respond to viral threats. The post Delivering protein nanoparticle vaccines via mRNA f…

↗
09
Institute for Protein Design

Creating multi-protein systems with atomic precision

Protein design is expanding from building single molecules to generating entire systems from scratch with parts that work together in ways nature never explored. The post Creating multi-protein systems with atomic precision first appeared…

↗
10
Institute for Protein Design

Hitting ‘undruggable’ disease targets

Custom proteins made with AI bind disordered proteins and peptides with atomic precision. The post Hitting ‘undruggable’ disease targets first appeared on Institute for Protein Design .

↗

模型与工具

30 SIGNALS
01
GitHub · EvolutionaryScale/esm

esm · v3.4.1.post1

This releases brings better compatibility between different implementations (HF / esm / mlx_lm) and allows use of a single set of model weights for all implementations. It also fixes multiple bugs mol_type compared against MOL_TYPE_NONPOLY…

↗
02
GitHub · EvolutionaryScale/esm

esm · v3.4.1

Added support for FoldCP Added support for loading HF-style checkpoints (ESMFold2) Various minor bug-fixes

↗
03
GitHub · EvolutionaryScale/esm

esm · v3.4.0

Added full support for ESMC and ESMFold2 Added test suite for both ESMC and ESMFold2 Added compatibility layer for huggingface port of ESMC and ESMFold2 Maintained back compatibility with legacy models such as ESMC and support legacy model…

↗
04
GitHub · google-deepmind/alphafold3

alphafold3 · AlphaFold v3.0.4

Version 3.0.4 makes AlphaFold 3 runnable on CPU-only machines and on Apple Silicon. Moreover, there are some performance improvements and small bug fixes. We thank everyone who reported issues, proposed new features, and submitted PRs! Cha…

↗
05
GitHub · NVIDIA/bionemo-framework

bionemo-framework · v3.0.0 - BioNeMo Recipes

This marks the first release from BioNeMo Recipes, a lighter-weight version of the BioNeMo model training framework which demonstrates NVIDIA-optimized reference architectures for biological foundation models. This release drops support fo…

↗
06
GitHub · google-deepmind/alphafold3

alphafold3 · AlphaFold v3.0.3

Version 3.0.3 changes the AlphaFold 3 code license from CC BY-NC-SA 4.0 to Apache 2.0. Moreover, it provides bug fixes and a performance improvement for large inputs. We thank everyone who reported issues, proposed new features, and submit…

↗
08
GitHub · google-deepmind/alphafold3

alphafold3 · AlphaFold v3.0.2

Version 3.0.2 provides new features, improves performance, improves documentation, and fixes bugs. AlphaFold v3.0.2 supports NVIDIA Blackwell GPUs out of the box. We thank everyone who reported issues, proposed new features, and submitted…

↗
09
GitHub · bytedance/Protenix

Protenix · v2.0.0: Protenix-v2 Model Released

What's changed 🚀 Key Highlights • Protenix-v2 Model Released: Introduced protenix-v2, an enhanced-capacity model (464M parameters). It delivers significant accuracy improvements in predicting challenging antibody-antigen complex structures…

↗
12
GitHub · bytedance/Protenix

Protenix · v1.0.8: Disable triton fused ops by default

What's Changed Triton fused ops for dropout residual are now disabled by default as they cause a slight drop in foldbench performance. They can be enabled via the FUSED_DROPOUT_RESIDUAL environment variable.

↗
15
GitHub · EvolutionaryScale/esm

esm · v3.2.3

Release Notes - ESM 3.2.3 bugfix: added chain ids to MolecularComplex bugfix: use biotite for mmcif conversion in MolecularComplex bugfix: updated sequence filtering in esm/utils/msa/filter_sequences.py for better handling of edge cases

↗
16
GitHub · NVIDIA/bionemo-framework

bionemo-framework · NVIDIA BioNeMo Framework v2.7

Updates & Improvements Evo2 model improvements: Context, tensor and data parallelism support in the prediction endpoint as well as support for context lengths over 8192 #1123 . Fixes #910 and #1048 . LoRA fine-tuning by @gabenavarro : #980…

↗
17
GitHub · jwohlwend/boltz

boltz · Boltz v2.2.1: Minor bug fixes

What's Changed fix: redundant PoseBustersPotential bounds by @simonlevine in #478 Fix help message in --use_potentials flag by @Alberto024 in #487 Minor simplification of Diffusion Loss by @shenoynikhil in #486 Fix: update filter_inputs_af…

↗
20
GitHub · jwohlwend/boltz

boltz · Boltz v2.2.0: Contact conditioning fixes, new potentials

Highlight Fixes for contact and pocket conditioning which was not fully functional for Boltz2 New potentials Kernels are now optional to avoid installation issues on non-linux platforms New security features for use of the MSA server (than…

↗
21
GitHub · jwohlwend/boltz

boltz · Boltz v2.1.1: New CUDA kernels from NVIDIA

New Features This release introduces two novel kernels from NVIDIA for the triangular attention and triangular multiplication layers, achieve 2x speedup and large memory savings! Changes The kernels are on by default for CUDA users with Am…

↗
24
GitHub · chaidiscovery/chai-lab

chai-lab · v0.6.1

What's Changed reflect python >= 3.10 in readme by @arogozhnikov in #316 Misc. improvements to templates by @wukevin in #315 Remove incorrect check on template bounds by @wukevin in #323 Use centralized downloading logic for RCSB by @wukev…

↗
25
GitHub · chaidiscovery/chai-lab

chai-lab · v0.6.0

What's Changed Major changes Template support by @wukevin in #300 Support for subsampling different MSAs at each recycle and running multiple trunks by @wukevin in #302 #305 #306 Minor changes Update README.md, mention L40s (48 GB is enoug…

↗
26
GitHub · google-deepmind/alphafold3

alphafold3 · AlphaFold v3.0.1

Version 3.0.1 provides new features, improves performance, improves documentation, and fixes bugs. We thank everyone who reported issues, proposed new features, and submitted PRs! Change log Below is a selection of new features, performanc…

↗
27
GitHub · chaidiscovery/chai-lab

chai-lab · v0.5.2: multiple small improvements

This release accumulates improvements over the past two weeks: Better CIFs and better output names, bugfix for multiple ligands, lower memory consumption by default, arbitrary number of diffusion samples; What's Changed CLI command to merg…

↗
28
GitHub · chaidiscovery/chai-lab

chai-lab · v0.5.1: fixes for glycan parsing

What's Changed Minor fixes to glycan parsing by @wukevin in #219 Additional fixes for glycans by @wukevin in #221 (tag and release were updated because previous did not deploy correctly to pypi) Full Changelog : v0.5.0...v0.5.1

↗

产业动态

83 SIGNALS

综合资讯

1 SIGNALS