# HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddle

arXiv: https://arxiv.org/abs/2207.05477 · HTML: https://mlsanity.com/paper/2207.05477/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 6 of 6)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [TurboTransformers: An Efficient GPU Serving System For Transformer Models](https://mlsanity.com/paper/2010.05680/) (2020)
- [LightSeq2: Accelerated Training for Transformer-based Models on GPUs](https://mlsanity.com/paper/2110.05722/) (2021)
- [FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours](https://mlsanity.com/paper/2203.00854/) (2022)

## Built on by (most cited first, 12 of 12)

- [PiFold: Toward effective and efficient protein inverse folding](https://mlsanity.com/paper/2209.12643/) (2022)
- [Large AI Models in Health Informatics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2303.11568/) (2023)
- [Protein Language Models and Structure Prediction: Connection and Progression](https://mlsanity.com/paper/2211.16742/) (2022)
- [HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative](https://mlsanity.com/paper/2207.13921/) (2022)
- [Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networks](https://mlsanity.com/paper/2212.03447/) (2022)
- [Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinement](https://mlsanity.com/paper/2305.15151/) (2023)
- [Technical Report of HelixFold3 for Biomolecular Structure Prediction](https://mlsanity.com/paper/2408.16975/) (2024)
- [Tessel: Boosting Distributed Execution of Large DNN Models via Flexible Schedule Search](https://mlsanity.com/paper/2311.15269/) (2023)
- [HelixFold-Multimer: Elevating Protein Complex Structure Prediction to New Heights](https://mlsanity.com/paper/2404.10260/) (2024)
- [FoldToken2: Learning compact, invariant and generative protein structure language](https://mlsanity.com/paper/2407.00050/) (2024)
- [Position: The Inevitable Transition to Machine Learning in Quantum Chemistry](https://mlsanity.com/paper/2607.18281/) (2026)
- [Accelerator Choice Is Not Enough: AlphaFold2 Inference on Cloud TPUs](https://mlsanity.com/paper/2609.34818/) (2026)

## Abstract (arXiv)

Accurate protein structure prediction can significantly accelerate the development of life science. The accuracy of AlphaFold2, a frontier end-to-end structure prediction system, is already close to that of the experimental determination techniques. Due to the complex model architecture and large memory consumption, it requires lots of computational resources and time to implement the training and inference of AlphaFold2 from scratch. The cost of running the original AlphaFold2 is expensive for most individuals and institutions. Therefore, reducing this cost could accelerate the development of life science. We implement AlphaFold2 using PaddlePaddle, namely HelixFold, to improve training and inference speed and reduce memory consumption. The performance is improved by operator fusion, tensor fusion, and hybrid parallelism computation, while the memory is optimized through Recompute, BFloat16, and memory read/write in-place. Compared with the original AlphaFold2 (implemented with Jax) and OpenFold (implemented with PyTorch), HelixFold needs only 7.5 days to complete the full end-to-end training and only 5.3 days when using hybrid parallelism, while both AlphaFold2 and OpenFold take about 11 days. HelixFold saves 1x training time. We verified that HelixFold's accuracy could be on par with AlphaFold2 on the CASP14 and CAMEO datasets. HelixFold's code is available on GitHub for free download: https://github.com/PaddlePaddle/PaddleHelix/tree/dev/apps/protein_folding/helixfold, and we also provide stable web services on https://paddlehelix.baidu.com/app/drug/protein/forecast.