Skip to content

Commit

Permalink
enforce exon sorting before annotating introns (#163)
Browse files Browse the repository at this point in the history
  • Loading branch information
akahles committed Jul 12, 2022
1 parent 26b9f3b commit a1991c8
Show file tree
Hide file tree
Showing 107 changed files with 59 additions and 50 deletions.
9 changes: 9 additions & 0 deletions spladder/classes/event.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
import numpy as np

from ..utils import sort_rows

class Event:

def __init__(self, event_type, chr=None, strand=None):
Expand Down Expand Up @@ -68,6 +70,8 @@ def get_intron_lens(self):
return _introns[:, 1] - _introns[:, 0]

def set_annotation_flag(self, anno_introns):

self.sort_exons()

### check annotation status of isoform 1
self.annotated = 3
Expand All @@ -83,3 +87,8 @@ def set_annotation_flag(self, anno_introns):
if not (self.exons2[i, 1], self.exons2[i + 1, 0]) in anno_introns:
self.annotated -= 2
break

def sort_exons(self):

self.exons1 = sort_rows(self.exons1)
self.exons2 = sort_rows(self.exons2)
Original file line number Diff line number Diff line change
Expand Up @@ -3,11 +3,11 @@
1 alt_3prime mRNA 5201 5500 . + . ID=alt_3prime.1_iso1;Parent=alt_3prime.1;GeneName="gene8";HasNovelJunction="Y"
1 alt_3prime exon 5201 5300 . + . Parent=alt_3prime.1_iso1
1 alt_3prime exon 5401 5500 . + . Parent=alt_3prime.1_iso1
1 alt_3prime mRNA 5201 5500 . + . ID=alt_3prime.1_iso2;Parent=alt_3prime.1;GeneName="gene8";HasNovelJunction="Y"
1 alt_3prime mRNA 5201 5500 . + . ID=alt_3prime.1_iso2;Parent=alt_3prime.1;GeneName="gene8";HasNovelJunction="N"
1 alt_3prime exon 5201 5300 . + . Parent=alt_3prime.1_iso2
1 alt_3prime exon 5351 5500 . + . Parent=alt_3prime.1_iso2
1 alt_3prime gene 6051 6750 . + . ID=alt_3prime.2;GeneName="gene10";HasNovelJunction="Y"
1 alt_3prime mRNA 6051 6750 . + . ID=alt_3prime.2_iso1;Parent=alt_3prime.2;GeneName="gene10";HasNovelJunction="Y"
1 alt_3prime mRNA 6051 6750 . + . ID=alt_3prime.2_iso1;Parent=alt_3prime.2;GeneName="gene10";HasNovelJunction="N"
1 alt_3prime exon 6051 6200 . + . Parent=alt_3prime.2_iso1
1 alt_3prime exon 6551 6750 . + . Parent=alt_3prime.2_iso1
1 alt_3prime mRNA 6051 6750 . + . ID=alt_3prime.2_iso2;Parent=alt_3prime.2;GeneName="gene10";HasNovelJunction="Y"
Expand All @@ -17,6 +17,6 @@
1 alt_3prime mRNA 5551 5850 . - . ID=alt_3prime.5_iso1;Parent=alt_3prime.5;GeneName="gene9";HasNovelJunction="Y"
1 alt_3prime exon 5551 5650 . - . Parent=alt_3prime.5_iso1
1 alt_3prime exon 5751 5850 . - . Parent=alt_3prime.5_iso1
1 alt_3prime mRNA 5551 5850 . - . ID=alt_3prime.5_iso2;Parent=alt_3prime.5;GeneName="gene9";HasNovelJunction="Y"
1 alt_3prime mRNA 5551 5850 . - . ID=alt_3prime.5_iso2;Parent=alt_3prime.5;GeneName="gene9";HasNovelJunction="N"
1 alt_3prime exon 5551 5700 . - . Parent=alt_3prime.5_iso2
1 alt_3prime exon 5751 5850 . - . Parent=alt_3prime.5_iso2
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Original file line number Diff line number Diff line change
Expand Up @@ -3,11 +3,11 @@
1 alt_3prime mRNA 5201 5500 . + . ID=alt_3prime.1_iso1;Parent=alt_3prime.1;GeneName="gene8";HasNovelJunction="Y"
1 alt_3prime exon 5201 5300 . + . Parent=alt_3prime.1_iso1
1 alt_3prime exon 5401 5500 . + . Parent=alt_3prime.1_iso1
1 alt_3prime mRNA 5201 5500 . + . ID=alt_3prime.1_iso2;Parent=alt_3prime.1;GeneName="gene8";HasNovelJunction="Y"
1 alt_3prime mRNA 5201 5500 . + . ID=alt_3prime.1_iso2;Parent=alt_3prime.1;GeneName="gene8";HasNovelJunction="N"
1 alt_3prime exon 5201 5300 . + . Parent=alt_3prime.1_iso2
1 alt_3prime exon 5351 5500 . + . Parent=alt_3prime.1_iso2
1 alt_3prime gene 6051 6750 . + . ID=alt_3prime.2;GeneName="gene10";HasNovelJunction="Y"
1 alt_3prime mRNA 6051 6750 . + . ID=alt_3prime.2_iso1;Parent=alt_3prime.2;GeneName="gene10";HasNovelJunction="Y"
1 alt_3prime mRNA 6051 6750 . + . ID=alt_3prime.2_iso1;Parent=alt_3prime.2;GeneName="gene10";HasNovelJunction="N"
1 alt_3prime exon 6051 6200 . + . Parent=alt_3prime.2_iso1
1 alt_3prime exon 6551 6750 . + . Parent=alt_3prime.2_iso1
1 alt_3prime mRNA 6051 6750 . + . ID=alt_3prime.2_iso2;Parent=alt_3prime.2;GeneName="gene10";HasNovelJunction="Y"
Expand All @@ -17,7 +17,7 @@
1 alt_3prime mRNA 6301 6750 . + . ID=alt_3prime.3_iso1;Parent=alt_3prime.3;GeneName="gene10";HasNovelJunction="Y"
1 alt_3prime exon 6301 6450 . + . Parent=alt_3prime.3_iso1
1 alt_3prime exon 6601 6750 . + . Parent=alt_3prime.3_iso1
1 alt_3prime mRNA 6301 6750 . + . ID=alt_3prime.3_iso2;Parent=alt_3prime.3;GeneName="gene10";HasNovelJunction="Y"
1 alt_3prime mRNA 6301 6750 . + . ID=alt_3prime.3_iso2;Parent=alt_3prime.3;GeneName="gene10";HasNovelJunction="N"
1 alt_3prime exon 6301 6450 . + . Parent=alt_3prime.3_iso2
1 alt_3prime exon 6551 6750 . + . Parent=alt_3prime.3_iso2
1 alt_3prime gene 6301 6750 . + . ID=alt_3prime.4;GeneName="gene10";HasNovelJunction="Y"
Expand All @@ -31,6 +31,6 @@
1 alt_3prime mRNA 5551 5850 . - . ID=alt_3prime.5_iso1;Parent=alt_3prime.5;GeneName="gene9";HasNovelJunction="Y"
1 alt_3prime exon 5551 5650 . - . Parent=alt_3prime.5_iso1
1 alt_3prime exon 5751 5850 . - . Parent=alt_3prime.5_iso1
1 alt_3prime mRNA 5551 5850 . - . ID=alt_3prime.5_iso2;Parent=alt_3prime.5;GeneName="gene9";HasNovelJunction="Y"
1 alt_3prime mRNA 5551 5850 . - . ID=alt_3prime.5_iso2;Parent=alt_3prime.5;GeneName="gene9";HasNovelJunction="N"
1 alt_3prime exon 5551 5700 . - . Parent=alt_3prime.5_iso2
1 alt_3prime exon 5751 5850 . - . Parent=alt_3prime.5_iso2
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
event_id chrm exon_pos alt_usage gene_id gene_name p_val p_val_adj dPSI mean_event_count_A mean_event_count_B log2FC_event_count mean_gene_exp_A mean_gene_exp_B log2FC_gene_exp
exon_skip.1 1 50-200:300-400:600-750 0:1:0 gene1 gene1 4.811778753222029e-10 2.8870672519332174e-09 0.616702306794285 35.08586895323417 9.376311915134902 1.9037976245357355 334.1722765209043 292.7045199476639 0.19114702598382038
exon_skip.9 1 9050-9150:9200-9301:9350-9450 0:1:0 gene15 gene15 0.40524286367664686 0.8995275736632284 -0.09291633522045145 69.93112545739696 53.413988503256235 0.3887171073454452 495.4718317969663 443.33183211071554 0.16041608609064717
exon_skip.8 1 8550-8650:8700-8801:8850-8950 0:1:0 gene14 gene14 0.6202054655784603 0.8995275736632284 0.003091298657809438 31.080863978941757 38.225154632724674 -0.2984957297324611 310.95618225753054 358.7314939698008 -0.2061931084887263
exon_skip.6 1 7550-7650:7700-7801:7850-7950 0:1:0 gene12 gene12 0.7776604746323357 0.8995275736632284 0.013616147697528502 27.189141476703583 28.747323146349835 -0.08039702582289543 221.73533171471072 207.16763607554458 0.09804002875719764
exon_skip.10 1 9550-9650:9700-9801:9850-9950 0:1:0 gene16 gene16 0.8741588278150877 0.8995275736632284 -0.01761397105920376 21.14907293278275 21.33922943817654 -0.012913656875475965 213.94508829780563 224.4741532357582 -0.069308779134718
exon_skip.7 1 8050-8150:8200-8301:8350-8450 0:1:0 gene13 gene13 0.8995275736632284 0.8995275736632284 -0.01612059250508885 35.55269583213776 37.925583849640844 -0.0932124320420975 313.65982094004676 309.29820779519844 0.020202261426950585
exon_skip.1 1 50-200:300-400:600-750 0:1:0 gene1 gene1 4.811778753222029e-10 2.8870672519332174e-09 0.616702306794285 35.08586895323417 9.376311915134902 1.9037976245357355 334.17227652090423 292.7045199476639 0.1911470259838186
exon_skip.9 1 9050-9150:9200-9301:9350-9450 0:1:0 gene15 gene15 0.405242863643404 0.8995275736770822 -0.09291633522045145 69.93112545739696 53.413988503256235 0.3887171073454452 495.4718317969663 443.33183211071554 0.16041608609064717
exon_skip.8 1 8550-8650:8700-8801:8850-8950 0:1:0 gene14 gene14 0.620205465556835 0.8995275736770822 0.003091298657809438 31.080863978941757 38.225154632724674 -0.2984957297324611 310.9561822575305 358.73149396980085 -0.2061931084887263
exon_skip.6 1 7550-7650:7700-7801:7850-7950 0:1:0 gene12 gene12 0.7776604746242519 0.8995275736770822 0.013616147697528502 27.189141476703583 28.747323146349835 -0.08039702582289543 221.73533171471072 207.16763607554458 0.09804002875719764
exon_skip.10 1 9550-9650:9700-9801:9850-9950 0:1:0 gene16 gene16 0.8741588278200897 0.8995275736770822 -0.01761397105920376 21.14907293278275 21.33922943817654 -0.012913656875475965 213.94508829780557 224.4741532357582 -0.069308779134718
exon_skip.7 1 8050-8150:8200-8301:8350-8450 0:1:0 gene13 gene13 0.8995275736770822 0.8995275736770822 -0.01612059250508885 35.55269583213776 37.925583849640844 -0.0932124320420975 313.65982094004676 309.29820779519844 0.020202261426950585
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
event_id chrm exon_pos alt_usage gene_id gene_name p_val p_val_adj dPSI mean_event_count_A mean_event_count_B log2FC_event_count mean_gene_exp_A mean_gene_exp_B log2FC_gene_exp
exon_skip.1 1 50-200:300-400:600-750 0:1:0 gene1 gene1 4.811778753222029e-10 2.8870672519332174e-09 0.616702306794285 35.08586895323417 9.376311915134902 1.9037976245357355 334.1722765209043 292.7045199476639 0.19114702598382038
exon_skip.9 1 9050-9150:9200-9301:9350-9450 0:1:0 gene15 gene15 0.40524286367664686 0.8995275736632284 -0.09291633522045145 69.93112545739696 53.413988503256235 0.3887171073454452 495.4718317969663 443.33183211071554 0.16041608609064717
exon_skip.8 1 8550-8650:8700-8801:8850-8950 0:1:0 gene14 gene14 0.6202054655784603 0.8995275736632284 0.003091298657809438 31.080863978941757 38.225154632724674 -0.2984957297324611 310.95618225753054 358.7314939698008 -0.2061931084887263
exon_skip.6 1 7550-7650:7700-7801:7850-7950 0:1:0 gene12 gene12 0.7776604746323357 0.8995275736632284 0.013616147697528502 27.189141476703583 28.747323146349835 -0.08039702582289543 221.73533171471072 207.16763607554458 0.09804002875719764
exon_skip.10 1 9550-9650:9700-9801:9850-9950 0:1:0 gene16 gene16 0.8741588278150877 0.8995275736632284 -0.01761397105920376 21.14907293278275 21.33922943817654 -0.012913656875475965 213.94508829780563 224.4741532357582 -0.069308779134718
exon_skip.7 1 8050-8150:8200-8301:8350-8450 0:1:0 gene13 gene13 0.8995275736632284 0.8995275736632284 -0.01612059250508885 35.55269583213776 37.925583849640844 -0.0932124320420975 313.65982094004676 309.29820779519844 0.020202261426950585
exon_skip.1 1 50-200:300-400:600-750 0:1:0 gene1 gene1 4.811778753222029e-10 2.8870672519332174e-09 0.616702306794285 35.08586895323417 9.376311915134902 1.9037976245357355 334.17227652090423 292.7045199476639 0.1911470259838186
exon_skip.9 1 9050-9150:9200-9301:9350-9450 0:1:0 gene15 gene15 0.405242863643404 0.8995275736770822 -0.09291633522045145 69.93112545739696 53.413988503256235 0.3887171073454452 495.4718317969663 443.33183211071554 0.16041608609064717
exon_skip.8 1 8550-8650:8700-8801:8850-8950 0:1:0 gene14 gene14 0.620205465556835 0.8995275736770822 0.003091298657809438 31.080863978941757 38.225154632724674 -0.2984957297324611 310.9561822575305 358.73149396980085 -0.2061931084887263
exon_skip.6 1 7550-7650:7700-7801:7850-7950 0:1:0 gene12 gene12 0.7776604746242519 0.8995275736770822 0.013616147697528502 27.189141476703583 28.747323146349835 -0.08039702582289543 221.73533171471072 207.16763607554458 0.09804002875719764
exon_skip.10 1 9550-9650:9700-9801:9850-9950 0:1:0 gene16 gene16 0.8741588278200897 0.8995275736770822 -0.01761397105920376 21.14907293278275 21.33922943817654 -0.012913656875475965 213.94508829780557 224.4741532357582 -0.069308779134718
exon_skip.7 1 8050-8150:8200-8301:8350-8450 0:1:0 gene13 gene13 0.8995275736770822 0.8995275736770822 -0.01612059250508885 35.55269583213776 37.925583849640844 -0.0932124320420975 313.65982094004676 309.29820779519844 0.020202261426950585
Loading

0 comments on commit a1991c8

Please sign in to comment.