JPred4 is the latest version of the popular protein secondary structure prediction server, using the JNet algorithm, one of the most accurate methods for secondary structure prediction. In addition to secondary structure prediction, JPred also predicts solvent accessibility and coiled-coil regions. The server handles up to 94,000 jobs per month and has performed over 1.5 million predictions for users in 179 countries. The JPred4 web server has been re-implemented in the Bootstrap framework and JavaScript to improve design, usability, and accessibility from mobile devices. JPred4 features higher accuracy, with a blind three-state (α-helix, β-strand, and coil) secondary structure prediction accuracy of 82.0%, and solvent accessibility prediction accuracy of 90% for residues <5% accessible. Results are reported on the website and through optional email summaries and batch submission results. Predictions are now presented in SVG format with options to view full multiple sequence alignments with and without gaps and insertions. The help-pages have been updated, and tool-tips and step-by-step tutorials have been added. JPred4 uses the JNet algorithm for secondary structure and residue solvent accessibility predictions. The JNet 2.0 neural network-based predictor has been retrained to make JNet 2.3.1 using 7-fold cross-validation on 1358 SCOPe/ASTRAL v.2.04 superfamily domain sequences. Multiple alignments for each sequence were built by PSI-BLAST through searching UniRef90. The final accuracy of JNet 2.3.1 was assessed in a blind test on 150 sequences from 150 superfamilies not used in training. The average secondary structure prediction Q3 score increased to 82.0% from 81.5% for JNet v.2.0, and solvent accessibility prediction accuracy rose to 90.0, 83.6, and 78.1% from 88.9, 82.4, and 77.8% for JNet v.2.0 for each of >0, >5 and >25% relative solvent accessibility thresholds. JPred4 results reporting includes all original formats and styles (PDF, HTML, etc.) as well as intermediary processing files. The primary visualization of a JPred4 prediction result is a scrollable SVG image generated by Jalview 2.9. The alignment returned shows the full-length query sequence without gaps necessary to accommodate insertions in sequences returned from the PSI-BLAST search. JPred4 introduces options to view the full multiple alignment including all residues in all sequences or download it for further analysis. For users with local Jalview installations, Jalview feature files are provided for easy annotation and analysis. All JPred4 jobs are stored on the server for 5 days. The median time forJPred4 is the latest version of the popular protein secondary structure prediction server, using the JNet algorithm, one of the most accurate methods for secondary structure prediction. In addition to secondary structure prediction, JPred also predicts solvent accessibility and coiled-coil regions. The server handles up to 94,000 jobs per month and has performed over 1.5 million predictions for users in 179 countries. The JPred4 web server has been re-implemented in the Bootstrap framework and JavaScript to improve design, usability, and accessibility from mobile devices. JPred4 features higher accuracy, with a blind three-state (α-helix, β-strand, and coil) secondary structure prediction accuracy of 82.0%, and solvent accessibility prediction accuracy of 90% for residues <5% accessible. Results are reported on the website and through optional email summaries and batch submission results. Predictions are now presented in SVG format with options to view full multiple sequence alignments with and without gaps and insertions. The help-pages have been updated, and tool-tips and step-by-step tutorials have been added. JPred4 uses the JNet algorithm for secondary structure and residue solvent accessibility predictions. The JNet 2.0 neural network-based predictor has been retrained to make JNet 2.3.1 using 7-fold cross-validation on 1358 SCOPe/ASTRAL v.2.04 superfamily domain sequences. Multiple alignments for each sequence were built by PSI-BLAST through searching UniRef90. The final accuracy of JNet 2.3.1 was assessed in a blind test on 150 sequences from 150 superfamilies not used in training. The average secondary structure prediction Q3 score increased to 82.0% from 81.5% for JNet v.2.0, and solvent accessibility prediction accuracy rose to 90.0, 83.6, and 78.1% from 88.9, 82.4, and 77.8% for JNet v.2.0 for each of >0, >5 and >25% relative solvent accessibility thresholds. JPred4 results reporting includes all original formats and styles (PDF, HTML, etc.) as well as intermediary processing files. The primary visualization of a JPred4 prediction result is a scrollable SVG image generated by Jalview 2.9. The alignment returned shows the full-length query sequence without gaps necessary to accommodate insertions in sequences returned from the PSI-BLAST search. JPred4 introduces options to view the full multiple alignment including all residues in all sequences or download it for further analysis. For users with local Jalview installations, Jalview feature files are provided for easy annotation and analysis. All JPred4 jobs are stored on the server for 5 days. The median time for