SAPPHIRE Sequence Analyser for the Prediction of Prokaryote Homology Inferred Regulatory Elements - is a neural network based classifier for σ70 promoter prediction in Pseudomonas (Reference: Coppens L & Lavigne R (2020) BMC Bioinformatics 21(1): 415).
PromoterHunter - is part of phiSITE database which is a collection of phage gene regulatory elements, genes, genomes and other related information, plus tools. (Reference: Klucar, L. et al. 2010. Nucleic Acids Res. 38(Database Issue): D366-D370).
PhagePromoter - is a tool for locating promoters in phage genomes, using machine learning methods. This is the first online tool for predicting promoters that uses phage promoter data and the first to identify both host and phage promoters with different motifs. It is part of Galaxy.(Reference: Sampaio M et al. (2019) Bioinformatics. 35(24): 5301-5302).
BacPP: Bacterial Promoter Prediction - A tool for accurate sigma-factor specific assignment in enterobacteria. Includes σ24, σ28, σ32, σ38, σ54 and σ70 with 84-97% accuracy. Requires registration. (Reference: S. de Avila e Silva et al. J. Theor. Biol., 287 (2011): 92–99).
Sigma70Pred is a web-server with the capability of identifying σ70 promoters - their SVM model, based on Dinucleotide Auto-Correlation, Dinucleotide Cross-Correlation, Dinucleotide Auto Cross-Correlation, Moran Auto-Correlation, Normalized Moreau-Broto Auto-Correlation, Parallel Correlation Pseudo Tri-Nucleotide Composition, etc., achieved a maximum accuracy 97.38%
iPro70-PseZNC - is a tool for identifying σ70 promoters with novel pseudo nucleotide composition (Reference: Lai H-Y et al. (2019) Mol Ther Nucleic Acids. 17: 337-346). I would recommend using <100 nt upstream from the start codon.
iPro54-PseKNC - is a sequence-based predictor for identifying sigma-54 promoters in prokaryote with pseudo k-tuple nucleotide composition. (Reference: Lin H et al. (2014) Nucleic Acids Res 42(21): 12961-12972).
CNNPromoter_b - Prediction of Bacterial Promoters by CNN models in genomic sequences. (Reference: Umarov RK, & Solovyev VV (2017) PLoS One. 12(2): e0171410).
Deep Learning Recognition using Convolutional Neural Networks (CNNPromoter & CNNProm) - Classification of Prokaryotic and Eukaryotic Promoters and non-promoter sequences (Reference: Umarov R.K & Solovyev V.V. (2017) PLoS One.12(2): :e0171410.
Virtual Footprint - offers two types of analyses (a) Regulon Analysis - analysis of a whole prokaryotic genome with one regulator pattern and (b) Promoter analysis - Analysis of a promoter region with several regulator patterns (Reference: R. Münch et al. 2005. Bioinformatics 2005 21: 4187-4189).
PePPER (University of Groningen, The Netherlands) is a webserver for prediction of prokaryote promoter elements and regulons (Reference: de Yong, A. et al. 2012. BMC Genomics 13:299).
ProPr54 - prediction of Sigma54 dependent Promoters and Regulon - offers the choice of an annotated bacteria genome or short sequences (Tristan Achterberg & Anne de Jong, University of Groningen, the Netherlands).
DOOR3 - Database of prOkaryotic OpeRons - offers high-performance web service for online operon prediction on user-provided genomic sequences; and, an intuitive genome browser to support visualization of user-selected data. Plus a huge database of transcriptional units. (Reference: X. Mao et al. 2014. Nucleic Acids Res. 42(Database issue): D654-9).
MLDSPP (Machine Learning and Duplex Stability based Promoter prediction in Prokaryotes) is another promoter prediction tool. (Reference: Paul S et al. (2024) J Chem Inf Model. 64(7): 2705-2719).
FindM (Find Motifs around Functional Sites) - choose Promoter Motifs from Motif Library
CNNPromoter_e - Prediction of Eukaryotic Promoters by CNN models in genomic sequences. (Reference: Umarov RK, & Solovyev VV (2017) PLoS One. 12(2): e0171410).
YAPP Eukaryotic Core Promoter Predictor - is a tool to scan for canonical core promoter elements - BREs, TATA boxes, INRs and DPEs, and synergistics combinations of these elements (more). The search results may be restricted to elements which lie within the functional range of a specified TSS.
Promoter2.0 - predicts transcription start sites of vertebrate PolII promoters in DNA sequences. It has been developed as an evolution of simulated transcription factors that interact with sequences in promoter regions. i It builds on principles that are common to neural networks and genetic algorithms. (Reference: Knudsen S (1999) Bioinformatics 15: 356-361).
iProEP - was developed for five species: Homo sapiens, Drosophila melanogaster, Caenorhabditis elegans, Bacillus subtilis, and Escherichia coli. The PseKNC and PCSF features were employed to formulate promoter samples. We adopted mRMR algorithm and IFS method to find out the optimal feature subsets. SVM algorithm was used to implement classification. 10-fold cross-validated results showed that the accuracies for H. sapiens, D. melanogaster, C. elegans, B. subtilis, and E. coli were respectively 93.3%, 93.9%, 95.7%, 95.2%, and 93.1% (Reference: Lai H-Y et al. (2019) Mol Ther Nucleic Acids 17: 337–346)
Transcription Terminator Prediction (Anne de Jong, University of Groningem, The Netherlands) - is part of the excellent Genome2D webserver for Analysis and Visualization of Bacterial Genomes and Transcriptomes
ARNold - finds rho-independent terminators in nucleic acid sequences using two complementary programs, Erpin and RNAmotif. The program colors the terminator stem and loop (References: Gautheret D, Lambert A. 2001. J Mol Biol. 313:1003–11 & Macke T. et al. 2001. Nucleic Acids Res. 29:4724–4735 ).
iTerm-PseKNC - is a webserver for the identification of bacterial transcriptional terminators based on machine learning method. In the predictor, 5-tuple nucletide frequency and physicochemical property were extracted to formulate samples. The binomial distribution technique was proposed to rank 1024 5-tuple nucleotides. Then the incremental feature selection (IFS) was used to determine the optimal features which could produce the maximum accuracy. The support vector machine (SVM) was utilized to perform prediction. Five-fold cross-validated results showed that 86.07% terminators and 99.46% non-terminators can be correctly recognized, respectively. (Reference: Lai H-Y et al. (2019) Mol Ther Nucleic Acids. 17: 337-346).