Skip to content

Instantly share code, notes, and snippets.

@k3yavi

k3yavi/selective_alignment.ipynb

Last active March 16, 2022 13:35
Show Gist options
  • Save k3yavi/a486647c35158a8296cec543ed9b526f to your computer and use it in GitHub Desktop.
Save k3yavi/a486647c35158a8296cec543ed9b526f to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
selective_alignment.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"--2019-10-31 07:37:55-- ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_mouse/release_M23/gencode.vM23.transcripts.fa.gz\n",
" => ‘gencode.vM23.transcripts.fa.gz.1’\n",
"Resolving ftp.ebi.ac.uk (ftp.ebi.ac.uk)... 193.62.197.74\n",
"Connecting to ftp.ebi.ac.uk (ftp.ebi.ac.uk)|193.62.197.74|:21... connected.\n",
"Logging in as anonymous ... Logged in!\n",
"==> SYST ... done. ==> PWD ... done.\n",
"==> TYPE I ... done. ==> CWD (1) /pub/databases/gencode/Gencode_mouse/release_M23 ... done.\n",
"==> SIZE gencode.vM23.transcripts.fa.gz ... 54441060\n",
"==> PASV ... done. ==> RETR gencode.vM23.transcripts.fa.gz ... done.\n",
"Length: 54441060 (52M) (unauthoritative)\n",
"\n",
" 0K .......... .......... .......... .......... .......... 0% 332K 2m40s\n",
" 50K .......... .......... .......... .......... .......... 0% 648K 2m1s\n",
" 53050K .......... .......... .......... .......... .......... 99% 35.8M 0s\n",
" 53100K .......... .......... .......... .......... .......... 99% 66.4M 0s\n",
" 53150K .......... ..... 100% 15.8M=3.3s\n",
"\n",
"2019-10-31 07:37:59 (15.9 MB/s) - ‘gencode.vM23.transcripts.fa.gz.1’ saved [54441060]\n",
"\n",
"--2019-10-31 07:37:59-- ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_mouse/release_M23/GRCm38.primary_assembly.genome.fa.gz\n",
" => ‘GRCm38.primary_assembly.genome.fa.gz.1’\n",
"Resolving ftp.ebi.ac.uk (ftp.ebi.ac.uk)... 193.62.197.74\n",
"Connecting to ftp.ebi.ac.uk (ftp.ebi.ac.uk)|193.62.197.74|:21... connected.\n",
"Logging in as anonymous ... Logged in!\n",
"==> SYST ... done. ==> PWD ... done.\n",
"==> TYPE I ... done. ==> CWD (1) /pub/databases/gencode/Gencode_mouse/release_M23 ... done.\n",
"==> SIZE GRCm38.primary_assembly.genome.fa.gz ... 773507376\n",
"==> PASV ... done. ==> RETR GRCm38.primary_assembly.genome.fa.gz ... done.\n",
"Length: 773507376 (738M) (unauthoritative)\n",
"\n",
" 0K .......... .......... .......... .......... .......... 0% 281K 44m45s\n",
" 50K .......... .......... .......... .......... .......... 0% 617K 32m34s\n",
"755300K .......... .......... .......... .......... .......... 99% 17.4M 0s\n",
"755350K .......... .......... ........ 100% 17.2M=59s\n",
"\n",
"2019-10-31 07:38:59 (12.5 MB/s) - ‘GRCm38.primary_assembly.genome.fa.gz.1’ saved [773507376]\n",
"\n"
]
}
],
"source": [
"%%bash\n",
"wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_mouse/release_M23/gencode.vM23.transcripts.fa.gz\n",
"wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_mouse/release_M23/GRCm38.primary_assembly.genome.fa.gz"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"%%bash\n",
"grep \"^>\" <(zcat GRCm38.primary_assembly.genome.fa.gz) | cut -d \" \" -f 1 > decoys.txt\n",
"sed -i -e 's/>//g' decoys.txt"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"%%bash\n",
"cat gencode.vM23.transcripts.fa.gz GRCm38.primary_assembly.genome.fa.gz > gentrome.fa.gz"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Threads = 12\n",
"Vertex length = 31\n",
"Hash functions = 5\n",
"Filter size = 68719476736\n",
"Capacity = 2\n",
"Files: \n",
"salmon_index/ref_k31_fixed.fa\n",
"--------------------------------------------------------------------------------\n",
"Round 0, 0:68719476736\n",
"Pass\tFilling\tFiltering\n",
"1\t126\t224\t\n",
"2\t261\t4\n",
"True junctions count = 14963867\n",
"False junctions count = 1213676\n",
"Hash table size = 16177543\n",
"Candidate marks count = 338137689\n",
"--------------------------------------------------------------------------------\n",
"Reallocating bifurcations time: 8\n",
"True marks count: 336727201\n",
"Edges construction time: 300\n",
"--------------------------------------------------------------------------------\n",
"Distinct junctions = 14963867\n",
"\n",
"for info, total work write each : 2.331 total work inram from level 3 : 4.322 total work raw : 25.000 \n",
"Bitarray 11923680384 bits (100.00 %) (array + ranks )\n",
"final hash 225456 bits (0.00 %) (nb in final hash 671)\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[2019-10-31 07:39:52.034] [jLog] [info] building index\n",
"out : salmon_index\n",
"[2019-10-31 07:39:53.725] [puff::index::jointLog] [info] Running fixFasta\n",
"\n",
"[Step 1 of 4] : counting k-mers\n",
"[2019-10-31 07:39:59.287] [puff::index::jointLog] [warning] It appears that this may be a GENCODE transcriptome (from analyzing the separators in the FASTA header). However, you have not set '|' as a header separator. If this is a GENCODE transcriptome, consider passing --gencode to the pufferfish index command.\n",
"\n",
"\n",
"[2019-10-31 07:39:59.303] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000191703.1|ENSMUSG00000103282.1|OTTMUSG00000050290.1|OTTMUST00000127724.1|Gm37275-201|Gm37275|30|processed_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:00.143] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000229312.1|ENSMUSG00000056486.18|OTTMUSG00000013428.7|OTTMUST00000171565.1|Chn1-211|Chn1|20|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:01.007] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179793.1|ENSMUSG00000095386.1|-|-|Gm17662-201|Gm17662|24|protein_coding|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:01.384] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000200713.1|ENSMUSG00000107308.1|OTTMUSG00000056069.1|OTTMUST00000138636.1|Gm43234-201|Gm43234|18|processed_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:01.688] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178537.1|ENSMUSG00000095668.1|OTTMUSG00000051351.2|OTTMUST00000129883.2|Trbd1-201|Trbd1|12|TR_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:01.688] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178862.1|ENSMUSG00000094569.1|OTTMUSG00000051360.2|OTTMUST00000129892.2|Trbd2-201|Trbd2|14|TR_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:02.770] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000165700.1|ENSMUSG00000091041.1|-|-|Gm17720-201|Gm17720|27|protein_coding|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179520.1|ENSMUSG00000094028.1|OTTMUSG00000051523.3|OTTMUST00000130131.3|Ighd4-1-201|Ighd4-1|11|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179883.1|ENSMUSG00000094552.1|OTTMUSG00000051524.2|OTTMUST00000130132.2|Ighd3-2-201|Ighd3-2|16|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000195858.1|ENSMUSG00000096420.2|OTTMUSG00000051529.2|OTTMUST00000130137.2|Ighd5-6-202|Ighd5-6|10|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179932.1|ENSMUSG00000096420.2|OTTMUSG00000051529.2|-|Ighd5-6-201|Ighd5-6|12|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000180001.1|ENSMUSG00000095656.1|OTTMUSG00000051530.2|OTTMUST00000130138.2|Ighd2-8-201|Ighd2-8|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178815.1|ENSMUSG00000094957.1|OTTMUSG00000051531.2|OTTMUST00000130141.2|Ighd5-5-201|Ighd5-5|10|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.120] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000177965.1|ENSMUSG00000094057.1|OTTMUSG00000051538.2|OTTMUST00000130152.2|Ighd2-7-201|Ighd2-7|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178909.1|ENSMUSG00000094268.1|OTTMUSG00000051557.2|OTTMUST00000130174.2|Ighd5-8-201|Ighd5-8|29|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000177646.1|ENSMUSG00000096884.1|OTTMUSG00000051571.2|OTTMUST00000130189.2|Ighd5-4-201|Ighd5-4|10|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178230.1|ENSMUSG00000096250.1|OTTMUSG00000051569.2|OTTMUST00000130197.2|Ighd2-6-201|Ighd2-6|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178483.1|ENSMUSG00000095592.1|OTTMUSG00000051572.2|OTTMUST00000130199.2|Ighd5-7-201|Ighd5-7|29|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179262.1|ENSMUSG00000093876.1|OTTMUSG00000051581.2|OTTMUST00000130180.2|Ighd5-3-201|Ighd5-3|10|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178549.1|ENSMUSG00000095897.1|OTTMUSG00000051560.2|OTTMUST00000130181.2|Ighd2-5-201|Ighd2-5|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000193012.1|ENSMUSG00000103203.1|OTTMUSG00000051561.2|OTTMUST00000130184.2|Gm37327-201|Gm37327|29|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179166.1|ENSMUSG00000096396.1|OTTMUSG00000051562.2|OTTMUST00000130185.2|Ighd5-2-201|Ighd5-2|10|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179560.1|ENSMUSG00000095444.1|OTTMUSG00000051582.2|OTTMUST00000130217.2|Ighd2-4-201|Ighd2-4|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178902.1|ENSMUSG00000096301.1|OTTMUSG00000051583.1|OTTMUST00000130218.1|Ighd6-2-201|Ighd6-2|29|IG_D_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000192089.1|ENSMUSG00000102532.1|OTTMUSG00000051589.1|OTTMUST00000130224.1|Gm37227-201|Gm37227|10|IG_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000177839.1|ENSMUSG00000096568.1|OTTMUSG00000051584.2|OTTMUST00000130219.2|Ighd2-3-201|Ighd2-3|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000170385.1|ENSMUSG00000095399.1|OTTMUSG00000051585.1|OTTMUST00000130220.1|Ighd6-1-201|Ighd6-1|29|IG_D_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000103439.1|ENSMUSG00000076630.1|OTTMUSG00000051586.2|OTTMUST00000130221.2|Ighd1-1-201|Ighd1-1|23|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000180266.1|ENSMUSG00000093818.1|OTTMUSG00000051588.2|OTTMUST00000130223.2|Ighd3-1-201|Ighd3-1|17|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000178811.1|ENSMUSG00000095549.1|OTTMUSG00000051590.1|OTTMUST00000130225.1|Ighd5-1-201|Ighd5-1|10|IG_D_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.135] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000103441.1|ENSMUSG00000076632.1|OTTMUSG00000051591.2|OTTMUST00000130226.2|Gm16968-201|Gm16968|23|IG_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.488] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000231713.1|ENSMUSG00000032727.14|OTTMUSG00000019751.6|OTTMUST00000173336.1|Mier3-208|Mier3|16|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.488] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000231466.1|ENSMUSG00000032727.14|OTTMUSG00000019751.6|OTTMUST00000173337.1|Mier3-207|Mier3|18|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.555] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000226589.1|ENSMUSG00000021767.19|OTTMUSG00000043207.9|OTTMUST00000170357.1|Kat6b-213|Kat6b|18|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.587] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000228114.1|ENSMUSG00000006522.17|OTTMUSG00000035523.5|OTTMUST00000170497.1|Itih3-206|Itih3|14|protein_coding|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.612] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000226226.1|ENSMUSG00000021798.14|OTTMUSG00000069987.3|OTTMUST00000170519.1|Ldb3-206|Ldb3|17|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.685] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000196221.1|ENSMUSG00000096749.2|OTTMUSG00000054129.2|OTTMUST00000134478.2|Trdd1-202|Trdd1|9|TR_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.686] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000179664.1|ENSMUSG00000096749.2|OTTMUSG00000054129.2|-|Trdd1-201|Trdd1|11|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.686] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000177564.1|ENSMUSG00000096176.1|OTTMUSG00000054130.2|OTTMUST00000134479.2|Trdd2-201|Trdd2|16|TR_D_gene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.686] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000103739.3|ENSMUSG00000076927.3|OTTMUSG00000054279.1|OTTMUST00000134692.1|Traj1-201|Traj1|29|TR_J_pseudogene|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.803] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000226961.1|ENSMUSG00000033004.15|OTTMUSG00000034690.3|OTTMUST00000170059.1|Mycbp2-208|Mycbp2|15|protein_coding|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:04.963] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000227223.1|ENSMUSG00000060794.8|OTTMUSG00000069888.2|OTTMUST00000169180.1|Tssk5-202|Tssk5|18|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:05.068] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000226615.1|ENSMUSG00000044250.8|OTTMUSG00000069720.1|OTTMUST00000168599.1|Pced1b-203|Pced1b|10|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:05.316] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000226153.1|ENSMUSG00000033450.8|OTTMUSG00000034757.2|OTTMUST00000168259.1|Tagap-202|Tagap|14|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:05.380] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000227002.1|ENSMUSG00000035435.17|OTTMUSG00000031262.3|OTTMUST00000168155.1|Abca17-203|Abca17|9|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"[2019-10-31 07:40:05.426] [puff::index::jointLog] [warning] Entry with header [ENSMUST00000226172.1|ENSMUSG00000002249.21|OTTMUSG00000024245.6|OTTMUST00000167695.2|Tead3-208|Tead3|11|lncRNA|], had length less than equal to the k-mer length of 31 (perhaps after poly-A clipping)\n",
"\n",
"[2019-10-31 07:41:09.442] [puff::index::jointLog] [warning] Removed 1603 transcripts that were sequence duplicates of indexed transcripts.\n",
"[2019-10-31 07:41:09.442] [puff::index::jointLog] [warning] If you wish to retain duplicate transcripts, please use the `--keepDuplicates` flag\n",
"[2019-10-31 07:41:09.444] [puff::index::jointLog] [info] Replaced 78,088,277 non-ATCG nucleotides\n",
"[2019-10-31 07:41:09.444] [puff::index::jointLog] [info] Clipped poly-A tails from 753 transcripts\n",
"wrote 140775 cleaned references\n",
"seqHash 256 : 6f92253eb7397009ce667653d94538bc1f0bd85fad71e5c45a7395f6cfe07ffe\n",
"seqHash 512 : dcbc04f4ca9b00b551dd2fb47c5c5adf4773ce09e589af3c32611a59216cf0d9733b5534a486d295ab01e315d9cee4efa8109039a6a92c34dfc584f7104d996a\n",
"nameHash 256 : 04f5965de3bd77b32ab9edb145ba349e7b187a3a80af10ae49c4e7651d7669c0\n",
"nameHash 512 : 58d3dba414d4acc3fa3c81f8306c1c09ecb9ded91b9706ad6cef63d222740630a169f7093de2d6d34237e5fc7d31a74cf2bba7d2d2ac9b9bf883edc717f99210\n",
"[2019-10-31 07:41:14.700] [puff::index::jointLog] [info] Filter size not provided; estimating from number of distinct k-mers\n",
"[2019-10-31 07:41:46.386] [puff::index::jointLog] [info] ntHll estimated 2272527625 distinct k-mers, setting filter size to 2^36\n",
"approximateContigTotalLength: 1120132586\n",
"counters:\n",
"3124333 946 850 35\n",
"contig count: 25054792 element count: 3027293225 complex nodes: 3126164\n",
"size: 3027293225\n",
"# of ones in rank vector: 25054791\n",
"size: 3027293225\n",
"[2019-10-31 08:03:30.189] [puff::index::jointLog] [info] Setting the index/BinaryGfa directory salmon_index\n",
"size = 3027293225\n",
"-----------------------------------------\n",
"| Loading contigs | Time = 497.28 ms\n",
"-----------------------------------------\n",
"size = 3027293225\n",
"-----------------------------------------\n",
"| Loading contig boundaries | Time = 245.75 ms\n",
"-----------------------------------------\n",
"Number of ones: 25054791\n",
"Number of ones per inventory item: 512\n",
"Inventory entries filled: 48936\n",
"[2019-10-31 08:03:36.644] [puff::index::jointLog] [info] Done wrapping the rank vector with a rank9sel structure.\n",
"[2019-10-31 08:03:47.922] [puff::index::jointLog] [info] contig count for validation: 25054791\n",
"[2019-10-31 08:04:22.119] [puff::index::jointLog] [info] Total # of Contigs : 25,054,791\n",
"[2019-10-31 08:04:22.119] [puff::index::jointLog] [info] Total # of numerical Contigs : 25,054,791\n",
"[2019-10-31 08:06:21.460] [puff::index::jointLog] [info] \n",
"Total # of segments we have position for : 25,054,791\n",
"[2019-10-31 08:06:23.012] [puff::index::jointLog] [info] total contig vec entries 346,506,409\n",
"[2019-10-31 08:06:23.012] [puff::index::jointLog] [info] bits per offset entry 29\n",
"[2019-10-31 08:06:45.809] [puff::index::jointLog] [info] there were 1,974,686 equivalence classes\n",
"[2019-10-31 08:07:33.112] [puff::index::jointLog] [info] # segments = 25,054,791\n",
"[2019-10-31 08:07:33.112] [puff::index::jointLog] [info] total length = 3,027,293,225\n",
"[2019-10-31 08:07:33.555] [puff::index::jointLog] [info] Reading the reference files ...\n",
"[2019-10-31 08:08:16.031] [puff::index::jointLog] [info] positional integer width = 32\n",
"[2019-10-31 08:08:16.031] [puff::index::jointLog] [info] seqSize = 3,027,293,225\n",
"[2019-10-31 08:08:16.031] [puff::index::jointLog] [info] rankSize = 3,027,293,225\n",
"[2019-10-31 08:08:16.031] [puff::index::jointLog] [info] edgeVecSize = 0\n",
"[2019-10-31 08:08:16.031] [puff::index::jointLog] [info] num keys = 2,275,649,495\n",
"\r",
"[Building BooPHF] 1.09 % elapsed: 0 min 1 sec remaining: 1 min 32 sec\r",
"[Building BooPHF] 1.1 % elapsed: 0 min 1 sec remaining: 1 min 32 sec\r",
"[Building BooPHF] 99.8 % elapsed: 1 min 8 sec remaining: 0 min 0 sec\r",
"[Building BooPHF] 100 % elapsed: 1 min 8 sec remaining: 0 min 0 sec\n",
"[2019-10-31 08:09:24.054] [puff::index::jointLog] [info] mphf size = 1421.44 MB\n",
"[2019-10-31 08:09:24.054] [puff::index::jointLog] [info] chunk size = 252,274,436\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 0 = [0, 252,274,436)\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 1 = [252,274,436, 504,548,881)\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 2 = [504,548,881, 756,823,336)\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 3 = [756,823,336, 1,009,097,772)\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 4 = [1,009,097,772, 1,261,372,208)\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 5 = [1,261,372,208, 1,513,646,644)\n",
"[2019-10-31 08:09:24.076] [puff::index::jointLog] [info] chunk 6 = [1,513,646,644, 1,765,921,080)\n",
"[2019-10-31 08:09:24.085] [puff::index::jointLog] [info] chunk 7 = [1,765,921,080, 2,018,195,516)\n",
"[2019-10-31 08:09:24.085] [puff::index::jointLog] [info] chunk 8 = [2,018,195,516, 2,270,469,952)\n",
"[2019-10-31 08:09:24.085] [puff::index::jointLog] [info] chunk 9 = [2,270,469,952, 2,522,744,388)\n",
"[2019-10-31 08:09:24.085] [puff::index::jointLog] [info] chunk 10 = [2,522,744,388, 2,775,018,824)\n",
"[2019-10-31 08:09:24.085] [puff::index::jointLog] [info] chunk 11 = [2,775,018,824, 3,027,293,195)\n",
"[2019-10-31 08:10:53.218] [puff::index::jointLog] [info] finished populating pos vector\n",
"[2019-10-31 08:10:53.218] [puff::index::jointLog] [info] writing index components\n",
"[2019-10-31 08:12:16.922] [puff::index::jointLog] [info] finished writing dense pufferfish index\n",
"[2019-10-31 08:12:18.849] [jLog] [info] done building index\n"
]
}
],
"source": [
"%%bash\n",
"salmon index -t gentrome.fa.gz -d decoys.txt -p 12 -i salmon_index"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment