EquiBind, is a SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand’s bound pose and orientation. EquiBind achieves significant speed-ups compared to traditional and recent baselines. 

 Diffusion Steps, Twists, and Turns for Molecular Docking

EigenFold is a diffusion generative model for protein structure prediction (i.e., known sequence -> distribution of structures). It is based on harmonic diffusion, which incorporates bond constraints in the diffusion modeling framework and results in a cascading-resolution generative process.

DiffDock-PP is a new approach to rigid-body protein-protein docking that is based on a diffusion generative model that learns to translate and rotate unbound protein structures into their bound conformations, and a confidence model that learns to rank different poses generated by the score model and select the best one.

CellProfiler is a free open-source software designed to enable biologists without training in computer vision or programming to quantitatively measure phenotypes from thousands of images automatically.

Multipool is a high-resolution genetic mapping for pooled sequencing.

Sprout is a novel generative model for ChIA-PET data that characterizes physical chromatin interactions and points of contact at high spatial resolution.

GERM is an approach to identifying conditional occupancy events for a protein from ChIA-PET data.

Given a database of DNA sequence motifs representing transcription factors and enhancer promoter interaction data, spatzie performs statistical analysis to identify co-enriched transcription factors.

PRESCIENT is a generative model for modeling single-cell time-series.