Welcome to the SCRATCH download page.

Thank you for your interest. All software and related material contained herein can be downloaded freely for academic, non-commercial, research use only.

For any other use, please contact pfbaldi [at] gmail [dot] com.

Copyright 2005-2021. Institute for Genomics and Bioinformatics. University of California, Irvine. USA.

1. SSpro, SSpro8, ACCpro, ACCpro20 : Protein Secondary Structure and Relative Solvent Accessibility Prediction

The 4 predictors are included in the SCRATCH suite of 1D predictors available for download here:

SCRATCH-1D release 2.0 (2021, UNIX version, 1.4 GB).
SCRATCH-1D release 2.0 for Ubuntu (2021, Ubuntu Only, 1.4 GB).
Installation instructions, documentation, training sets. The package currently includes:

A bug in SCRATCH-1D release 2.0, containing SSpro 6.0 and ACCpro 6.0, was fixed on Sept 12, 2021. If you downloaded the package prior to that date, we strongly recommend that you reinstall it.

Previous releases still available: References:

C.N. Magnan & P. Baldi (2014). SSpro/ACCpro 5: almost perfect prediction of protein secondary structure and relative solvent accessibility using profiles, machine learning and structural similarity.
Bioinformatics, vol 30 (18), 2592-2597. [PDF] [PDF at Bioinformatics website]

J. Cheng, A. Randall, M. Sweredoski, & P. Baldi. SCRATCH: a Protein Structure and Structural Feature Prediction Server.
Nucleic Acids Research, vol. 33 (web server issue), w72-76, (2005).[PDF] [PDF at NAR website]

2. EVALpro 1.0: software package to evaluate the accuracy of a profile-based predictor as a function of the max cosine similarity between training and test profiles.

Download EVALpro 1.0 source code and examples (44 MB, Linux/Mac version) | Installation instructions & Documentation

3. MUpro 1.1: Prediction of Stability Changes (delta delta G) of Single Site Mutations from Protein Sequences

Download MUpro 1.1 source code and executable (200K, Linux version) | Installation instructions | Access MUpro server | MUpro dataset (1615 mutations) | MUpro dataset (388 mutations)

J. Cheng, A. Randall, & P. Baldi. Prediction of Protein Stability Changes for Single-Site Mutations Using Support Vector Machines. Proteins, vol. 62, no. 4, pp. 1125-1132, (2006). [PDF][PDF at Proteins website]

4. DOMpro 1.0: Protein Domain Prediction

Download DOMpro 1.0 (Linux version, about 1M) | Access DOMpro web server | Multi-domain dataset | Single domain dataset

J. Cheng, M. Sweredoski, & P. Baldi. DOMpro: Protein Domain Prediction Using Profiles, Secondary Structure, Relative Solvent Accessibility, and Recursive Neural Networks. Knowledge Discovery and Data Mining, vol. 13, no. 1, pp. 1-20, (2006). [PDF]

5. DIpro 2.0: Protein Disulfide Bond Prediction

Download DIpro 2.0 here (Linux version) | Access DIpro Web Server |Download Dataset

[1] J. Cheng, H. Saigo, & P. Baldi. Large-Scale Prediction of Disulphide Bridges Using Kernel Methods, Two-Dimensional Recursive Neural Networks, and Weighted Graph Matching. Proteins, vol. 62, no. 3, pp. 617-629, (2006). [PDF] [PDF at Proteins website]
[2] P. Baldi, J. Cheng, & A. Vullo. Large-Scale Prediction of Disulphide Bond Connectivity. Advances in Neural Information Processing Systems 17 (NIPS 2004), L. Saul,Y. Weiss, and L. Bottou editors, MIT press, pp.97-104, Cambridge, MA, (2005). [PDF] [PDF at NIPS website]

6. BETApro 1.0: Prediction of beta-residue pairs, beta-strand pairs, strand alignment, pairing direction, and beta-sheet topology.

Download BETApro1.0 here (Linux version) | Access BETApro Web Server| Download Dataset

J. Cheng & P. Baldi. Three-Stage Prediction of Protein Beta-Sheets by Neural Networks, Alignments, and Graph Algorithms. Bioinformatics, vol. 21, Suppl 1, pp. i75-84, (2005). [PDF] [PDF at Bioinformatics website]

7. DISpro1.0: Prediction of disordered regions from protein sequences.

Download DISpro1.0 here (Linux version) |Access DISpro Web Server |Download Dataset
Click here or see readme.txt in the zip file for the installation instructions.

J. Cheng, M. Sweredoski, & P. Baldi. Accurate Prediction of Protein Disordered Regions by Mining Protein Structure Data. Data Mining and Knowledge Discovery, vol. 11, no. 3, pp. 213-222, (2005). [PDF] [PDF at DAMI website]

8. SELECTpro: Protein Model Scoring/Selection and Side-Chain Prediction.
Access SELECTpro Web Server

SELECTpro 1.0: full version includes bundled feature predictors
download/install sizes:(680 Mb, 1.6 Gb)
Download SELECTpro1.0 (Linux version)| Overview and Installation Instructions

SELECTpro Solo: does not include feature predictors
download/install sizes:(3 Mb, 13 Mb)
Download SELECTpro Solo (Linux version)| Overview and Installation Instructions

A. Randall & P. Baldi. SELECTpro: effective protein model selection using a structure-based energy function resistant to BLUNDERS. BMC Structural Biology, vol. 8, 52, (2008). [PDF]

9. SOLpro: Prediction of protein solubility upon overexpression

Download SOLpro (12Mb, Linux version) | Installation instructions | Access SOLpro server | Download Dataset | Cross-validations

C. N. Magnan, A. Randall, & P. Baldi. SOLpro: accurate sequence-based prediction of protein solubility. Bioinformatics, vol. 25, 17, (2009). [PDF]

10. SIDEpro: a novel machine learning approach for the fast and accurate prediction of side-chain conformations

SIDEpro predicts side-chain conformations for protein backbones. SIDEpro can accommodate non-standard amino acids including PTMs.
Download Linux version | Installation instructions | Rotamer library | SIDEpro training set|FPTM set |NSA dataset
download/install sizes:(165 Mb, 210 Mb)

K. Nagata, A. Randall, & P. Baldi. SIDEpro: a novel machine learning approach for the fast and accurate prediction of side-chain conformations. Proteins , vol. 80, 1, (2012).

11. Polymorphic Antigen Cross Reactivity Analysis

The archive file consists of Perl scripts and data files to replicate the computational analysis presented in the manuscript. Download | Download Windows version | Overview
download sizes:(1.0 Mb)

Manuscript submitted for review December 2012:
E. Baum, A. Randall, M. Zeller, P. Baldi, & A. Barbour. Quantifying cross-reactive antibody binding and inferring epitopes among Borrelia burgdorferi OspC variants using protein microarray data

12. VIRALpro: Prediction of capsid and tail proteins

VIRALpro release 1.0 (linux version, 25 MB) | installation instructions | Experimental Data

C. Galiez, C. Magnan, F. Coste, and P. Baldi. VIRALpro: a tool to identify viral capsid and tail sequences. Bioinformatics, 32 (9): 1405-1407, (2016).

13. CCpro: Congruence Coefficient

CCpro computes the congruence coefficient between two aligned contact or distance maps. It is a measure of similarity that can be used in fold recognition. CCpro release 1.0 (linux version, 400 KB) | installation instructions

P. DiLena and P. Baldi. The Alignment and Scoring of Contact and Distance Maps for Fold Recognition.

Third-party tools used in the software: BLAST, PSI-BLAST, and SVM-light.

For technical issues, please email pfbaldi [at] gmail [dot] com and yuzok [at] ics [dot] uci [dot] edu.
For commercial licenses, please email igb-license [at] ics [dot] uci [dot] edu.