diff --git a/scripts/Pre-processing.ipynb b/scripts/Pre-processing.ipynb
index 4556c74ce2115a19ab680dfe7e22a4b9c4bdd9dc..9ff43f2c57c96a7e5e1a2ea79bfe552982cb0390 100644
--- a/scripts/Pre-processing.ipynb
+++ b/scripts/Pre-processing.ipynb
@@ -30,13 +30,13 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "── Attaching core tidyverse packages ────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──\n",
+ "── Attaching core tidyverse packages ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──\n",
"✔ dplyr 1.1.4 ✔ readr 2.1.5\n",
"✔ forcats 1.0.0 ✔ stringr 1.5.1\n",
"✔ ggplot2 3.4.4 ✔ tibble 3.2.1\n",
"✔ lubridate 1.9.3 ✔ tidyr 1.3.0\n",
"✔ purrr 1.0.2 \n",
- "── Conflicts ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──\n",
+ "── Conflicts ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──\n",
"✖ dplyr::filter() masks stats::filter()\n",
"✖ dplyr::lag() masks stats::lag()\n",
"ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors\n",
@@ -400,26 +400,48 @@
"metadata": {},
"outputs": [
{
- "ename": "ERROR",
- "evalue": "Error in `mutate()`:\nℹ In argument: `pc_valid = is_valid/total_read`.\nCaused by error:\n! object 'is_valid' not found\n",
- "output_type": "error",
- "traceback": [
- "Error in `mutate()`:\nℹ In argument: `pc_valid = is_valid/total_read`.\nCaused by error:\n! object 'is_valid' not found\nTraceback:\n",
- "1. EMOTE_parse_read(fastq_file = \"../data/pre-processing_examples/Example_1.fastq.gz\", \n . features = rf, force = T)",
- "2. mutate(stat_tb, pc_valid = is_valid/total_read) %>% mutate(demux_filename = paste0(out_dir, \n . \"/\", fq_basename, \"_\", tolower(group), \".fastq.gz\"))",
- "3. mutate(., demux_filename = paste0(out_dir, \"/\", fq_basename, \n . \"_\", tolower(group), \".fastq.gz\"))",
- "4. mutate(stat_tb, pc_valid = is_valid/total_read)",
- "5. mutate.data.frame(stat_tb, pc_valid = is_valid/total_read)",
- "6. mutate_cols(.data, dplyr_quosures(...), by)",
- "7. withCallingHandlers(for (i in seq_along(dots)) {\n . poke_error_context(dots, i, mask = mask)\n . context_poke(\"column\", old_current_column)\n . new_columns <- mutate_col(dots[[i]], data, mask, new_columns)\n . }, error = dplyr_error_handler(dots = dots, mask = mask, bullets = mutate_bullets, \n . error_call = error_call, error_class = \"dplyr:::mutate_error\"), \n . warning = dplyr_warning_handler(state = warnings_state, mask = mask, \n . error_call = error_call))",
- "8. mutate_col(dots[[i]], data, mask, new_columns)",
- "9. mask$eval_all_mutate(quo)",
- "10. eval()",
- "11. .handleSimpleError(function (cnd) \n . {\n . local_error_context(dots, i = frame[[i_sym]], mask = mask)\n . if (inherits(cnd, \"dplyr:::internal_error\")) {\n . parent <- error_cnd(message = bullets(cnd))\n . }\n . else {\n . parent <- cnd\n . }\n . message <- c(cnd_bullet_header(action), i = if (has_active_group_context(mask)) cnd_bullet_cur_group_label())\n . abort(message, class = error_class, parent = parent, call = error_call)\n . }, \"object 'is_valid' not found\", base::quote(NULL))",
- "12. h(simpleError(msg, call))",
- "13. abort(message, class = error_class, parent = parent, call = error_call)",
- "14. signal_abort(cnd, .file)"
- ]
+ "data": {
+ "text/html": [
+ "<table class=\"dataframe\">\n",
+ "<caption>A data.frame: 2 × 5</caption>\n",
+ "<thead>\n",
+ "\t<tr><th scope=col>group</th><th scope=col>is_valid_readseq</th><th scope=col>total_read</th><th scope=col>pc_valid</th><th scope=col>demux_filename</th></tr>\n",
+ "\t<tr><th scope=col><chr></th><th scope=col><int></th><th scope=col><int></th><th scope=col><dbl></th><th scope=col><chr></th></tr>\n",
+ "</thead>\n",
+ "<tbody>\n",
+ "\t<tr><td>INVALID</td><td> 0</td><td> 17</td><td>0.0000</td><td>../data/pre-processing_examples/Example_1_demux/Example_1_invalid.fastq.gz</td></tr>\n",
+ "\t<tr><td>VALID </td><td>9983</td><td>9983</td><td>0.9983</td><td>../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz </td></tr>\n",
+ "</tbody>\n",
+ "</table>\n"
+ ],
+ "text/latex": [
+ "A data.frame: 2 × 5\n",
+ "\\begin{tabular}{lllll}\n",
+ " group & is\\_valid\\_readseq & total\\_read & pc\\_valid & demux\\_filename\\\\\n",
+ " <chr> & <int> & <int> & <dbl> & <chr>\\\\\n",
+ "\\hline\n",
+ "\t INVALID & 0 & 17 & 0.0000 & ../data/pre-processing\\_examples/Example\\_1\\_demux/Example\\_1\\_invalid.fastq.gz\\\\\n",
+ "\t VALID & 9983 & 9983 & 0.9983 & ../data/pre-processing\\_examples/Example\\_1\\_demux/Example\\_1\\_valid.fastq.gz \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/markdown": [
+ "\n",
+ "A data.frame: 2 × 5\n",
+ "\n",
+ "| group <chr> | is_valid_readseq <int> | total_read <int> | pc_valid <dbl> | demux_filename <chr> |\n",
+ "|---|---|---|---|---|\n",
+ "| INVALID | 0 | 17 | 0.0000 | ../data/pre-processing_examples/Example_1_demux/Example_1_invalid.fastq.gz |\n",
+ "| VALID | 9983 | 9983 | 0.9983 | ../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz |\n",
+ "\n"
+ ],
+ "text/plain": [
+ " group is_valid_readseq total_read pc_valid demux_filename \n",
+ "1 INVALID 0 17 0.0000 ../data/pre-processing_examples/Example_1_demux/Example_1_invalid.fastq.gz\n",
+ "2 VALID 9983 9983 0.9983 ../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
}
],
"source": [
@@ -431,12 +453,34 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"id": "9bb4d784-8ae4-49a8-b648-8972a19f1e12",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "DNAStringSet object of length 9983:\n",
+ " width seq\n",
+ " [1] 19 TTCAGCAGGAATGCCGAGA\n",
+ " [2] 19 CAGCAGGAATGCCGAGACC\n",
+ " [3] 19 GAAGTAGAATCAGTAATTT\n",
+ " [4] 19 CATGCGAGAGCGGTATTAT\n",
+ " [5] 19 TTAAGGGCGCACGGTGGAT\n",
+ " ... ... ...\n",
+ "[9979] 19 GCACAAAAAATGACCAAGA\n",
+ "[9980] 19 CCGCTCTTCCGATCTTAAG\n",
+ "[9981] 19 TATTGATATGCAAGATGAA\n",
+ "[9982] 19 TCAGTCAAGCTGATTTAAA\n",
+ "[9983] 19 TAAAAGCTACGCACGTTTT"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
- "fq_streamer = FastqStreamer(\"../data/pre-processing_examples/Example_1_valid.fastq.gz\")\n",
+ "fq_streamer = FastqStreamer(\"../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz\")\n",
"sr <- yield(fq_streamer)\n",
"sr@sread"
]
@@ -468,7 +512,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 7,
"id": "b13d7122-84f3-4ca4-a17f-0c6cb79ca173",
"metadata": {},
"outputs": [],
@@ -479,10 +523,59 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"id": "a54f7041-4a64-498e-8a0b-112aa5806b68",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<table class=\"dataframe\">\n",
+ "<caption>A EMOTE_features: 3 × 7</caption>\n",
+ "<thead>\n",
+ "\t<tr><th scope=col>name</th><th scope=col>start</th><th scope=col>width</th><th scope=col>pattern_type</th><th scope=col>pattern</th><th scope=col>max_mismatch</th><th scope=col>readid_prepend</th></tr>\n",
+ "\t<tr><th scope=col><chr></th><th scope=col><dbl></th><th scope=col><dbl></th><th scope=col><dbl></th><th scope=col><list></th><th scope=col><dbl></th><th scope=col><lgl></th></tr>\n",
+ "</thead>\n",
+ "<tbody>\n",
+ "\t<tr><td>readseq </td><td>14</td><td>19</td><td>1</td><td>ACTG</td><td>0</td><td>FALSE</td></tr>\n",
+ "\t<tr><td>Recognition.seq</td><td> 1</td><td> 3</td><td>2</td><td> AGG</td><td>0</td><td>FALSE</td></tr>\n",
+ "\t<tr><td>Control.seq </td><td>11</td><td> 3</td><td>2</td><td> CGC</td><td>0</td><td>FALSE</td></tr>\n",
+ "</tbody>\n",
+ "</table>\n"
+ ],
+ "text/latex": [
+ "A EMOTE\\_features: 3 × 7\n",
+ "\\begin{tabular}{lllllll}\n",
+ " name & start & width & pattern\\_type & pattern & max\\_mismatch & readid\\_prepend\\\\\n",
+ " <chr> & <dbl> & <dbl> & <dbl> & <list> & <dbl> & <lgl>\\\\\n",
+ "\\hline\n",
+ "\t readseq & 14 & 19 & 1 & ACTG & 0 & FALSE\\\\\n",
+ "\t Recognition.seq & 1 & 3 & 2 & AGG & 0 & FALSE\\\\\n",
+ "\t Control.seq & 11 & 3 & 2 & CGC & 0 & FALSE\\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/markdown": [
+ "\n",
+ "A EMOTE_features: 3 × 7\n",
+ "\n",
+ "| name <chr> | start <dbl> | width <dbl> | pattern_type <dbl> | pattern <list> | max_mismatch <dbl> | readid_prepend <lgl> |\n",
+ "|---|---|---|---|---|---|---|\n",
+ "| readseq | 14 | 19 | 1 | ACTG | 0 | FALSE |\n",
+ "| Recognition.seq | 1 | 3 | 2 | AGG | 0 | FALSE |\n",
+ "| Control.seq | 11 | 3 | 2 | CGC | 0 | FALSE |\n",
+ "\n"
+ ],
+ "text/plain": [
+ " name start width pattern_type pattern max_mismatch readid_prepend\n",
+ "1 readseq 14 19 1 ACTG 0 FALSE \n",
+ "2 Recognition.seq 1 3 2 AGG 0 FALSE \n",
+ "3 Control.seq 11 3 2 CGC 0 FALSE "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
"rf"
]
@@ -510,10 +603,63 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"id": "6000958d-e2c8-437a-896a-7ddf9bcd3bf9",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<table class=\"dataframe\">\n",
+ "<caption>A EMOTE_features: 4 × 7</caption>\n",
+ "<thead>\n",
+ "\t<tr><th scope=col>name</th><th scope=col>start</th><th scope=col>width</th><th scope=col>pattern_type</th><th scope=col>pattern</th><th scope=col>max_mismatch</th><th scope=col>readid_prepend</th></tr>\n",
+ "\t<tr><th scope=col><chr></th><th scope=col><dbl></th><th scope=col><dbl></th><th scope=col><dbl></th><th scope=col><list></th><th scope=col><dbl></th><th scope=col><lgl></th></tr>\n",
+ "</thead>\n",
+ "<tbody>\n",
+ "\t<tr><td>readseq </td><td>14</td><td>19</td><td>1</td><td>ACTG</td><td>0</td><td>FALSE</td></tr>\n",
+ "\t<tr><td>Recognition.seq</td><td> 1</td><td> 3</td><td>2</td><td> AGG</td><td>0</td><td>FALSE</td></tr>\n",
+ "\t<tr><td>Control.seq </td><td>11</td><td> 3</td><td>2</td><td> CGC</td><td>0</td><td>FALSE</td></tr>\n",
+ "\t<tr><td>UMI </td><td> 4</td><td> 7</td><td>1</td><td> ACG</td><td>0</td><td> TRUE</td></tr>\n",
+ "</tbody>\n",
+ "</table>\n"
+ ],
+ "text/latex": [
+ "A EMOTE\\_features: 4 × 7\n",
+ "\\begin{tabular}{lllllll}\n",
+ " name & start & width & pattern\\_type & pattern & max\\_mismatch & readid\\_prepend\\\\\n",
+ " <chr> & <dbl> & <dbl> & <dbl> & <list> & <dbl> & <lgl>\\\\\n",
+ "\\hline\n",
+ "\t readseq & 14 & 19 & 1 & ACTG & 0 & FALSE\\\\\n",
+ "\t Recognition.seq & 1 & 3 & 2 & AGG & 0 & FALSE\\\\\n",
+ "\t Control.seq & 11 & 3 & 2 & CGC & 0 & FALSE\\\\\n",
+ "\t UMI & 4 & 7 & 1 & ACG & 0 & TRUE\\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/markdown": [
+ "\n",
+ "A EMOTE_features: 4 × 7\n",
+ "\n",
+ "| name <chr> | start <dbl> | width <dbl> | pattern_type <dbl> | pattern <list> | max_mismatch <dbl> | readid_prepend <lgl> |\n",
+ "|---|---|---|---|---|---|---|\n",
+ "| readseq | 14 | 19 | 1 | ACTG | 0 | FALSE |\n",
+ "| Recognition.seq | 1 | 3 | 2 | AGG | 0 | FALSE |\n",
+ "| Control.seq | 11 | 3 | 2 | CGC | 0 | FALSE |\n",
+ "| UMI | 4 | 7 | 1 | ACG | 0 | TRUE |\n",
+ "\n"
+ ],
+ "text/plain": [
+ " name start width pattern_type pattern max_mismatch readid_prepend\n",
+ "1 readseq 14 19 1 ACTG 0 FALSE \n",
+ "2 Recognition.seq 1 3 2 AGG 0 FALSE \n",
+ "3 Control.seq 11 3 2 CGC 0 FALSE \n",
+ "4 UMI 4 7 1 ACG 0 TRUE "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
"rf = EMOTE_add_read_feature(rf, name = \"UMI\", start = 4, width = 7, pattern = \"ACG\", pattern_type = 1, readid_prepend = T)\n",
"\n",
@@ -541,10 +687,55 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 10,
"id": "3b8ccb4d-98ad-487f-b577-37a09749f5ea",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<table class=\"dataframe\">\n",
+ "<caption>A data.frame: 2 × 8</caption>\n",
+ "<thead>\n",
+ "\t<tr><th scope=col>group</th><th scope=col>is_valid_readseq</th><th scope=col>is_valid_Recognition.seq</th><th scope=col>is_valid_Control.seq</th><th scope=col>is_valid_UMI</th><th scope=col>total_read</th><th scope=col>pc_valid</th><th scope=col>demux_filename</th></tr>\n",
+ "\t<tr><th scope=col><chr></th><th scope=col><int></th><th scope=col><int></th><th scope=col><int></th><th scope=col><int></th><th scope=col><int></th><th scope=col><dbl></th><th scope=col><chr></th></tr>\n",
+ "</thead>\n",
+ "<tbody>\n",
+ "\t<tr><td>INVALID</td><td>5163</td><td>5127</td><td> 93</td><td>4355</td><td>5180</td><td>0.000</td><td>../data/pre-processing_examples/Example_1_demux/Example_1_invalid.fastq.gz</td></tr>\n",
+ "\t<tr><td>VALID </td><td>4820</td><td>4820</td><td>4820</td><td>4820</td><td>4820</td><td>0.482</td><td>../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz </td></tr>\n",
+ "</tbody>\n",
+ "</table>\n"
+ ],
+ "text/latex": [
+ "A data.frame: 2 × 8\n",
+ "\\begin{tabular}{llllllll}\n",
+ " group & is\\_valid\\_readseq & is\\_valid\\_Recognition.seq & is\\_valid\\_Control.seq & is\\_valid\\_UMI & total\\_read & pc\\_valid & demux\\_filename\\\\\n",
+ " <chr> & <int> & <int> & <int> & <int> & <int> & <dbl> & <chr>\\\\\n",
+ "\\hline\n",
+ "\t INVALID & 5163 & 5127 & 93 & 4355 & 5180 & 0.000 & ../data/pre-processing\\_examples/Example\\_1\\_demux/Example\\_1\\_invalid.fastq.gz\\\\\n",
+ "\t VALID & 4820 & 4820 & 4820 & 4820 & 4820 & 0.482 & ../data/pre-processing\\_examples/Example\\_1\\_demux/Example\\_1\\_valid.fastq.gz \\\\\n",
+ "\\end{tabular}\n"
+ ],
+ "text/markdown": [
+ "\n",
+ "A data.frame: 2 × 8\n",
+ "\n",
+ "| group <chr> | is_valid_readseq <int> | is_valid_Recognition.seq <int> | is_valid_Control.seq <int> | is_valid_UMI <int> | total_read <int> | pc_valid <dbl> | demux_filename <chr> |\n",
+ "|---|---|---|---|---|---|---|---|\n",
+ "| INVALID | 5163 | 5127 | 93 | 4355 | 5180 | 0.000 | ../data/pre-processing_examples/Example_1_demux/Example_1_invalid.fastq.gz |\n",
+ "| VALID | 4820 | 4820 | 4820 | 4820 | 4820 | 0.482 | ../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz |\n",
+ "\n"
+ ],
+ "text/plain": [
+ " group is_valid_readseq is_valid_Recognition.seq is_valid_Control.seq is_valid_UMI total_read pc_valid demux_filename \n",
+ "1 INVALID 5163 5127 93 4355 5180 0.000 ../data/pre-processing_examples/Example_1_demux/Example_1_invalid.fastq.gz\n",
+ "2 VALID 4820 4820 4820 4820 4820 0.482 ../data/pre-processing_examples/Example_1_demux/Example_1_valid.fastq.gz "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
"report = EMOTE_parse_read(\n",
" fastq_file = \"../data/pre-processing_examples/Example_1.fastq.gz\",\n",
@@ -573,10 +764,36 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
"id": "a42ea938-09f8-49cb-946d-eaeb53de509a",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Warning message in open.connection(con, \"rb\"):\n",
+ "“cannot open file '../data/pre-processing_examples/Example_1_valid.fastq.gz': No such file or directoryâ€\n"
+ ]
+ },
+ {
+ "ename": "ERROR",
+ "evalue": "Error in open.connection(con, \"rb\"): cannot open the connection\n",
+ "output_type": "error",
+ "traceback": [
+ "Error in open.connection(con, \"rb\"): cannot open the connection\nTraceback:\n",
+ "1. FastqStreamer(\"../data/pre-processing_examples/Example_1_valid.fastq.gz\")",
+ "2. FastqStreamer(\"../data/pre-processing_examples/Example_1_valid.fastq.gz\")",
+ "3. callGeneric(con, n = 1e+06, readerBlockSize = readerBlockSize, \n . verbose = verbose)",
+ "4. eval(call, parent.frame())",
+ "5. eval(call, parent.frame())",
+ "6. FastqStreamer(con, n = 1e+06, readerBlockSize = readerBlockSize, \n . verbose = verbose)",
+ "7. FastqStreamer(con, n = 1e+06, readerBlockSize = readerBlockSize, \n . verbose = verbose)",
+ "8. open(con, \"rb\")",
+ "9. open.connection(con, \"rb\")"
+ ]
+ }
+ ],
"source": [
"fq_streamer = FastqStreamer(\"../data/pre-processing_examples/Example_1_valid.fastq.gz\")\n",
"sr <- yield(fq_streamer)\n",