Skip to content

Commit

Permalink
Update remaining docs for v1.4.0 release.
Browse files Browse the repository at this point in the history 
PiperOrigin-RevId: 452420550
  • Loading branch information
@pichuan @copybara-github
pichuan authored and copybara-github committed Jun 2, 2022
1 parent 32876df commit 7b43b45
Show file tree
Hide file tree
Showing 4 changed files with 65 additions and 59 deletions.
6 changes: 6 additions & 0 deletions docs/deeptrio-details-training-data.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,12 @@
| 1.1.0 | 4 HG001/NA12891/NA12892 trios<br>7 HG005/HG006/HG007 trios <br>3 HG002/HG003/HG004 trios| 566,589,652<sup>[(1)](#vfootnote1)</sup> |
| 1.2.0 | (Same model as 1.1.0) | |
| 1.3.0 | (Same model as 1.1.0) | |
| 1.4.0 | 4 HG001/NA12891/NA12892 trios<br>7 HG005/HG006/HG007 trios <br>3 HG002/HG003/HG004 trios | 704,228,446 |
| Parent model | | |
| 1.1.0 | 7 HG005/HG006/HG007 trios <br> 3 HG002/HG003/HG004 trios | 315,847,934 |
| 1.2.0 | (Same model as 1.1.0) | |
| 1.3.0 | (Same model as 1.1.0) | |
| 1.4.0 | 7 HG005/HG006/HG007 trios <br> 3 HG002/HG003/HG004 trios | 457,374,516 |

### WES models

Expand All @@ -21,10 +23,12 @@
| 1.1.0 | 27 HG001/NA12891/NA12892 trios<br>6 HG005/HG006/HG007 trios <br>7 HG002/HG003/HG004 trios | 18,002,596 |
| 1.2.0 | (Same model as 1.1.0) | |
| 1.3.0 | (Same model as 1.1.0) | |
| 1.4.0 | 27 HG001/NA12891/NA12892 trios<br>6 HG005/HG006/HG007 trios <br>6 HG002/HG003/HG004 trios | 27,776,416 |
| Parent model | | |
| 1.1.0 | 6 HG005/HG006/HG007 trios <br> 6 HG002/HG003/HG004 trios | 4,131,018 |
| 1.2.0 | (Same model as 1.1.0) | |
| 1.3.0 | (Same model as 1.1.0) | |
| 1.4.0 | 6 HG005/HG006/HG007 trios <br> 6 HG002/HG003/HG004 trios | 13,036,995 |

### PACBIO models<sup>[(2)](#vfootnote2)</sup><sup>[(3)](#vfootnote3)</sup>

Expand All @@ -34,10 +38,12 @@
| 1.1.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG003/HG004 trios | 397,610,700 |
| 1.2.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG003/HG004 trios | 406,893,180<sup>[(4)](#vfootnote4)</sup> |
| 1.3.0 | 2 HG005/HG006/HG007 trio <br>10 HG002/HG003/HG004 trios | 539,382,124<sup>[(5)](#vfootnote5)</sup> |
| 1.4.0 | (Same model as 1.3.0) | |
| Parent model | | |
| 1.1.0 | 1 HG005/HG006/HG007 trio <br> 8 HG002/HG003/HG004 trios | 386,418,918 |
| 1.2.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG003/HG004 trios | 392,749,204<sup>[(4)](#vfootnote4)</sup> |
| 1.3.0 | 2 HG005/HG006/HG007 trio <br>10 HG002/HG003/HG004 trios | 533,353,050<sup>[(5)](#vfootnote5)</sup> |
| 1.4.0 | (Same model as 1.3.0) | |


<a name="vfootnote1">(1)</a>: We include HG002/HG003/HG004 for training WGS
Expand Down
2 changes: 1 addition & 1 deletion docs/deepvariant-details.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -303,7 +303,7 @@ An example usage:

```bash
BIN_VERSION=1.4.0
gsutil -m cp gs://deepvariant/models/DeepVariant/${BIN_VERSION}/DeepVariant-inception_v3-${BIN_VERSION}-rc2+data-pacbio_standard/model.ckpt* .
gsutil -m cp gs://deepvariant/models/DeepVariant/${BIN_VERSION}/DeepVariant-inception_v3-${BIN_VERSION}+data-pacbio_standard/model.ckpt* .

sudo docker run \
-v $PWD:/input \
Expand Down
2 changes: 1 addition & 1 deletion docs/show-examples.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ Once you have a make_examples output tfrecord file, then you can run
INPUT_DIR="${PWD}/quickstart-testdata"
OUTPUT_DIR="${PWD}/quickstart-output"

BIN_VERSION="1.3.0" # show_examples is available only in version 1.0.0 and later.
BIN_VERSION="1.4.0" # show_examples is available only in version 1.0.0 and later.
sudo docker run \
-v "${INPUT_DIR}":"/input" \
-v "${OUTPUT_DIR}":"/output" \
Expand Down
114 changes: 57 additions & 57 deletions docs/trio-merge-case-study.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ serially is not the most effective approach.
```
N_SHARDS=$(nproc) # Or change to the number of cores you want to use
CAPTURE_BED=agilent_sureselect_human_all_exon_v5_b37_targets.bed
VERSION=1.3.0
VERSION=1.4.0
declare -a trio=(HG002 HG003 HG004)
for SAMPLE in "${trio[@]}"
Expand Down Expand Up @@ -223,16 +223,16 @@ The output is:
```
Checking: /data/deepvariant.cohort.vcf.gz
Family: [Sample_Diag-excap51-HG003-EEogPU + Sample_Diag-excap51-HG004-EEogPU] -> [Sample_Diag-excap51-HG002-EEogPU]
Concordance Sample_Diag-excap51-HG002-EEogPU: F:56629/57124 (99.13%) M:57014/57138 (99.78%) F+M:56384/57014 (98.90%)
Concordance Sample_Diag-excap51-HG002-EEogPU: F:56909/57378 (99.18%) M:57287/57388 (99.82%) F+M:56726/57304 (98.99%)
Sample Sample_Diag-excap51-HG002-EEogPU has less than 99.0 concordance with both parents. Check for incorrect pedigree or sample mislabelling.
815/57369 (1.42%) records did not conform to expected call ploidy
57271/57369 (99.83%) records were variant in at least 1 family member and checked for Mendelian constraints
210/57271 (0.37%) records had indeterminate consistency status due to incomplete calls
636/57271 (1.11%) records contained a violation of Mendelian constraints
810/57551 (1.41%) records did not conform to expected call ploidy
57481/57551 (99.88%) records were variant in at least 1 family member and checked for Mendelian constraints
139/57481 (0.24%) records had indeterminate consistency status due to incomplete calls
586/57481 (1.02%) records contained a violation of Mendelian constraints
```

From this report, we know that there is a 1.11% Mendelian violation rate, and
0.37% of the records had incomplete calls (with `.`) so RTG couldn't determine
From this report, we know that there is a 1.02% Mendelian violation rate, and
0.24% of the records had incomplete calls (with `.`) so RTG couldn't determine
whether there is violation or not.

## Single sample quality metrics
Expand Down Expand Up @@ -261,9 +261,9 @@ done

| Sample | [3]ts | [4]tv | [5]ts/tv | [6]ts (1st ALT) | [7]tv (1st ALT) | [8]ts/tv (1st ALT) |
| ------ | ----- | ----- | -------- | --------------- | --------------- | ------------------ |
| HG002 | 29819 | 11626 | 2.56 | 29809 | 11606 | 2.57 |
| HG003 | 29686 | 11670 | 2.54 | 29677 | 11649 | 2.55 |
| HG004 | 29920 | 11801 | 2.54 | 29906 | 11783 | 2.54 |
| HG002 | 29865 | 11620 | 2.57 | 29852 | 11597 | 2.57 |
| HG003 | 29725 | 11684 | 2.54 | 29715 | 11664 | 2.55 |
| HG004 | 29977 | 11774 | 2.55 | 29967 | 11759 | 2.55 |

If you want to restrict to the truth BED files, use this command:

Expand All @@ -285,9 +285,9 @@ Which resulted in this table:

| Sample | [3]ts | [4]tv | [5]ts/tv | [6]ts (1st ALT) | [7]tv (1st ALT) | [8]ts/tv (1st ALT) |
| ------ | ----- | ----- | -------- | --------------- | --------------- | ------------------ |
| HG002 | 27688 | 10533 | 2.63 | 27680 | 10520 | 2.63 |
| HG003 | 27324 | 10502 | 2.60 | 27319 | 10491 | 2.60 |
| HG004 | 27474 | 10592 | 2.59 | 27467 | 10580 | 2.60 |
| HG002 | 27700 | 10532 | 2.63 | 27692 | 10519 | 2.63 |
| HG003 | 27355 | 10508 | 2.60 | 27351 | 10497 | 2.61 |
| HG004 | 27487 | 10594 | 2.59 | 27480 | 10584 | 2.60 |


### Rtg vcfstats
Expand All @@ -310,69 +310,69 @@ HG002:

```
Location : /data/HG002.vcf.gz
Failed Filters : 14776
Passed Filters : 45080
SNPs : 41414
Failed Filters : 14791
Passed Filters : 45065
SNPs : 41450
MNPs : 0
Insertions : 1866
Deletions : 1777
Insertions : 1845
Deletions : 1747
Indels : 19
Same as reference : 4
SNP Transitions/Transversions: 2.56 (41696/16271)
Total Het/Hom ratio : 1.49 (26956/18120)
SNP Het/Hom ratio : 1.51 (24883/16531)
SNP Transitions/Transversions: 2.57 (41757/16262)
Total Het/Hom ratio : 1.48 (26926/18135)
SNP Het/Hom ratio : 1.51 (24904/16546)
MNP Het/Hom ratio : - (0/0)
Insertion Het/Hom ratio : 1.11 (981/885)
Deletion Het/Hom ratio : 1.52 (1073/704)
Insertion Het/Hom ratio : 1.06 (951/894)
Deletion Het/Hom ratio : 1.51 (1052/695)
Indel Het/Hom ratio : - (19/0)
Insertion/Deletion ratio : 1.05 (1866/1777)
Indel/SNP+MNP ratio : 0.09 (3662/41414)
Insertion/Deletion ratio : 1.06 (1845/1747)
Indel/SNP+MNP ratio : 0.09 (3611/41450)
```

HG003:

```
Location : /data/HG003.vcf.gz
Failed Filters : 15654
Passed Filters : 44919
SNPs : 41321
Failed Filters : 15639
Passed Filters : 44934
SNPs : 41376
MNPs : 0
Insertions : 1850
Deletions : 1729
Indels : 18
Same as reference : 1
SNP Transitions/Transversions: 2.52 (41489/16448)
Total Het/Hom ratio : 1.48 (26775/18143)
SNP Het/Hom ratio : 1.49 (24728/16593)
Insertions : 1831
Deletions : 1705
Indels : 20
Same as reference : 2
SNP Transitions/Transversions: 2.52 (41551/16483)
Total Het/Hom ratio : 1.47 (26741/18191)
SNP Het/Hom ratio : 1.49 (24738/16638)
MNP Het/Hom ratio : - (0/0)
Insertion Het/Hom ratio : 1.15 (988/862)
Deletion Het/Hom ratio : 1.51 (1041/688)
Indel Het/Hom ratio : - (18/0)
Insertion/Deletion ratio : 1.07 (1850/1729)
Indel/SNP+MNP ratio : 0.09 (3597/41321)
Insertion Het/Hom ratio : 1.10 (960/871)
Deletion Het/Hom ratio : 1.50 (1023/682)
Indel Het/Hom ratio : - (20/0)
Insertion/Deletion ratio : 1.07 (1831/1705)
Indel/SNP+MNP ratio : 0.09 (3556/41376)
```

HG004:

```
Location : /data/HG004.vcf.gz
Failed Filters : 15365
Passed Filters : 45316
SNPs : 41686
Failed Filters : 15362
Passed Filters : 45319
SNPs : 41724
MNPs : 0
Insertions : 1860
Deletions : 1750
Insertions : 1852
Deletions : 1720
Indels : 19
Same as reference : 1
SNP Transitions/Transversions: 2.55 (41517/16304)
Total Het/Hom ratio : 1.57 (27656/17659)
SNP Het/Hom ratio : 1.59 (25573/16113)
Same as reference : 4
SNP Transitions/Transversions: 2.56 (41594/16279)
Total Het/Hom ratio : 1.56 (27637/17678)
SNP Het/Hom ratio : 1.59 (25594/16130)
MNP Het/Hom ratio : - (0/0)
Insertion Het/Hom ratio : 1.13 (986/874)
Deletion Het/Hom ratio : 1.60 (1078/672)
Insertion Het/Hom ratio : 1.12 (979/873)
Deletion Het/Hom ratio : 1.55 (1045/675)
Indel Het/Hom ratio : - (19/0)
Insertion/Deletion ratio : 1.06 (1860/1750)
Indel/SNP+MNP ratio : 0.09 (3629/41686)
Insertion/Deletion ratio : 1.08 (1852/1720)
Indel/SNP+MNP ratio : 0.09 (3591/41724)
```

### Run hap.py to calculate the accuracy of DeepVariant generated call sets
Expand Down Expand Up @@ -401,6 +401,6 @@ Accuracy F1 scores:

Sample | Indel | SNP
------ | -------- | --------
HG002 | 0.971084 | 0.993661
HG003 | 0.965795 | 0.993012
HG004 | 0.972641 | 0.993467
HG002 | 0.974142 | 0.993779
HG003 | 0.966972 | 0.993778
HG004 | 0.972279 | 0.993899

0 comments on commit 7b43b45

Please sign in to comment.