The field of high-throughput biological sequencing has seen significant advancements in terms of speed and cost-effectiveness. However, the challenge lies in extracting meaningful information from these sequences, especially due to the limitations of low-throughput experimental characterizations. One particular challenge is accurately predicting protein functions directly from their primary amino-acid sequences. In this study, the authors address this challenge by applying machine learning techniques using artificial recurrent neural networks (RNN). They specifically focus on classifying protein function directly from primary sequence without relying on sequence alignment, heuristic scoring, or feature engineering. The RNN models used in this study incorporate long-short-term-memory (LSTM) units and are trained on publicly available annotated datasets from UniProt. The results demonstrate that the RNN models achieve high performance for in-class prediction of four important protein functions tested. In fact, they outperform other machine learning algorithms that utilize sequence-derived protein features. Additionally, the RNN models are capable of making out-of-class predictions for phylogenetically distinct protein families with similar functions, including proteins belonging to the CRISPR-associated nuclease, ferritin-like iron storage, and cytochrome P450 families. Furthermore, when applied to the partially unannotated UniRef100 database, the trained RNN models not only predict candidates validated by existing annotations but also identify currently unannotated sequences. Some predictions made by the RNN models for the ferritin-like iron sequestering function were experimentally validated. Notably, these validated sequences differ significantly from known characterized proteins and each other, making them challenging to predict using popular bioinformatics methods. Overall, as sequencing and experimental characterization data continue to increase rapidly, this machine learning approach based on RNN holds great potential for discovering and predicting homologues for a wide range of protein functions. By leveraging primary amino acid sequences without relying on traditional bioinformatics methods such as sequence alignment or feature engineering, this approach offers a promising avenue for advancing our understanding of protein function.
High-throughput biological sequencing has become faster and cheaper. This means scientists can study DNA and proteins more quickly and affordably. Extracting meaningful information from these sequences is hard because there isn't a lot of experimental data available. Predicting what proteins do based on their building blocks (amino acids) is really challenging. Scientists are using special computer programs called artificial recurrent neural networks (RNN) to help with this challenge. These RNN models are trained using a big database of protein information called UniProt. The RNN models are really good at predicting certain protein functions, even better than other computer programs that use different methods. The RNN models can also make predictions for similar protein families that haven't been studied yet. Scientists have tested the predictions made by the RNN models and found them to be accurate for some protein functions, like iron sequestering. This machine learning approach using RNN has a lot of potential for discovering new proteins and predicting what they do."
Exploring Protein Function with Artificial Recurrent Neural Networks
The field of high-throughput biological sequencing has seen significant advancements in terms of speed and cost-effectiveness. However, the challenge lies in extracting meaningful information from these sequences, especially due to the limitations of low-throughput experimental characterizations. One particular challenge is accurately predicting protein functions directly from their primary amino-acid sequences.
Machine Learning for Protein Function Prediction
In this study, the authors address this challenge by applying machine learning techniques using artificial recurrent neural networks (RNN). They specifically focus on classifying protein function directly from primary sequence without relying on sequence alignment, heuristic scoring, or feature engineering. The RNN models used in this study incorporate long-short-term-memory (LSTM) units and are trained on publicly available annotated datasets from UniProt.
High Performance In-Class Predictions
The results demonstrate that the RNN models achieve high performance for in-class prediction of four important protein functions tested. In fact, they outperform other machine learning algorithms that utilize sequence derived protein features. Additionally, the RNN models are capable of making out-of-class predictions for phylogenetically distinct protein families with similar functions, including proteins belonging to the CRISPR associated nuclease ferritin like iron storage and cytochrome P450 families.
Identifying Unannotated Sequences
Furthermore when applied to the partially unannotated UniRef100 database the trained RNN models not only predict candidates validated by existing annotations but also identify currently unannotated sequences Some predictions made by the RNN models for the ferritin like iron sequestering function were experimentally validated Notably these validated sequences differ significantly from known characterized proteins and each other making them challenging to predict using popular bioinformatics methods
A Promising Avenue for Advancing Our Understanding of Protein Function
Overall as sequencing and experimental characterization data continue to increase rapidly this machine learning approach based on RNN holds great potential for discovering and predicting homologues for a wide range of protein functions By leveraging primary amino acid sequences without relying on traditional bioinformatics methods such as sequence alignment or feature engineering this approach offers a promising avenue for advancing our understanding of protein function
As high-throughput biological sequencing becomes faster and cheaper, the need to extract useful information from sequencing becomes ever more paramount, often limited by low-throughput experimental characterizations. For proteins, accurate prediction of their functions directly from their primary amino-acid sequences has been a long standing challenge. Here, machine learning using artificial recurrent neural networks (RNN) was applied towards classification of protein function directly from primary sequence without sequence alignment, heuristic scoring or feature engineering. The RNN models containing long-short-term-memory (LSTM) units trained on public, annotated datasets from UniProt achieved high performance for in-class prediction of four important protein functions tested, particularly compared to other machine learning algorithms using sequence-derived protein features. RNN models were used also for out-of-class predictions of phylogenetically distinct protein families with similar functions, including proteins of the CRISPR-associated nuclease, ferritin-like iron storage and cytochrome P450 families. Applying the trained RNN models on the partially unannotated UniRef100 database predicted not only candidates validated by existing annotations but also currently unannotated sequences. Some RNN predictions for the ferritin-like iron sequestering function were experimentally validated, even though their sequences differ significantly from known, characterized proteins and from each other and cannot be easily predicted using popular bioinformatics methods. As sequencing and experimental characterization data increases rapidly, the machine-learning approach based on RNN could be useful for discovery and prediction of homologues for a wide range of protein functions.
