Merge pull request #9 from RenneLab/v3.2

V3.2

docs/source/about.rst

@@ -22,6 +22,13 @@ Lead Developer
 Changelog
 ---------
 
+
+    * 0.3.2 (2023-08) Changes include:
+
+      * Misc Bugfixes and Refinements
+      * Add duplicate hybrid filtration (by HybRecord.id) options to hyb_filter
+      * Add duplicate hybrid filtration to example analyses
+
     * 0.3.1 (2023-08) Changes include:
 
       * Misc Bugfixes and Refinements
@@ -31,6 +38,7 @@ Changelog
       * Change default plot colors to the Bang Wong scheme [Wong2011]_ for
         colorblind accessibility
       * Documentation corrections
+      * Spellcheck
 
     * 0.3.0 (2023-04) Major Codebase And API Overhaul. Changes include:
 

example_01_type_mirna_analysis/README.rst

@@ -23,7 +23,7 @@ The data files can be downloaded and uncompressed by using the command::
 The unpacked hyb data-files require ~2 GB of space.
 The completed output of the analysis requires ~1.5 GB of space.
 
-Summary Analysis Example Output
+Type-miRNA Analysis Example Output
 -------------------------------
 
 .. image:: ../example_01_type_mirna_analysis/example_output/combined_analysis_types_hybrid_types.png

example_01_type_mirna_analysis/analysis_python.py

@@ -40,6 +40,11 @@
 # Set hybrid segment types to remove as part of quality control (QC)
 remove_types = ['rRNA', 'mitoch-rRNA']
 
+# Initialize Combined Analysis
+combined_analysis = hybkit.analysis.Analysis(
+    analysis_types=['type', 'mirna'], name='Combined Analysis'
+)
+
 # Iterate over each input file, find the segment types, and save the output
 #   in the output directory.
 for in_file_path in input_files:
@@ -56,13 +61,14 @@
     file_analysis = hybkit.analysis.Analysis(
         analysis_types=['type', 'mirna'], name=in_file_label
     )
-    combined_analysis = hybkit.analysis.Analysis(
-        analysis_types=['type', 'mirna'], name='Combined Analysis'
-    )
 
     # Open one HybFile entry for reading, and one for writing
     with hybkit.HybFile(in_file_path, 'r', hybformat_id=True) as in_file, \
          hybkit.HybFile(out_file_path, 'w') as out_file:
+
+        # Track last record identifier, to use only one record per read
+        last_record_id = None
+
         # Iterate over each record of the input file
         for hyb_record in in_file:
             hyb_record.eval_types()  # Find segment types
@@ -74,10 +80,16 @@
                 if hyb_record.has_prop('any_seg_type_is', remove_type):
                     use_record = False
                     break
+
             # If record has an excluded type, continue to next record without analyzing.
             if not use_record:
                 continue
 
+            # If record is a duplicate, skip it.
+            elif hyb_record.id == last_record_id:
+                continue
+            last_record_id = hyb_record.id
+
             # Set the dataset label for the record
             hyb_record.set_flag('dataset', in_file_label)
 

example_01_type_mirna_analysis/analysis_shell.sh

@@ -9,7 +9,7 @@ NOTES="""
 Analysis for type/mirna analysis performed using shell scripts.
 
 Provided as an example of usage of hybkit shell executable scripts.
-This will produce identical output to analysis_python.py version,
+This will produce identical output to the analysis_python.py version,
 though that implementation is more efficient.
 
 See: 'README.rst' for this analysis for more information.
@@ -70,6 +70,7 @@ hyb_filter -i ${EVAL_FILES[*]} --verbose \
            -o ${QC_FILES} \
            --exclude any_seg_type_is rRNA \
            --exclude_2 any_seg_type_is mitoch-rRNA \
+           --skip_dup_id_after \
 
 # Cleanup intermediate files
 rm -v ${OUT_DIR}/*evaluated*.hyb

example_01_type_mirna_analysis/example_output/GSM2720020_WT_BR1_qc_mirna_results.csv

@@ -1,6 +1,6 @@
-mirna_analysis_count,445194
-has_mirna,272840
-non_mirna,172354
-mirnas_5p,238924
-mirnas_3p,11441
-mirna_dimers,22475
+mirna_analysis_count,209937
+has_mirna,155572
+non_mirna,54365
+mirnas_5p,128134
+mirnas_3p,6006
+mirna_dimers,21432

example_01_type_mirna_analysis/example_output/GSM2720020_WT_BR1_qc_type_all_seg_types.csv

@@ -1,12 +1,12 @@
-mRNA,477847
-miRNA,279775
-pseudogene,92391
-KSHV-miRNA,15540
-pr-tr,10915
-tRNA,7734
-miscRNA,2482
-snRNA,1413
-lincRNA,1372
-snoRNA,915
-Ig,3
+mRNA,194862
+miRNA,167593
+pseudogene,41245
+KSHV-miRNA,9411
+pr-tr,2870
+tRNA,1684
+miscRNA,683
+lincRNA,612
+snoRNA,497
+snRNA,414
+Ig,2
 Trec,1

example_01_type_mirna_analysis/example_output/GSM2720020_WT_BR1_qc_type_hybrid_types.csv

@@ -1,91 +1,89 @@
-miRNA--mRNA,187311
-mRNA--mRNA,112621
-miRNA--pseudogene,31252
-mRNA--pseudogene,20701
-miRNA--miRNA,20260
-pseudogene--mRNA,15354
-KSHV-miRNA--mRNA,10060
-pseudogene--pseudogene,9186
-mRNA--miRNA,8716
-miRNA--pr-tr,4579
-tRNA--mRNA,3511
-KSHV-miRNA--pseudogene,1920
-pr-tr--mRNA,1909
-tRNA--pseudogene,1616
-mRNA--pr-tr,1540
-miRNA--tRNA,1178
-pseudogene--miRNA,1168
-KSHV-miRNA--miRNA,1090
-miRNA--KSHV-miRNA,1047
-miRNA--miscRNA,829
-miscRNA--mRNA,699
-pr-tr--pr-tr,681
-mRNA--KSHV-miRNA,587
-mRNA--tRNA,575
-miRNA--snRNA,562
-pr-tr--pseudogene,560
-miRNA--lincRNA,495
-pseudogene--pr-tr,313
-lincRNA--mRNA,312
-tRNA--miRNA,310
-snoRNA--mRNA,291
-miscRNA--pseudogene,287
-snRNA--mRNA,263
-KSHV-miRNA--pr-tr,254
-mRNA--lincRNA,252
-pr-tr--miRNA,250
-mRNA--miscRNA,228
-mRNA--snRNA,213
-miRNA--snoRNA,202
-pseudogene--tRNA,194
-snoRNA--pseudogene,132
-miscRNA--miRNA,108
-KSHV-miRNA--tRNA,107
-pseudogene--miscRNA,98
-KSHV-miRNA--snRNA,96
-snRNA--pseudogene,96
-pseudogene--snRNA,88
-pseudogene--KSHV-miRNA,85
-lincRNA--pseudogene,82
-mRNA--snoRNA,82
+miRNA--mRNA,102489
+mRNA--mRNA,33159
+miRNA--miRNA,19328
+miRNA--pseudogene,16077
+mRNA--pseudogene,7179
+pseudogene--mRNA,6233
+KSHV-miRNA--mRNA,5552
+mRNA--miRNA,4580
+pseudogene--pseudogene,4490
+miRNA--pr-tr,1518
+KSHV-miRNA--pseudogene,1109
+KSHV-miRNA--miRNA,1027
+miRNA--KSHV-miRNA,999
+pseudogene--miRNA,736
+tRNA--mRNA,679
+miRNA--tRNA,364
+pr-tr--mRNA,362
+mRNA--pr-tr,321
+mRNA--KSHV-miRNA,305
+tRNA--pseudogene,284
+miRNA--lincRNA,277
+miRNA--snRNA,226
+miscRNA--mRNA,216
+miRNA--miscRNA,202
+miRNA--snoRNA,149
+snoRNA--mRNA,138
+pr-tr--pseudogene,135
+pr-tr--pr-tr,130
+mRNA--tRNA,130
+miscRNA--pseudogene,107
+lincRNA--mRNA,107
+tRNA--miRNA,98
+pseudogene--pr-tr,92
+mRNA--lincRNA,87
 KSHV-miRNA--KSHV-miRNA,78
-snoRNA--miRNA,68
-tRNA--tRNA,65
-miscRNA--miscRNA,62
-lincRNA--miRNA,58
-pseudogene--lincRNA,46
-snoRNA--snoRNA,45
-KSHV-miRNA--miscRNA,42
-tRNA--pr-tr,35
-tRNA--KSHV-miRNA,32
-snRNA--miRNA,30
-KSHV-miRNA--lincRNA,28
-lincRNA--lincRNA,26
-pseudogene--snoRNA,26
-pr-tr--KSHV-miRNA,22
-tRNA--miscRNA,22
-lincRNA--pr-tr,19
-miscRNA--pr-tr,16
-pr-tr--miscRNA,15
-snRNA--snRNA,14
-pr-tr--tRNA,12
-pr-tr--lincRNA,11
-snoRNA--snRNA,11
-pr-tr--snRNA,10
-snRNA--miscRNA,8
+KSHV-miRNA--pr-tr,78
+pr-tr--miRNA,68
+pseudogene--KSHV-miRNA,67
+snoRNA--pseudogene,61
+pseudogene--tRNA,58
+snRNA--mRNA,52
+miscRNA--miRNA,49
+mRNA--snRNA,43
+snoRNA--miRNA,42
+mRNA--miscRNA,42
+KSHV-miRNA--tRNA,36
+snoRNA--snoRNA,28
+mRNA--snoRNA,28
+lincRNA--pseudogene,27
+pseudogene--miscRNA,27
+KSHV-miRNA--snRNA,24
+pseudogene--snRNA,22
+lincRNA--lincRNA,21
+snRNA--pseudogene,21
+lincRNA--miRNA,19
+pseudogene--lincRNA,18
+KSHV-miRNA--lincRNA,18
+snRNA--miRNA,16
+miscRNA--miscRNA,11
+pseudogene--snoRNA,11
+tRNA--KSHV-miRNA,11
+pr-tr--KSHV-miRNA,10
+tRNA--pr-tr,8
 KSHV-miRNA--snoRNA,7
-lincRNA--KSHV-miRNA,4
-snoRNA--pr-tr,4
-lincRNA--tRNA,4
-tRNA--lincRNA,4
-snRNA--pr-tr,4
-lincRNA--miscRNA,3
-snRNA--tRNA,2
-miRNA--Ig,2
+KSHV-miRNA--miscRNA,7
+lincRNA--pr-tr,6
+tRNA--tRNA,4
+pr-tr--lincRNA,4
+miscRNA--pr-tr,3
+lincRNA--KSHV-miRNA,2
+tRNA--miscRNA,2
+snRNA--snRNA,2
 miscRNA--KSHV-miRNA,2
-tRNA--snRNA,2
+pr-tr--tRNA,2
+tRNA--lincRNA,2
+snoRNA--snRNA,2
+pr-tr--miscRNA,1
+snRNA--tRNA,1
 miscRNA--lincRNA,1
 pseudogene--Ig,1
+tRNA--snRNA,1
 mRNA--Trec,1
+pr-tr--snRNA,1
 snoRNA--KSHV-miRNA,1
 snoRNA--lincRNA,1
+snoRNA--pr-tr,1
+miRNA--Ig,1
+lincRNA--miscRNA,1
+snRNA--miscRNA,1