metient 0.1.1.dev2__tar.gz → 0.1.1.dev3__tar.gz

{metient-0.1.1.dev2 → metient-0.1.1.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.0
 Name: metient
-Version: 0.1.1.dev2
+Version: 0.1.1.dev3
 Summary: UNKNOWN
 Home-page: https://github.com/divyakoyy/metient.git
 Author: UNKNOWN

{metient-0.1.1.dev2 → metient-0.1.1.dev3}/README.md

@@ -23,14 +23,16 @@ Each row in the tsv should correspond to the reference and variant read counts a
 The required fields for the tsv file:
 | Column name | Description |
 |----------|----------|
-| **anatomical_site_index** | Zero-based index for anatomical_site_label column | 
+| **anatomical_site_index** | Zero-based index for anatomical_site_label column. Rows with the same anatomical site index and cluster_index will get pooled together.| 
 | **anatomical_site_label** | Name of the anatomical site |
+| **character_label** | Zero-based index for character_label column |
 | **character_label** | Name of the mutation or cluster of mutations. This is used in visualizations, so it should be short. NOTE: due to graphing dependencies, this string cannot contain colons. |
-| **cluster_index** | If using a clustering method, the cluster index that this mutation belongs to. NOTE: this must correspond to the indices used in the tree txt file. |
+| **cluster_index** | If using a clustering method, the cluster index that this mutation belongs to. NOTE: this must correspond to the indices used in the tree txt file. Rows with the same anatomical site index and cluster_index will get pooled together.|
 | **ref** | The number of reads that map to the reference allele for this mutation or mutation cluster in this anatomical site. |
 | **var** | The number of reads that map to the variant allele for this mutation or mutation cluster in this anatomical site. |
-| **var_read_prob** | Let j = character_index. This is the probabilty of observing a read from the variant allele for mutation at j in a cell bearing the mutation. Thus, if mutation at j occurred at a diploid locus, this should be 0.5. In a haploid cell (e.g., male sex chromosome), this should be 1.0. If a copy-number aberration (CNA) duplicated the reference allele in the lineage bearing mutation j prior to j occurring, there will be two reference alleles and a single variant allele in all cells bearing j, such that var_read_prob = 0.3333. This gives Metient the ability to correct for the effect CNAs have on the relationship between VAF (i.e., the proportion of alleles bearing the mutation) and subclonal frequency (i.e., the proportion of cells bearing the mutation). This is modeled around PairTree's VAF correction, see S2.2 of [PairTree's supplementary info](https://aacr.silverchair-cdn.com/aacr/content_public/journal/bloodcancerdiscov/3/3/10.1158_2643-3230.bcd-21-0092/9/bcd-21-0092_supplementary_information_suppsm_sf1-sf21.pdf?Expires=1709221974&Signature=dJH6~Dg-6gEb-S88i0wDGW28QZn16keQj34Vo2tAvJL2cUJrQo48afpHPp-a2zAwQa~ET6SDgw3hb3ITacB06GDUc3GYCdCgYtfPMjFGwygFj-Q9xf-c44VAvwiyliwsBXK1shZmURlFMwSjzkwRwasuWu50sMNmeJSoVyX3nQ-rRBlK93aDR5s9c0l-p4aGvTi6QmfKJPsxXaHB4Lz5yXSl3Xd~JPK-Y~ltC14epDRb~MiSPWUFCAiYetUXcQ7J7vd6b4XQKT9PnYkjQtUq55tLSoUkOGe5JkJ32NXCeoT~l-XD97pCeDYVDOYzAuOkAG0tDYrPebEh2TGTA3fnbA__&Key-Pair-Id=APKAIE5G5CRDK6RD3PGA) for more details. |
 | **site_category** | Must be one of `primary` or `metastasis`. If multiple primaries are specified (i.e., the true primary is not known), we will run Metient multiple times with each primary used as the true primary. Output files are saved with the suffix `_{anatomical_site_label}` to indicate which primary was used in that run. |
+| **var_read_prob** | This gives Metient the ability to correct for the effect copy number alterations CNAs) have on the relationship between VAF (i.e., the proportion of alleles bearing the mutation) and subclonal frequency (i.e., the proportion of cells bearing the mutation). Let j = character_index. This is the probabilty of observing a read from the variant allele for mutation at j in a cell bearing the mutation. Thus, if mutation at j occurred at a diploid locus, this should be 0.5. In a haploid cell (e.g., male sex chromosome), this should be 1.0. If a CNA duplicated the reference allele in the lineage bearing mutation j prior to j occurring, there will be two reference alleles and a single variant allele in all cells bearing j, such that var_read_prob = 0.3333. If using a CN caller that reports major and minor CN: `var_read_prob = (p*maj)/(p*(maj+min)+(1-p)*2)`, where `p` is tumor purity, `maj` is major CN, `min` is minor CN, and we're assuming the variant allele has major CN. For more information, see S2.2 of [PairTree's supplementary info](https://aacr.silverchair-cdn.com/aacr/content_public/journal/bloodcancerdiscov/3/3/10.1158_2643-3230.bcd-21-0092/9/bcd-21-0092_supplementary_information_suppsm_sf1-sf21.pdf?Expires=1709221974&Signature=dJH6~Dg-6gEb-S88i0wDGW28QZn16keQj34Vo2tAvJL2cUJrQo48afpHPp-a2zAwQa~ET6SDgw3hb3ITacB06GDUc3GYCdCgYtfPMjFGwygFj-Q9xf-c44VAvwiyliwsBXK1shZmURlFMwSjzkwRwasuWu50sMNmeJSoVyX3nQ-rRBlK93aDR5s9c0l-p4aGvTi6QmfKJPsxXaHB4Lz5yXSl3Xd~JPK-Y~ltC14epDRb~MiSPWUFCAiYetUXcQ7J7vd6b4XQKT9PnYkjQtUq55tLSoUkOGe5JkJ32NXCeoT~l-XD97pCeDYVDOYzAuOkAG0tDYrPebEh2TGTA3fnbA__&Key-Pair-Id=APKAIE5G5CRDK6RD3PGA) for more details. |
+
 
         anatomical_site_index    anatomical_site_label    cluster_index    character_label    ref    var     var_read_prob    site_category    num_mutations
         0    breast    0    HER2    982    78    0.43    primary   54 

{metient-0.1.1.dev2 → metient-0.1.1.dev3}/metient/lib/vertex_labeling.py

@@ -919,7 +919,7 @@ def calibrate(tree_fns, tsv_fns, print_config, output_dir, run_names,
               Os, batch_size, custom_colors, bias_weights, solve_polytomies):
     
     if not (len(tree_fns) == len(tsv_fns) == len(run_names)):
-        raise ValueError("Inputs Ts, tsv_fns, primary_sites and run_names must have equal length (length = number of patients in cohort")
+        raise ValueError("Inputs Ts, tsv_fns, and run_names must have equal length (length = number of patients in cohort")
 
     if isinstance(tree_fns[0], str):
         Ts = []

{metient-0.1.1.dev2 → metient-0.1.1.dev3}/metient/util/data_extraction_util.py

@@ -2,7 +2,6 @@ import csv
 import numpy as np
 import os
 import torch
-import copy
 from collections import OrderedDict
 import pandas as pd
 import sys
@@ -14,7 +13,6 @@ print("CUDA GPU:",torch.cuda.is_available())
 if torch.cuda.is_available():
     torch.set_default_tensor_type(torch.cuda.FloatTensor)
 
-
 def get_adjacency_matrix_from_txt_edge_list(txt_file):
     edges = []
     max_idx = -1
@@ -44,28 +42,14 @@ def get_mut_to_cluster_map_from_pyclone_output(pyclone_cluster_fn, min_mut_thres
 
 def pool_input_tsv(tsv_fn, output_dir, run_name):
     '''
+    Pool reads from the same anatomical site index and cluster index
     '''
-    df = pd.read_csv(tsv_fn, delimiter="\t")
-    mut_name_to_cluster_id = {}
-    cluster_id_to_mut_names = {}
-    for _,row in df.iterrows():
-        cid = int(row['cluster_index'])
-        mut_name_to_cluster_id[row['character_label']] = cid
-        if cid not in cluster_id_to_mut_names:
-            cluster_id_to_mut_names[cid] = []
-        cluster_id_to_mut_names[cid].append(row['character_label'])
-    
-    cluster_id_to_cluster_name = {k:";".join(list(v)) for k,v in cluster_id_to_mut_names.items()}
-    cols = df.columns
-
-    df = df.drop(columns=["cluster_index"])
-    _, output_fn = write_pooled_tsv_from_clusters(df, mut_name_to_cluster_id, cluster_id_to_cluster_name, {}, 
-                                                  output_dir, run_name, ";", None)
+    df = pd.read_csv(tsv_fn, delimiter="\t")  
+    assert(set(df['site_category'])==set(['primary', 'metastasis']))
+    _, output_fn = write_pooled_tsv_from_clusters(df, {}, output_dir, run_name, None)
     return output_fn
 
-def write_pooled_tsv_from_clusters(df, mut_name_to_cluster_id, cluster_id_to_cluster_name,
-                                   aggregation_rules, output_dir, patient_id, cluster_sep, 
-                                   mutation_sep):
+def write_pooled_tsv_from_clusters(df, aggregation_rules, output_dir, patient_id, mutation_sep):
     '''
     After clustering with any clustering algorithm, prepares tsvs by pooling mutations belonging 
     to the same cluster
@@ -74,7 +58,7 @@ def write_pooled_tsv_from_clusters(df, mut_name_to_cluster_id, cluster_id_to_clu
         df: pandas DataFrame with reqiured columns: [character_label, 
         anatomical_site_index, anatomical_site_label, ref, var, var_read_prob, site_category]
 
-        mut_name_to_cluster_id: dictionary mapping mutation name ('character_label' in input df)
+        mut_idx_to_cluster_id: dictionary mapping mutation index ('character_index' in input df)
         to a cluster id
 
         cluster_id_to_cluster_name: dictionary mapping a cluster id to the name in the output tsv
@@ -94,8 +78,8 @@ def write_pooled_tsv_from_clusters(df, mut_name_to_cluster_id, cluster_id_to_clu
 
     '''
 
-    required_cols = ["anatomical_site_index", "anatomical_site_label", 
-                      "character_label", "ref","var", 
+    required_cols = ["anatomical_site_index", "anatomical_site_label", "cluster_index",
+                     "character_index", "character_label", "ref","var", 
                      "var_read_prob", "site_category"]
     
     all_cols = required_cols + list(aggregation_rules.keys())
@@ -116,33 +100,34 @@ def write_pooled_tsv_from_clusters(df, mut_name_to_cluster_id, cluster_id_to_clu
     df['ref'] = df.apply(lambda row: row['total_reads_corrected']-row['var'], axis=1)
     df['var_read_prob'] = 0.5
 
-    df['cluster'] = df.apply(lambda row: mut_name_to_cluster_id[row['character_label']] if row['character_label'] in mut_name_to_cluster_id else np.nan, axis=1)
-    df = df.dropna(subset=['cluster'])
+    #df['cluster'] = df.apply(lambda row: mut_idx_to_cluster_id[row['character_index']] if row['character_index'] in mut_idx_to_cluster_id else np.nan, axis=1)
+    df = df.dropna(subset=['cluster_index'])
+
+    # Save the number of mutations in each cluster before pooling
+    cluster_id_to_num_muts = df.groupby('cluster_index')['character_index'].nunique().to_dict()
+    cluster_id_to_mut_names = df.groupby('cluster_index')['character_label'].unique().apply(list).to_dict()
 
     # 2. Pool reference and variant allele counts from all mutations within a cluster
-    pooled_df = df.drop(['character_label', 'anatomical_site_index'], axis=1)
+    pooled_df = df.drop(['character_label','character_index'], axis=1) # we're going to add this back in later
 
     # TODO: validate that site_category is the same for each anatomical site
-    ref_var_rules = {'ref': np.sum, 'var': np.sum,'total_reads_corrected': np.sum, "var_read_prob": 'first', 'site_category':'first'}
+    ref_var_rules = {'ref': np.sum, 'var': np.sum,'total_reads_corrected': np.sum, "var_read_prob": 'first', 
+                     'site_category':'first', 'anatomical_site_label':lambda x: ';'.join(set(x)),}
+
+    pooled_df = pooled_df.groupby(['cluster_index', 'anatomical_site_index'], as_index=False).agg({**ref_var_rules, **aggregation_rules})
 
-    pooled_df = pooled_df.groupby(['cluster', 'anatomical_site_label'], as_index=False).agg({**ref_var_rules, **aggregation_rules})
-    
-    pooled_df['character_label'] = pooled_df.apply(lambda row: cluster_id_to_cluster_name[row['cluster']], axis=1)
-    
     # 3. Add indices for mutations, samples and anatomical sites as needed for input format
-    pooled_df['character_index'] = pooled_df['cluster'].astype(int)
+    pooled_df['character_index'] = pooled_df['cluster_index'].tolist()
     pooled_df['anatomical_site_index'] = pooled_df.apply(lambda row: list(pooled_df['anatomical_site_label'].unique()).index(row["anatomical_site_label"]), axis=1)
-    all_cols.append("total_reads_corrected")
-    all_cols.append("character_index")
-    pooled_df = pooled_df[all_cols]
     
     # 4. Do some post-processing, e.g. adding number of mutations and shortening character label for display
-    pooled_df['num_mutations'] = pooled_df.apply(lambda row: len(row['character_label'].split(cluster_sep)), axis=1)
-    pooled_df['full_label'] = pooled_df['character_label']
-    pooled_df['character_label'] = pooled_df.apply(lambda row:get_pruned_mut_label(row['character_label'], cluster_sep, mutation_sep), axis=1)
+    pooled_df['num_mutations'] = pooled_df.apply(lambda row:cluster_id_to_num_muts[int(row['character_index'])], axis=1)
+    pooled_df['character_label'] = pooled_df.apply(lambda row:get_pruned_mut_label(cluster_id_to_mut_names[row['cluster_index']], mutation_sep), axis=1)
     pooled_df['total_reads_corrected'] = pooled_df['total_reads_corrected'].round(0).astype(int)
     pooled_df['var'] = pooled_df['var'].round(0).astype(int)
     pooled_df['ref'] = pooled_df.apply(lambda row: row['total_reads_corrected']-row['var'], axis=1)
+    all_cols.append('num_mutations')
+    pooled_df = pooled_df[all_cols]
 
     # Save
     output_fn = os.path.join(output_dir, f"{patient_id}_clustered_SNVs.tsv")
@@ -162,71 +147,70 @@ def calc_var_read_prob(major_cn, minor_cn, purity):
     var_read_prob = (p*major_cn)/x
     return var_read_prob
     
-def write_pooled_tsv_from_conipher_pyclone_clusters(input_data_tsv_fn, clusters_tsv_fn, 
-                                           aggregation_rules, output_dir, patient_id,
-                                           cluster_sep, mutation_sep):
+# def write_pooled_tsv_from_conipher_pyclone_clusters(input_data_tsv_fn, clusters_tsv_fn, 
+#                                            aggregation_rules, output_dir, patient_id,
+#                                            cluster_sep, mutation_sep):
 
-    '''
-    After clustering with PyClone using CONIPHER (https://github.com/McGranahanLab/CONIPHER-wrapper),
-    prepares tsvs by pooling mutations belonging to the same cluster
+#     '''
+#     After clustering with PyClone using CONIPHER (https://github.com/McGranahanLab/CONIPHER-wrapper),
+#     prepares tsvs by pooling mutations belonging to the same cluster
 
-    Args:
-        tsv_fn: path to tsv with reqiured columns: [#sample_index, sample_label, 
-        character_index, character_label, anatomical_site_index, anatomical_site_label, 
-        ref, var]
+#     Args:
+#         tsv_fn: path to tsv with reqiured columns: [#sample_index, sample_label, 
+#         character_index, character_label, anatomical_site_index, anatomical_site_label, 
+#         ref, var]
 
-        clusters_tsv_fn: PyClone results tsv that maps each mutation to a cluster id
+#         clusters_tsv_fn: PyClone results tsv that maps each mutation to a cluster id
         
-        aggregation_rules: dictionary indicating how to aggregate any extra columns that are not in 
-        the required columns (specificied above). e.g. "first" aggregation rules can be used for columns 
-        shared by rows with the same anatomical_site_label, since we are aggregating within an
-        anatomical_site_label. 
+#         aggregation_rules: dictionary indicating how to aggregate any extra columns that are not in 
+#         the required columns (specificied above). e.g. "first" aggregation rules can be used for columns 
+#         shared by rows with the same anatomical_site_label, since we are aggregating within an
+#         anatomical_site_label. 
 
-        output_dir: where to save clustered tsv
+#         output_dir: where to save clustered tsv
 
-        patient_id: name of patient used in tsv filename
+#         patient_id: name of patient used in tsv filename
 
-        cluster_sep: string that separates names of mutations when creating a cluster name.
-        e.g. cluster name for mutations ABC:4:3 and DEF:1:2 with cluster_sep=";" will be 
-        "ABC:4:3;DEF:1:2"
+#         cluster_sep: string that separates names of mutations when creating a cluster name.
+#         e.g. cluster name for mutations ABC:4:3 and DEF:1:2 with cluster_sep=";" will be 
+#         "ABC:4:3;DEF:1:2"
 
-        mutation_sep: string that separates information about a variant, e.g.":" for a mutation
-        named ABC:4:3. Can be None if variants are not formatted this way.
+#         mutation_sep: string that separates information about a variant, e.g.":" for a mutation
+#         named ABC:4:3. Can be None if variants are not formatted this way.
 
 
-    Outputs:
+#     Outputs:
 
-        Saves pooled tsv at {output_dir}/{patient_id}_clustered_SNVs.tsv
+#         Saves pooled tsv at {output_dir}/{patient_id}_clustered_SNVs.tsv
 
-    '''
+#     '''
 
-    df = pd.read_csv(input_data_tsv_fn, delimiter="\t", index_col=0)
-    pyclone_df = pd.read_csv(clusters_tsv_fn, delimiter="\t")
-    mut_name_to_cluster_id = dict()
-    cluster_id_to_mut_names = dict()
-    # 1. Get mapping between mutation names and PyClone cluster ids
-    for _, row in df.iterrows():
-        mut_items = row['character_label'].split(":")
-        cluster_id = pyclone_df[(pyclone_df['CHR']==int(mut_items[1]))&(pyclone_df['POS']==int(mut_items[2]))&(pyclone_df['REF']==mut_items[3])]['treeCLUSTER'].unique()
-        assert(len(cluster_id) <= 1)
-        if len(cluster_id) == 1:
-            cluster_id = int(cluster_id.item())
-            mut_name_to_cluster_id[row['character_label']] = cluster_id
-            if cluster_id not in cluster_id_to_mut_names:
-                cluster_id_to_mut_names[cluster_id] = set()
-            else:
-                cluster_id_to_mut_names[cluster_id].add(row['character_label'])
+#     df = pd.read_csv(input_data_tsv_fn, delimiter="\t", index_col=0)
+#     pyclone_df = pd.read_csv(clusters_tsv_fn, delimiter="\t")
+#     mut_idx_to_cluster_id = dict()
+#     cluster_id_to_mut_names = dict()
+#     # 1. Get mapping between mutation names and PyClone cluster ids
+#     for _, row in df.iterrows():
+#         mut_items = row['character_label'].split(":")
+#         cluster_id = pyclone_df[(pyclone_df['CHR']==int(mut_items[1]))&(pyclone_df['POS']==int(mut_items[2]))&(pyclone_df['REF']==mut_items[3])]['treeCLUSTER'].unique()
+#         assert(len(cluster_id) <= 1)
+#         if len(cluster_id) == 1:
+#             cluster_id = int(cluster_id.item())
+#             mut_idx_to_cluster_id[int(row['character_index'])] = cluster_id
+#             if cluster_id not in cluster_id_to_mut_names:
+#                 cluster_id_to_mut_names[cluster_id] = set()
+#             else:
+#                 cluster_id_to_mut_names[cluster_id].add(row['character_label'])
 
-    # 2. Set new names for clustered mutations
-    cluster_id_to_cluster_name = {k:cluster_sep.join(list(v)) for k,v in cluster_id_to_mut_names.items()}
+#     # 2. Set new names for clustered mutations
+#     cluster_id_to_cluster_name = {k:cluster_sep.join(list(v)) for k,v in cluster_id_to_mut_names.items()}
 
-    print(patient_id, {k:v for k,v in list(mut_name_to_cluster_id.items())[:3]})
-    df['var_read_prob'] = df.apply(lambda row: calc_var_read_prob(row['major_cn'], row['minor_cn'], row['purity']), axis=1)
-    df['site_category'] = df.apply(lambda row: 'primary' if 'primary' in row['anatomical_site_label'] else 'metastasis', axis=1)
+#     df['var_read_prob'] = df.apply(lambda row: calc_var_read_prob(row['major_cn'], row['minor_cn'], row['purity']), axis=1)
+#     df['site_category'] = df.apply(lambda row: 'primary' if 'primary' in row['anatomical_site_label'] else 'metastasis', axis=1)
 
-    # 3. Pool mutations and write to file
-    return write_pooled_tsv_from_clusters(df, mut_name_to_cluster_id, cluster_id_to_cluster_name,
-                                          aggregation_rules, output_dir, patient_id, cluster_sep, mutation_sep)
+#     # 3. Pool mutations and write to file
+#     return write_pooled_tsv_from_clusters(df, mut_idx_to_cluster_id, cluster_id_to_cluster_name,
+#                                           aggregation_rules, output_dir, patient_id, cluster_sep, mutation_sep)
 
 def is_resolved_polytomy_cluster(cluster_label):
     '''
@@ -399,23 +383,26 @@ def get_ref_var_omega_matrices(tsv_filepaths):
 
     return ref_matrices, var_matrices, omega_matrices, ordered_sites, idx_to_label_dicts, idx_to_num_muts
 
-def get_pruned_mut_label(mut_label, cluster_sep, mutation_sep, k=2):
+def get_pruned_mut_label(mut_names, mutation_sep, k=2):
+
+    # If mutation names contain colons (e.g. LOC1:9:12312321), take everything before the first 
+    # colon for displaying since otherwise we can't display the label w/ our graphing library dependencies
     if mutation_sep != None:
-        gene_names = [item.split(mutation_sep)[0] for item in mut_label.split(cluster_sep)]
+        gene_names = [item.split(mutation_sep)[0] for item in mut_names]
     else:
-        gene_names = [item for item in mut_label.split(cluster_sep)]
+        gene_names = [item for item in mut_names]
 
-    gene_candidates = []
+    gene_candidates = set()
     for gene in gene_names:
         gene = gene.upper()
         if gene in CANCER_DRIVER_GENES:
-            gene_candidates.append(gene)
+            gene_candidates.add(gene)
         elif gene in ENSEMBLE_TO_GENE_MAP:
-            gene_candidates.append(ENSEMBLE_TO_GENE_MAP[gene])
+            gene_candidates.add(ENSEMBLE_TO_GENE_MAP[gene])
     final_genes = gene_names if len(gene_candidates) == 0 else gene_candidates
    
     k = k if len(final_genes) > k else len(final_genes)
-    return "_".join(final_genes[:k])
+    return "_".join(list(final_genes)[:k])
 
 def get_primary_sites(tsv_filepath):
     # For tsvs with very large fields
@@ -579,15 +566,6 @@ def _get_adj_matrix_from_machina_tree(tree_edges, idx_to_character_label, remove
     ret_dict = {v:k for k,v in ret_dict.items()}
     return T, ret_dict
 
-def get_index_to_cluster_label_from_corrected_sim_tsv(ref_var_fn):
-    df = pd.read_csv(ref_var_fn, sep="\t")
-    idx_to_label = {}
-    labels = df['character_label'].unique()
-    for label in labels:
-        idx = df[df['character_label']==label]['character_index'].unique().item()
-        idx_to_label[idx] = label
-    return idx_to_label
-
 def get_adj_matrices_from_spruce_mutation_trees(mut_trees_filename, idx_to_character_label, is_sim_data=False):
     '''
     When running MACHINA's generatemutationtrees executable (SPRUCE), it provides a txt file with

{metient-0.1.1.dev2 → metient-0.1.1.dev3}/metient.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.0
 Name: metient
-Version: 0.1.1.dev2
+Version: 0.1.1.dev3
 Summary: UNKNOWN
 Home-page: https://github.com/divyakoyy/metient.git
 Author: UNKNOWN

{metient-0.1.1.dev2 → metient-0.1.1.dev3}/setup.py

@@ -4,4 +4,4 @@ with open('requirements.txt') as f:
     requirements = f.read().splitlines()
     #print(requirements)
 
-setup(name='metient', version='0.1.1.dev2', url="https://github.com/divyakoyy/metient.git", packages=['metient', 'metient.util', 'metient.lib'], install_requires=requirements,)
+setup(name='metient', version='0.1.1.dev3', url="https://github.com/divyakoyy/metient.git", packages=['metient', 'metient.util', 'metient.lib'], install_requires=requirements,)