Feng Cui

Feng Cui

Auto-generated profile, based on publicly available information

Feng Cui

Thomas H. Gosnell School of Life Sciences, College of Science, Rochester Institute of Technology

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 April 2019 in BMC Systems Biology
Verified
Journal Article
Open access
PDF file
KKKishan Kc
Kishan Kc
RLRui Li
Rui Li
FCFeng Cui
Feng Cui
QYQi Yu
Qi Yu
AHAnne R. Haake
Anne R. Haake
The topological landscape of gene interaction networks provides a rich source of information for inferring functional patterns of genes or proteins. However, it is still a challenging task to aggregate heterogeneous biological information such as gene expression and gene interactions to achieve more accurate inference for prediction and discovery of new gene interactions. In particular, how to generate a unified vector representation to integrate diverse input data is a key challenge addressed here. We propose a scalable and robust deep learning framework to learn embedded representations to unify known gene interactions and gene expression for gene interaction predictions. These low- dimensional embeddings derive deeper insights into the structure of rapidly accumulating and diverse gene interaction networks and greatly simplify downstream modeling. We compare the predictive power of our deep embeddings to the strong baselines. The results suggest that our deep embeddings achieve significantly more accurate predictions. Moreover, a set of novel gene interaction predictions are validated by up-to-date literature-based database entries. The proposed model demonstrates the importance of integrating heterogeneous information about genes for gene network inference. GNE is freely available under the GNU General Public License and can be downloaded from GitHub ( https://github.com/kckishan/GNE ).

17 July 2020 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
PYPeng-Nien Yin
Peng-Nien Yin
KKKishan Kc
Kishan Kc
SWShishi Wei
Shishi Wei
QYQi Yu
Qi Yu
RLRui Li
Rui Li
FCFeng Cui
Feng Cui
Background: One of the most challenging tasks for bladder cancer diagnosis is to histologically differentiate two early stages, non-invasive Ta and superficially invasive T1, the latter of which is associated with a significantly higher risk of disease progression. Indeed, in a considerable number of cases, Ta and T1 tumors look very similar under microscope, making the distinction very difficult even for experienced pathologists. Thus, there is an urgent need for a favoring system based on machine learning (ML) to distinguish between the two stages of bladder cancer. Methods: A total of 1177 images of bladder tumor tissues stained by hematoxylin and eosin were collected by pathologists at University of Rochester Medical Center, which included 460 non-invasive (stage Ta) and 717 invasive (stage T1) tumors. Automatic pipelines were developed to extract features for three invasive patterns characteristic to the T1 stage bladder cancer (i.e., desmoplastic reaction, retraction artifact, and abundant pinker cytoplasm), using imaging processing software ImageJ and CellProfiler. Features extracted from the images were analyzed by a suite of machine learning approaches. Results: We extracted nearly 700 features from the Ta and T1 tumor images. Unsupervised clustering analysis failed to distinguish hematoxylin and eosin images of Ta vs. T1 tumors. With a reduced set of features, we successfully distinguished 1177 Ta or T1 images with an accuracy of 91–96% by six supervised learning methods. By contrast, convolutional neural network (CNN) models that automatically extract features from images produced an accuracy of 84%, indicating that feature extraction driven by domain knowledge outperforms CNN-based automatic feature extraction. Further analysis revealed that desmoplastic reaction was more important than the other two patterns, and the number and size of nuclei of tumor cells were the most predictive features. Conclusions: We provide a ML-empowered, feature-centered, and interpretable diagnostic system to facilitate the accurate staging of Ta and T1 diseases, which has a potential to apply to other types of cancer.

15 February 2019 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
JZJimmy F. Zhang
Jimmy F. Zhang
APAlex R. Paciorkowski
Alex R. Paciorkowski
PCPaul Alfred Craig
Paul Alfred Craig
FCFeng Cui
Feng Cui
Functional characterization of single nucleotide variants (SNVs) involves two steps, the first step is to convert DNA to protein and the second step is to visualize protein sequences with their structures. As massively parallel sequencing has emerged as a leading technology in genomics, resulting in a significant increase in data volume, direct visualization of SNVs together with associated protein sequences/structures in a new user interface (UI) would be a more effective way to assess their potential effects on protein function. We have developed BioVR, an easy-to-use interactive, virtual reality (VR)-assisted platform for integrated visual analysis of DNA/RNA/protein sequences and protein structures using Unity3D and the C# programming language. It utilizes the cutting-edge Oculus Rift, and Leap Motion hand detection, resulting in intuitive navigation and exploration of various types of biological data. Using Gria2 and its associated gene product as an example, we present this proof-of-concept software to integrate protein and nucleic acid data. For any amino acid or nucleotide of interest in the Gria2 sequence, it can be quickly linked to its corresponding location on Gria2 protein structure and visualized within VR. Using innovative 3D techniques, we provide a VR-based platform for visualization of DNA/RNA sequences and protein structures in aggregate, which can be extended to view omics data.

1 April 2022 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Open access
KKKishan Kc
Kishan Kc
RLRui Li
Rui Li
FCFeng Cui
Feng Cui
AHAnne R. Haake
Anne R. Haake
Biomedical interaction networks have incredible potential to be useful in the prediction of biologically meaningful interactions, identification of network biomarkers of disease, and the discovery of putative drug targets. Recently, graph neural networks have been proposed to effectively learn representations for biomedical entities and achieved state-of-the-art results in biomedical interaction prediction. These methods only consider information from immediate neighbors but cannot learn a general mixing of features from neighbors at various distances. In this paper, we present a higher-order graph convolutional network (HOGCN)to aggregate information from the higher-order neighborhood for biomedical interaction prediction. Specifically, HOGCN collects feature representations of neighbors at various distances and learns their linear mixing to obtain informative representations of biomedical entities. Experiments on four interaction networks, including protein-protein, drug-drug, drug-target, and gene-disease interactions, show that HOGCN achieves more accurate and calibrated predictions. HOGCN performs well on noisy, sparse interaction networks when feature representations of neighbors at various distances are considered. Moreover, a set of novel interaction predictions are validated by literature-based case studies.

28 September 2017 in Cell Cycle
Verified
Journal Article
Open access
FBFeifei Bao
Feifei Bao
PLPeter R. LoVerso
Peter R. LoVerso
JFJeffrey N. Fisk
Jeffrey N. Fisk
VZVictor B. Zhurkin
Victor B. Zhurkin
FCFeng Cui
Feng Cui
The tumor suppressor protein p53 interacts with DNA in a sequence-dependent manner. Thousands of p53 binding sites have been mapped genome-wide in normal and cancer cells. However, the way p53 selectively binds its cognate sites in different types of cells is not fully understood. Here, we performed a comprehensive analysis of 25 published p53 cistromes and identified 3,551 and 6,039 ‘high-confidence’ binding sites in normal and cancer cells, respectively. Our analysis revealed 2 distinct epigenetic features underlying p53-DNA interactions in vivo. First, p53 binding sites are associated with transcriptionally active histone marks (H3K4me3 and H3K36me3) in normal-cell chromatin, but with repressive histone marks (H3K27me3) in cancer-cell chromatin. Second, p53 binding sites in cancer cells are characterized by a lower level of DNA methylation than their counterparts in normal cells, probably related to global hypomethylation in cancers. Intriguingly, regardless of the cell type, p53 sites are highly enriched in the endogenous retroviral elements of the ERV1 family, highlighting the importance of this repeat family in shaping the transcriptional network of p53. Moreover, the p53 sites exhibit an unusual combination of chromatin patterns: high nucleosome occupancy and, at the same time, high sensitivity to DNase I. Our results suggest that p53 can access its target sites in a chromatin environment that is non-permissive to most DNA-binding transcription factors, which may allow p53 to act as a pioneer transcription factor in the context of chromatin.

9 May 2023 in Frontiers in Bioinformatics
Verified
Journal Article
Open access
IOIsaac Olatunji
Isaac Olatunji
FCFeng Cui
Feng Cui
Metastasis of cancer is directly related to death in almost all cases, however a lot is yet to be understood about this process. Despite advancements in the available radiological investigation techniques, not all cases of Distant Metastasis (DM) are diagnosed at initial clinical presentation. Also, there are currently no standard biomarkers of metastasis. Early, accurate diagnosis of DM is however crucial for clinical decision making, and planning of appropriate management strategies. Previous works have achieved little success in attempts to predict DM from either clinical, genomic, radiology, or histopathology data. In this work we attempt a multimodal approach to predict the presence of DM in cancer patients by combining gene expression data, clinical data and histopathology images. We tested a novel combination of Random Forest (RF) algorithm with an optimization technique for gene selection, and investigated if gene expression pattern in the primary tissues of three cancer types (Bladder Carcinoma, Pancreatic Adenocarcinoma, and Head and Neck Squamous Carcinoma) with DM are similar or different. Gene expression biomarkers of DM identified by our proposed method outperformed Differentially Expressed Genes (DEGs) identified by the DESeq2 software package in the task of predicting presence or absence of DM. Genes involved in DM tend to be more cancer type specific rather than general across all cancers. Our results also indicate that multimodal data is more predictive of metastasis than either of the three unimodal data tested, and genomic data provides the highest contribution by a wide margin. The results re-emphasize the importance for availability of sufficient image data when a weakly supervised training technique is used. Code is made available at: https://github.com/rit-cui-lab/Multimodal-AI-for-Prediction-of-Distant-Metastasis-in-Carcinoma-Patients.