# PaddlePaddle/PaddleHelix

Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

Repository: https://github.com/PaddlePaddle/PaddleHelix
Canonical: https://ross.abutalabs.com/products/paddlehelix
Language: Python
License: NOASSERTION
License Family: other
Topics: biocomputing, machine-learning, deeplearning, rna-structure-prediction, dti, representation-learning, graph-networks, protein-structure-prediction, self-supervised-learning, ppi, molecule-design, protein-folding, ddi, protein-docking, protein-design
Last push: 2026-03-31T05:01:26+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 8, longevity 100
- inputs: {"age_days": 2112, "days_push": 155, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1119, forks 228 (observed 2026-08-28T04:03:39.434248+00:00)

## What it is
PaddleHelix is a bio-computing platform built on PaddlePaddle featuring large-scale representation learning and multi-task deep learning for biomolecular tasks. It includes models like HelixFold3 for protein and biomolecular structure prediction, HelixDock for protein-ligand docking, and tools for RNA structure prediction, drug-target interaction, and molecule design.

## Use cases
- predict protein 3d structure from sequence
- predict protein-ligand docking poses
- predict rna secondary structure
- drug-target interaction prediction
- design new molecules with deep learning
- molecular property prediction with graph neural networks
- protein-protein interaction prediction

## When to choose
- you need open-source AlphaFold3-like biomolecular structure prediction
- you work on drug discovery tasks like DTI, DDI, or molecular docking
- you want pre-trained molecular or protein representation models on PaddlePaddle

## When to avoid
- you need a PyTorch or TensorFlow ecosystem instead of PaddlePaddle
- you only need general-purpose machine learning without bio-computing focus
- commercial use of HelixFold3 is required, since its license is restricted to non-commercial academic research

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: bioinformatics, machine-learning, deep-learning, healthcare
- platform: python, windows
- tags: bio-computing, protein-folding, rna-structure-prediction, drug-discovery, molecular-docking, graph-neural-networks, self-supervised-learning, alphafold, paddlepaddle, linux, macos

## Member repositories
- PaddlePaddle/PaddleHelix (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:39.434248+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:09.143848+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/PaddleHelix (fetched 2026-08-28T04:03:39.434248+00:00, sha 96ca1a666c3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.