Skip to content

Commit

Permalink
Update deeptrio training data.
Browse files Browse the repository at this point in the history
PiperOrigin-RevId: 387162875
  • Loading branch information
pichuan authored and copybara-github committed Jul 27, 2021
1 parent bcf48b3 commit 6c6cdc6
Showing 1 changed file with 15 additions and 6 deletions.
21 changes: 15 additions & 6 deletions docs/deeptrio-details-training-data.md
Original file line number Diff line number Diff line change
@@ -1,31 +1,37 @@
# DeepTrio training data

### WGS models
### WGS models<sup>[(1)](#vfootnote1)</sup>

| version | Replicates | #examples |
| ------------ | ---------------------------------- | ----------- |
| Child model | | |
| 1.1.0 | 4 HG001/NA12891/NA12892 trios<br>7 HG005/HG006/HG007 trios <br>3 HG002/HG004/HG004 trios<sup>[(1)](#vfootnote1)</sup>| 566,589,652 |
| 1.1.0 | 4 HG001/NA12891/NA12892 trios<br>7 HG005/HG006/HG007 trios <br>3 HG002/HG004/HG004 trios| 566,589,652 |
| 1.2.0 | (Same model as 1.1.0) | |
| Parent model | | |
| 1.1.0 | 7 HG005/HG006/HG007 trios <br> 3 HG002/HG004/HG004 trios<sup>[(1)](#vfootnote1)</sup> | 315,847,934 |
| 1.1.0 | 7 HG005/HG006/HG007 trios <br> 3 HG002/HG004/HG004 trios | 315,847,934 |
| 1.2.0 | (Same model as 1.1.0) | |

### WES models

| version | Replicates | #examples |
| ------------ | ----------------------------------------------- | ---------- |
| Child model | | |
| 1.1.0 | 27 HG001/NA12891/NA12892 trios<br>6 HG005/HG006/HG007 trios <br>7 HG002/HG004/HG004 trios | 18,002,596 |
| 1.2.0 | (Same model as 1.1.0) | |
| Parent model | | |
| 1.1.0 | 6 HG005/HG006/HG007 trios <br> 6 HG002/HG004/HG004 trios | 4,131,018 |
| 1.2.0 | (Same model as 1.1.0) | |

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

| version | Replicates | #examples |
| ------------ | ---------------------------------- | ----------- |
| Child model | | |
| 1.1.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG004/HG004 trios<sup>[(2)](#vfootnote2)</sup> | 397,610,700 |
| 1.1.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG004/HG004 trios | 397,610,700 |
| 1.2.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG004/HG004 trios | 406,893,180<sup>[(4)](#vfootnote4)</sup> |
| Parent model | | |
| 1.1.0 | 1 HG005/HG006/HG007 trio <br> 8 HG002/HG004/HG004 trios<sup>[(3)](#vfootnote3)</sup> | 386,418,918 |
| 1.1.0 | 1 HG005/HG006/HG007 trio <br> 8 HG002/HG004/HG004 trios | 386,418,918 |
| 1.2.0 | 1 HG005/HG006/HG007 trio <br>8 HG002/HG004/HG004 trios | 392,749,204<sup>[(4)](#vfootnote4)</sup> |


<a name="vfootnote1">(1)</a>: We include HG002/HG003/HG004 for training WGS
Expand All @@ -37,3 +43,6 @@ PacBio model training.

<a name="vfootnote3">(3)</a>: PacBio training data contains training examples
with haplotag sorted images and unsorted images.

<a name="vfootnote4">(4)</a>: In v1.2.0, we updated the NIST truth versions we
used for training.

0 comments on commit 6c6cdc6

Please sign in to comment.