Predicts small RNA targets in a sequence database using a plant-based scoring metric. Deep sequencing and computational methods are used to identify, profile and analyze non-conserved MIRNA genes in Arabidopsis thaliana.
Allows users to assess three-dimensional genomic interactions. The EP2vec's goal is to capture global sequence information. This program can serve for subsequent classification of enhancer-promoter interactions (EPIs) through supervised learning. This program includes two stages including the unsupervised feature extraction and supervised learning.
Aims to reconstruct regulatory landscapes from genomic features along the genome. TargetFinder is a computational method that integrates hundreds of genomics datasets to identify the minimal subset necessary for predicting individual enhancer-promoter interactions across the genome. It also includes techniques for mining massive collections of experimental data to shed new light on the mechanisms of distal gene regulation.
Determines enhancer-promoter interactions (EPIs) using only sequence-based features. SPEID locates putative enhancers and promoters in a particular cell type. It is based on a predictive model trained for that cell type. This tool assists users in the recognition of possible important non-coding mutations that may reduce or disrupt chromatin loops in cancer genomes. It is useful for the investigation of genomic sequence-level interactions.
Defines and predicts long-range enhancer-promoter interactions (EPI). PEP uses two complementary approaches strategies to exploit sequence-based information: PEP-Motif which uses transcription factor (TF) binding motifs as features and PEP-Word which extracts more generic sequence features via a word embedding model. This software incorporates also PEP-Integrate that combines selected features generated form PEP-Motif and PEP-Word.
Predicts enhancer-promoter interaction (EPI). Combine-CNN-Enhancer-and-Promoters is a simple convolutional neural network (CNN) architecture for EPI prediction. This tool is able to analyze subsequence features to identify transcription factor (TF) binding motifs.
Detects enhancer-associated genes within and across topologically associated domains (TADs) using epigenetic and transcriptomic data. InTAD tests for significant correlations between genes and enhancers co-located in the same TAD. This program includes features to control the sensitivity of the workflow as well as to generate plots that depicts predicted chromosome conformation.