An algorithm for prediction of highly effective AVPs based on experimentally validated positive and negative data sets. AVPpred contains four prediction models : the composition-based, physico-chemical properties and sequence alignment-based were implemented in the web server to make comprehensive predictions. AVPpred would be helpful for researchers working for the development of peptide-based antiviral therapeutics.
A web server for prediction and design of antiviral compounds. AVCpred web server includes the following modules: (i) Submissions (allows users to submit on or more molecules at a time), (ii) Design analogs (user can design analogs based on given building blocks and predict their inhibition on the viruses), (iii) Draw structure (can sketch the structure of the query molecule using Marvin editor), and (iv) Search (provides the users a search tool to browse the compounds used in our datasets. In this module, different compounds targeting the viruses are stored in a database).
Detects highly specific and selective peptides. PHASTpep can be applied from simple purified protein screens to more complex in vitro cell, in vivo, or ex vivo tissue screening. This method allows the importation of sequences, pulls out the portion of DNA corresponding to the displayed peptides, translates the sequences into amino acids, and calculates the frequency of each unique peptide.
A regression-based algorithm to predict the antiviral activity in terms of IC50 values (μM). AVP-IC50Pred is developed using peptides with quantitative and experimentally proven antiviral activity from AVPdb -Database of Antiviral Peptides. and HIPdb -Database of HIV inhibiting peptides. We have also utilized important features like amino acid composition, binary and physicochemical properties etc. for model development, and multiple machine learning algorithms (SVM, Random Forest, IBk and K*) were employed. The AVP-IC50Pred web server is anticipated to assist the researchers working on antiviral therapeutics by enabling them to computationally screen many compounds and focus experimental validation on the most promising set of peptides, thus reducing cost and time efforts.
Predicts fusion peptide domain of retroviruses, including HERV, HIV, SIV, HTLV and MLV. Fptool is a sequence-based FP model combining Hidden Markov Method with similarity comparison. FP model predicts np-FP domain through two phases. Firstly, it adopted HMM method to determine the existence and rough location of np-FP. Subsequently, it performed similarity comparison for a more precise np-FP.
0 - 0 of 0