updated rule likelihood inputs

rules/kmerApproach.snk

@@ -456,7 +456,8 @@ rule createDistanceMatrixOverKmersOfV:
     input:
         kmers = 'data/auxiliary/kmers/{kmer}/spaSequences.counts.json'
     output:
-        V_kmers_distances = 'data/auxiliary/kmers/{kmer}/V_kmers.distances.npz'
+        V_kmers_distances = 'data/auxiliary/kmers/{kmer}/V_kmers.distances.npz',
+        V_kmers = 'data/auxiliary/kmers/{kmer}/V_kmers.json'
     params:
         k = lambda wildcards: wildcards.kmer,
         hamming_distance_cutoff = 5,

rules/probabilistic.snk

@@ -65,7 +65,9 @@ rule calcLikelihoods:
         expected = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/expected_counts.json',
         observed = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/alignment.counts.json',
         kmerError = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/kmer_error.txt',
-        kmerCoverageEstimate = determineKmerCoverageEstimateFile()
+        kmerCoverageEstimate = determineKmerCoverageEstimateFile(),
+        V_kmers_distances = 'data/auxiliary/kmers/{kmer}/V_kmers.distances.npz',
+        V_kmers = 'data/auxiliary/kmers/{kmer}/V_kmers.json'
     output:
         likelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/likelihoods_cov.json',
         unexpectedLikelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/unexpected_likelihoods_cov.json'
@@ -86,7 +88,7 @@ rule calcLikelihoods:
     singularity:
         'docker://phspo/ckmertools:iterationset-tests'
     shell:
-        'c_kmertools --e {input.expected} --c {params.cpus} --m 0 --o {input.observed} --kmererror {params.e} --d {params.deviationCutoff} --target {output.likelihoods} --unexpected {output.unexpectedLikelihoods} --log {log} --itersetType {params.itersetType}'
+        'c_kmertools --e {input.expected} --c {params.cpus} --m 0 --o {input.observed} --kmererror {params.e} --d {params.deviationCutoff} --target {output.likelihoods} --unexpected {output.unexpectedLikelihoods} --log {log} --itersetType {params.itersetType} --hammingdist {input.V_kmers_distances} --kmersindex {input.V_kmers}'
 
 
 rule calcLikelihoods_Generative:

scripts/calcDistanceMatrixVkmers.py

@@ -5,8 +5,13 @@ from scipy.sparse import coo_matrix, vstack, save_npz
 from sklearn.metrics import pairwise_distances_chunked, pairwise_distances
 
 ##############INPUT######################################
+cutoff = snakemake.params['hamming_distance_cutoff']
+kmers_file = snakemake.input['kmers']
+mem = snakemake.params['mem'][:-1]
+V_kmers_distances_file = snakemake.output['V_kmers_distances']
+V_kmers_file = snakemake.output['V_kmers']
 # eg "spaSequences.counts.json"
-f = open(snakemake.input['kmers'], "r")
+f = open(kmers_file, "r")
 expected_json = f.read()
 person_dict = json.loads(expected_json)
 
@@ -19,7 +24,7 @@ m = len(kmers[0])
 
 #########################################################
 # eg 5
-ALLOWED_DISTANCE = int(snakemake.params['hamming_distance_cutoff'])/m
+ALLOWED_DISTANCE = int(cutoff)/m
 def reduce_func(D_chunk, start):
     neigh = np.where(D_chunk < ALLOWED_DISTANCE, D_chunk, 0)
     return (neigh * m).astype('u1')
@@ -44,7 +49,7 @@ print(M.shape)
 cpus = -1
 # working_memory = 1024
 # eg snakemake.params['mem'] = 1G
-working_memory = int(snakemake.params['mem'][:-1]) * 1000 - 500
+working_memory = int(mem) * 1000 - 500
 gen = pairwise_distances_chunked(kmers_int, reduce_func=reduce_func, metric="hamming", n_jobs=cpus,
                                  working_memory=working_memory)
 
@@ -74,7 +79,8 @@ print("Matrix shape:", M.shape)
 print("Density of sparse matrix: ", M.getnnz() / np.prod(M.shape))
 M = M.tocoo()
 # eg 'V_kmer_distances.npz'
-save_npz(snakemake.output['V_kmers_distances'], M)
-# https://github.com/rogersce/cnpy
-# https://stackoverflow.com/questions/36433030/load-scipy-sparse-csr-matrix-in-c
+save_npz(V_kmers_distances_file, M)
+
+with open(V_kmers_file, 'w', encoding='utf-8') as f:
+    json.dump(kmers, f, ensure_ascii=False, indent=4)