#sbgridsoftware — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #sbgridsoftware, aggregated by home.social.
-
New Title Alert: PXDesignBench- is a protein design evaluation suite for monomer and binder tasks that standardizes sequence generation, structure consistency assessment, and downstream metrics across tools including ProteinMPNN, ESMFold, AlphaFold2, and Protenix.
Learn more here: https://github.com/bytedance/PXDesignBench
-
New Title Alert: MolDiff- is a diffusion framework designed for generating 3D drug-like molecules, achieving a sampling success rate of over 99%. This tool addresses the atom-bond inconsistency problem in 3D molecule diffusion generation and serves as a backbone for applications such as pocket-based generation and linker generation.
Learn more here: https://github.com/pengxingang/MolDiff/
-
New Title Alert: Protein-quest- is a Python package to search/retrieve/filter proteins and protein structures.
Learn more here: https://www.bonvinlab.org/protein-quest/
-
New Title Alert: MassiveFold- a tool designed to expand structure prediction sampling by optimizing the parallelization of AlphaFold-based predictions across GPU clusters.
Learn more here: https://github.com/GBLille/MassiveFold
-
New Title Alert: MolSnapper- is a tool for conditioning diffusion models to generate 3D drug-like molecules, built on the MolDiff codebase. It integrates pretrained models and provides a streamlined workflow for sampling molecules from defined pockets, making it suitable for structure-based drug design applications.
Learn more here: https://github.com/oxpig/MolSnapper
-
New Title Alert: MiCSPARC- is a CryoSPARC-based cryo-EM pipeline for microtubule image processing that combines automated filament tracing, particle picking, fast 3D refinement, protofilament-number assignment, alignment, register correction, and seam search to determine structures of decorated and undecorated microtubules.
Learn more here: https://github.com/wieczoreklab/MiCSPARC
-
New Title Alert: Napari-SegSelect- is a plugin for Napari to select a connected component from a Membrain-seg segmentation.
Learn more here: https://napari-hub.org/plugins/napari-segselect
-
New Title Alert: AFmassive- is a modified AlphaFold implementation for massive conformational sampling, derived from AlphaFold v2.3.2 and designed to integrate with MassiveFold for parallelized prediction workflows.
Learn more here: https://github.com/GBLille/AFmassive/
-
New Title Alert: MemBrain-v2- is a tool that includes MemBrain-seg, MemBrain-pick, MemBrain-stats, and several Napari tools.
Learn more here: https://github.com/CellArchLab/MemBrain-v2/tree/main
-
New Title Alert: PXDesign- is a de novo protein-binder design suite combining a diffusion generator (PXDesign-d) with Protenix and AF2-IG confidence models for candidate selection and ranking.
Learn more here: https://protenix.github.io/pxdesign/
-
New Title Alert: vossvolvox- a C++17 command-line tools for analyzing molecular structures, specifically for computing volumes, channels, cavities, and tunnel geometry from various molecular input formats. Intended for structural biology and molecular biophysics.
Learn more here: https://github.com/vosslab/vossvolvox
-
New Title Alert: mBER-open- is a protein design framework for antibody binder design that leverages structure templates and sequence conditioning in backpropagation-based design through AlphaFold-Multimer.
Learn more here: https://github.com/manifoldbio/mber-open/
-
New Title Alert: easymode- a collection of general pretrained networks for cellular cryoET.
Learn more here: https://mgflast.github.io/easymode/
-
New Title Alert: ThermoMPNN- is a graph neural network (GNN) designed to predict changes in stability for protein point mutants using transfer learning.
Learn more here: https://github.com/Kuhlman-Lab/ThermoMPNN
-
New Title Alert: Slabify- is a command-line tool designed for the automatic segmentation of lamella slabs in cryo-electron tomography (cryo-ET) volumes.
Learn more here: https://github.com/CellArchLab/slabify-et
-
New Title Alert: MagCalEM- Accurate magnification determination for cryoEM determining the correct magnified pixel size of single-particle cryoEM micrographs is necessary to maximise resolution and enable accurate model building.
Learn more here: https://www.mrc-lmb.cam.ac.uk/crusso/magCalEM/index.html
-
New Title Alert: LASErMPNN- is an all-atom ligand-conditioned protein sequence design and sidechain packing model that accounts for the presence of small molecules, including hydrogens.
Learn more here: https://github.com/polizzilab/LASErMPNN/tree/main
-
New Title Alert: IsoNet2- a deep-learning software package for simultaneous missing wedge correction, denoising, and CTF correction in cryo-electron tomography reconstructions using a deep neural network trained on information from the original tomogram(s).
Learn more here: https://github.com/IsoNet-cryoET/IsoNet2
-
New Title Alert: IsoNet2- a deep-learning software package for simultaneous missing wedge correction, denoising, and CTF correction in cryo-electron tomography reconstructions using a deep neural network trained on information from the original tomogram(s).
Learn more here: https://github.com/IsoNet-cryoET/IsoNet2
-
Technical Notes: January's software push includes updates to 15 titles -- anvi’o, BioXTAS RAW, ChemEx, CryomaskR, DeepRank-GNN-esm, DSSR, GROMACS, Icecream, IMP, PowerFit, PyEM, RDKit, SRAToolkit, Volume_Seg_Tool, and XDS.
More here: https://sbgrid.org/software/recent/archive/2026/01/
-
New Title Alert: ImmuneBuilder- is a high-performance deep learning framework developed by the Oxford Protein Informatics Group (OPIG) specifically for predicting the 3D structures of immune receptor proteins.
Learn more here: https://github.com/oxpig/ImmuneBuilder
-
New Title Alert: Foundry- is a unified framework for protein design that provides tooling and infrastructure for using and training models including RFdiffusion3 (all-atom generative design), RosettaFold3 (structure prediction), and ProteinMPNN/LigandMPNN (inverse folding).
Learn more here: https://rosettacommons.github.io/foundry/
-
New Title Alert: ConSurf- is a bioinformatics tool designed for estimating the evolutionary conservation of amino and nucleic acid positions in protein, DNA, and RNA molecules.
Learn more here: https://github.com/Rostlab/ConSurf
-
New Title Alert: Calc_level_chimeraX- is a ChimeraX plugin to predict and visualize isosurface levels for 3D density maps. This tool is based on a 3D-CNN initially developed to predict the isosurface levels of 3D density maps, as required by SIREn.
Learn more here: https://github.com/mariacarreira/calc_level_ChimeraX
-
New Title Alert: ThermoMPNN-D- is a Siamese neural network designed to predict stability changes from protein double point mutations.
Learn more here: https://github.com/Kuhlman-Lab/ThermoMPNN-D
-
New Title Alert: REPIC- REliable PIcking by Consensus (REPIC) is a consensus methodology for harnessing multiple cryogenic-electron microscopy (cryo-EM) particle picking algorithms.
Learn more here: https://github.com/ccameron/REPIC
-
New Title Alert: cryomaskR- is a desktop application that provides WYSIWYG mask generation for cryo-electron microscopy data analysis.
Learn more here: https://mcalbyrne.com/cryomaskr.html
-
New Title Alert: meteor- a tool for computing crystallographic difference maps that specializes in robust identification of weak signals from minor populations such as bound ligands or time-resolved experimental changes.
Learn more here: https://github.com/rs-station/meteor
-
Technical Notes: This month's software push includes updates to BioEmu, BoltzGen, ChimeraX, DOCK, Google Cloud SDK, HADDOCK3, NAMD, OpenFold, ORCA, pytom-match-pick, pyTME, SamTOOLS, Schrödinger 2025-3 and 2025-4, and Topaz.
More information here: https://sbgrid.org/software/recent/archive/2025/12/
-
New Title Alert: Protein-Hunter- a tool for exploiting structure hallucination within diffusion for protein design. A fast, fine-tuning-free framework for de novo protein design.
Learn more here: https://github.com/yehlincho/Protein-Hunter
-
New Title Alert: CryoSiam- a self-supervised deep learning framework that works on dense and subtomogram levels.
Learn more here: https://frosinastojanovska.github.io/cryosiam-docs/