Workflow for Automated Comparative Protein Sequences Analysis

None

/* Accepts sequences in FASTA format and extracts the information from them for a better understanding of the multiple sequence alignment and trees plots. It uses regular expression for the extraction
Input: Sequences; 
Output: result; string with description of each sequence in FASTA format
*/

// Extract the FASTA description from each sequence
import java.util.regex.Pattern;
import java.util.regex.Matcher;

StringBuffer temp = new StringBuffer();
String information="";
// regular expression to extract only the sequence description
Pattern pattern = Pattern.compile (">(\\w+.*)\\s");
Matcher matcher = pattern.matcher(Sequences);

while(matcher.find()){
	information=matcher.group(1);
	temp.append(information + "\n");
}

// Output sequence description
String result = temp.toString();

Name	Type	Description
Seqs_Fetch	workflow
T_coffee	workflow
Muscle	workflow
ClustalW2	workflow
emma	soaplab	Endpoint http://www.ebi.ac.uk/soaplab/services/alignment_multiple.emma
emma_sprotein_seq	stringconstant	Value Yes
emma_osformat_outseq	stringconstant	Value clustal
email	stringconstant	Value achille.zappa@istge.it
database	stringconstant	Value uniprot
ML_reps	stringconstant	Value 3
NJ_reps	stringconstant	Value 50
MAFFT	workflow
ClustalW2_ML	workflow
ClustalW2_NJ	workflow
Muscle_ML	workflow
Muscle_NJ	workflow
emma_ML	workflow
emma_NJ	workflow
Tcoffee_ML	workflow
Tcoffee_NJ	workflow
MAFFT_ML	workflow
MAFFT_NJ	workflow
Seqs_Descriptions	beanshell	Script /* Accepts sequences in FASTA format and extracts the information from them for a better understanding of the multiple sequence alignment and trees plots. It uses regular expression for the extraction Input: Sequences; Output: result; string with description of each sequence in FASTA format / // Extract the FASTA description from each sequence import java.util.regex.Pattern; import java.util.regex.Matcher; StringBuffer temp = new StringBuffer(); String information=""; // regular expression to extract only the sequence description Pattern pattern = Pattern.compile (">(\\w+.)\\s"); Matcher matcher = pattern.matcher(Sequences); while(matcher.find()){ information=matcher.group(1); temp.append(information + "\n"); } // Output sequence description String result = temp.toString();

Name	Inputs	Outputs
Seqs_Descriptions	Sequences	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell_5	inputs	result
Beanshell_2_4	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell_5	inputs	result
Beanshell_2_4	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell_5	inputs	result
Beanshell_2_4	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell_5	inputs	result
Beanshell_2_4	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell	inputs	result
Beanshell_2	inputs	result
Beanshell_3	inputs	result
Beanshell_2_2	inputs	result
Beanshell_4	inputs	result
Beanshell_2_3	inputs	result
Beanshell_5	inputs	result
Beanshell_2_4	inputs	result

Name	Description
seqs
o
t1
emmaln
CW_NJ1
CW_NJ2
CW_ML2
CW_ML1
W2_ML2
W2_ML1
W2_NJ2
W2_NJ1
T_ML2
T_ML1
T_NJ1
T_NJ2
mm
Mu_NJ2
Mu_NJ1
Mu_ML2
Mu_ML1
MA_NJ1
MA_NJ2
MA_ML2
MA_ML1
W2-O
W2-aln
W2-nj
W2-t
TC_aln
TC_dnd
MAFFT_out
desc

Source	Sink
seqs_ids	Seqs_Fetch:Sequences_or_IDs
database:value	Seqs_Fetch:DB
emma:outseq	T_coffee:Sequences
email:value	T_coffee:email
Seqs_Fetch:sequences	Muscle:Sequences
email:value	Muscle:email
Seqs_Fetch:sequences	ClustalW2:Sequences
email:value	ClustalW2:Email_address
emma_sprotein_seq:value	emma:sprotein_sequence
emma_osformat_outseq:value	emma:osformat_outseq
Seqs_Fetch:sequences	emma:sequence_direct_data
Seqs_Fetch:sequences	MAFFT:s
ClustalW2:ClustalW2_alignment	ClustalW2_ML:s
ML_reps:value	ClustalW2_ML:r
ClustalW2:ClustalW2_alignment	ClustalW2_NJ:in
NJ_reps:value	ClustalW2_NJ:r
Muscle:MUSCLE_alignment	Muscle_ML:s
ML_reps:value	Muscle_ML:r
Muscle:MUSCLE_alignment	Muscle_NJ:in
NJ_reps:value	Muscle_NJ:r
emma:outseq	emma_ML:s
ML_reps:value	emma_ML:r
emma:outseq	emma_NJ:in
NJ_reps:value	emma_NJ:r
T_coffee:TCoffee_aln	Tcoffee_ML:s
ML_reps:value	Tcoffee_ML:r
T_coffee:TCoffee_aln	Tcoffee_NJ:in
NJ_reps:value	Tcoffee_NJ:r
MAFFT:s	MAFFT_ML:s
ML_reps:value	MAFFT_ML:r
MAFFT:s	MAFFT_NJ:in
NJ_reps:value	MAFFT_NJ:r
Seqs_Fetch:sequences	Seqs_Descriptions:Sequences
Seqs_Fetch:sequences	seqs
emma:dendoutfile	o
T_coffee:TCoffee_alignment	t1
emma:outseq	emmaln
emma_NJ:out	CW_NJ1
emma_NJ:outree	CW_NJ2
emma_ML:out	CW_ML2
emma_ML:outree	CW_ML1
ClustalW2_ML:out	W2_ML2
ClustalW2_ML:outree	W2_ML1
ClustalW2_NJ:out	W2_NJ2
ClustalW2_NJ:outree	W2_NJ1
Tcoffee_ML:out	T_ML2
Tcoffee_ML:outree	T_ML1
Tcoffee_NJ:out	T_NJ1
Tcoffee_NJ:outree	T_NJ2
Muscle:MUSCLE_alignment	mm
Muscle_NJ:out	Mu_NJ2
Muscle_NJ:outree	Mu_NJ1
Muscle_ML:out	Mu_ML2
Muscle_ML:outree	Mu_ML1
MAFFT_NJ:out	MA_NJ1
MAFFT_NJ:outree	MA_NJ2
MAFFT_ML:out	MA_ML2
MAFFT_ML:outree	MA_ML1
ClustalW2:ClustalW2_output	W2-O
ClustalW2:ClustalW2_alignment	W2-aln
ClustalW2:ClustalW2_nj_tree	W2-nj
ClustalW2:ClustalW2_phylip_tree	W2-t
T_coffee:TCoffee_aln	TC_aln
T_coffee:TCoffee_dnd	TC_dnd
MAFFT:s	MAFFT_out
Seqs_Descriptions:result	desc

Workflow for Automated Comparative Protein Sequences Analysis

Preview

Run

Run this Workflow in the Taverna Workbench...

Workflow Components

Endpoint

Value

Value

Value

Value

Value

Value

Script

Reviews (0)

Comments (0)

Other workflows that use similar services (24)