Single-end Support

.coveragerc

@@ -5,5 +5,5 @@ show_missing = True
 branch = True
 omit = 
     */yeat/_version.py
-    */yeat/Snakefile
+    */yeat/workflows/snakefiles/*
     */yeat/tests/*

CHANGELOG.md

@@ -10,8 +10,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - Input fastq read support:
     - Pacbio raw and corrected reads (#47)
-    - Oxford Nanopore raw, corrected, and HAC (#47)
-- Support for Nanopore-reads assembly with Flye and Canu (#47)
+    - Oxford Nanopore raw, corrected, and HAC reads (#47)
+    - Single-end Illumina reads (#50)
+- Support for Nanopore-reads assembly with Flye and Canu (#47, #50)
 - New assemblers:
     - Hifiasm and Hifiasm-meta (#49)
 

README.md

@@ -51,6 +51,7 @@ $ yeat --outdir {path} {config}
 | Readtype  | Algorithm |
 | ------------- | ------------- |
 | paired  | spades, megahit, unicycler |
+| single  | spades, megahit, unicycler |
 | pacbio-raw  | flye, canu |
 | pacbio-corr  | flye, canu |
 | pacbio-hifi  | flye, canu, hifiasm, hifiasm-meta |
@@ -72,8 +73,8 @@ $ yeat --outdir {path} {config}
         },
         "sample2": {
             "paired": [
-                "yeat/tests/data/Animal_289_R1.fastq.gz",
-                "yeat/tests/data/Animal_289_R2.fastq.gz"
+                "yeat/tests/data/Animal_289_R1.fq.gz",
+                "yeat/tests/data/Animal_289_R2.fq.gz"
             ]
         },
         "sample3": {
@@ -89,7 +90,7 @@ $ yeat --outdir {path} {config}
     },
     "assemblers": [
         {
-            "label": "default-spades",
+            "label": "spades-default",
             "algorithm": "spades",
             "extra_args": "",
             "samples": [
@@ -106,7 +107,7 @@ $ yeat --outdir {path} {config}
             ]
         },
         {
-            "label": "nanoflye",
+            "label": "flye_ONT",
             "algorithm": "flye",
             "extra_args": "",
             "samples": [

environment.yml

@@ -26,3 +26,4 @@ dependencies:
     - nanoplot>=1.20
     - hifiasm>=0.19
     - hifiasm_meta>=hamtv0.3
+    - gfatools>=0.5

pytest.ini

@@ -4,3 +4,5 @@ markers =
     long: long running tests
     hifi: pacbio hifi-reads tests
     nano: oxford nanopore-reads tests
+filterwarnings =
+    ignore::DeprecationWarning:ratelimiter.*

yeat/cli/cli.py

@@ -7,7 +7,7 @@
 # Development Center.
 # -------------------------------------------------------------------------------------------------
 
-from . import downsample
+from . import illumina
 from .config import AssemblerConfig
 from argparse import Action, ArgumentParser
 import json
@@ -26,16 +26,16 @@
         },
         "sample2": {
             "paired": [
-                "yeat/tests/data/Animal_289_R1.fastq.gz",
-                "yeat/tests/data/Animal_289_R2.fastq.gz",
+                "yeat/tests/data/Animal_289_R1.fq.gz",
+                "yeat/tests/data/Animal_289_R2.fq.gz",
             ]
         },
         "sample3": {"pacbio-hifi": ["yeat/tests/data/ecoli.fastq.gz"]},
         "sample4": {"nano-hq": ["yeat/tests/data/ecolk12mg1655_R10_3_guppy_345_HAC.fastq.gz"]},
     },
     "assemblers": [
         {
-            "label": "default-spades",
+            "label": "spades-default",
             "algorithm": "spades",
             "extra_args": "",
             "samples": ["sample1", "sample2"],
@@ -46,7 +46,7 @@
             "extra_args": "genomeSize=4.8m",
             "samples": ["sample3"],
         },
-        {"label": "nanoflye", "algorithm": "flye", "extra_args": "", "samples": ["sample4"]},
+        {"label": "flye_ONT", "algorithm": "flye", "extra_args": "", "samples": ["sample4"]},
     ],
 }
 
@@ -93,7 +93,8 @@ def options(parser):
 def get_parser(exit_on_error=True):
     parser = ArgumentParser(exit_on_error=exit_on_error)
     options(parser)
-    downsample.options(parser)
+    illumina.fastp_options(parser)
+    illumina.downsample_options(parser)
     parser.add_argument("config", type=str, help="config file")
     return parser
 

yeat/cli/config.py

@@ -13,11 +13,12 @@
 
 
 PAIRED = ("spades", "megahit", "unicycler")
+SINGLE = ("spades", "megahit", "unicycler")
 PACBIO = ("canu", "flye", "hifiasm", "hifiasm-meta")
 OXFORD = ("canu", "flye")
-ALGORITHMS = set(PAIRED + PACBIO + OXFORD)
+ALGORITHMS = set(PAIRED + SINGLE + PACBIO + OXFORD)
 
-ILLUMINA_READS = ("paired",)
+ILLUMINA_READS = ("paired", "single")
 PACBIO_READS = ("pacbio-raw", "pacbio-corr", "pacbio-hifi")
 OXFORD_READS = ("nano-raw", "nano-corr", "nano-hq")
 LONG_READS = PACBIO_READS + OXFORD_READS
@@ -84,44 +85,53 @@ def create_sample_and_assembler_objects(self):
         ]
 
     def batch(self):
-        self.paired_assemblers = []
-        self.pacbio_assemblers = []
-        self.oxford_assemblers = []
+        self.paired_sample_labels = set()
+        self.paired_assemblers = set()
+        self.single_sample_labels = set()
+        self.single_assemblers = set()
+        self.pacbio_sample_labels = set()
+        self.pacbio_assemblers = set()
+        self.oxford_sample_labels = set()
+        self.oxford_assemblers = set()
         for assembler in self.assemblers:
             self.determine_assembler_workflow(assembler)
         self.batch = {
             "paired": {
-                "samples": self.get_batch_samples(self.paired_assemblers),
+                "samples": self.get_samples(self.paired_sample_labels),
                 "assemblers": self.paired_assemblers,
             },
+            "single": {
+                "samples": self.get_samples(self.single_sample_labels),
+                "assemblers": self.single_assemblers,
+            },
             "pacbio": {
-                "samples": self.get_batch_samples(self.pacbio_assemblers),
+                "samples": self.get_samples(self.pacbio_sample_labels),
                 "assemblers": self.pacbio_assemblers,
             },
             "oxford": {
-                "samples": self.get_batch_samples(self.oxford_assemblers),
+                "samples": self.get_samples(self.oxford_sample_labels),
                 "assemblers": self.oxford_assemblers,
             },
         }
 
     def determine_assembler_workflow(self, assembler):
-        readtypes = set()
         for sample in assembler.samples:
-            readtypes.update({self.samples[sample].readtype})
-        if assembler.algorithm in PAIRED and readtypes.intersection(ILLUMINA_READS):
-            self.paired_assemblers.append(assembler)
-        elif assembler.algorithm in PACBIO and readtypes.intersection(PACBIO_READS):
-            self.pacbio_assemblers.append(assembler)
-        elif assembler.algorithm in OXFORD and readtypes.intersection(OXFORD_READS):
-            self.oxford_assemblers.append(assembler)
-
-    def get_batch_samples(self, assemblers):
-        samples = {}
-        for assembler in assemblers:
-            samples = samples | dict(
-                (key, self.samples[key]) for key in assembler.samples if key in self.samples
-            )
-        return samples
+            readtype = self.samples[sample].readtype
+            if readtype == "paired":
+                self.paired_sample_labels.add(sample)
+                self.paired_assemblers.add(assembler)
+            elif readtype == "single":
+                self.single_sample_labels.add(sample)
+                self.single_assemblers.add(assembler)
+            elif readtype in PACBIO_READS:
+                self.pacbio_sample_labels.add(sample)
+                self.pacbio_assemblers.add(assembler)
+            elif readtype in OXFORD_READS:
+                self.oxford_sample_labels.add(sample)
+                self.oxford_assemblers.add(assembler)
+
+    def get_samples(self, labels):
+        return {label: self.samples[label] for label in labels}
 
     def to_dict(self, args, readtype="all"):
         if readtype == "all":
@@ -130,18 +140,24 @@ def to_dict(self, args, readtype="all"):
         else:
             samples = self.batch[readtype]["samples"]
             assemblers = self.batch[readtype]["assemblers"]
+        label_to_samples = {}
+        for assembler in assemblers:
+            label_to_samples[assembler.label] = [
+                sample for sample in assembler.samples if sample in samples
+            ]
         return dict(
             samples={label: sample.to_string() for label, sample in samples.items()},
             labels=[assembler.label for assembler in assemblers],
             assemblers={assembler.label: assembler.algorithm for assembler in assemblers},
             extra_args={assembler.label: assembler.extra_args for assembler in assemblers},
-            label_to_samples={assembler.label: assembler.samples for assembler in assemblers},
+            label_to_samples=label_to_samples,
             sample_readtype={label: sample.readtype for label, sample in samples.items()},
             threads=args.threads,
             downsample=args.downsample,
             coverage=args.coverage,
             genomesize=args.genome_size,
             seed=args.seed,
+            length_required=args.length_required,
         )
 
 
@@ -184,3 +200,15 @@ def check_canu_required_params(self):
             raise ValueError(
                 "Canu requires at least 4 avaliable cores; increase `--threads` to 4 or more"
             )
+
+    def __members(self):
+        return (self.label,)
+
+    def __eq__(self, other):
+        if type(other) is type(self):
+            return self.__members() == other.__members()
+        else:
+            return False
+
+    def __hash__(self):
+        return hash(self.__members())

yeat/cli/downsample.py → yeat/cli/illumina.py

@@ -10,6 +10,18 @@
 from argparse import ArgumentTypeError
 
 
+def fastp_options(parser):
+    illumina = parser.add_argument_group("fastp arguments")
+    illumina.add_argument(
+        "-l",
+        "--length-required",
+        type=int,
+        metavar="L",
+        default=50,
+        help="discard reads shorter than the required L length during fastp; by default L=50",
+    )
+
+
 def check_positive(value):
     try:
         value = int(value)
@@ -20,33 +32,33 @@ def check_positive(value):
     return value
 
 
-def options(parser):
-    short = parser.add_argument_group("downsample arguments")
-    short.add_argument(
+def downsample_options(parser):
+    illumina = parser.add_argument_group("downsample arguments")
+    illumina.add_argument(
         "-c",
         "--coverage",
         type=check_positive,
         metavar="C",
         default=150,
         help="target an average depth of coverage Cx when auto-downsampling; by default, C=150",
     )
-    short.add_argument(
+    illumina.add_argument(
         "-d",
         "--downsample",
         type=int,
         metavar="D",
         default=0,
         help="randomly sample D reads from the input rather than assembling the full set; set D=0 to perform auto-downsampling to a desired level of coverage (see --coverage); set D=-1 to disable downsampling; by default D=0",
     )
-    short.add_argument(
+    illumina.add_argument(
         "-g",
         "--genome-size",
         type=int,
         metavar="G",
         default=0,
         help="provide known genome size in base pairs (bp); by default, G=0",
     )
-    short.add_argument(
+    illumina.add_argument(
         "--seed",
         type=int,
         metavar="S",

yeat/tests/__init__.py

@@ -7,8 +7,10 @@
 # Development Center.
 # -------------------------------------------------------------------------------------------------
 
+import json
 import multiprocessing
 import os
+from pathlib import Path
 from pkg_resources import resource_filename
 
 
@@ -20,3 +22,23 @@ def data_file(path):
 
 def get_core_count():
     return multiprocessing.cpu_count()
+
+
+def write_config(labels, wd, cfg):
+    data = json.load(open(data_file(f"configs/{cfg}")))
+    assemblers = []
+    for assembler in data["assemblers"]:
+        if assembler["label"] in labels:
+            assemblers.append(assembler)
+    data["assemblers"] = assemblers
+    json.dump(data, open(Path(wd) / cfg, "w"))
+    return assemblers
+
+
+def files_exists(wd, assemblers, expected):
+    analysis_dir = Path(wd).resolve() / "analysis"
+    for assembler in assemblers:
+        for sample in assembler["samples"]:
+            label = assembler["label"]
+            algorithm = assembler["algorithm"]
+            assert (analysis_dir / sample / label / algorithm / expected).exists()