Drug REpurposing using AI/ML tools - for Rare Diseases (DREAM-RD): A case study with Fragile X Syndrome (FXS)
Agastheeswaramoorthy, K.; Sevilimedu, A.
Show abstract
Drug repositioning is emerging as an increasingly relevant option for rare disease therapy and management. Various methods for identifying suitable drug candidates have been tried and range from clinical symptomatic repurposing to data driven strategies which are based on the disease-specific gene or protein expression, modification, signalling and physiological perturbation profiles. The use of Artificial Intelligence (AI) and machine learning algorithms (ML) allows one to combine diverse data sets, and extract disease-specific data profiles which may not be intuitive or apparent from a subset of data. In this case study with Fragile X syndrome and autism, we have used multiple computational methodologies to extract profiles, which are then combined to arrive at a comprehensive signature (disease DEG). This DEG was then used to interrogate the large collection of drug-induced perturbation profiles present in public databases, to find appropriate small molecules to reverse or mimic the disease-profiles. We have labelled this pipeline Drug Repurposing using AI/ML tools - for Rare Diseases (DREAM-RD). We have shortlisted over 100 FDA approved drugs using the aforementioned pipeline, which may potentially be useful to ameliorate autistic phenotypes associated with FXS.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Cluster analysis on high dimensional RNA-seq data with applications to cancer research- An evaluation study 93%
- Two-Step Mixed Model Approach to Analyzing Differential Alternative RNA Splicing 93%
- Applying machine learning in motor activity time series of depressed bipolar and unipolar patients. 93%
Similar papers in this journal
- Protein profiling of WERI RB1 and etoposide resistant WERI ETOR reveals new insights into topoisomerase inhibitor resistance in retinoblastoma 94%
- Multi-run Concrete Autoencoder to Identify Prognostic lncRNAs for 12 Cancers 93%
- Data independent acquisition mass spectrometry (DIA-MS) analysis of FFPE rectal cancer samples offers in depth proteomics characterization of response to neoadjuvant chemoradiotherapy 92%
Similar papers in this journal
- Discovering Key Transcriptomic Regulators in Pancreatic Ductal Adenocarcinoma using Dirichlet Process Gaussian Mixture Model 94%
- Novel ratio-metric features enable the identification of new driver genes across cancer types 94%
- Candidate genes associated with neurological manifestations of COVID-19: Meta-analysis using multiple computational approaches 93%
Similar papers in this journal
- Universal nature of drug treatment responses in drug-tissue-wide model-animal experiments using tensordecomposition-based unsupervised featureextraction 94%
- Tensor decomposition-Based Unsupervised Feature Extraction Applied to Single-Cell Gene Expression Analysis 94%
- Analysis of Pan-Omics Data in Human Interactome Network (APODHIN) 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.