Using deep learning to annotate the protein universe
Explore this paper's citation graph
Summary
This approach extends the coverage of Pfam by >9.5%, exceeding additions made over the last decade, and predicts function for 360 human reference proteome proteins with no previous Pfam annotation, suggesting that deep learning models will be a core component of future protein annotation tools.
- Type
- preprint
- Published
- 2019-05-03
- Cited by
- 310
- References
- 71
- Access
- Open access
- OpenAlex
- https://openalex.org/W2943203634
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:155813226
Keywords
Benchmark (surveying), Sequence (biology), Computer science, Protein sequencing, Computational biology
References
- DEEPre: sequence-based enzyme EC number prediction by deep learning
- Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning
- End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
- On the difficulty of training recurrent neural networks
- Distilling the Knowledge in a Neural Network
- A deep learning framework for modeling structural features of RNA-binding protein targets
- A helix propensity scale based on experimental studies of peptides and proteins.
- Sequence context-specific profiles for homology searching
- Fast and sensitive protein alignment using DIAMOND
- Basic local alignment search tool.
- Long Short-Term Memory
- Hidden Markov model speed heuristic and iterative HMM search procedure
- TOP-IDP-scale: a new amino acid scale measuring propensity for intrinsic disorder.
- RAPSearch2: a fast and memory-efficient protein similarity search tool for next-generation sequencing data
- SCOP database in 2004: refinements integrate structure and sequence family data
- Compressive genomics for protein databases
- Pfam: A comprehensive database of protein domain families based on seed alignments
- HMMER web server: interactive sequence similarity searching
- Pfam: clans, web tools and services
- Accelerated Profile HMM Searches
Cited by
- Population-Based Black-Box Optimization for Biological Sequence Design
- Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples
- Evolutionary context-integrated deep sequence modeling for protein engineering
- Transfer learning improves antibiotic resistance class prediction
- Transforming the Language of Life: Transformer Neural Networks for Protein Prediction Tasks
- Predicting Antibody Developability from Sequence using Machine Learning
- Unifying the known and unknown microbial coding sequence space
- Incorporating genome-based phylogeny and trait similarity into diversity assessments helps to resolve a global collection of human gut metagenomes
- Classification of G protein-coupled receptors using attention mechanism
- FuncPEP: A Database of Functional Peptides Encoded by Non-Coding RNAs
- Fixed-Length Protein Embeddings using Contextual Lenses
- Applying machine learning to predict viral assembly for adeno-associated virus capsid libraries
- The application potential of machine learning and genomics for understanding natural product diversity, chemistry, and therapeutic translatability.
- Expanding functional protein sequence spaces using generative adversarial networks
- The language of proteins: NLP, machine learning & protein sequences
- Multidimensional Scaling for Gene Sequence Data with Autoencoders
- Accelerating biological insight for understudied genes.
- Deep protein representations enable recombinant protein expression prediction
- Visualizing and Annotating Protein Sequences using A Deep Neural Network
- Improving Protein Function Annotation via Unsupervised Pre-training: Robustness, Efficiency, and Insights
Related papers
- A Review on Protein Structure Prediction
- General overview on structure prediction of twilight-zone proteins
- The unexpected structure of the designed protein Octarellin V.1 forms a challenge for protein structure prediction tools.
- Principles, challenges and advances in ab initio protein structure prediction.
- Approaches to prediction of protein structure
- In silico strategy to model LMP1 of Epstein–Barr virus protein