Skip to content

Predict protein local properties using sequence or profile information.

License

Notifications You must be signed in to change notification settings

realbigws/Predict_Property

Repository files navigation

===================================
Predict_Property standalone package
(v1.01) 2018.10.01 
===================================

Title:
Predict_Property: a Standalone Package for Protein Structure Property Prediction

Abstract:
This package predicts Secondary Structure Element (SS3 and SS8), Solvent Accessibility (ACC), Order/Disorder prediction (DISO), and TransMembrane topology (TM2 and TM8) for the input protein using either pure sequence information or evolutionary profile information. 

Author: 
Sheng Wang

Email:
realbigws@gmail.com



============
Publication:
============

[1]
RaptorX-Property: a Web Server for Protein Structure Property Prediction
       Sheng Wang#*, Wei Li*, Shiwang Liu, Jinbo Xu#
                                            Nucleic Acids Research, 2016

[2]
Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields
       Sheng Wang#, Jian Peng, Jianzhu Ma, Jinbo Xu#
                                            Scientific Reports, 2016

[3]
AUCpreD: Proteome-level Protein Disorder Prediction by AUC-maximized Deep Convolutional Neural Fields
       Sheng Wang#, Jianzhu Ma, Jinbo Xu#
                                            ECCB, 2016
                                            Bioinformatics, 2016

[4]
AUC-maximized Deep Convolutional Neural Fields for Protein Sequence Labeling
       Sheng Wang, Siqi Sun, Jinbo Xu#
                                            ECML/PKDD, 2016

[5]
PredMP: a web server for de novo prediction and visualization of membrane proteins
       Sheng Wang#, Shiyang Fei, Zongan Wang, Yu Li, Jinbo Xu, Feng Zhao#, Xin Gao#
                                            Bioinformatics, 2018


========
Install:
========

1. download the package
git clone https://github.com/realbigws/Predict_Property

--------------

2. compile

cd source_code/
	make
cd ../

--------------

3. the package to generate evolutionary profile information in TGT format could be found at:
    https://github.com/realbigws/TGT_Package



======
Usage:
======


#----------- Predict_Property --------------#

Predict_Property v1.02 [Mar-05-2019]
    Predict protein local properties using sequence or profile information

USAGE:  ./Predict_Property.sh <-i input_fasta | input_tgt> [-o out_root]
                              [-t diso_thres] [-T topo_thres] [-H home]

Options:

***** required arguments *****
-i input_fasta :  input protein sequence file in FASTA format
(or)
-i input_tgt   :  input protein profile file in TGT format

***** optional arguments *****
-o out_root    :  default output would the current directory.
                  [default = './${input_name}_PROP']

-t diso_thres  :  threshold to determine disordered residue. [default = 0.5]

-T topo_thres  :  threshold to determine transmembrane residue. [default = 0.5]

-H home        :  home directory of Predict_Property.sh
                  [default = ~/GitBucket/Predict_Property]



#------------ AUCpreD -----------------------#

AUCpreD v1.04 [Oct-01-2018]
    Predict order/disorder regions using sequence or profile information

USAGE:  ./AUCpreD.sh <-i input_fasta | input_tgt> [-o out_root]
                     [-t threshold] [-k keep_file] [-l real_label] [-H home]

Options:

***** required arguments *****
-i input_fasta :  input protein sequence file in FASTA format
(or)
-i input_tgt   :  input protein profile file in TGT format

***** optional arguments *****
-o out_root    :  default output would be XXXX.diso_MODE at the current directory,
                  where XXXX is the input name, and MODE is profile or noprof.
                  [default = './' ]

-t threshold   :  threshold to determine disordered residue. [default = 0.5]

-k keep_file   :  keep the intermediate files if its value is 1 [default = 0]

-l real_label  :  real Order/Disorder label file, in three lines [default = null]

-H home        :  home directory of AUCpreD.sh
                  [default = ~/GitBucket/Predict_Property]



#------------ PDBTM_Topology_Pred ------------#

PDBTM_Topology_Pred v1.05 [Mar-05-2019]
    Predict PDBTM Topology labels using sequence or profile information

USAGE:  ./PDBTM_Topology_Pred.sh <-i input_fasta | input_tgt> [-o out_root]
                  [-t threshold] [-k keep_file] [-l real_label] [-H home]

Options:

***** required arguments *****
-i input_fasta :  input protein sequence file in FASTA format
(or)
-i input_tgt   :  input protein profile file in TGT format

***** optional arguments *****
-o out_root    :  default output would be XXXX.topo_MODE at the current directory,
                  where XXXX is the input name, and MODE is profile or noprof.
                  we also output XXXX.topo_simp for simplified result.
                  [default = './' ]

-t threshold   :  threshold to determine transmembrane residue. [default = 0.5]

-k keep_file   :  keep the intermediate files if its value is 1 [default = 0]

-l real_label  :  real PDBTM Topology label file, in  three lines [default = null]

-H home        :  home directory of PDBTM_Topology_Pred.sh
                  [default = ~/GitBucket/Predict_Property]




========
Example:
========

#-> 1. Predict_Property
./Predict_Property.sh -i example/1pazA.tgt


#-> 2. AUCpreD
./AUCpreD.sh -i example/T0530.tgt


#-> 3. PDBTM_Topology_Pred
./PDBTM_Topology_Pred.sh -i example/1bhaA.tgt




=============
Output files:
=============

1. overall detailed results:
	SeqID.all

e.g., file 'T0530.all' in tmp/T0530/ folder. This file contains all the detail prediction results for Secondary Structure Element (SS3 and SS8), Solvent Accessibility (ACC), Order/Disorder prediction (DISO), and TransMembrane topology (TM2 and TM8).

------------------

2. detailed results in separate files:
	SeqID.ss3
	SeqID.ss8
	SeqID.acc
	SeqID.tm2
	SeqID.tm8
	SeqID.diso

These files contain the detail prediction results in the form of probability.

------------------

3. simple results in separate files:
	SeqID.ss3_simp
	SeqID.ss8_simp
	SeqID.acc_simp
	SeqID.tm2_simp
	SeqID.tm8_simp
	SeqID.diso_simp

These files contain the simple prediction results in one line.

------------------

About

Predict protein local properties using sequence or profile information.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published