add makefile and readme_AD

Makefile

@@ -0,0 +1,169 @@
+ALL = rama coma oops stats befa lipa peptide merg dssp2cm peptmpi cdlearn
+TOOLS = tools/extract_distances \
+      tools/1pga_helix_orientation \
+      tools/R0003_collect_SS \
+      tools/num_helix_residues \
+      tools/count_charged_residues \
+      tools/icm2icm \
+      tools/initialize_test \
+      tools/turn_analyser \
+      tools/hbond_pattern \
+      tools/rmsd/rmsd \
+      tools/rmsd/rmsd_debug \
+      tools/rmsd/rmsd_dihedral \
+      tools/energy_landscape_charts/list_large_basins \
+      tools/checkpoint_split/checkpoint_split \
+      tools/thermodynamics/thermo \
+      tools/energy_landscape_charts/beta \
+      tools/energy_landscape_charts/rmsdbasin \
+      tools/energy_landscape_charts/rmsdbasin_dihedral
+
+OS = $(shell uname -s)
+CFLAGS = -std=c99 -O2 # -D_GNU_SOURCE #-fgnu89-inline
+CPP=g++
+CPPFLAGS = -Wall -O2
+OPENMPFLAGS = -fopenmp
+LDFLAGS = -lm
+LDFLAGS_DEBUG = -lm
+
+ifeq ($(OS), Linux)
+	CFLAGS = -std=c99 -Wall -O2 #-Wno-unused-result 
+	CFLAGS_DEBUG = -std=c99 -Wall -O0 -g -DDEBUG #-Wno-unused-result -g
+	ifneq ($(shell which mpicc),)
+		MPICC = mpicc
+		MPILDFLAGS = $(LDFLAGS)
+		ALL := $(ALL) peptmpi
+	endif
+endif
+
+ifeq ($(OS), Darwin)
+	CFLAGS = -std=c99 -Wall -O2
+	CFLAGS_DEBUG = -std=c99 -Wall -O0 -g -arch i386 -DDEBUG
+	ifneq ($(shell which mpicc),)
+		MPICC = mpicc
+		MPILDFLAGS = $(LDFLAGS)
+		ALL := $(ALL) peptmpi
+	endif
+endif
+
+ifeq ($(OS), SunOS)
+	CFLAGS = -xO2
+	ifneq ($(shell which mpcc),)
+		MPICC = mpcc
+		MPILDFLAGS = -lmpi $(LDFLAGS)
+		ALL := $(ALL) peptmpi
+	endif
+endif
+
+all : $(ALL)
+
+tools : $(TOOLS)
+
+rama : aadict.c ramachandran.c vector.c peptide.c rotation.c params.c error.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+coma : aadict.c cm.c params.h error.h 
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+oops : oops.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+stats : statistics.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+befa : aadict.c bfactor.c peptide.c rotation.c vector.c params.c error.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+lipa : aadict.c pauling.c peptide.c rotation.c vector.c params.c error.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+#internal cdlearn program
+cdlearn : aadict.c energy.c cdlearn.c metropolis.c flex.c peptide.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DLJ_HBONDED_HARD -DLJ_NEIGHBOUR_HARD $(OPENMPFLAGS) $^ $(LDFLAGS) -o $@
+
+cdlearn_debug : aadict.c energy.c cdlearn.c metropolis.c flex.c peptide.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS_DEBUG) -DLJ_HBONDED_HARD -DLJ_NEIGHBOUR_HARD $^ $(LDFLAGS_DEBUG) -o $@
+
+#serial peptide program (MC, nested sampling)
+peptide : nested.c aadict.c energy.c main.c metropolis.c flex.c peptide.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c canonicalAA.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@ -g
+
+peptide_debug : nested.c aadict.c energy.c main.c metropolis.c flex.c peptide.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS_DEBUG) $^ $(LDFLAGS_DEBUG) -o $@
+
+#parallel peptmpi program (parallel tempering, nested sampling)
+peptmpi : nested.c aadict.c energy.c main.c metropolis.c flex.c peptide.c probe.c random16.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(MPICC) $(CFLAGS) -DPARALLEL $^ $(MPILDFLAGS) -o $@
+
+peptmpi_debug : nested.c aadict.c energy.c main.c metropolis.c flex.c peptide.c probe.c random16.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(MPICC) $(CFLAGS_DEBUG) -DPARALLEL $^ $(LDFLAGS_DEBUG) -o $@
+
+merg : mergie.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+dssp2cm : dssp2cm.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+#TOOLS
+
+tools/extract_distances : aadict.c energy.c tools/tools_main.c metropolis.c peptide.c flex.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DEXTRACT_DISTANCES $^ $(LDFLAGS) -o $@
+
+tools/1pga_helix_orientation : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c flex.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DHELIX_ORIENTATION $^ $(LDFLAGS) -o $@
+
+tools/R0003_collect_SS : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c flex.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DR0003_SSBOND $^ $(LDFLAGS) -o $@
+
+tools/num_helix_residues : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c probe.c flex.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DNUM_HELIX_RESIDUES $^ $(LDFLAGS) -o $@
+
+tools/count_charged_residues : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c flex.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DCOUNT_CHARGED_RESIDUES $^ $(LDFLAGS) -o $@
+
+tools/icm2icm : tools/icm2icm.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+tools/initialize_test : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c flex.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DINITIALIZE_TEST $^ $(LDFLAGS) -o $@
+
+tools/turn_analyser : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c flex.c probe.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DTURN_ANALYSER $^ $(LDFLAGS) -o $@
+
+tools/hbond_pattern : tools/tools_main.c aadict.c energy.c metropolis.c peptide.c probe.c flex.c rotation.c vector.c params.c error.c checkpoint_io.c vdw.c
+	$(CC) $(CFLAGS) -DHBOND_PATTERN $^ $(LDFLAGS) -o $@
+
+tools/rmsd/rmsd : aadict.c peptide.c tools/rmsd/rmsd.c tools/rmsd/rmsd_main.c rotation.c vector.c flex.c params.c metropolis.c energy.c error.c vdw.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+tools/rmsd/rmsd_debug : aadict.c peptide.c tools/rmsd/rmsd.c tools/rmsd/rmsd_main.c rotation.c vector.c flex.c params.c metropolis.c energy.c error.c vdw.c
+	$(CC) $(CFLAGS_DEBUG) $^ $(LDFLAGS_DEBUG) -o $@
+
+tools/rmsd/rmsd_dihedral : aadict.c peptide.c tools/rmsd/rmsd.c tools/rmsd/rmsd_main.c flex.c rotation.c vector.c params.c metropolis.c energy.c error.c vdw.c
+	$(CC) $(CFLAGS) -DRMS_DIHEDRAL $^ $(LDFLAGS) -o $@
+
+tools/energy_landscape_charts/list_large_basins : tools/energy_landscape_charts/list_large_basins.c
+	$(CC) $(CFLAGS) $^ $(LDFLAGS) -o $@
+
+tools/checkpoint_split/checkpoint_split : tools/checkpoint_split/checkpoint_split.c tools/checkpoint_split/rmsd.c params.c vector.c rotation.c aadict.c peptide.c metropolis.c energy.c error.c vdw.c
+	$(CC) $(CFLAGS)  $^ $(LDFLAGS) -o $@
+
+#CPP TOOLS
+
+tools/thermodynamics/thermo : tools/thermodynamics/thermo.cpp
+	$(CPP) $(CPPFLAGS) $^ $(LDFLAGS) -o $@
+
+tools/energy_landscape_charts/beta : tools/energy_landscape_charts/beta.cpp
+	$(CPP) $(CPPFLAGS) $^ $(LDFLAGS) -o $@
+
+tools/energy_landscape_charts/rmsdbasin : tools/energy_landscape_charts/rmsdbasin.cpp
+	$(CPP) $(CPPFLAGS) $(OPENMPFLAGS) $^ $(LDFLAGS) -o $@
+
+tools/energy_landscape_charts/rmsdbasin_dihedral : tools/energy_landscape_charts/rmsdbasin.cpp
+	$(CPP) $(CPPFLAGS) $(OPENMPFLAGS) -DRMS_DIHEDRAL $^ $(LDFLAGS) -o $@
+
+wrap :
+	tar -zcvf crankite.tar.gz README ChangeLog TODO COPYING Makefile *.[ch] viewer.ps *.sh *.awk engh-huber-2001.txt peptide-contacts.txt *.py tests tools
+
+clean :
+	$(RM) $(ALL) $(TOOLS)

README

@@ -0,0 +1,148 @@
+			CRANKITE
+	A Fast Polypeptide Backbone Conformation Sampler
+
+CRANKITE is a suite of programs for simulating backbone conformations of
+polypeptides and proteins. The core of the suite is an efficient Metropolis
+Monte Carlo sampler of backbone conformations in continuous three-dimensional
+space in atomic details. In contrast to other programs relying on local
+Metropolis moves in the space of dihedral angles, the sampler utilizes local
+crankshaft rotations of rigid peptide bonds in Cartesian case. The sampler
+allows fast simulation and analysis of secondary structure formation and
+conformational changes for proteins of average length.
+
+
+1. Compilation and Usage
+
+The package provides Makefile recognized by GNU make (or gmake), which builds
+the suite. So fire up "make"! Most programs in the suite are controlled through
+various options given on the command line. Invalid options (or the valid option
+"-h") trigger the output of usage notes. The following programs are provided in
+the suite from most to least important.
+
+peptide
+	The Metropolis polypeptide backbone conformation sampler. A very short
+	simulation can be run by using a command like
+
+		./peptide -r 1000x25 -t 201 d1ctf__.pdb
+
+	This will read the initial conformation from file d1ctf__.pdb, perform
+	25,000 Metropolis moves, while recording a contact map and a snapshot
+	conformation every 1000 steps. The output will have 25 contact maps and
+	25 snapshots. To get help with more options one can use "./peptide -h".
+
+peptmpi
+	The same as peptide, but compiled for parallel-tempered simulations
+	using MPI.
+
+lipa
+	Converts dihedrals to a 3D-structure in PDB format. Each input line
+	should start from a 1-letter residue id and dihedral angles phi and psi
+	separated by spaces, e.g. "Q -57 -47". Optionally, the valence angle
+	tau and the cis/trans angle omega can be given in the fourth and fifth
+	positions. The sixth optional angle is interpreted as a chi_1 dihedral
+	to add an gamma side chain atom. 
+
+	The omitted phi and psi angles are assigned random values appropriate
+	for polypeptides to minimize clashes. This feature can be used to
+	create a random coil conformation by providing a sole residue id in
+	each line of input.
+
+	This program is an approximate inverse of rama and one can pipe rama
+	output through lipa to recreate	the original structure. This inversion
+	is not ideal, because it assumes reasonable but not precise values for
+	ignored and omitted bond lengths angles. This program can be used to
+	create an arbitrary initial conformation for "peptide". 
+
+rama
+	Calculates backbone dihedrals for a polypeptide in PDB format. In
+	addition, valence geometry of each CA atom is characterized in terms of
+	an N-CA-C valence angle tau and a normalized solid angle formed by
+	three bonds with heavy atoms. The solid angle is positive for L-amino
+	acids and negative for D-amino acids. Side-chain dihedral angles
+	chi_1 are also reported. Other calculated characteristics of local
+	polypeptide conformation include CA-CA and CB-CB distances between
+	adjacent residues, pseudo-dihedral angles CB-CA-CA-CB, etc.
+
+coma
+	Calculates a contact map for a protein structure in a PDB file.
+	Contacts are defined by a cut-off distance between CA or CB atoms. Some
+	of this functionality is also integrated in "peptide". The program can
+	also produce a distance matrix.
+
+befa
+	Produces a mean structure with B-factors for the multiple models in an
+	NMR-style PDB file. Calculation of B-factors for a simulation
+	trajectory is reliable only if the trajectory is very short (less than
+	100 steps per residue).
+
+stats
+	Basic statistical pipe tool to calculate means, standard deviations,
+	extreme values, and statistical inefficiencies for a stream of data.
+
+merg.sh
+	Merges and sorts output files that are produced during a Sun MPI
+	parallel-tempered run using "mprun -B". The files to be merged should
+	be listed on the command line. The script and the merg executable are
+	useful only on Sun clusters.
+
+cdlearn.sh
+	An example script to set up Contrastive Divergence learning (see below)
+	from a dataset of PDB structures. The script uses 2 parameters: the
+	number of available cluster nodes and a file with the list of PDB id's.
+	This script distributes tasks over cluster nodes using PBS (Portable
+	Batch System). Each node receives a PBS job diverge.pbs.
+
+viewer.sh
+	PDB viewer produces a stereo pair in a printable PostScript format. It
+	uses a PDB file name as a command line parameter. PDB files are parsed
+	by the oops executable that is called from the script.
+
+By default, all the programs read data from the standard input (stdin) and
+write to the standard output (stdout), so that one can use them in a pipeline.
+If a file name is given on the command line, the input is redirected from this
+file. The option "-o file_name" allows one to redirect the output to a file.
+This is an example of a pipeline that involves most programs in the suite
+
+	./rama d1ctf__.pdb | ./lipa | ./peptide -r 500x10 | ./befa | ./coma
+
+Here, rama calculates dihedral angles for d1ctf__ and passes them to lipa to
+recreate a 3d structure, which is passed to peptide for a short simulation
+producing 10 snapshots, then befa averages them, and finally coma produces a
+contact map for the average structure.
+
+We implemented an alternative way of setting initial conformation for
+"peptide". One can enter a sequence of residues directly on the command line,
+e.g.,
+
+	./peptide -r 4096x200 ABCDEFGHabcdefgh
+
+This will run simulations on the 16-residue polypeptide, starting from the
+first 8 residues in alpha-helical state and the last 8 residues in beta-strand
+conformation.
+
+The default force-field used by peptide includes hard-core van der Waals
+repulsions and square-well interpeptide hydrogen bonding. One can also specify
+Go-type interactions between side-chains by providing a regularized contact
+map. For example,
+
+	./peptide -r 4096x200 -p _B=beta-16.in WHATISMYSMEARARM
+
+where the file beta-16.in (provided in the package) contains the regularized
+contact map corresponding to 16-residue beta-hairpin. The above example starts
+simulations from alpha-helical conformation and turns it into a beta-hairpin in
+less than 15 seconds on a 3.2 GHz Pentium D system.
+
+The peptide's option "-p" is perhaps the most powerful option, which allows one
+to control many parameters of the program, including force-field constants.
+This option is intended to be customizable and flexible. To learn more about
+this option in the current version, we would like to refer the reader to the
+source code.
+
+
+2. Conclusion
+
+CRANKITE was created as an extremely light-weight suite not overburdened with
+excessive command line options and configuration files. While usable as is,
+to unlock its full power, one will need to familiarize oneself with CRANKITE
+internals. CRANKITE source code is available without any warranty under
+the terms of GNU General Public License version 2.

README_AD

@@ -0,0 +1,24 @@
+folding with AutoDock potential:
+
+example usage:
+
+peptide -r 10000x3000 -t 2 apgvgvapgvgv -p Bias=NULL,external=5,con8,2,1.0,external2=4,con8,2,1.0,Opt=1,0.5,0.5,-0.5 -o output.pdb
+
+external=5,con8,2,1.0
+This calls the autodock grid maps. It will look for rigidReceptor.*.map. 
+con8 is the a file indicating the residues to score, usually just all residue number.
+2 is a thermo factor that is an addition to the original temperature.
+1.0 calls the reconstruction of side chain during the scoring.
+
+external2=4,con8,2,1.0 
+This calls the cyclic procedure to create an artificial peptide bond between first and last residue.
+con8 is meaningless right now, but can be used to indicate the location of the cyclic bond in the future.
+2 is the thermo factor, and it will overwrite the previous one in external.
+1.0 is meaningless right now, but can be used to flag the cyclic bond type, etc.
+
+Opt=1,0.5,0.5,-0.5
+This calls the optimizing/docking procedure. Opt=0 is to use regular MC.
+The following 3 numbers is the weight of the target energy in the optimizing procedure.
+In the example above:
+targetE = 0.5 * totalE + 0.5 * externalE + (-0.5) * firstlastE
+Note that totalE includes internalE, externalE and firstlastE. So the above weights scale down the internal energy by a factor of 2 and remove the energy between the first and last residues. The default weights are set to be 1, 0, 0.