mlsanityData to 7 Oct 2026

HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddle

arXiv 2207.05477 ↗First posted 12 Jul 2022cs.DC cs.LG q-bio.BMcited by 12

Not on the map. Why?

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 6 of its 25 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

6 of 25 references.

References · 6

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020Reformer: The Efficient Transformercited by 1,658
  3. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  4. 2020TurboTransformers: An Efficient GPU Serving System For Transformer Modelscited by 71
  5. 2021LightSeq2: Accelerated Training for Transformer-based Models on GPUscited by 19
  6. 2022FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hourscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 3; 2025: 0; 2026: 2.

12 papers.

  1. 2022PiFold: Toward effective and efficient protein inverse foldingcited by 82
  2. 2023Large AI Models in Health Informatics: Applications, Challenges, and the Futurecited by 61
  3. 2022Protein Language Models and Structure Prediction: Connection and Progressioncited by 17
  4. 2022HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternativecited by 15
  5. 2022Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networkscited by 14
  6. 2023Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinementcited by 11
  7. 2024Technical Report of HelixFold3 for Biomolecular Structure Predictioncited by 6
  8. 2023Tessel: Boosting Distributed Execution of Large DNN Models via Flexible Schedule Searchcited by 2
  9. 2024HelixFold-Multimer: Elevating Protein Complex Structure Prediction to New Heightscited by 2
  10. 2024FoldToken2: Learning compact, invariant and generative protein structure languagecited by 1
  11. 2026Position: The Inevitable Transition to Machine Learning in Quantum Chemistrycited by 0
  12. 2026Accelerator Choice Is Not Enough: AlphaFold2 Inference on Cloud TPUscited by 0