updates to doc; syncing changes

.github/workflows/build_docker.yml

@@ -95,7 +95,7 @@ jobs:
             pip install tox
             tox run -e py310
       -
-        name: Build and push
+        name: Push docker image
         uses: docker/build-push-action@v4
         id: Push
         with:

README.md

@@ -81,6 +81,8 @@ pip install ont_project/
 pip install --upgrade seaborn
 ```
 
+Take a look at the directory [usecase](usecases/) to run some example usecases.
+
 If the installation fails due to dependency issues, you can alternatively run it as a Docker image that comes with the dependencies and runs Jupyter lab:
 ```{bash}
 # to update the Docker image if a new one was published
@@ -100,10 +102,6 @@ conda create -y -n ont_project_venv python=3.10 pip
 ```
 Some scripts activate the virtual environment, so you have to change it to `conda activate ont_project_venv`.
 
-## Usecases
-
-Take a look at the directory [usecase](usecases/), in particular [enrich_usecase](usecases/enrich_usecase.py) which combines the simulator with ReadFish (and optionally NanoSim).
-
 ### Comparison with UNCALLED
 
 We tried comparing with UNCALLED, but it didn't work due to a segmentation fault without any useful error message, see [uncalled_comparison](uncalled_comparison.md) for details.

usecases/README.md

@@ -39,6 +39,7 @@ pip install -e './[readfish]'
 # git submodule update --init --depth 1 external/ont_nanosim
 # bash usecases/install_usecase_deps.sh
 
+# adapt config in ~/ont_project_all/ont_project/usecases/configs/ to fit your setup
 ~/ont_project_all/ont_project/usecases/replicate_run_submission.sh "sampler_per_rolling_window_channel"
 ~/ont_project_all/ont_project/usecases/enrich_usecase_submission.sh
 ```

usecases/configs/enrich_usecase/chr202122_run/sampler_per_window/README.md

@@ -0,0 +1 @@
+Used for Docker workflow pipeline

usecases/configs/enrich_usecase/full_genome_run/sampler_per_window/README.md

@@ -0,0 +1 @@
+Used to enrich chr20, 21 from the human genome

usecases/configs/enrich_usecase/test_config/sampler_per_window/README.md

@@ -0,0 +1 @@
+Config to test the setup

usecases/configs/enrich_usecase/dummy/sampler_per_window/config.toml → usecases/configs/enrich_usecase/test_config/sampler_per_window/config.toml

@@ -1,22 +1,21 @@
 run_dir = "simulator_run" # where reads, logs, pafs etc. will be written to
-n_channels = 512
-# n_channels = 4
+n_channels = 5
 acceleration_factor = 10
-run_duration = 300.0
+run_duration = 200
 
 #################################################
 # Optional arguments
 #################################################
 
 # reads_file = "nanosim_reads/perfect_reads_seed1_aligned_reads.fasta"
-ref_genome_path = "data/chm13v2.0_normalized1000000firsttwo.fa.gz"
+ref_genome_path = "data/chm13v2.0_normalized.fa.gz"
 sim_params_file = "sim_params.dill"
 rotating = true
-mux_scan_period = 100 # seconds, accounting for acceleration
-mux_scan_duration = 10 # seconds
+# mux_scan_period = 5400 # 90 minutes
+# mux_scan_duration = 100 # seconds
 
 # readfish params
-readfish_config_file = "configs/readfish_enrich_chr1.toml"
+readfish_config_file = "configs/readfish_enrich_chr2021.toml"
 # readfish_method = "unblock_all"
 readfish_method = "targeted_seq"
 
@@ -25,4 +24,5 @@ readfish_method = "targeted_seq"
 #################################################
 seqsum_param_extr_file = "data/20190809_zymo_seqsum.txt"
 n_channels_full = 512
-gap_sampler_type = "sampler_per_window"
+# gap_sampler_type = "sampler_per_window"
+gap_sampler_type = "sampler_per_rolling_window_channel"

usecases/configs/enrich_usecase/dummy/readfish_enrich_chr1.toml → usecases/configs/enrich_usecase/test_config/sampler_per_window/readfish_enrich_chr2021.toml

@@ -4,14 +4,15 @@ host = "ignored"
 port = 9999
 
 [conditions]
-reference = "data/chm13v2.0_normalized1000000firsttwo.mmi"
+# reference = "data/chm13v2.0_normalized.mmi"
+reference = "fake_mapper"
 
 [conditions.0]
-name = "enrich_chr_1"
+name = "enrich_chr_20_21"
 control = false
 min_chunks = 0 # no decision made whenever <= min_chunks have been received from a read
 max_chunks = 12
-targets = ["chr1"]
+targets = ["chr20", "chr21"]
 single_on = "stop_receiving"
 multi_on = "stop_receiving"
 single_off = "unblock"

usecases/configs/run_replication/test_config/README.md

@@ -0,0 +1 @@
+Config to test the setup

usecases/configs/run_replication/test_config/config.toml

@@ -0,0 +1,16 @@
+run_dir = "simulator_run" # where reads, logs, pafs etc. will be written to
+n_channels = 5
+run_duration = 10000
+
+#################################################
+# Optional arguments
+#################################################
+
+sim_params_file = "sim_params.dill"
+
+#################################################
+# Parameter extraction arguments
+#################################################
+seqsum_param_extr_file = "data/20190809_zymo_seqsum.txt"
+n_channels_full = 512
+gap_sampler_type = "constant_gaps"

usecases/enrich_usecase.py

@@ -22,37 +22,6 @@
 source ~/ont_project_all/ont_project_venv/bin/activate
 export PATH=~/ont_project_all/tools/bin:$PATH && which minimap2
 
-mkdir dummy_random && cd dummy_random
-ln -s ../data .
-ln -s ../configs/dummy/random configs
-python ~/ont_project_all/ont_project/usecases/enrich_usecase.py
-
-cd ..
-mkdir dummy_constant_gaps && cd dummy_constant_gaps
-ln -s ../data .
-ln -s ../configs/dummy/constant_gaps configs
-python ~/ont_project_all/ont_project/usecases/enrich_usecase.py
-
-cd ..
-mkdir dummy_replication && cd dummy_replication
-ln -s ../data .
-ln -s ../configs/dummy/replication configs
-python ~/ont_project_all/ont_project/usecases/enrich_usecase.py
-
-cd ..
-mkdir dummy_sampler_per_window && cd dummy_sampler_per_window
-ln -s ../data .
-ln -s ../configs/dummy/sampler_per_window configs
-python ~/ont_project_all/ont_project/usecases/enrich_usecase.py
-# Press Ctrl+C to stop script, then plots are created
-
-cd ..
-mkdir full_run_sampler_per_window && cd full_run_sampler_per_window
-ln -s ../data .
-ln -s ../configs/full_run/sampler_per_window configs
-python ~/ont_project_all/ont_project/usecases/enrich_usecase.py
-
-cd ..
 mkdir full_genome_run_sampler_per_window && cd full_genome_run_sampler_per_window
 ln -s ../data .
 ln -s ../configs/full_genome_run/sampler_per_window configs