# Can the raw\_score values be compared across different cell/sample types, transcription factors, and variants?

**URL:** <https://www.alphagenomecommunity.com/t/can-the-raw-score-values-be-compared-across-different-cell-sample-types-transcription-factors-and-variants/883>\
**Category:** Help & Support\
**Tags:** testing\
**Created:** [May 4, 2026, 5:33am UTC](https://www.alphagenomecommunity.com/t/can-the-raw-score-values-be-compared-across-different-cell-sample-types-transcription-factors-and-variants/883 "2026-05-04T05:33:39Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Chao\_Li](https://yyz2.discourse-cdn.com/watermelon/user_avatar/www.alphagenomecommunity.com/chao_li/32/1158_2.png) [@Chao\_Li](https://www.alphagenomecommunity.com/u/Chao_Li)\
**Post date:** [May 4, 2026, 5:33am UTC](https://www.alphagenomecommunity.com/t/can-the-raw-score-values-be-compared-across-different-cell-sample-types-transcription-factors-and-variants/883/1 "2026-05-04T05:33:39Z")

</div>

Hi,

I am evaluating the effects of a set of variants across all available transcription factors via chip\_tf scorer. For each variant, I obtained raw\_score values across multiple transcription factors and biosamples.

I would like to ask whether these raw\_score values are directly comparable:  
across different biosamples,  
across different transcription factors, and  
across different variants.

Or are there recommended normalization or comparison strategies for these scenarios?

Best regards,

Chao Li

---

<div class="post-metadata">

**Author:** ![Tumi\_Makgatho](https://yyz2.discourse-cdn.com/watermelon/user_avatar/www.alphagenomecommunity.com/tumi_makgatho/32/703_2.png) [@Tumi\_Makgatho](https://www.alphagenomecommunity.com/u/Tumi_Makgatho)\
**Post date:** [May 5, 2026, 12:48pm UTC](https://www.alphagenomecommunity.com/t/can-the-raw-score-values-be-compared-across-different-cell-sample-types-transcription-factors-and-variants/883/2 "2026-05-05T12:48:13Z")

</div>

Hi There!

Thanks for reaching out.

You should avoid using the `raw_score` for comparisons across biosamples or modalities and instead use the `quantile_score` which was specifically implemented to make raw variant scores more interpretable and comparable across different assays and genomic contexts.

The `quantile_score` is calibrated by calculating the raw effect scores for a reference set of ~350,000 common SNPs to establish an empirical background distribution for every biosample and modality. Your input variant’s raw score is then mapped to its percentile rank within that distribution.

A `quantile_score` of 0.9 means that the predicted change for your variant is greater than 90% of the effects predicted for the reference set. This can be compared against `quantile_score`results from other modalities and biosamples.

Kind regards,  
Tumi

---

<div class="post-metadata">

**Author:** ![Chao\_Li](https://yyz2.discourse-cdn.com/watermelon/user_avatar/www.alphagenomecommunity.com/chao_li/32/1158_2.png) [@Chao\_Li](https://www.alphagenomecommunity.com/u/Chao_Li)\
**Post date:** [May 5, 2026, 1:21pm UTC](https://www.alphagenomecommunity.com/t/can-the-raw-score-values-be-compared-across-different-cell-sample-types-transcription-factors-and-variants/883/3 "2026-05-05T13:21:36Z")

</div>

Thanks for you reply.

Best regards,

Chao Li