updated docs

docs/source/configuration.rst

@@ -20,10 +20,17 @@ The format of configuration file which is one of the inputs for ``xpore-diffmod`
 
     out: <DIR_PATH_FOR_OUTPUTS>
     
-    (OPTIONAL)
+    criteria:
+        readcount_min: <15>
+        readcount_max: <1000>
+        
     method:
         prefiltering:
             method: t-test
             threshold: <P_VALUE_THRESHOLD>
+        max_iters: <500>
+        stopping_criterial: <0.0001>
+        
+
 
 

docs/source/preparation.rst

@@ -8,11 +8,13 @@ Data preparation from raw reads
     guppy_basecaller -i </PATH/TO/FAST5> -s </PATH/TO/FASTQ> --flowcell <FLOWCELL_ID> --kit <KIT_ID> --device auto -q 0 -r   
 
 2. Align to transcriptome::
+   
    minimap2 -ax map-ont -uf -t 3 --secondary=no <MMI> <PATH/TO/FASTQ.GZ> > <PATH/TO/SAM> 2>> <PATH/TO/SAM_LOG>
    samtools view -Sb <PATH/TO/SAM> | samtools sort -o <PATH/TO/BAM> - &>> <PATH/TO/BAM_LOG>
    samtools index <PATH/TO/BAM> &>> <PATH/TO/BAM_INDEX_LOG>
 
 3. Resquiggle using `nanopolish eventalign <https://nanopolish.readthedocs.io/en/latest/quickstart_eventalign.html>`_::
+   
    nanopolish index -d <PATH/TO/FAST5_DIR> <PATH/TO/FASTQ_FILE>
    nanopolish eventalign --reads <PATH/TO/FASTQ_FILE> \
    --bam <PATH/TO/BAM_FILE> \

docs/source/scripts.rst

@@ -7,14 +7,47 @@ We provide 2 main scripts to run the analysis of differential RNA modifications
 
 1. ``xpore-dataprep``
 
+Input
+-------
+
+Usage example
+--------------
+
 =================  ==========  =============== =============
 Argument name(s)    Required    Default value   Description
 =================  ==========  =============== =============
---eventalign        Yes             NA          eventalign filepath, the output from nanopolish.         
---summary           Yes             NA          eventalign summary filepath, the output from nanopolish.
---out_dir           Yes             NA          output directory.
+--eventalign=FILE       Yes         NA              Eventalign filepath, the output from nanopolish.         
+--summary=FILE          Yes         NA              Eventalign summary filepath, the output from nanopolish.
+--out_dir=DIR           Yes         NA              Output directory.
+--ensembl=NUM           No          91              Ensembl version for gene-transcript mapping.
+--species=STR           No          homo_sapiens    Species for ensembl gene-transcript mapping.
+--genome                No          False           To run on Genomic coordinates. Without this argument, the program will run on transcriptomic coordinates.
+--n_processes=NUM       No          1               Number of processes to run.
+--readcount_max=NUM     No          1000            Maximum read counts per gene.
+--resume                No          False           With this argument, the program will resume from the previous run.
 =================  ==========  =============== =============
 
+Output
+--------
 
 2. ``xpore-diffmod``
 
+Input
+--------
+
+Usage example
+--------------
+
+=================  ==========  =============== =============
+Argument name(s)    Required    Default value   Description
+=================  ==========  =============== =============
+--config=FILE           Yes         NA              Yaml configuraion filepath.
+--n_processes=NUM       No          1               Number of processes to run.
+--save_models           No          False           With this argument, the program will save the model parameters for each id.
+--resume                No          False           With this argument, the program will resume from the previous run.
+--ids=LIST              No          []              Gene / Transcript ids to model.
+=================  ==========  =============== =============
+
+Output
+--------
+

xpore/scripts/dataprep.py

@@ -24,15 +24,14 @@ def get_args():
     required.add_argument('--summary', dest='summary', help='eventalign summary filepath, the output from nanopolish.',required=True)
     required.add_argument('--out_dir', dest='out_dir', help='output directory.',required=True)
 
+    # Optional
     required.add_argument('--ensembl', dest='ensembl', help='ensembl version for gene-transcript mapping.',type=int, default=91)
     required.add_argument('--species', dest='species', help='species for ensembl gene-transcript mapping.', default='homo_sapiens')
-
-    # Optional
     # parser.add_argument('--features', dest='features', help='Signal features to extract.',type=list,default=['norm_mean'])
     optional.add_argument('--genome', dest='genome', help='to run on Genomic coordinates. Without this argument, the program will run on transcriptomic coordinates',default=False,action='store_true') 
     optional.add_argument('--n_processes', dest='n_processes', help='number of processes to run.',type=int, default=1)
     optional.add_argument('--readcount_max', dest='readcount_max', help='maximum read counts per gene.',type=int, default=1000)
-    optional.add_argument('--resume', dest='resume', help='resume from the previous run.',default=False,action='store_true') #todo
+    optional.add_argument('--resume', dest='resume', help='with this argument, the program will resume from the previous run.',default=False,action='store_true') #todo
 
     parser._action_groups.append(optional)
     return parser.parse_args()

xpore/scripts/diffmod.py

@@ -24,10 +24,10 @@ def get_args():
 
     # Optional arguments
     optional.add_argument('--n_processes', dest='n_processes', help='number of processes to run.',type=int,default=1)
-    optional.add_argument('--save_models', dest='save_models', help='save the models.',default=False,action='store_true') # todo
-    optional.add_argument('--resume', dest='resume', help='resume from the previous run.',default=False,action='store_true') 
+    optional.add_argument('--save_models', dest='save_models', help='with this argument, the program will save the model parameters for each id.',default=False,action='store_true') # todo
+    optional.add_argument('--resume', dest='resume', help='with this argument, the program will resume from the previous run.',default=False,action='store_true') 
 
-    optional.add_argument('--ids', dest='ids', help='gene ids or transcript ids.',default=[],nargs='*')
+    optional.add_argument('--ids', dest='ids', help='gene / transcript ids to model.',default=[],nargs='*')
 
     parser._action_groups.append(optional)
     return parser.parse_args()