Skip to content

Commit a6f633d

Browse files
sbooeshaghisbooeshaghi
committed
Created using Colab
1 parent 15fa63a commit a6f633d

File tree

1 file changed

+284
-10
lines changed

1 file changed

+284
-10
lines changed

‎docs/UNIFORM.ipynb

+284-10
Original file line numberDiff line numberDiff line change
@@ -226,11 +226,11 @@
226226
"! seqspec file -m rna -f json -s file -k all spec.yaml"
227227
],
228228
"metadata": {
229-
"id": "8AUi7mH31BiL",
230-
"outputId": "010c4942-27e2-4623-b7c1-86504e2ef4df",
231229
"colab": {
232230
"base_uri": "https://localhost:8080/"
233-
}
231+
},
232+
"id": "8AUi7mH31BiL",
233+
"outputId": "010c4942-27e2-4623-b7c1-86504e2ef4df"
234234
},
235235
"execution_count": 12,
236236
"outputs": [
@@ -280,11 +280,11 @@
280280
"! seqspec file -m protein -f json -s file -k all spec.yaml | jq '.[].url' | xargs wget --continue --quiet --show-progress"
281281
],
282282
"metadata": {
283-
"id": "c1ZjLfnb1EL2",
284-
"outputId": "d87fb519-e67d-448e-df2b-2ca5b74e7452",
285283
"colab": {
286284
"base_uri": "https://localhost:8080/"
287-
}
285+
},
286+
"id": "c1ZjLfnb1EL2",
287+
"outputId": "d87fb519-e67d-448e-df2b-2ca5b74e7452"
288288
},
289289
"execution_count": 13,
290290
"outputs": [
@@ -349,11 +349,11 @@
349349
"! seqspec file -m rna -s read -f paired -k filename spec.yaml | tr \"\\t\\n\" \" \""
350350
],
351351
"metadata": {
352-
"id": "UmwOAvSu2hik",
353-
"outputId": "a9851d77-485e-419d-e1a7-8ebdc48cda07",
354352
"colab": {
355353
"base_uri": "https://localhost:8080/"
356-
}
354+
},
355+
"id": "UmwOAvSu2hik",
356+
"outputId": "a9851d77-485e-419d-e1a7-8ebdc48cda07"
357357
},
358358
"execution_count": 31,
359359
"outputs": [
@@ -385,14 +385,288 @@
385385
"\n",
386386
"# standard quantification\n",
387387
"! kb count \\\n",
388-
"--h5ad -t 16 -m 32G \\\n",
388+
"--h5ad \\\n",
389+
"-t 16 \\\n",
390+
"-m 32G \\\n",
389391
"-i index.idx \\\n",
390392
"-g t2g.txt \\\n",
391393
"-o kb_out \\\n",
392394
"-x $(seqspec index -m rna -t kb -s file spec.yaml) \\\n",
393395
"-w $(seqspec file -m rna -s region -k filename spec.yaml) \\\n",
394396
"$(seqspec file -m rna -s read -f paired -k filename spec.yaml | tr \"\\t\\n\" \" \")"
395397
]
398+
},
399+
{
400+
"cell_type": "code",
401+
"source": [
402+
"# spliced, unspliced, ambiguous reference\n",
403+
"! kb ref \\\n",
404+
"--workflow nac \\\n",
405+
"-i index.idx \\\n",
406+
"-g t2g.txt \\\n",
407+
"-f1 spl.fa \\\n",
408+
"-f2 unspl.fa \\\n",
409+
"-c1 spl.t2c.txt \\\n",
410+
"-c2 unspl.t2c.txt \\\n",
411+
"$(gget ref --ftp -w dna,gtf homo_sapiens)\n",
412+
"\n",
413+
"# spliced, unspliced, ambiguous quantification\n",
414+
"! kb count \\\n",
415+
"--h5ad \\\n",
416+
"--workflow=nac \\\n",
417+
"-t 32 \\\n",
418+
"-m 64G \\\n",
419+
"-i index.idx \\\n",
420+
"-g t2g.txt \\\n",
421+
"-c1 spl.t2c.txt \\\n",
422+
"-c2 unspl.t2c.txt \\\n",
423+
"-o kb_out_nac \\\n",
424+
"-x $(seqspec index -m rna -t kb -s file spec.yaml) \\\n",
425+
"-w $(seqspec file -m rna -s region -k filename spec.yaml) \\\n",
426+
"$(seqspec file -m rna -s read -f paired -k filename spec.yaml | tr \"\\t\\n\" \" \")"
427+
],
428+
"metadata": {
429+
"id": "TpfdS7oS4bFy"
430+
},
431+
"execution_count": null,
432+
"outputs": []
433+
},
434+
{
435+
"cell_type": "markdown",
436+
"source": [
437+
"### `STARsolo`"
438+
],
439+
"metadata": {
440+
"id": "ZGYN-d6245Jq"
441+
}
442+
},
443+
{
444+
"cell_type": "code",
445+
"source": [
446+
"# download reference\n",
447+
"## todo\n",
448+
"\n",
449+
"# run quantification\n",
450+
"! star \\\n",
451+
"--soloFeatures Gene \\\n",
452+
"--genomeDir index \\\n",
453+
"--soloType Droplet \\\n",
454+
"--soloCBwhitelist \\\n",
455+
"$(seqspec file -m rna -s region -k filename spec.yaml) \\\n",
456+
"$(seqspec index -m rna -t starsolo -s file spec.yaml) \\\n",
457+
"--readFilesIn $(seqspec file -m rna -s read -f paired -k filename spec.yaml | tr \"\\t\\n\" \" \")"
458+
],
459+
"metadata": {
460+
"id": "QWN3QgbA4-vo"
461+
},
462+
"execution_count": null,
463+
"outputs": []
464+
},
465+
{
466+
"cell_type": "code",
467+
"source": [
468+
"! seqspec file -m rna -s read -f paired -k filename spec.yaml | awk '{print \"-1 \"$1\" -2 \"$2}'"
469+
],
470+
"metadata": {
471+
"id": "4BIrMTgH58Tk",
472+
"outputId": "5454b71b-03fa-4da2-b2a3-d111a576ec1e",
473+
"colab": {
474+
"base_uri": "https://localhost:8080/"
475+
}
476+
},
477+
"execution_count": 33,
478+
"outputs": [
479+
{
480+
"output_type": "stream",
481+
"name": "stdout",
482+
"text": [
483+
"-1 rna_R1_SRR18677638.fastq.gz -2 rna_R2_SRR18677638.fastq.gz\n"
484+
]
485+
}
486+
]
487+
},
488+
{
489+
"cell_type": "markdown",
490+
"source": [
491+
"### `simpleaf`"
492+
],
493+
"metadata": {
494+
"id": "K6D0Gyn45ZpL"
495+
}
496+
},
497+
{
498+
"cell_type": "code",
499+
"source": [
500+
"! mkdir -p simpleaf_ref\n",
501+
"\n",
502+
"# Download reference genome and gene annotations\n",
503+
"! wget -qO- https://cf.10xgenomics.com/supp/cell-exp/refdata-gex-GRCh38-2020-A.tar.gz | tar xzf - --strip-components=1 -C ./simpleaf_ref\n",
504+
"\n",
505+
"# simpleaf index\n",
506+
"! simpleaf index \\\n",
507+
"--output ./out \\\n",
508+
"--fasta ./simpleaf_ref/fasta/genome.fa \\\n",
509+
"--gtf ./simpleaf_ref/genes/genes.gtf \\\n",
510+
"--rlen 91 \\\n",
511+
"--threads 16 \\\n",
512+
"--use-piscem # remove this if missing piscem\n",
513+
"\n",
514+
"! simpleaf quant \\\n",
515+
"-r cr-like \\\n",
516+
"-i simpleaf_ref/ \\\n",
517+
"-m t2g.txt \\\n",
518+
"-c $(seqspec index -m rna -t simpleaf -s file spec.yaml) \\\n",
519+
"-o out/ -x $w \\\n",
520+
"$(seqspec file -m rna -s read -f paired -k filename spec.yaml | awk '{print \"-1 \"$1\" -2 \"$2}')"
521+
],
522+
"metadata": {
523+
"id": "n-EtzzQU5cTX"
524+
},
525+
"execution_count": null,
526+
"outputs": []
527+
},
528+
{
529+
"cell_type": "markdown",
530+
"source": [
531+
"## Single-cell/nuclei TAG quantification"
532+
],
533+
"metadata": {
534+
"id": "OGc3z4a96dxL"
535+
}
536+
},
537+
{
538+
"cell_type": "markdown",
539+
"source": [
540+
"### `kb-python (kallisto bustools)`"
541+
],
542+
"metadata": {
543+
"id": "Ts3Nst9W6eni"
544+
}
545+
},
546+
{
547+
"cell_type": "code",
548+
"source": [
549+
"# build alignment reference\n",
550+
"kb ref \\\n",
551+
"--workflow kite \\\n",
552+
"-i index.idx \\\n",
553+
"-g t2g.txt \\\n",
554+
"-f1 transcriptome.fa \\\n",
555+
"tag_feature_barcodes.txt\n",
556+
"\n",
557+
"w=$(seqspec onlist -m tag -o onlist.txt -s region-type -i barcode spec.yaml)\n",
558+
"x=$(seqspec index -m tag -t kb -s file spec.yaml)\n",
559+
"f=$(seqspec file -m tag -s read -f paired -k url spec.yaml | tr \"\\t\\n\" \" \")\n",
560+
"\n",
561+
"# perform alignment, error correction, and counting\n",
562+
"kb count \\\n",
563+
"--workflow kite \\\n",
564+
"-i index.idx \\\n",
565+
"-g t2g.txt \\\n",
566+
"-x $x \\\n",
567+
"-w $w \\\n",
568+
"-o out --h5ad -t 2 \\\n",
569+
"$f"
570+
],
571+
"metadata": {
572+
"id": "xGhxxFDI6ePO"
573+
},
574+
"execution_count": null,
575+
"outputs": []
576+
},
577+
{
578+
"cell_type": "markdown",
579+
"source": [
580+
"## Single-cell/nuclei PROTEIN quantification"
581+
],
582+
"metadata": {
583+
"id": "S9gJjEVE6ltZ"
584+
}
585+
},
586+
{
587+
"cell_type": "markdown",
588+
"source": [
589+
"### `kb-python` (kallisto bustools)"
590+
],
591+
"metadata": {
592+
"id": "Tfp3h6y06ob7"
593+
}
594+
},
595+
{
596+
"cell_type": "code",
597+
"source": [
598+
"# build alignment reference\n",
599+
"kb ref \\\n",
600+
"--workflow kite \\\n",
601+
"-i index.idx \\\n",
602+
"-g t2g.txt \\\n",
603+
"-f1 transcriptome.fa \\\n",
604+
"protein_feature_barcodes.txt\n",
605+
"\n",
606+
"w=$(seqspec onlist -m protein -o onlist.txt -s region-type -i barcode spec.yaml)\n",
607+
"x=$(seqspec index -m protein -t kb -s file spec.yaml)\n",
608+
"f=$(seqspec file -m protein -s read -f paired -k url spec.yaml | tr \"\\t\\n\" \" \")\n",
609+
"\n",
610+
"# perform alignment, error correction, and counting\n",
611+
"kb count \\\n",
612+
"--workflow kite \\\n",
613+
"-i index.idx \\\n",
614+
"-g t2g.txt \\\n",
615+
"-x $x \\\n",
616+
"-w $w \\\n",
617+
"-o out --h5ad -t 2 \\\n",
618+
"$f"
619+
],
620+
"metadata": {
621+
"id": "YCkH0Qq76n9H"
622+
},
623+
"execution_count": null,
624+
"outputs": []
625+
},
626+
{
627+
"cell_type": "markdown",
628+
"source": [
629+
"## Single-cell/nuclei CRISPR quantification"
630+
],
631+
"metadata": {
632+
"id": "g3mrKO3j6v2E"
633+
}
634+
},
635+
{
636+
"cell_type": "markdown",
637+
"source": [
638+
"Note that single-cell CRISPR guide RNAs can be quantified in the same way as TAG and PROTEIN data. Simply supply the guide RNA barcode file as the “feature barcodes” file."
639+
],
640+
"metadata": {
641+
"id": "X2Da0_y86yPz"
642+
}
643+
},
644+
{
645+
"cell_type": "code",
646+
"source": [],
647+
"metadata": {
648+
"id": "kupLer4S6wZW"
649+
},
650+
"execution_count": null,
651+
"outputs": []
652+
},
653+
{
654+
"cell_type": "markdown",
655+
"source": [
656+
"## Single-cell/nuclei ATAC quantification"
657+
],
658+
"metadata": {
659+
"id": "olhjtMy660Iy"
660+
}
661+
},
662+
{
663+
"cell_type": "code",
664+
"source": [],
665+
"metadata": {
666+
"id": "ThaYUsgv60oO"
667+
},
668+
"execution_count": null,
669+
"outputs": []
396670
}
397671
],
398672
"metadata": {

0 commit comments

Comments
 (0)