first pass

slim  script modifciations and add output to gitignore

Update Makefile and development documentation for verification process

Comment out test for GC tract length as it is not supported in SmcKApproxCoalescent

cycle instead of tick

Author: hossam26644

.gitignore

@@ -95,4 +95,7 @@ tmp__NOBACKUP__
 .DS_Store
 
 # vscode stuff
-.vscode
+.vscode
+
+# verfification files
+verification/*

Makefile

@@ -27,6 +27,10 @@ clang-format:
 tags:
 	ctags -f TAGS msprime/*.c lib/*.[c,h] msprime/*.py tests/*.py algorithms.py
 
+verification:
+	pip install -e ".[verification]"
+	$(MAKE) -C data
+	python verification.py -t 4 -d verification
 
 clean:
 	rm -fR build

data/Makefile

@@ -1,4 +1,4 @@
-all: scrm ms msHOT slim seq-gen msms msprime-0.7.4
+all: scrm ms msHOT slim seq-gen msms msprime-0.7.4 discoal
 
 seq-gen:
 	rm -fR seq-gen Seq-Gen* 1.3.4.tar.gz
@@ -9,12 +9,12 @@ seq-gen:
 
 slim:
 	rm -fR SLiM*
-	wget https://github.com/MesserLab/SLiM/archive/refs/tags/v3.7.1.tar.gz
-	tar -zxvf v3.7.1.tar.gz 
-	mkdir SLiM-3.7.1/build
+	wget https://github.com/MesserLab/SLiM/archive/refs/tags/v5.1.tar.gz
+	tar -zxvf v5.1.tar.gz
+	mkdir SLiM-5.1/build
 	# Arbitrarily using 4 threads to build here..
-	cd SLiM-3.7.1/build && cmake .. && make -j 4
-	cp SLiM-3.7.1/build/slim ./
+	cd SLiM-5.1/build && cmake .. && make -j 4
+	cp SLiM-5.1/build/slim ./
 
 scrm:
 	wget https://github.com/scrm/scrm/releases/download/v1.7.2/scrm-src.tar.gz

docs/development.md

@@ -760,6 +760,15 @@ directory.
 Please read the comments at the top of the `verification.py` script for details
 on how to write and run these tests.
 
+The make rule `verification` bundles the three steps in one command: installs the dependencies, 
+compiles customised versions of `ms` (and other tools), and runs all the tests sequentially. 
+
+To invoke this rule run the command:
+```
+$ make verification
+```
+The output should be in the directory: `/verification`
+
 ## Benchmarking
 
 Benchmarks to measure performance are in the `benchmarks` folder and are run using

verification.py

@@ -141,7 +141,7 @@ def write_slim_script(outfile, format_dict):
         initializeRecombinationRate({RHO});
     }}
     // create a population
-    1
+    1 early()
     {{
         {POP_STRS};
         sim.tag = 0;
@@ -151,11 +151,11 @@ def write_slim_script(outfile, format_dict):
     {{
         if (sim.tag == 0) {{
             if (sim.treeSeqCoalesced()) {{
-                sim.tag = sim.generation;
+                sim.tag = sim.cycle;
                 catn(sim.tag + ': COALESCED');
             }}
         }}
-        if (sim.generation == sim.tag * 10) {{
+        if (sim.cycle == sim.tag * 10) {{
             sim.simulationFinished();
             catn('Ran a further ' + sim.tag * 10 + ' generations');
             sim.treeSeqOutput('{OUTFILE}');
@@ -185,7 +185,7 @@ def write_sweep_slim_script(outfile, format_dict):
                     sim.simulationFinished();
         }}
 
-        1 {{
+        1 early(){{
             // save this run's identifier, used to save and restore
             defineConstant("simID", getSeed());
             sim.addSubpop("p1", {POPSIZE});
@@ -195,7 +195,7 @@ def write_sweep_slim_script(outfile, format_dict):
         2 late() {{
             // save the state of the simulation
             sim.treeSeqOutput("/tmp/slim_" + simID + ".trees");
-            target = sample(p1.genomes, 1);
+            target = sample(p1.haplosomes, 1);
             target.addNewDrawnMutation(m2, {SWEEPPOS});
         }}
         2:2000 late() {{
@@ -208,15 +208,15 @@ def write_sweep_slim_script(outfile, format_dict):
                 if (fixed)
                 {{
                     if (sim.getValue("flag") == 1){{
-                        sim.rescheduleScriptBlock(s1,
-                        start=sim.generation+{TAU}, end=sim.generation+{TAU});
+                        community.rescheduleScriptBlock(s1,
+                        start=sim.cycle+{TAU}, end=sim.cycle+{TAU});
                     }}
                 }}
                 else
                 {{
                     sim.readFromPopulationFile("/tmp/slim_" + simID + ".trees");
                     setSeed(rdunif(1, 0, asInteger(2^62) - 1));
-                    target = sample(p1.genomes, 1);
+                    target = sample(p1.haplosomes, 1);
                     target.addNewDrawnMutation(m2, {SWEEPPOS});
                 }}
             }}
@@ -946,9 +946,9 @@ def sample_recap_simplify(slim_ts, sample_size, Ne, r, mu):
             demography=demography,
             recombination_rate=r,
             # TODO is this needed now? Shouldn't be, right?
-            start_time=slim_ts.metadata["SLiM"]["generation"],
+            start_time=slim_ts.metadata["SLiM"]["cycle"],
         )
-    logging.debug(f"pyslim: slim generation:{slim_ts.metadata['SLiM']['generation']}")
+    logging.debug(f"pyslim: slim generation:{slim_ts.metadata['SLiM']['cycle']}")
     alive_inds = pyslim.individuals_alive_at(recap, 0)
     keep_indivs = np.random.choice(alive_inds, sample_size, replace=False)
     keep_nodes = []
@@ -3823,7 +3823,7 @@ def test_gc_correlation_between_trees(self):
         seq_length = 500
         # tests both Hudson as well as SMC K
         # by setting hull_offset to seq_length are essentially simulating Hudson
-        models = ["hudson", msprime.SmcKApproxCoalescent(hull_offset=seq_length)]
+        models = ["hudson"]
         predicted_prob = np.zeros([gc_length_rate_ratio.size, seq_length], dtype=float)
         empirical_prob_first = np.zeros(
             [2, gc_length_rate_ratio.size, seq_length], dtype=float
@@ -4949,6 +4949,8 @@ def test_smck_vs_smckapprox_multiple_bottleneck(self):
             sequence_length=5e7,
         )
 
+    '''
+    Commented as gc is not yet supported in SmcKApproxCoalescent
     def test_gc_tract_length_smc(self):
         """
         Runs the check for the mean length of gene conversion tracts.
@@ -5132,6 +5134,7 @@ def test_smc_k_num_trees_gc(self):
         pyplot.tight_layout()
         pyplot.savefig(self.output_dir / "breakpoints_boxplot.png")
         pyplot.close()
+    '''
 
     def test_out_of_africa_migration_model(self):
         s_no = 10