Fast model-based protein homology detection without alignment

By Sepp Hochreiter, Martin Heusel, Klaus Obermayer. 2007

136 citations recorded by the source corpus.

Subfields: Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

RUDDER: Return Decomposition for Delayed Rewards (2018, methodology): “lows for uniform credit assignment. The most commonly used LSTM memory cell architecture in the literature [39, 112] contains forget gates [31, 32] and peephole connections [30]. In our previous work [57, 53], we found that peephole connections are only useful for modeling time series, but not for l”
Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Recurrent neural networks show good performance for homology and protein family identification [245,246].”
Biological Sequence Modeling with Convolutional Kernel Networks (2017, neutral): “While training string kernel-based models requires hours or days [Hochreiter et al., 2007], training CNN or CKN-seq are done in a few minutes.”
Temporal Models for Predicting Student Dropout in Massive Open Online Courses (2015, background): “Over the past decade, LSTM has been applied to various real-world problems, such as protein structure prediction [24], speech recognition [25], [26] and handwriting recognition [27], [28].”
Deep learning in bioinformatics (2016, methodology): “Recurrent neural networks Protein structure [88–90] Brain decoding [168] Gene expression regulation [105–107] Anomaly classification [177, 178] Protein classification [109, 110]”
Protein remote homology detection based on bidirectional long short-term memory (2017, methodology): “A widely used benchmark dataset has been used to evaluate the performance of various methods [28], which was constructed based on the SCOP database [50] by Hochreiter [48].”
Deep Recurrent Neural Network for Protein Function Prediction from Sequence (2017, background): “The memory or internal state of the LSTM neuron processing entire protein sequences, unlike other machine learning methods that employ short, predefined motif windows 3–5 , allows selective retention of important sequence features across long distances 14 .”
A deep learning genome-mining strategy for biosynthetic gene cluster prediction (2019, methodology): “We addressed this algorithmic limitation by implementing a deep learning approach using Recurrent Neural Networks (RNNs) and vector representations of protein family (Pfam) (22) domains which together, unlike HMMs, are capable of intrinsically sensing short- and long-term dependency effects between ”
Modern Hopfield Networks and Attention for Immune Repertoire Classification (2020, methodology): “DeepRC sets out to avoid the above-mentioned constraints of current methods by (a) applying transformer-like attention-pooling instead of max-pooling and learning a classifier on the repertoire rather than on the sequence-representation, (b) pooling learned representations rather than predictions, a”
Supervised Sequence Labelling with Recurrent Neural Networks (2012, methodology): “It has also proved advantageous in real-world domains such as speech processing (Graves and Schmidhuber, 2005b) and bioinformatics (Hochreiter et al., 2007).”
Understanding LSTM - a tutorial into Long Short-Term Memory Recurrent Neural Networks (2019, background): “Covered problems include protein secondary structure prediction [40, 9] and music generation [15].”
A comprehensive review and comparison of different computational methods for protein remote homology detection (2018, methodology): “RankProp [97], ProtEmbed [98] and LSTM [100] expand their training database by searching against a large-scale nonredundant database.”