A Survey of Network Representation Learning Methods for Link Prediction in Biological Network

Personalized decision support system for tailoring IgA nephropathy treatment strategies

BACKGROUND

The ongoing debate surrounding the use of immunosuppressive treatments for IgA nephropathy (IgAN) underscores the demand for personalized and effective strategies.

METHODS

Analyzed data from 807 IgAN patients over 5+ years using three methods: Random Forest with molecular biomarkers, network biomarkers with graph engineering, and an auto-encoder model. All models were trained using identical demographic, clinical, and pathological data, employing an 80-20 split for training and testing purposes.

RESULTS

In the comprehensive assessment of IgAN prognosis, the Random Forest model, employing molecular biomarkers, demonstrated strong performance metrics (AUC = 0.83, sensitivity = 0.51, specificity = 0.96). However, traditional graph feature engineering on patient-specific networks outperformed these results with an AUC of 0.90, sensitivity of 0.64, and specificity of 0.94. The Auto-encoder model showed the best accuracy (AUC = 0.91, sensitivity = 0.46, specificity = 0.96). The findings highlighted the superior predictive capabilities of network biomarkers over molecular biomarkers for adverse renal outcome prediction in IgAN. Consequently, we integrated Auto-encoder-derived Network Biomarkers with Random Forest Models to enhance prognostic precision in diverse IgAN treatment scenarios. The prediction for the prognosis of patients receiving supportive care, glucocorticoid therapy, and immunosuppressant treatment yielded AUC values of 0.95, 0.96, and 1, respectively, indicating high specificity. Drawing from these insights, we pioneered the development of an innovative decision support model for IgAN treatment. This model demonstrated the ability to make medical decisions comparable to those by experienced nephrologists, enabling the customization of personalized disease management strategies.

CONCLUSION

Our system accurately predicted IgAN prognosis and evaluated various treatment efficacies, aiding physicians in devising optimal therapeutic strategies for patients.

Effective holistic characterization of small molecule effects using heterogeneous biological networks

The two most common reasons for attrition in therapeutic clinical trials are efficacy and safety. We integrated heterogeneous data to create a human interactome network to comprehensively describe drug behavior in biological systems, with the goal of accurate therapeutic candidate generation. The Computational Analysis of Novel Drug Opportunities (CANDO) platform for shotgun multiscale therapeutic discovery, repurposing, and design was enhanced by integrating drug side effects, protein pathways, protein-protein interactions, protein-disease associations, and the Gene Ontology, and complemented with its existing drug/compound, protein, and indication libraries. These integrated networks were reduced to a "multiscale interactomic signature" for each compound that describe its functional behavior as vectors of real values. These signatures are then used for relating compounds to each other with the hypothesis that similar signatures yield similar behavior. Our results indicated that there is significant biological information captured within our networks (particularly via side effects) which enhance the performance of our platform, as evaluated by performing all-against-all leave-one-out drug-indication association benchmarking as well as generating novel drug candidates for colon cancer and migraine disorders corroborated via literature search. Further, drug impacts on pathways derived from computed compound-protein interaction scores served as the features for a random forest machine learning model trained to predict drug-indication associations, with applications to mental disorders and cancer metastasis highlighted. This interactomic pipeline highlights the ability of Computational Analysis of Novel Drug Opportunities to accurately relate drugs in a multitarget and multiscale context, particularly for generating putative drug candidates using the information gleaned from indirect data such as side effect profiles and protein pathway information.

Evolution of brain functional plasticity associated with increasing symptom severity in degenerative cervical myelopathy

BACKGROUND

Advanced imaging modalities have helped elucidate the cerebral alterations associated with neurological impairment caused by degenerative cervical myelopathy (DCM), but it remains unknown how brain functional network changes at different stages of myelopathy severity in DCM patients, and if patterns in network connectivity can be used to predict transition to more myelopathic stages of DCM.

METHODS

This pilot cross-sectional study, which involves the collection of resting-state functional MRI (rs-fMRI) images and the modified Japanese Orthopedic Association (mJOA) score, enrolled 116 participants (99 patients and 17 healthy controls) from 2016 to 2021. The patient cohort included 21patients with asymptomatic spinal cord compression, 48 mild DCM patients, and 20 moderate or severe DCM patients. Functional connectivity networks were quantified for all participants, and the transition matrices were quantified to determine the differences in network connectivity through increasingly myelopathic stages of DCM. Additionally, a link prediction model was used to determine whether more severe stages of DCM can be predicted from less symptomatic stages using the transition matrices.

FINDINGS

Results indicated interruptions in most connections within the sensorimotor network in conjunction with spinal cord compression, while compensatory connectivity was observed within and between primary and secondary sensorimotor regions, subcortical regions, visuospatial regions including the cuneus, as well as the brainstem and cerebellum. A link prediction model achieved an excellent predictive performance in estimating connectivity of more severe myelopathic stages of DCM, with the highest area under the receiver operator curve (AUC) of 0.927 for predicting mild DCM from patients with asymptomatic spinal cord compression.

INTERPRETATION

A series of predictable changes in functional connectivity occur throughout the stages of DCM pathogenesis. The brainstem and cerebellum appear highly influential in optimizing sensorimotor function during worsening myelopathy. The link predication model can inclusively estimate brain alterations associated with myelopathy severity.

FUNDING

NIH/NINDS grants (1R01NS078494-01A1, and 2R01NS078494).