update r4 release

HKU-BAL · Jun 28, 2021 · 305bb88 · 305bb88
1 parent 2fbf193
commit 305bb88
Show file tree

Hide file tree

Showing 9 changed files with 105 additions and 51 deletions.
diff --git a/README.md b/README.md
diff --git a/docs/quick_demo/illumina_quick_demo.md b/docs/quick_demo/illumina_quick_demo.md
@@ -49,7 +49,7 @@ echo -e "${CONTIGS}\t${START_POS}\t${END_POS}" > ${INPUT_DIR}/quick_demo.bed
 ### Option 1. Docker pre-built image
 
 ```bash
-BIN_VERSION='v0.1-r3'
+BIN_VERSION='v0.1-r4'
 THREADS=4
 cd ${OUTPUT_DIR}
 
@@ -124,6 +124,8 @@ conda install -c conda-forge boost=1.67.0 -y
 echo "Environment:" ${CONDA_PREFIX}
 # Make sure in Clair3 directory
 cd Clair3
+# cd ${CONDA_PREFIX}/bin if installing Clair3 using bioconda
+
 cd preprocess/realign
 g++ -std=c++14 -O1 -shared -fPIC -o realigner ssw_cpp.cpp ssw.c realigner.cpp
 g++ -std=c++11 -shared -fPIC -o debruijn_graph -O3 debruijn_graph.cpp -I ${CONDA_PREFIX}/include -L ${CONDA_PREFIX}/lib

diff --git a/docs/quick_demo/ont_quick_demo.md b/docs/quick_demo/ont_quick_demo.md
@@ -49,7 +49,7 @@ echo -e "${CONTIGS}\t${START_POS}\t${END_POS}" > ${INPUT_DIR}/quick_demo.bed
 
 ```bash
 THREADS=4
-BIN_VERSION="v0.1-r3"
+BIN_VERSION="v0.1-r4"
 
 cd ${OUTPUT_DIR}
 # Run Clair3 using one command

diff --git a/docs/quick_demo/pacbio_hifi_quick_demo.md b/docs/quick_demo/pacbio_hifi_quick_demo.md
@@ -50,7 +50,7 @@ echo -e "${CONTIGS}\t${START_POS}\t${END_POS}" > ${INPUT_DIR}/quick_demo.bed
 
 ```bash
 THREADS=4
-BIN_VERSION="v0.1-r3"
+BIN_VERSION="v0.1-r4"
 
 cd ${OUTPUT_DIR}
 # Run Clair3 using one command

diff --git a/docs/training_data.md b/docs/training_data.md
@@ -54,9 +54,11 @@
 
 Download models from [here](http://www.bio8.cs.hku.hk/clair3/clair3_models/) or click on the links below.
 
-|      File       |  Platform   | Training Samples | In the docker image by default |                             Link                             |
-| :-------------: | :---------: | :--------------: | :----------------------------: | :----------------------------------------------------------: |
-|   ont.tar.gz    |     ONT     |   HG001,2,4,5    |              Yes               | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ont.tar.gz) |
-| ont_1235.tar.gz |     ONT     |   HG001,2,3,5    |                                | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ont_1235.tar.gz) |
-|   hifi.tar.gz   | PacBio HiFi |   HG001,2,4,5    |              Yes               | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/hifi.tar.gz) |
-|   ilmn.tar.gz   |  Illumina   |   HG001,2,4,5    |              Yes               | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ilmn.tar.gz) |
+|       File        |  Platform   |                       Training samples                       | Included in the bioconda package | Included in the docker image | Release |   Date   | Basecaller |                             Link                             |
+| :---------------: | :---------: | :----------------------------------------------------------: | -------------------------------- | :--------------------------: | :-----: | :------: | :--------: | :----------------------------------------------------------: |
+|    ont.tar.gz     |     ONT     |                         HG001,2,4,5                          | Yes                              |             Yes              |    1    | 20210517 |  Guppy3,4  | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ont.tar.gz) |
+|  ont_1235.tar.gz  |     ONT     |                         HG001,2,3,5                          |                                  |                              |    1    | 20210517 |  Guppy3,4  | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ont_1235.tar.gz) |
+| ont_guppy5.tar.gz |     ONT     | Base model: HG001,2,4,5 (Guppy3,4) <br>Fine-tuning data: HG002 (Guppy5_sup) | Yes                              |             Yes              |    1    | 20210609 |   Guppy5   | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ont_guppy5.tar.gz) |
+| ont_guppy2.tar.gz |     ONT     |                         HG001,2,3,4                          |                                  |             Yes              |    1    | 20210627 |   Guppy2   | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ont_guppy2.tar.gz) |
+|    hifi.tar.gz    | PacBio HiFi |                         HG001,2,4,5                          | Yes                              |             Yes              |    1    | 20210517 |     NA     | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/hifi.tar.gz) |
+|    ilmn.tar.gz    |  Illumina   |                         HG001,2,4,5                          | Yes                              |             Yes              |    1    | 20210517 |     NA     | [Download](http://www.bio8.cs.hku.hk/clair3/clair3_models/ilmn.tar.gz) |
diff --git a/scripts/clair3.sh b/scripts/clair3.sh
@@ -49,7 +49,7 @@ while true; do
 
     -- ) shift; break; ;;
     -h|--help ) print_help_messages; break ;;
-    * ) print_help_messages; exit 1 ;;
+    * ) print_help_messages; exit 0 ;;
    esac
 done
 
@@ -133,14 +133,20 @@ time ${PARALLEL} --retries ${RETRIES} -C ' ' --joblog ${LOG_PATH}/parallel_1_cal
 
 
 echo "[INFO] Merge chunked contigs vcf files"
-cat ${PILEUP_VCF_PATH}/pileup_*.vcf | ${PYPY} ${CLAIR3} SortVcf --output_fn ${OUTPUT_FOLDER}/pileup.vcf
+${PYPY} ${CLAIR3} SortVcf \
+    --input_dir ${PILEUP_VCF_PATH} \
+    --vcf_fn_prefix "pileup" \
+    --output_fn ${OUTPUT_FOLDER}/pileup.vcf \
+    --sampleName ${SAMPLE} \
+    --ref_fn ${REFERENCE_FILE_PATH}
+
 bgzip -f ${OUTPUT_FOLDER}/pileup.vcf
 tabix -f -p vcf ${OUTPUT_FOLDER}/pileup.vcf.gz
 
 if [ ${PILEUP_ONLY} == True ]; then
     echo "[INFO] Only call pileup output with --pileup_only, output file: ${OUTPUT_FOLDER}/pileup.vcf.gz"
     echo "[INFO] Finish calling!"
-    exit 1;
+    exit 0;
 fi
 
 # Whatshap phasing and haplotaging
@@ -221,7 +227,13 @@ time ${PARALLEL} --retries ${RETRIES} --joblog ${LOG_PATH}/parallel_6_call_var_b
 
 ##Merge pileup and full alignment vcf
 ##-----------------------------------------------------------------------------------------------------------------------
-cat ${FULL_ALIGNMENT_OUTPUT_PATH}/full_alignment_*.vcf | ${PYPY} ${CLAIR3} SortVcf --output_fn ${OUTPUT_FOLDER}/full_alignment.vcf
+${PYPY} ${CLAIR3} SortVcf \
+    --input_dir ${FULL_ALIGNMENT_OUTPUT_PATH} \
+    --vcf_fn_prefix "full_alignment" \
+    --output_fn ${OUTPUT_FOLDER}/full_alignment.vcf \
+    --sampleName ${SAMPLE} \
+    --ref_fn ${REFERENCE_FILE_PATH}
+
 cat ${CANDIDATE_BED_PATH}/*.* > ${CANDIDATE_BED_PATH}/full_aln_regions
 bgzip -f ${OUTPUT_FOLDER}/full_alignment.vcf
 tabix -f -p vcf ${OUTPUT_FOLDER}/full_alignment.vcf.gz
@@ -245,7 +257,13 @@ time ${PARALLEL} --retries ${RETRIES} --joblog ${LOG_PATH}/parallel_7_merge_vcf.
     --ref_fn ${REFERENCE_FILE_PATH} \
     --ctgName {1}" ::: ${CHR[@]} |& tee ${LOG_PATH}/7_merge_vcf.log
 
-cat ${TMP_FILE_PATH}/merge_output/merge_*.vcf | ${PYPY} ${CLAIR3} SortVcf --output_fn ${OUTPUT_FOLDER}/merge_output.vcf
+${PYPY} ${CLAIR3} SortVcf \
+    --input_dir ${TMP_FILE_PATH}/merge_output \
+    --vcf_fn_prefix "merge" \
+    --output_fn ${OUTPUT_FOLDER}/merge_output.vcf \
+    --sampleName ${SAMPLE} \
+    --ref_fn ${REFERENCE_FILE_PATH}
+
 if [ ${GVCF} == True ]; then cat ${TMP_FILE_PATH}/merge_output/merge_*.gvcf | ${PYPY} ${CLAIR3} SortVcf --output_fn ${OUTPUT_FOLDER}/merge_output.gvcf; fi
 bgzip -f ${OUTPUT_FOLDER}/merge_output.vcf
 tabix -f -p vcf ${OUTPUT_FOLDER}/merge_output.vcf.gz

diff --git a/scripts/clair3_hifi_quick_demo.sh b/scripts/clair3_hifi_quick_demo.sh
@@ -2,7 +2,7 @@ PLATFORM='hifi'
 INPUT_DIR="${HOME}/clair3_pacbio_hifi_quickDemo"
 OUTPUT_DIR="${INPUT_DIR}/output"
 THREADS=4
-BIN_VERSION="v0.1-r3"
+BIN_VERSION="v0.1-r4"
 
 ## Create local directory structure
 mkdir -p ${INPUT_DIR}

diff --git a/scripts/clair3_ilmn_quick_demo.sh b/scripts/clair3_ilmn_quick_demo.sh
@@ -3,7 +3,7 @@ PLATFORM='ilmn'
 INPUT_DIR="${HOME}/clair3_illumina_quickDemo"
 OUTPUT_DIR="${INPUT_DIR}/output"
 THREADS=4
-BIN_VERSION="v0.1-r3"
+BIN_VERSION="v0.1-r4"
 
 ## Create local directory structure
 mkdir -p ${INPUT_DIR}

diff --git a/scripts/clair3_ont_quick_demo.sh b/scripts/clair3_ont_quick_demo.sh
@@ -3,7 +3,7 @@ PLATFORM='ont'
 INPUT_DIR="${HOME}/clair3_ont_quickDemo"
 OUTPUT_DIR="${INPUT_DIR}/output"
 THREADS=4
-BIN_VERSION="v0.1-r3"
+BIN_VERSION="v0.1-r4"
 
 ## Create local directory structure
 mkdir -p ${INPUT_DIR}