# How to interpret junction\_End starting in an intron?

**URL:** <https://www.alphagenomecommunity.com/t/how-to-interpret-junction-end-starting-in-an-intron/723>\
**Category:** Help & Support\
**Created:** [November 21, 2025, 10:21am UTC](https://www.alphagenomecommunity.com/t/how-to-interpret-junction-end-starting-in-an-intron/723 "2025-11-21T10:21:48Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![magiduck](https://yyz2.discourse-cdn.com/watermelon/user_avatar/www.alphagenomecommunity.com/magiduck/32/668_2.png) [@magiduck](https://www.alphagenomecommunity.com/u/magiduck)\
**Post date:** [November 21, 2025, 10:21am UTC](https://www.alphagenomecommunity.com/t/how-to-interpret-junction-end-starting-in-an-intron/723/1 "2025-11-21T10:21:48Z")

</div>

Hello all,

I am wondering how I should interpret the “smaller\_splice” in the image / table below.

Some context: this is a gene on the negative strand, so I would understand that the junction\_Start is the 3′ splice acceptor site and junction\_End 5′ splice donor site.

The “big\_splice” seems to make sense to me, starting at the end of exon1 going to the cassette exon, but the “smaller\_splice” seems to start in the middle of the intron, does this mean that alphagenome predicts that anything before is an exon, or could it be that it is a second splice donor that is ignored after the one that should be there at the end of exon1?

Thank you in advance for the feedback.

 ![image (32)](https://canada1.discourse-cdn.com/watermelon/original/1X/08fabf005753a602d5afeef8579d75f7cf3bfc35.jpeg)

| junction\_Start | junction\_End | name | output\_type | variant\_scorer | track\_name | track\_strand | Assay title | ontology\_curie | biosample\_name | biosample\_type | raw\_score | quantile\_score |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 173915186 | 173917218 | big\_splice | SPLICE\_JUNCTIONS | SpliceJunctionScorer() | junction\_UBERON:0002107 polyA plus RNA-seq | . | polyA plus RNA-seq | UBERON:0002107 | liver | tissue | 0.20898438 | 0.993351 |
| 173915186 | 173917218 | big\_splice | SPLICE\_JUNCTIONS | SpliceJunctionScorer() | junction\_UBERON:0002107 total RNA-seq | . | total RNA-seq | UBERON:0002107 | liver | tissue | 0.1607666 | 0.9912486 |
| 173915115 | 173916406 | smaller\_splice | SPLICE\_JUNCTIONS | SpliceJunctionScorer() | junction\_UBERON:0002107 total RNA-seq | . | total RNA-seq | UBERON:0002107 | liver | tissue | 0.12902832 | 0.9890026 |
| 173915115 | 173916406 | smaller\_splice | SPLICE\_JUNCTIONS | SpliceJunctionScorer() | junction\_UBERON:0002107 polyA plus RNA-seq | . | polyA plus RNA-seq | UBERON:0002107 | liver | tissue | 0.11065674 | 0.9868027 |

---

<div class="post-metadata">

**Author:** ![Jun\_Cheng](https://yyz2.discourse-cdn.com/watermelon/user_avatar/www.alphagenomecommunity.com/jun_cheng/32/23_2.png) [@Jun\_Cheng](https://www.alphagenomecommunity.com/u/Jun_Cheng)\
**Post date:** [December 17, 2025, 3:29pm UTC](https://www.alphagenomecommunity.com/t/how-to-interpret-junction-end-starting-in-an-intron/723/2 "2025-12-17T15:29:38Z")

</div>

Hi, it looks like the “smaller\_splice” starts (5’, on the right) from an annotated exon in one of the transcript? The end of the junction (left side) looks like a newly predicted acceptor. This does not mean the model is predicting a big exon before the smaller\_splice junction, there might be another smaller junction being predicted, try lower [filter\_threshold](https://github.com/google-deepmind/alphagenome/blob/6822ebaff9421a2f31bed526a76d0eeeba471315/src/alphagenome/visualization/plot_components.py#L1027C7-L1027C23) argument and see if it is being visualized in the reference and alternative predictions. Note that, looks like you are looking at the variant prediction annData, there only junctions relevant to variant score is shown.