documentation edits

tiger.md

@@ -1,44 +1,36 @@
-## TIGER Cas13 Efficacy Prediction
+## TIGER Online Tool for Cas13 Efficacy Prediction
 
-Welcome to TIGER!
-This Hugging Face space is an online tool that accompanies our Nature Biotechnology article.
-TIGER's ability to make accurate on- and off-target predictions enables biologists to both design highly effective gRNAs and precisely modulate transcript expression by engineering gRNA mismatches.
-If you utilize our model, please consider citing us:
+Welcome to TIGER! This online tool that accompanies our *Nature Biotechnology* article.
+TIGER's ability to make accurate on- and off-target predictions enables users to 1) design highly effective gRNAs and 2) precisely modulate transcript expression by engineered gRNA-target mismatches. 
 
+If you use TIGER, please consider citing our study:
 > Wessels, H.-H., Stirn, A., Méndez-Mancilla, A., Kim, E. J., Hart, S. K., Knowles, D. A., & Sanjana, N. E. (2023). Prediction of on-target and off-target activity of CRISPR–Cas13d guide RNAs using deep learning. Nature Biotechnology. https://doi.org/10.1038/s41587-023-01830-8
 
-[//]: # (In our article, TIGER predicts log2 fold-change (LFC) from target sequence, guide sequence, and additional scalar features.)
 
-[//]: # (Prior to training, we normalize our survival screen's LFC values on a per-gene basis to discourage TIGER from learning which target transcripts come from more essential genes.)
+Please note that this precompiled, online tool differs from the manuscript slightly.
+First, this version of TIGER predicts using just target and guide sequence (see Figure 3c). Second, we map TIGER's predictions to the unit interval to make estimates more interpretable: a Guide Score of 1 corresponds to high gRNA activity (i.e. desirable).
+A Guide Score of 0 denotes no/minimal activity.
+This transformation is monotonic and therefore preserves Spearman, AUROC, and AUPRC performance.
+These estimates (transformations of log-fold-change predictions from TIGER) appear in the "Guide Score" column of this online tool’s output.
 
-[//]: # (As such, TIGER outputs a normalized LFC estimate.)
+### Using the TIGER Online Tool
 
-This tool differs from our manuscript in two ways.
-First, this version of TIGER predicts using just target and guide sequence, which will marginally reduce performance (fig 3c).
-Second, we map TIGER's predictions to the unit interval to make estimates more interpretable: a one corresponds to high gRNA activity and a zero denotes no activity.
-This transformation, maps estimates with no detectable Cas13 activity to (0,0.025] and the most active 2.5% of estimates to [0.975,1)
-This transformation is monotonically decreasing and therefore preserves Spearman, AUROC, and AUPRC performance.
-These transformed LFC estimates appear in the `Guide Score` column of our prediction tables.
+The tool supports two methods for transcript entry:
+1) Manual entry of a single transcript
+2) Uploading a FASTA file that can contain one or more transcripts. Each transcript must have a unique ID.
 
+The tool has three run modes:
+- Report all on-target gRNAs for each provided transcript. This mode does not support off-target identification.
+- Report the top 10 most active, on-target gRNAs for each provided transcript. This mode allows for the optional identification of off-target effects.
+- Report the top 10 most active, on-target gRNAs for each provided transcript and their titration candidates (all possible single mismatches with predicted knockdown). Larger guide scores correspond to more transcript knockdown. This mode also does not support off-target identification.
 
-### Using TIGER
+The tool uses version 19 of Gencode (protein-coding and lncRNA) to identify off-target candidates.
 
-We support two methods for transcript entry:
-- Manual entry of a single transcript
-- Uploading a FASTA file that can contain one or many transcripts provided each has a unique ID
-
-We currently offer three run modes:
-- We report all on-target gRNAs for each provided transcript. This mode does not support off-target identification due to current computational constraints.
-- We report the top ten most active, on-target gRNAs for each provided transcript. This mode allows for the optional identification of off-target effects.
-- We report the top ten most active, on-target gRNAs for each provided transcript and their titration candidates (all possible single mismatches). This mode also does not support off-target identification due to current computational constraints.
-
-We use version 19 of gencode (protein-coding and lncRNA) to identify off-target candidates.
-
-### Feature Roadmap
+### Future Development Plans
 
 - Off-target scanning speed improvements
-- Off-target scanning for titration mode
-- Allow user to select more than the top ten guides per transcript
+- Off-target scanning for titration (engineered mismatch) mode
+- Allow users to select more than the top ten guides per transcript
 - Incorporate non-scalar features (target accessibility, hybridization energies, etc...)
 
 To report bugs or to request additional features, please click the "Community" button in the top right corner of this screen and start a new discussion.