🌌towards v0.3.2 (#15)

* 🦹‍♂️deal with old edge case

* 🧜‍♂️add 1d-coordinates

* 👨‍🌾impl dataclass

* 👮‍♂️fix unchange

* 🏃‍♂️add funcs for Identifier

* 👨‍🎨add pipe_scheduled_ranged_map_res_df

* ⚡change pytest-timeout

* 🦼add demo files

* ☔fix test path

* 🌬fix command.py output path

* 🦽add time for test_single_select

* add auto_assign

* add time

README.md

@@ -24,7 +24,7 @@ Profiling Protein Structures from Protein Data Bank and integrate various resour
 
 ## Install
 
-> Notice: require Python Environment >= 3.6, Platform Independent
+> Notice: require Python Environment >= 3.7, Platform Independent
 
 Install by `pip` command.
 

pdb_profiling/__init__.py

@@ -4,7 +4,7 @@
 # @Author: ZeFeng Zhu
 # @Last Modified: 2020-05-13 08:54:09 pm
 # @Copyright (c) 2020 MinghuiGroup, Soochow University
-__version__ = '0.2.12'
+__version__ = '0.3.2'
 
 
 def default_config(folder='./'):

pdb_profiling/commands/command.py

@@ -100,7 +100,7 @@ def do_nothing(dfrm):
 @click.option('--column', type=str, default=None)
 @click.option('--sep', type=str, default='\t')
 @click.option('--chunksize', type=int, help="the chunksize parameter", default=50)
-@click.option('--auto_assign/--no-auto_assign', default=True, is_flag=True)
+@click.option('--auto_assign/--no-auto_assign', default=False, is_flag=True)
 @click.option('--sleep/--no-sleep', default=True, is_flag=True)
 @click.pass_context
 def id_mapping(ctx, input, column, sep, chunksize, auto_assign, sleep):
@@ -283,7 +283,7 @@ def residue_mapping(ctx, input, chunksize, output, sleep):
                    na_values=['NULL', 'null', ''], chunksize=chunksize)
     sqlite_api = ctx.obj['custom_db']
     if output is not None:
-        output = Path(output)
+        output = ctx.obj['folder']/output
     done = 0
     for df in dfs:
         for col in ('new_pdb_range_raw', 'new_unp_range_raw', 'conflict_pdb_index'):
@@ -294,7 +294,7 @@ def residue_mapping(ctx, input, chunksize, output, sleep):
                     row.new_unp_range_raw,
                     row.new_pdb_range_raw,
                     conflict_pdb_index=row.conflict_pdb_index,
-                    struct_asym_id=row.struct_asym_id) for _, row in df.iterrows()]
+                    struct_asym_id=row.struct_asym_id) for row in df.to_records()]
         with Progress(*progress_bar_args) as p:
             res = ob.run(p.track).result()
         res_mapping_df = concat(res, sort=False, ignore_index=True)
@@ -442,7 +442,7 @@ def export_residue_remapping(ctx, with_id, sele, output):
             if df.shape[0] == 0:
                 continue
             df.rename(columns={'edUniProt': 'UniProt'}).to_csv(
-                output, index=False, mode='a+', sep='\t', header=not output_path.exists())
+                output_path, index=False, mode='a+', sep='\t', header=not output_path.exists())
     console.log(f'result saved in {output_path}')
 
 
@@ -524,7 +524,7 @@ def export_smr_residue_remapping(ctx, identity_cutoff, length_cutoff, with_id, s
             if df.shape[0] == 0:
                 continue
             df.rename(columns={'edUniProt': 'UniProt'}).to_csv(
-                output, index=False, mode='a+', sep='\t',header=not output_path.exists())
+                output_path, index=False, mode='a+', sep='\t', header=not output_path.exists())
     console.log(f'result saved in {output_path}')
     #full_df = read_csv(output_path, sep='\t', keep_default_na=False)
     #best_indexes = full_df.groupby(['UniProt','Pos', 'Alt']).select_rank.idxmin()

pdb_profiling/cython/cyrange.pyx

@@ -235,7 +235,7 @@ cpdef bint isin_range(object input_range, int value):
     return False
 
 
-cpdef int convert_index(object lrange, object rrange, int site):
+cdef int convert_index(object lrange, object rrange, int site) except *:
     # convert from rrange to lrange
     cdef int lstart, rstart, lend, rend
     for (lstart, lend), (rstart, rend) in zip(lrange, rrange):

pdb_profiling/processors/__init__.py

@@ -7,12 +7,13 @@
 from pdb_profiling.processors.pdbe.record import (
     Base, 
     PDB, 
-    PDBAssemble,
+    PDBAssembly,
     PDBInterface,
     SIFTS,
     Compounds,
     PDBs,
-    SIFTSs
+    SIFTSs,
+    RCSB1DCoordinates,
     )
 from pdb_profiling.processors.pdbe.api import PDBeModelServer, PDBArchive, PDBVersioned
 from pdb_profiling.processors.uniprot.api import UniProtINFO, UniProtAPI

pdb_profiling/processors/pdbe/__init__.py

@@ -8,27 +8,6 @@
 from re import compile as re_compile
 from pdb_profiling.processors.database import SqliteDB
 
-common_pat = r'^(?=.*[A-Za-z])(?=.*\d)[A-Za-z\d]'
-
-
-pats = dict(pdb_id=re_compile(common_pat+r'{4}$'),
-            pdb_entity_id=re_compile(common_pat+r'{4}_[0-9]+$'),
-            UniProt=re_compile(common_pat+r'{6,}[\-]*[0-9]*$'),
-            pdb_complex_id=re_compile(r'PDB-CPX-[0-9]+'))
-
-
-def default_id_tag(identifier: str, default: str = '', raise_error: bool = False):
-    try:
-        for pat_name, pat in pats.items():
-            if bool(pat.fullmatch(identifier)):
-                return pat_name
-    except Exception:
-        raise ValueError(f"Invalid Identifier: {identifier} !")
-    if raise_error:
-        raise ValueError(f'Unexpected Identifiers: {identifier}')
-    else:
-        return default
-
 
 class PDBeDB(SqliteDB):
 

pdb_profiling/processors/pdbe/api.py

@@ -14,7 +14,7 @@
 from unsync import unsync, Unfuture
 from random import choice
 from hashlib import sha1
-from pdb_profiling.processors.pdbe import default_id_tag
+from pdb_profiling.processors.recordbase import IdentifierBase
 from pdb_profiling.utils import related_dataframe, flatten_dict, pipe_out, dumpsParams
 from pdb_profiling.log import Abclog
 from pdb_profiling.fetcher.webfetch import UnsyncFetch
@@ -43,6 +43,16 @@
 FUNCS = []
 
 
+def mask_ib(i, default='', raise_error=False):
+    if i.source == 'PDB' and i.level == 'entry':
+        return 'pdb_id'
+    elif i.source == 'UniProt':
+        return 'UniProt'
+    elif raise_error:
+        raise AssertionError('Unexpected Case!')
+    else:
+        return default
+
 def str_number_converter(x):
     try:
         return int(x)
@@ -207,7 +217,7 @@ def yieldCommon(data: Dict) -> Generator:
                 for key in value:
                     if isinstance(value[key], (Dict, List)):
                         value[key] = json.dumps(value[key]).decode('utf-8')
-            yield values, (default_id_tag(pdb, '_code_'),), (pdb,)
+            yield values, (mask_ib(IdentifierBase(pdb), '_code_'),), (pdb,)
 
     @staticmethod
     @dispatch_on_set('api/pdb/entry/polymer_coverage/')
@@ -348,8 +358,7 @@ def yieldSIFTSAnnotation(data: Dict) -> Generator:
                                     continue
                                 chain[key] = json.dumps(value).decode(
                                     'utf-8') if isinstance(value, Dict) else value
-                            chain[default_id_tag(
-                                top_root, raise_error=True)] = top_root
+                            chain[mask_ib(IdentifierBase(top_root), raise_error=True)] = top_root
                             chain[sec_root] = annotation
                         yield chains, None
             elif len(data[top_root].keys()) == 1 and 'PDB' in data[top_root].keys():