Biology subjects

Ju, C. J.-T.

Publications and source records attributed to Ju, C. J.-T..

6 recordsLinked to original sources

bioRxiv2020

Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases

The widespread of Coronavirus has led to a worldwide pandemic with a high mortality rate. Currently, the knowledge accumulated from different studies about this virus is very limited. Leveraging a wide-range of biological knowledge, such as gene on-tology and protein-protein interaction (PPI) networks from other closely related species presents a vital approach to infer the molecular impact of a new species. In this paper, we propose the transferred multi-relational embedding model Bio-JOIE to capture the knowledge of gene ontology and PPI networks, which demonstrates superb capability in modeling the SARS-CoV-2-human protein interactions. Bio-JOIE jointly trains two model components. The knowledge model encodes the relational facts from the protein and GO domains into separated embedding spaces, using a hierarchy-aware encoding technique employed for the GO terms. On top of that, the transfer model learns a non-linear transformation to transfer the knowledge of PPIs and gene ontology annotations across their embedding spaces. By leveraging only structured knowledge, Bio-JOIE significantly outperforms existing state-of-the-art methods in PPI type prediction on multiple species. Furthermore, we also demonstrate the potential of leveraging the learned representations on clustering proteins with enzymatic function into enzyme commission families. Finally, we show that Bio-JOIE can accurately identify PPIs between the SARS-CoV-2 proteins and human proteins, providing valuable insights for advancing research on this new disease.

bioinformatics↗

bioRxiv2020

JEDI: Circular RNA Prediction based on Junction Encoders and Deep Interaction among Splice Sites

Circular RNA is a novel class of endogenous non-coding RNAs that have been largely discovered in eukaryotic transcriptome. The circular structure arises from a non-canonical splicing process, where the donor site backsplices to an upstream acceptor site. These circular form of RNAs are conserved across species, and often show tissue or cell-specific expression. Emerging evidences have suggested its vital roles in gene regulation, which are further associated with various types of diseases. As the fundamental effort to elucidate its function and mechanism, numerous efforts have been devoted to predicting circular RNA from its primary sequence. However, statistical learning methods are constrained by the information presented with explicit features, and the existing deep learning approach falls short on fully exploring the positional information of the splice sites and their deep interaction. We present an effective and robust end-to-end framework, JEDI, for circular RNA prediction using only the nucleotide sequence. Our framework first leverages the attention mechanism to encode each junction site based on deep bidirectional recurrent neural networks and then presents the novel cross-attention layer to model deep interaction among these sites for backsplicing. Finally, JEDI is capable of not only addressing the task of circular RNA prediction but also interpreting the relationships among splice sites to discover the hotspots for backsplicing within a gene region. Experimental evaluations demonstrate that JEDI significantly outperforms several state-of-the-art approaches in circular RNA prediction on both isoform-level and gene-level. Moreover, JEDI also shows promising results on zero-shot backsplicing discovery, where none of the existing approaches can achieve. The implementation of our framework is available at https://github.com/hallogameboy/JEDI.

bioinformatics↗

bioRxiv2019

Mutation effect estimation on protein-protein interactions using deep contextualized representation learning

The functional impact of protein mutations is reflected on the alteration of conformation and thermodynamics of protein-protein interactions (PPIs). Quantifying the changes of two interacting proteins upon mutations are commonly carried out by computational approaches. Hence, extensive research efforts have been put to the extraction of energetic or structural features on proteins, followed by statistical learning methods to estimate the effects of mutations to PPI properties. Nonetheless, such features require extensive human labors and expert knowledge to obtain, and have limited abilities to reflect point mutations. We present an end-to-end deep learning framework, MuPIPR, to estimate the effects of mutations on PPIs. MuPIPR incorporates a contextualized representation mechanism of amino acids to propagate the effects of a point mutation to surrounding amino acid representations, therefore amplifying the subtle change in a long protein sequence. On top of that, MuPIPR leverages a Siamese residual recurrent convolutional neural encoder to encode a wildtype protein pair and its mutation pair. Multiple-layer perceptron regressors are applied to the protein pair representations to predict the quantifiable changes of PPI properties upon mutations. Experimental evaluations show that MuPIPR outperforms various state-of-the-art systems on the change of binding affinity prediction and the buried surface area prediction. The software implementation is available at https://github.com/guangyu-zhou/MuPIPR

bioinformatics↗

bioRxiv2019

Learning Representations for Gene Ontology Terms by Contextualized Text Encoders

Protein functions can be described by the Gene Ontology (GO) terms, allowing us to compare the functions of two proteins by measuring the similarity of the terms assigned to them. Recent works have applied neural network models to derive the vector representations for GO terms and compute similarity scores for these terms by comparing their vector embeddings. There are two typical ways to embed GO terms into vectors; a model can either embed the definitions of the terms or the topology of the terms in the ontology. In this paper, we design three tasks to critically evaluate the GO embeddings of two recent neural network models, and further introduce additional models for embedding GO terms, adapted from three popular neural network frameworks: Graph Convolution Network (GCN), Embeddings from Language Models (ELMo), and Bidirectional Encoder Representations from Transformers (BERT), which have not yet been explored in previous works. Task 1 studies edge cases where the GO embeddings may not provide meaningful similarity scores for GO terms. We find that all neural network based methods fail to produce high similarity scores for related terms when these terms have low Information Content values. Task 2 is a canonical task which estimates how well GO embeddings can compare functions of two orthologous genes or two interacting proteins. The best neural network methods for this task are those that embed GO terms using their definitions, and the differences among such methods are small. Task 3 evaluates how GO embeddings affect the performance of GO annotation methods, which predict whether a protein should be labeled by certain GO terms. When the annotation datasets contain many samples for each GO label, GO embeddings do not improve the classification accuracy. Machine learning GO annotation methods often remove rare GO labels from the training datasets so that the model parameters can be efficiently trained. We evaluate whether GO embeddings can improve prediction of rare labels unseen in the training datasets, and find that GO embeddings based on the BERT framework achieve the best results in this setting. We present our embedding methods and three evaluation tasks as the basis for future research on this topic.

bioinformatics↗

bioRxiv2018

Lasagna: Multifaceted Protein-Protein Interaction Prediction Based on Siamese Residual RCNN

Sequence-based protein-protein interaction (PPI) prediction represents a fundamental computational biology problem. To address this problem, extensive research efforts have been made to extract predefined features from the sequences. Based on these features, statistical algorithms are learned to classify the PPIs. However, such explicit features are usually costly to extract, and typically have limited coverage on the PPI information. Hence, we present an end-to-end framework, Lasagna, for PPI predictions using only the primary sequences of a protein pair. Lasagna incorporates a deep residual recurrent convolutional neural network in the Siamese learning architecture, which leverages both robust local features and contextualized information that are significant for capturing the mutual influence of protein sequences. Our framework relieves the data pre-processing efforts that are required by other systems, and generalizes well to different application scenarios. Experimental evaluations show that Lasagna outperforms various state-of-the-art systems on the binary PPI prediction problem. Moreover, it shows a promising performance on more challenging problems of interaction type prediction and binding affinity estimation, where existing approaches fall short. The implementation of our framework is available at https://github.com/muhaochen/seq_ppi.git

bioinformatics↗

bioRxiv2017

TahcoRoll: An Efficient Approach for Signature Profiling in Genomic Data through Variable-Length k-mers

k-mer profiling has been one of the trending approaches to analyze read data generated by high-throughput sequencing technologies. The tasks of k-mer profiling include, but are not limited to, counting the frequencies and determining the occurrences of short sequences in a dataset. The notion of k-mer has been extensively used to build de Bruijn graphs in genome or transcriptome assembly, which requires examining all possible k-mers presented in the dataset. Recently, an alternative way of profiling has been proposed, which constructs a set of representative k-mers as genomic markers and profiles their occurrences in the sequencing data. This technique has been applied in both transcript quantification through RNA-Seq and taxonomic classification of metagenomic reads. Most of these applications use a set of fixed-size k-mers since the majority of existing k-mer counters are inadequate to process genomic sequences with variable-length k-mers. However, choosing the appropriate k is challenging, as it varies for different applications. As a pioneer work to profile a set of variable-length k-mers, we propose TahcoRoll in order to enhance the Aho-Corasick algorithm. More specifically, we use one bit to represent each nucleotide, and integrate the rolling hash technique to construct an efficient in-memory data structure for this task. Using both synthetic and real datasets, results show that TahcoRoll outperforms existing approaches in either or both time and memory efficiency without using any disk space. In addition, compared to the most efficient state-of-the-art k-mer counters, such as KMC and MSBWT, TahcoRoll is the only approach that can process long read data from both PacBio and Oxford Nanopore on a commodity desktop computer. The source code of TahcoRoll is implemented in C++14, and available at https://github.com/chelseaju/TahcoRoll.git.

bioinformatics↗