Rui Fa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Rui Fa has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
Rodrigo C. de Lamare
Department of Electronics, The University of York, Heslington, York, YO10 5DD, UK
16 shared publicationsBasel Abu-Jamous
Department of Electronic and Computer Engineering, Brunel University, UK
9 shared publications- Asoke Kumar Nandi
Brunel University of London
8 shared publications - David J. Roberts
Biomedical Research Centre Haematology Theme, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; NHS Blood and Transplant, John Radcliffe Hospital, Oxford, UK
6 shared publications Asoke K. Nandi
Department of Electronic and Computer Engineering, Brunel University, Uxbridge, UB8 3PH, United Kingdom
5 shared publications- Bayan S. Sharif
School of Electrical and Electronic Engineering, Newcastle University, UK
4 shared publications
Latest Publications
- Open Access
- 24 January 2024
- Published by JMIR Publications Inc. in JMIR Preprints
A SHAP Value-Based Variable Selection Method Improves the Prediction of Prolonged Hospital Length of Stay (Preprint)
BACKGROUND A prolonged length of hospitalization drains both human and material hospital resources as well having a deleterious psychological effect on the patient. Some patients are at greater risk of a prolonged hospital stay than others and it is important to identify them in the first days after admission so as to implement appropriate care as soon as possible and program staff and bed occupancy needs. OBJECTIVE The objective of this study is to optimize the prediction of prolonged length of hospital stay (LOS) by refining the selection of variables using an interpretable machine-learning algorithm. METHODS Deidentified patient administrative and clinical data from various sources are stored in our University Hospital’s Clinical Data Warehouse, which contains data from 134,840 adult patients with 273,693 hospitalizations between 2016 and 2018. We conducted a two-stage predictive modeling experiment. Initially, we utilized conventional clinical variables and composite variables (by aggregating appropriate conventional variables to form new variables) in several machine-learning algorithms to select the best-performing model. Next, we employed the SHAP method to identify the most important predictive variables and used these to further improve the predictive model. RESULTS XGBoost with an undersampling method outperformed other methods with an AUC-ROC of 0.802 (95% CI: 0.801-0.803) and an F2 score of 0.533 (95% CI: 0.533-0.534). The predictive performance was equivalent if we selected half the number of variables based on the SHAP-value with an AUC-ROC of 0.804 (95%: CI: 0.803-0.805) and F2 score of 0.536 (95%: CI: 0.535-0.536). This consistency held for significant variable reduction with SHAP values of more than 70% from 523 to 150. CONCLUSIONS SHAP-value-based variable selection allowed a reduction in the number of variables for equivalent predictive performance, making optimum prediction of prolonged LOS easier to implement in routine clinical practice by prioritizing the predictive factors.
- 24 January 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA SHAP Value-Based Variable Selection Method Improves the Prediction of Prolonged Hospital Length of Stay (Preprint)
BACKGROUND A prolonged length of hospitalization drains both human and material hospital resources as well having a deleterious psychological effect on the patient. Some patients are at greater risk of a prolonged hospital stay than others and it is important to identify them in the first days after admission so as to implement appropriate care as soon as possible and program staff and bed occupancy needs. OBJECTIVE The objective of this study is to optimize the prediction of prolonged length of hospital stay (LOS) by refining the selection of variables using an interpretable machine-learning algorithm. METHODS Deidentified patient administrative and clinical data from various sources are stored in our University Hospital’s Clinical Data Warehouse, which contains data from 134,840 adult patients with 273,693 hospitalizations between 2016 and 2018. We conducted a two-stage predictive modeling experiment. Initially, we utilized conventional clinical variables and composite variables (by aggregating appropriate conventional variables to form new variables) in several machine-learning algorithms to select the best-performing model. Next, we employed the SHAP method to identify the most important predictive variables and used these to further improve the predictive model. RESULTS XGBoost with an undersampling method outperformed other methods with an AUC-ROC of 0.802 (95% CI: 0.801-0.803) and an F2 score of 0.533 (95% CI: 0.533-0.534). The predictive performance was equivalent if we selected half the number of variables based on the SHAP-value with an AUC-ROC of 0.804 (95%: CI: 0.803-0.805) and F2 score of 0.536 (95%: CI: 0.535-0.536). This consistency held for significant variable reduction with SHAP values of more than 70% from 523 to 150. CONCLUSIONS SHAP-value-based variable selection allowed a reduction in the number of variables for equivalent predictive performance, making optimum prediction of prolonged LOS easier to implement in routine clinical practice by prioritizing the predictive factors.
- Open Access
- 23 July 2019
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 14 (7) , e0209958
Using deep maxout neural networks to improve the accuracy of function prediction from protein interaction networks
Protein-protein interaction network data provides valuable information that infers direct links between genes and their biological roles. This information brings a fundamental hypothesis for protein function prediction that interacting proteins tend to have similar functions. With the help of recently-developed network embedding feature generation methods and deep maxout neural networks, it is possible to extract functional representations that encode direct links between protein-protein interactions information and protein function. Our novel method, STRING2GO, successfully adopts deep maxout neural networks to learn functional representations simultaneously encoding both protein-protein interactions and functional predictive information. The experimental results show that STRING2GO outperforms other protein-protein interaction network-based prediction methods and one benchmark method adopted in a recent large scale protein function prediction competition.
- 23 July 2019
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 14 (7) , e0209958
Open AccessUsing deep maxout neural networks to improve the accuracy of function prediction from protein interaction networks
Protein-protein interaction network data provides valuable information that infers direct links between genes and their biological roles. This information brings a fundamental hypothesis for protein function prediction that interacting proteins tend to have similar functions. With the help of recently-developed network embedding feature generation methods and deep maxout neural networks, it is possible to extract functional representations that encode direct links between protein-protein interactions information and protein function. Our novel method, STRING2GO, successfully adopts deep maxout neural networks to learn functional representations simultaneously encoding both protein-protein interactions and functional predictive information. The experimental results show that STRING2GO outperforms other protein-protein interaction network-based prediction methods and one benchmark method adopted in a recent large scale protein function prediction competition.
- Open Access
- 11 June 2018
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 13 (6) , e0198216
Predicting human protein function with multi-task deep neural networks
Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.
- 11 June 2018
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 13 (6) , e0198216
Open AccessPredicting human protein function with multi-task deep neural networks
Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.
- Open Access
Predicting Human Protein Function with Multi-task Deep Neural Networks
Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.
Open AccessPredicting Human Protein Function with Multi-task Deep Neural Networks
Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.
- Open Access
- 4 June 2015
- Published by Springer Nature in BMC Bioinformatics
- Vol. 16 (1) , 184
UNCLES: method for the identification of genes differentially consistently co-expressed in a specific subset of datasets
Collective analysis of the increasingly emerging gene expression datasets are required. The recently proposed binarisation of consensus partition matrices (Bi-CoPaM) method can combine clustering results from multiple datasets to identify the subsets of genes which are consistently co-expressed in all of the provided datasets in a tuneable manner. However, results validation and parameter setting are issues that complicate the design of such methods. Moreover, although it is a common practice to test methods by application to synthetic datasets, the mathematical models used to synthesise such datasets are usually based on approximations which may not always be sufficiently representative of real datasets.
- 4 June 2015
- Published by Springer Nature in BMC Bioinformatics
- Vol. 16 (1) , 184
Open AccessUNCLES: method for the identification of genes differentially consistently co-expressed in a specific subset of datasets
Collective analysis of the increasingly emerging gene expression datasets are required. The recently proposed binarisation of consensus partition matrices (Bi-CoPaM) method can combine clustering results from multiple datasets to identify the subsets of genes which are consistently co-expressed in all of the provided datasets in a tuneable manner. However, results validation and parameter setting are issues that complicate the design of such methods. Moreover, although it is a common practice to test methods by application to synthetic datasets, the mathematical models used to synthesise such datasets are usually based on approximations which may not always be sufficiently representative of real datasets.
- 1 April 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 962-966
Scalable clustering based on enhanced-SMART for large-scale FMRI datasets
In this paper, we propose a scalable clustering paradigm to address the problems of excessive computational load and limited clustering performance in large-scale data. The proposed method employs the enhanced splitting merging awareness tactics (E-SMART) algorithm. The large-scale dataset is divided into many sub-datasets sampled randomly from original data. These sub-datasets are clustered using E-SMART with the number of clusters K detected automatically and the resulting partitions are combined and re-clustered. We evaluate our method using synthetic fMRI datasets with different noise levels and one real fMRI dataset. Results show that the accuracy and execution time outperforms the traditional clustering algorithms in large-scale datasets.
- 1 April 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 962-966
Scalable clustering based on enhanced-SMART for large-scale FMRI datasets
In this paper, we propose a scalable clustering paradigm to address the problems of excessive computational load and limited clustering performance in large-scale data. The proposed method employs the enhanced splitting merging awareness tactics (E-SMART) algorithm. The large-scale dataset is divided into many sub-datasets sampled randomly from original data. These sub-datasets are clustered using E-SMART with the number of clusters K detected automatically and the resulting partitions are combined and re-clustered. We evaluate our method using synthetic fMRI datasets with different noise levels and one real fMRI dataset. Results show that the accuracy and execution time outperforms the traditional clustering algorithms in large-scale datasets.
- Open Access
- 1 January 2015
- Published by Wiley in International Journal of Antennas and Propagation
- Vol. 2015, 1-10
Direct Data Domain Sparsity-Based STAP Utilizing Subaperture Smoothing Techniques
We propose a novel direct data domain (D3) sparsity-based space-time adaptive processing (STAP) algorithm utilizing subaperture smoothing techniques for airborne radar applications. Different from either normal sparsity-based STAP or D3 sparsity-based STAP, the proposed algorithm firstly uses only the snapshot in the cell under test (CUT) to generate multiple subsnapshots by exploiting the space-time structure of the steering vector and the uncorrelated nature of the components of the interference covariance matrix. Since the interference spectrum is sparse in the whole angle-Doppler plane, by employing a sparse regularization, the generated multiple subsnapshots are jointly used to recover the interference spectrum. The interference covariance matrix is then estimated from the interference spectrum, followed by the space-time filtering and the target detection. Simulation results illustrate that the proposed algorithm outperforms the generalized forward/backward method, the conventional D3 least squares STAP algorithm, and the existing D3 sparsity-based STAP algorithm. Furthermore, compared with the normal sparsity-based STAP algorithm using multiple snapshots, the proposed algorithm can also avoid the performance degradation caused by discrete interferers merely appearing in the CUT.
- 1 January 2015
- Published by Wiley in International Journal of Antennas and Propagation
- Vol. 2015, 1-10
Open AccessDirect Data Domain Sparsity-Based STAP Utilizing Subaperture Smoothing Techniques
We propose a novel direct data domain (D3) sparsity-based space-time adaptive processing (STAP) algorithm utilizing subaperture smoothing techniques for airborne radar applications. Different from either normal sparsity-based STAP or D3 sparsity-based STAP, the proposed algorithm firstly uses only the snapshot in the cell under test (CUT) to generate multiple subsnapshots by exploiting the space-time structure of the steering vector and the uncorrelated nature of the components of the interference covariance matrix. Since the interference spectrum is sparse in the whole angle-Doppler plane, by employing a sparse regularization, the generated multiple subsnapshots are jointly used to recover the interference spectrum. The interference covariance matrix is then estimated from the interference spectrum, followed by the space-time filtering and the target detection. Simulation results illustrate that the proposed algorithm outperforms the generalized forward/backward method, the conventional D3 least squares STAP algorithm, and the existing D3 sparsity-based STAP algorithm. Furthermore, compared with the normal sparsity-based STAP algorithm using multiple snapshots, the proposed algorithm can also avoid the performance degradation caused by discrete interferers merely appearing in the CUT.
- Open Access
- 29 September 2014
- Published by Springer Nature in BMC Bioinformatics
- Vol. 15 (1) , 1-20
Comprehensive analysis of forty yeast microarray datasets reveals a novel subset of genes (APha-RiB) consistently negatively associated with ribosome biogenesis
The scale and complexity of genomic data lend themselves to analysis using sophisticated mathematical techniques to yield information that can generate new hypotheses and so guide further experimental investigations. An ensemble clustering method has the ability to perform consensus clustering over the same set of genes from different microarray datasets by combining results from different clustering methods into a single consensus result. In this paper we have performed comprehensive analysis of forty yeast microarray datasets. One recently described Bi-CoPaM method can analyse expressions of the same set of genes from various microarray datasets while using different clustering methods, and then combine these results into a single consensus result whose clusters’ tightness is tunable from tight, specific clusters to wide, overlapping clusters. This has been adopted in a novel way over genome-wide data from forty yeast microarray datasets to discover two clusters of genes that are consistently co-expressed over all of these datasets from different biological contexts and various experimental conditions. Most strikingly, average expression profiles of those clusters are consistently negatively correlated in all of the forty datasets while neither profile leads or lags the other. The first cluster is enriched with ribosomal biogenesis genes. The biological processes of most of the genes in the second cluster are either unknown or apparently unrelated although they show high connectivity in protein-protein and genetic interaction networks. Therefore, it is possible that this mostly uncharacterised cluster and the ribosomal biogenesis cluster are transcriptionally oppositely regulated by some common machinery. Moreover, we anticipate that the genes included in this previously unknown cluster participate in generic, in contrast to specific, stress response processes. These novel findings illuminate coordinated gene expression in yeast and suggest several hypotheses for future experimental functional work. Additionally, we have demonstrated the usefulness of the Bi-CoPaM-based approach, which may be helpful for the analysis of other groups of (microarray) datasets from other species and systems for the exploration of global genetic co-expression.
- 29 September 2014
- Published by Springer Nature in BMC Bioinformatics
- Vol. 15 (1) , 1-20
Open AccessComprehensive analysis of forty yeast microarray datasets reveals a novel subset of genes (APha-RiB) consistently negatively associated with ribosome biogenesis
The scale and complexity of genomic data lend themselves to analysis using sophisticated mathematical techniques to yield information that can generate new hypotheses and so guide further experimental investigations. An ensemble clustering method has the ability to perform consensus clustering over the same set of genes from different microarray datasets by combining results from different clustering methods into a single consensus result. In this paper we have performed comprehensive analysis of forty yeast microarray datasets. One recently described Bi-CoPaM method can analyse expressions of the same set of genes from various microarray datasets while using different clustering methods, and then combine these results into a single consensus result whose clusters’ tightness is tunable from tight, specific clusters to wide, overlapping clusters. This has been adopted in a novel way over genome-wide data from forty yeast microarray datasets to discover two clusters of genes that are consistently co-expressed over all of these datasets from different biological contexts and various experimental conditions. Most strikingly, average expression profiles of those clusters are consistently negatively correlated in all of the forty datasets while neither profile leads or lags the other. The first cluster is enriched with ribosomal biogenesis genes. The biological processes of most of the genes in the second cluster are either unknown or apparently unrelated although they show high connectivity in protein-protein and genetic interaction networks. Therefore, it is possible that this mostly uncharacterised cluster and the ribosomal biogenesis cluster are transcriptionally oppositely regulated by some common machinery. Moreover, we anticipate that the genes included in this previously unknown cluster participate in generic, in contrast to specific, stress response processes. These novel findings illuminate coordinated gene expression in yeast and suggest several hypotheses for future experimental functional work. Additionally, we have demonstrated the usefulness of the Bi-CoPaM-based approach, which may be helpful for the analysis of other groups of (microarray) datasets from other species and systems for the exploration of global genetic co-expression.
- Open Access
- 1 September 2014
Dual-Layer Network Representation Exploiting Information Characterization
- 1 September 2014
Open AccessDual-Layer Network Representation Exploiting Information Characterization