# Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

arXiv: https://arxiv.org/abs/1609.00680 · HTML: https://mlsanity.com/paper/1609.00680/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2016.

## Built on by (most cited first, 30 of 31)

- [Diffusion-based Molecule Generation with Informative Prior Bridges](https://mlsanity.com/paper/2209.00865/) (2022)
- [E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking](https://mlsanity.com/paper/2210.06069/) (2022)
- [MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems](https://mlsanity.com/paper/2306.17525/) (2023)
- [Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model](https://mlsanity.com/paper/2110.15527/) (2021)
- [Exploring evolution-aware & -free protein language models as protein function predictors](https://mlsanity.com/paper/2206.06583/) (2022)
- [Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review](https://mlsanity.com/paper/2303.06471/) (2023)
- [Protein Language Models and Structure Prediction: Connection and Progression](https://mlsanity.com/paper/2211.16742/) (2022)
- [Which transformer architecture fits my data? A vocabulary bottleneck in self-attention](https://mlsanity.com/paper/2105.03928/) (2021)
- [Generative Pretrained Autoregressive Transformer Graph Neural Network applied to the Analysis and Discovery of Novel Proteins](https://mlsanity.com/paper/2305.04934/) (2023)
- [OpenProteinSet: Training data for structural biology at scale](https://mlsanity.com/paper/2308.05326/) (2023)
- [Pandemic Drugs at Pandemic Speed: Infrastructure for Accelerating COVID-19 Drug Discovery with Hybrid Machine Learning- and Physics-based Simulations on High Performance Computers](https://mlsanity.com/paper/2103.02843/) (2021)
- [HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels](https://mlsanity.com/paper/2202.10716/) (2022)
- [Multi-task Bioassay Pre-training for Protein-ligand Binding Affinity Prediction](https://mlsanity.com/paper/2306.04886/) (2023)
- [Protein-RNA interaction prediction with deep learning: Structure matters](https://mlsanity.com/paper/2107.12243/) (2021)
- [Protein sequence-to-structure learning: Is this the end(-to-end revolution)?](https://mlsanity.com/paper/2105.07407/) (2021)
- [PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction](https://mlsanity.com/paper/2206.12240/) (2022)
- [G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation](https://mlsanity.com/paper/2106.11920/) (2021)
- [Symmetry Structured Convolutional Neural Networks](https://mlsanity.com/paper/2203.02056/) (2022)
- [Multiscale Graph Neural Networks for Protein Residue Contact Map Prediction](https://mlsanity.com/paper/2212.02251/) (2022)
- [Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective](https://mlsanity.com/paper/2212.14041/) (2022)
- [BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models](https://mlsanity.com/paper/2512.00283/) (2025)
- [tFold-TR: Combining Deep Learning Enhanced Hybrid Potential Energy for Template-Based Modeling Structure Refinement](https://mlsanity.com/paper/2105.04350/) (2021)
- [Learning to Discover Medicines](https://mlsanity.com/paper/2202.07096/) (2022)
- [CoGANPPIS: A Coevolution-enhanced Global Attention Neural Network for Protein-Protein Interaction Site Prediction](https://mlsanity.com/paper/2303.06945/) (2023)
- [Improving Protein-peptide Interface Predictions in the Low Data Regime](https://mlsanity.com/paper/2306.00557/) (2023)
- [MATE-Pred: Multimodal Attention-based TCR-Epitope interaction Predictor](https://mlsanity.com/paper/2401.08619/) (2023)
- [Kirigami: large convolutional kernels improve deep learning-based RNA secondary structure prediction](https://mlsanity.com/paper/2406.02381/) (2024)
- [ContactNet: Geometric-Based Deep Learning Model for Predicting Protein-Protein Interactions](https://mlsanity.com/paper/2406.18314/) (2024)
- [Learning from B Cell Evolution: Adaptive Multi-Expert Diffusion for Antibody Design via Online Optimization](https://mlsanity.com/paper/2508.02834/) (2025)
- [LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning](https://mlsanity.com/paper/2607.22777/) (2026)

## Abstract (arXiv)

Recently exciting progress has been made on protein contact prediction, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. This paper presents a new deep learning method that predicts contacts by integrating both evolutionary coupling (EC) and sequence conservation information through an ultra-deep neural network formed by two deep residual networks. This deep neural network allows us to model very complex sequence-contact relationship as well as long-range inter-contact correlation. Our method greatly outperforms existing contact prediction methods and leads to much more accurate contact-assisted protein folding. Tested on three datasets of 579 proteins, the average top L long-range prediction accuracy obtained our method, the representative EC method CCMpred and the CASP11 winner MetaPSICOV is 0.47, 0.21 and 0.30, respectively; the average top L/10 long-range accuracy of our method, CCMpred and MetaPSICOV is 0.77, 0.47 and 0.59, respectively. Ab initio folding using our predicted contacts as restraints can yield correct folds (i.e., TMscore>0.6) for 203 test proteins, while that using MetaPSICOV- and CCMpred-predicted contacts can do so for only 79 and 62 proteins, respectively. Further, our contact-assisted models have much better quality than template-based models. Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0.5. By contrast, when the training proteins of our method are used as templates, homology modeling can only do so for 10 of them. One interesting finding is that even if we do not train our prediction models with any membrane proteins, our method works very well on membrane protein prediction. Finally, in recent blind CAMEO benchmark our method successfully folded 5 test proteins with a novel fold.