-
Notifications
You must be signed in to change notification settings - Fork 67
fix: treat deletions as undetermined in nearest node distance #1765
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
+131
−13
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,6 +1,7 @@ | ||
| use crate::alphabet::nuc::Nuc; | ||
| use crate::analyze::is_sequenced::is_nuc_sequenced; | ||
| use crate::analyze::letter_ranges::NucRange; | ||
| use crate::analyze::nuc_del::NucDelRange; | ||
| use crate::analyze::nuc_sub::NucSub; | ||
| use crate::coord::range::NucRefGlobalRange; | ||
| use crate::graph::node::GraphNodeKey; | ||
|
|
@@ -21,6 +22,7 @@ pub fn graph_find_nearest_nodes( | |
| graph: &AuspiceGraph, | ||
| qry_nuc_subs: &[NucSub], | ||
| qry_missing: &[NucRange], | ||
| qry_deletions: &[NucDelRange], | ||
| aln_range: &NucRefGlobalRange, | ||
| ) -> Result<Vec<TreePlacementInfo>, Report> { | ||
| let masked_ranges = graph.data.meta.placement_mask_ranges(); | ||
|
|
@@ -29,7 +31,14 @@ pub fn graph_find_nearest_nodes( | |
| let nodes_by_placement_score = DftPre::new(graph.get_exactly_one_root()?, |node| graph.iter_children_of(node)) | ||
| .map(|(_, node)| { | ||
| let node_payload = node.payload(); | ||
| let distance = tree_calculate_node_distance(node_payload, qry_nuc_subs, qry_missing, aln_range, masked_ranges); | ||
| let distance = tree_calculate_node_distance( | ||
| node_payload, | ||
| qry_nuc_subs, | ||
| qry_missing, | ||
| qry_deletions, | ||
| aln_range, | ||
| masked_ranges, | ||
| ); | ||
| let prior = get_prior(node_payload); | ||
| TreePlacementInfo { | ||
| node_key: node.key(), | ||
|
|
@@ -69,6 +78,7 @@ fn tree_calculate_node_distance( | |
| node: &AuspiceGraphNodePayload, | ||
| qry_nuc_subs: &[NucSub], | ||
| qry_missing: &[NucRange], | ||
| qry_deletions: &[NucDelRange], | ||
| aln_range: &NucRefGlobalRange, | ||
| masked_ranges: &[NucRefGlobalRange], | ||
| ) -> i64 { | ||
|
|
@@ -105,11 +115,13 @@ fn tree_calculate_node_distance( | |
| } | ||
| } | ||
|
|
||
| // determine the number of sites that are mutated in the node but missing in seq. | ||
| // determine the number of sites that are mutated in the node but missing or deleted in seq. | ||
| // for these we can't tell whether the node agrees with seq | ||
| let mut undetermined_sites = 0_i64; | ||
| for pos in node.tmp.substitutions.keys() { | ||
| if !is_nuc_sequenced(*pos, &masked_qry_missing, aln_range) { | ||
| if !is_nuc_sequenced(*pos, &masked_qry_missing, aln_range) | ||
| || qry_deletions.iter().any(|del| del.range().contains(*pos)) | ||
| { | ||
| undetermined_sites += 1; | ||
| } | ||
| } | ||
|
|
@@ -234,7 +246,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 0); | ||
|
|
||
|
|
@@ -249,7 +269,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 3); | ||
|
|
||
|
|
@@ -264,7 +292,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 5); | ||
|
|
||
|
|
@@ -279,7 +315,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 5); | ||
|
|
||
|
|
@@ -294,7 +338,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 4); | ||
|
|
||
|
|
@@ -309,7 +361,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 20); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 3); | ||
|
|
||
|
|
@@ -324,7 +384,15 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![NucRefGlobalRange::from_usize(0, 100)]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 0); | ||
|
|
||
|
|
@@ -343,7 +411,15 @@ mod tests { | |
| NucRefGlobalRange::from_usize(30, 50), | ||
| ]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 3); | ||
|
|
||
|
|
@@ -358,10 +434,51 @@ mod tests { | |
| let aln_range = NucRefGlobalRange::from_usize(0, 30); | ||
| let masked_ranges = vec![NucRefGlobalRange::from_usize(12, 13)]; | ||
|
|
||
| let result = tree_calculate_node_distance(&node, &qry_nuc_subs, &qry_missing, &aln_range, &masked_ranges); | ||
| let qry_deletions: Vec<NucDelRange> = vec![]; | ||
| let result = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
|
|
||
| assert_eq!(result, 3); | ||
|
|
||
| Ok(()) | ||
| } | ||
|
|
||
| #[rstest] | ||
| fn deletion_covering_node_mutations_reduces_distance() -> Result<(), Report> { | ||
| let node = node_with_simple_nuc_subs(); | ||
| let qry_nuc_subs: Vec<NucSub> = vec![]; | ||
| let qry_missing: Vec<NucRange> = vec![]; | ||
| let aln_range = NucRefGlobalRange::from_usize(0, 100); | ||
| let masked_ranges = vec![]; | ||
|
|
||
| let no_deletions: Vec<NucDelRange> = vec![]; | ||
| let distance_without_del = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &no_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
| assert_eq!(distance_without_del, 5); | ||
|
|
||
| let qry_deletions = vec![NucDelRange::from_usize(10, 25)]; | ||
| let distance_with_del = tree_calculate_node_distance( | ||
| &node, | ||
| &qry_nuc_subs, | ||
| &qry_missing, | ||
| &qry_deletions, | ||
| &aln_range, | ||
| &masked_ranges, | ||
| ); | ||
| assert_eq!(distance_with_del, 2); | ||
|
|
||
| Ok(()) | ||
| } | ||
| } | ||
|
Comment on lines
+451
to
484
Member
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Tests that adding a del reduces distance metric |
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Dels are new passed to distance metric calculation and counted same as unknowns or unsequenced. But I imagine it can also be treat differently if needed.