update info text + minor help changes (#10)

* update info text + minor help changes

* remove extra space

MANIFEST.in

@@ -1,2 +1,3 @@
+include kb_python/info.txt
 include kb_python/whitelists/*
 recursive-include kb_python/bins *

kb_python/config.py

@@ -45,19 +45,19 @@
 REFERENCES = [
     Reference(
         'human',
-        'https://github.com/pachterlab/kallisto-transcriptome-indices/releases/download/ensembl-96/homo_sapiens.tar.gz',
+        'https://caltech.box.com/shared/static/v1nm7lpnqz5syh8dyzdk2zs8bglncfib.gz',
         None, None
     ),
     Reference(
         'mouse',
-        'https://github.com/pachterlab/kallisto-transcriptome-indices/releases/download/ensembl-96/mus_musculus.tar.gz',
+        'https://caltech.box.com/shared/static/vcaz6cujop0xuapdmz0pplp3aoqc41si.gz',
         None, None
     )
 ]
 REFERENCES_MAPPING = {r.name: r for r in REFERENCES}
 # File names that are in the tar.gz file.
 INDEX_FILENAME = 'transcriptome.idx'
-T2G_FILENAME = 'transcript_to_genes.txt'
+T2G_FILENAME = 'transcripts_to_genes.txt'
 
 
 class UnsupportedOSException(Exception):

kb_python/constants.py

@@ -1,3 +1,5 @@
+INFO_FILENAME = 'info.txt'
+
 # Default filenames
 CDNA_FILENAME = 'cdna.fa'
 INTRON_FILENAME = 'introns.fa'

kb_python/info.txt

@@ -0,0 +1,36 @@
+kb is a python package for rapidly pre-processing single-cell RNA-seq data. It is a wrapper for the methods described in
+
+Melsted, Booeshaghi et al., Modular and efficient pre-processing of single-cell RNA-seq, bioRxiv, 2019
+
+The goal of the wrapper is to simplify downloading and running of the kallisto [1] and bustools [2] programs. It was inspired by Sten Linnarsson’s loompy fromfq command (http://linnarssonlab.org/loompy/kallisto/index.html)
+
+The kb program consists of two parts:
+
+The `kb ref` command builds or downloads a species-specific index for pseudoalignment of reads. This command must be run prior to `kb count`, and it runs the `kallisto index` [1].
+
+The `kb count` command runs the kallisto [1] and bustools [2] programs. It can be used for pre-processing of data from a variety of single-cell RNA-seq technologies, and for a number of different workflows (e.g. production of gene count matrices, RNA velocity analyses, etc.). The output can be saved in a variety of formats including mix and loom. Examples are provided below.
+
+
+Examples
+========
+(1) kb ref -i transcriptome.idx -g transcripts_to_genes.txt -f1 cdna.fa Mus_musculus.GRCm38.dna.primary_assembly.fa Mus_musculus.GRCm38.98.gtf
+(2) kb count -i transcriptome.idx -g transcripts_to_genes.txt -x 10xv2 -o output --loom Reads1.fastq.gz Reads2.fasta.gz
+Build a Kallisto index and transcripts-to-genes mapping using the mouse transcriptome, generated from the provided genomic FASTA and GTF. Then, generate count matrices with the built index and transcripts-to-genes mapping. Convert the final count matrix to a .loom file.
+
+(1) kb ref -i transcriptome.idx -g transcripts_to_genes.txt -f1 cdna.fa Mus_musculus.GRCm38.dna.primary_assembly.fa Mus_musculus.GRCm38.98.gtf
+(2) kb count -i transcriptome.idx -g transcripts_to_genes.txt -x 10xv2 -w 10xv2_whitelist -o output --h5ad Reads1.fastq.gz Reads2.fasta.gz
+Build a Kallisto index and transcripts-to-genes mapping using the mouse transcriptome, generated from the provided genomic FASTA and GTF. Then, generate count matrices with the built index, transcripts-to-genes mapping and provided whitelist. Convert the final count matrix to a .h5ad file.
+
+(1) kb ref -i transcriptome.idx -g transcripts_to_genes.txt -d mouse
+(2) kb count -i transcriptome.idx -g transcripts_to_genes.txt -x 10xv2 -o output Reads1.fastq.gz Reads2.fasta.gz
+Instead of building a Kallisto index locally, download a pre-built index. Then, generate count matrices with the built index and transcripts-to-genes mapping.
+
+(1) kb ref -i transcriptome.idx -g transcripts_to_genes.txt -f1 cdna.fa -f2 introns.fa -c1 cdna_transcripts_to_capture.txt -c2 intron_transcripts_to_capture --lamanno Mus_musculus.GRCm38.dna.primary_assembly.fa Mus_musculus.GRCm38.98.gtf
+(2) kb count -i transcriptome.idx -g transcripts_to_genes.txt -x 10xv2 -o output -c1 cdna_transcripts_to_capture.txt -c2 intron_transcripts_to_capture.txt --lamanno Reads1.fastq.gz Reads2.fasta.gz
+Prepare files (Kallisto index, transcripts-to-genes mapping, cDNA transcripts to capture, intron transcripts to capture) for RNA velocity based on Lamanno et al. 2018 logic. Then, calculate RNA velocity using the prepared files.
+
+
+References
+==========
+[1] Bray, N. L., Pimentel, H., Melsted, P., & Pachter, L. (2016). Near-optimal probabilistic RNA-seq quantification. Nature biotechnology, 34(5), 525.
+[2] Melsted, P., Booeshaghi, A. S., Gao, F., da Veiga Beltrame, E., Lu, L., Hjorleifsson, K. E., ... & Pachter, L. (2019). Modular and efficient pre-processing of single-cell RNA-seq. BioRxiv, 673285.

kb_python/main.py

@@ -3,9 +3,11 @@
 import os
 import shutil
 import sys
+import textwrap
 
 from . import __version__
-from .config import REFERENCES_MAPPING, TECHNOLOGIES, TEMP_DIR
+from .config import PACKAGE_PATH, REFERENCES_MAPPING, TECHNOLOGIES, TEMP_DIR
+from .constants import INFO_FILENAME
 from .count import count, count_lamanno
 from .ref import download_reference, ref, ref_lamanno
 from .utils import get_bustools_version, get_kallisto_version
@@ -18,7 +20,16 @@ def display_info():
     kallisto: {}
     bustools: {}
     '''.format(__version__, kallisto_version, bustools_version)
-    print(info)
+    with open(os.path.join(PACKAGE_PATH, INFO_FILENAME), 'r') as f:
+        print(
+            '{}\n{}'.format(
+                info, '\n'.join([
+                    line.strip()
+                    if line.startswith('(') else textwrap.fill(line, width=80)
+                    for line in f.readlines()
+                ])
+            )
+        )
     sys.exit(1)
 
 
@@ -135,6 +146,8 @@ def setup_ref_args(parser, parent):
         help='Build a kallisto index and transcript-to-gene mapping',
         parents=[parent],
     )
+    parser_ref._actions[0].help = parser_ref._actions[0].help.capitalize()
+
     required_ref = parser_ref.add_argument_group('required arguments')
     required_ref.add_argument(
         '-i',
@@ -194,7 +207,10 @@ def setup_ref_args(parser, parent):
     )
     parser_ref.add_argument(
         '--lamanno',
-        help='Prepare files for RNA velocity based on Lamanno',
+        help=(
+            'Prepare files for RNA velocity based on '
+            'La Manno et al. 2018 logic'
+        ),
         action='store_true'
     )
     parser_ref.add_argument(
@@ -225,6 +241,8 @@ def setup_count_args(parser, parent):
         help='Generate count matrices from a set of single-cell FASTQ files',
         parents=[parent],
     )
+    parser_count._actions[0].help = parser_count._actions[0].help.capitalize()
+
     required_count = parser_count.add_argument_group('required arguments')
     required_count.add_argument(
         '-i',
@@ -299,7 +317,7 @@ def setup_count_args(parser, parent):
 
     parser_count.add_argument(
         '--lamanno',
-        help='Calculate RNA velocity based on Lamanno',
+        help='Calculate RNA velocity based on La Manno et al. 2018 logic',
         action='store_true'
     )
     parser_count.add_argument(
@@ -327,6 +345,7 @@ def main():
     parser = argparse.ArgumentParser(
         description='kb_python {}'.format(__version__)
     )
+    parser._actions[0].help = parser._actions[0].help.capitalize()
     parser.add_argument(
         '--list',
         help='Display list of supported single-cell technologies',