utility src and modcheck files

README.md

@@ -3,6 +3,7 @@
 ## NB this repo is under development and is not ready for production use
 
 Fast de novo protein model generation from covarying sequences using predicted distances and iterative model building.
+
 See the [pre-print](https://arxiv.org/abs/1811.12355) for more.
 
 ## Requirements
@@ -18,9 +19,13 @@ This repo also includes other software in binary form:
 - PSIPRED
 - PSICOV
 - FreeContact
+- Various utility scripts, the source of which is in `src`
 
 ## Installation
 
+As it makes use of a lot of different software, installation can be a little tricky.
+However we have aimed to make it as straightforward as possible.
+These instructions should work for a Linux system:
 ...
 
 ## Usage

modcheck/dope.scr

@@ -0,0 +1,20 @@
+# Example for: model.assess_dope()
+
+from modeller import *
+from modeller.scripts import complete_pdb
+
+env = environ()
+env.libs.topology.read(file='$(LIB)/top_heav.lib')
+env.libs.parameters.read(file='$(LIB)/par.lib')
+
+# Read a model previously generated by Modeller's automodel class
+mdl = complete_pdb(env, './temp.pdb')
+
+# Select all atoms in the first chain
+atmsel = selection(mdl.chains[0])
+
+score = atmsel.assess_dopehr()
+#score = atmsel.assess_dope()
+
+print(score)
+

run_dmpfold.sh

@@ -204,3 +204,5 @@ if [ -e CLUSTER_005.pdb ]; then
     ./qmodope_mainens CLUSTER_005.pdb
     mv best_qdope.pdb final_5.pdb
 fi
+
+rm dope.scr qmodcheck qmodope_mainens modcheckpot.dat

src/Makefile

@@ -0,0 +1,71 @@
+######################################################################
+#	Makefile for DMPfold utilities                               #
+######################################################################
+
+#### CC		Command to execute C compiler
+#### CFLAGS	Flags to pass to C compiler.
+
+INCDIR		= .
+CC		= cc
+
+CFLAGS		= -O
+LIBS		= -lm
+
+all:		aln2fasta contact2noe cov21stats fasta2tlc hbond2noe hbond2ssnoe pdbhfilt qmodcheck qmodcheck_mainens tmclust alnstats dmp_makepredmaps
+
+install:
+		/bin/cp aln2fasta contact2noe cov21stats fasta2tlc hbond2noe hbond2ssnoe pdbhfilt qmodcheck qmodcheck_mainens tmclust alnstats dmp_makepredmaps ../bin
+
+clean:
+		/bin/rm -f aln2fasta contact2noe cov21stats fasta2tlc hbond2noe hbond2ssnoe pdbhfilt qmodcheck qmodcheck_mainens tmclust alnstats dmp_makepredmaps *.o
+
+psipred:	sspred_avpred.c ssdefs.h sspred_net.h
+		$(CC) $(CFLAGS) sspred_avpred.c $(LIBS) -o psipred
+
+psipass2:	sspred_hmulti.c ssdefs.h sspred_net2.h
+		$(CC) $(CFLAGS) sspred_hmulti.c $(LIBS) -o psipass2
+
+chkparse:	chkparse.c
+		$(CC) $(CFLAGS) chkparse.c $(LIBS) -o chkparse
+
+seq2mtx:	seq2mtx.c
+		$(CC) $(CFLAGS) seq2mtx.c $(LIBS) -o seq2mtx
+
+pfilt:		pfilt.c
+		$(CC) $(CFLAGS) pfilt.c $(LIBS) -o pfilt
+
+aln2fasta:	aln2fasta.c
+		$(CC) $(CFLAGS) aln2fasta.c $(LIBS) -o aln2fasta
+
+contact2noe:	contact2noe.c
+		$(CC) $(CFLAGS) contact2noe.c $(LIBS) -o contact2noe
+
+cov21stats:	cov21stats.c
+		$(CC) $(CFLAGS) cov21stats.c $(LIBS) -o cov21stats
+
+fasta2tlc:	fasta2tlc.c
+		$(CC) $(CFLAGS) fasta2tlc.c $(LIBS) -o fasta2tlc
+
+hbond2noe:	hbond2noe.c
+		$(CC) $(CFLAGS) hbond2noe.c $(LIBS) -o hbond2noe
+
+hbond2ssnoe:	hbond2ssnoe.c
+		$(CC) $(CFLAGS) hbond2ssnoe.c $(LIBS) -o hbond2ssnoe
+
+pdbhfilt:	pdbhfilt.c
+		$(CC) $(CFLAGS) pdbhfilt.c $(LIBS) -o pdbhfilt
+
+qmodcheck:	qmodcheck.c
+		$(CC) $(CFLAGS) qmodcheck.c $(LIBS) -o qmodcheck
+
+qmodcheck_mainens:	qmodcheck_mainens.c
+		$(CC) $(CFLAGS) qmodcheck_mainens.c $(LIBS) -o qmodcheck_mainens
+
+tmclust:	tmclust.c
+		$(CC) $(CFLAGS) tmclust.c $(LIBS) -o tmclust
+
+alnstats:	alnstats.c
+		$(CC) $(CFLAGS) alnstats.c $(LIBS) -o alnstats
+
+dmp_makepredmaps:	dmp_makepredmaps.c
+		$(CC) $(CFLAGS) dmp_makepredmaps.c $(LIBS) -o dmp_makepredmaps

src/aln2fasta.c

@@ -0,0 +1,69 @@
+/* Filter gaps relative to 1st sequence from FASTA format alignment DTJ July 2011 */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <math.h>
+#include <string.h>
+
+#define MAXSEQLEN 1000000
+
+#define FALSE 0
+#define TRUE 1
+
+enum aacodes
+{
+    ALA, ARG, ASN, ASP, CYS,
+    GLN, GLU, GLY, HIS, ILE,
+    LEU, LYS, MET, PHE, PRO,
+    SER, THR, TRP, TYR, VAL,
+    GAP, UNK
+};
+
+const char     *rescodes = "ARNDCQEGHILKMFPSTWYVBZX";
+
+/* Dump a rude message to standard error and exit */
+void
+                fail(char *errstr)
+{
+    fprintf(stderr, "\n*** %s\n\n", errstr);
+    exit(-1);
+}
+
+/* Convert AA letter to numeric code (0-22) */
+int
+                aanum(int ch)
+{
+    static int      aacvs[] =
+    {
+	999, 0, 20, 4, 3, 6, 13, 7, 8, 9, 22, 11, 10, 12, 2,
+	22, 14, 5, 1, 15, 16, 22, 19, 17, 22, 18, 21
+    };
+
+    return (isalpha(ch) ? aacvs[ch & 31] : 22);
+}
+
+
+int main(int argc, char **argv)
+{
+    int             i, j, ngap, naa, seqlen = 0, seqcount=0, nid;
+    char            desc[MAXSEQLEN], refseq[MAXSEQLEN], seq[MAXSEQLEN], buf[MAXSEQLEN], *p;
+    FILE           *ifp;
+
+    if (argc < 2)
+	fail("Usage: aln2fasta aln-file");
+
+    ifp = fopen(argv[1], "r");
+    if (!ifp)
+	fail("Unable to open aln file!");
+
+    nid = 1;
+    for (;;)
+    {
+	if (!fgets(buf, MAXSEQLEN, ifp))
+	    break;
+	printf(">SEQ%06d\n%s", nid++, buf);
+    }
+
+    return 0;
+}