Added variant ions and more complex satellite ion definitions to the theoretical model

.github/workflows/rust.yml

@@ -28,6 +28,8 @@ jobs:
         cargo build -p rustyms --no-default-features --features rand
         cargo build -p rustyms --no-default-features --features rayon
         cargo build -p rustyms --no-default-features --features mzdata
+        cargo build -p rustyms --no-default-features --features glycan-render
+        cargo build -p rustyms --no-default-features --features glycan-render-bitmap
 
   fmt:
     runs-on: ubuntu-latest

.github/workflows/scripts/update-all-databases.sh

@@ -41,11 +41,9 @@ function make-ontologies {
     curl https://raw.githubusercontent.com/HUPO-PSI/mzIdentML/master/cv/XLMOD.obo \
         > ${db_data}/XLMOD.obo
     curl -L http://purl.obolibrary.org/obo/gno.obo \
-        | sed '/(property_value: GNO:00000(022|023|041|042|101|102) .*$\n)|(def: .*$\n)/d' \
-        | gzip -c \
-        > ${db_data}/GNOme.obo.gz
+        > ${db_data}/GNOme.obo
     curl -L https://glycosmos.org/download/glycosmos_glycans_list.csv \
-        | gzip -c > ${db_data}/glycosmos_glycans_list.csv.gz
+        > ${db_data}/glycosmos_glycans_list.csv
 
 
     echo "Serializing the other databases..."

.gitignore

@@ -7,6 +7,7 @@ Cargo.lock
 errors.dat
 *.dat.Z
 *.dat
+*.html
 GNOme.obo
 glycosmos_glycans_list.csv
 .venv/

Cargo.toml

@@ -27,15 +27,17 @@ codegen-units = 1
 
 [workspace.dependencies]
 afl = "0.15"
+base64 = "0.22"
 bincode = "1.3"
 clap = { version = "4.5", features = ["derive", "cargo"] }
 directories = "6.0"
 flate2 = "1.0"
 iai-callgrind = "0.14"
 itertools = "0.14"
-mzdata = "0.44"
+mzdata = {version="0.49", default-features = false, features = ["miniz_oxide"]}
 ndarray = "0.16"
 ordered-float = { version = "4.6", features = ["serde"] }
+png = "0.17"
 probability = "0.20"
 pyo3 = "0.23"
 rand = "0.9"
@@ -45,8 +47,10 @@ roxmltree = "0.20"
 serde = { version = "1.0", features = ["derive", "rc"] }
 serde_json = "1.0"
 similar = "2.7"
+swash = "0.2"
 thin-vec = { version = "0.2", features = ["serde"] }
-uom = { version = "0.36", features = ["use_serde", "usize", "isize"] }
+uom = { version = "0.36", default-features = false, features = ["use_serde", "usize", "isize", "f64"] }
+zeno = {version = "0.3.2" }
 
 [workspace.lints.rust]
 unexpected_cfgs = { level = "allow", check-cfg = [

examples/de-novo-align/Cargo.toml

@@ -7,7 +7,7 @@ license.workspace = true
 publish = false
 
 [dependencies]
-rustyms = { path = "../../rustyms" }
+rustyms = { path = "../../rustyms", default-features=false, features = ["align", "identification"] }
 clap = { workspace = true }
 itertools = { workspace = true }
 rayon = { workspace = true }

examples/ion-explorer/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "ion-explorer"
+version = "0.1.0"
+authors.workspace = true
+edition.workspace = true
+license.workspace = true
+publish = false
+
+[dependencies]
+clap = { workspace = true }
+directories = { workspace = true }
+itertools = { workspace = true }
+mzdata = { workspace = true, features = ["mgf", "mzml", "thermo"] }
+rustyms = { path = "../../rustyms", default-features = false, features = [
+    "mzdata",
+    "identification",
+] }
+serde_json = { workspace = true }
+
+[lints]
+workspace = true

examples/ion-explorer/README.md

@@ -0,0 +1,7 @@
+# Ion explorer
+
+```
+argo run -p ion-explorer --release -- --in-path /home/douwe/Downloads/raw_data/COVID19_IgG_14_DENOVO_5.csv --raw-file-directory /home/douwe/Downloads/raw_data/ --out-path .
+```
+
+This takes an identified peptides file and extracts and bins all peaks surrounding the main fragment series. This helps in discovering which fragments and neutral losses are actually generated by the used fragmentation method. It returns a separate csv file for all fragments with the mz, count, and average intensity for all detected peaks.

examples/ion-explorer/figure.r

@@ -0,0 +1,33 @@
+library(ggplot2)
+
+for (file in c("start", "fragment_b", "fragment_y", "fragment_v_0", "fragment_w_0", "fragment_w_1", "fragment_w_2", "fragment_w_3", "fragment_w_4", "fragment_w_5", "fragment_w_6", "fragment_precursor")) {
+    data = read.csv(paste(file, ".csv", sep=""), header=TRUE);
+    # data = data[data$count > 1000,];
+
+    plot = ggplot(data, aes(x=mz, y=count, size=avg_intensity, colour=avg_intensity)) +
+        geom_point() +
+        scale_size_continuous(range = c(0.25, 3)) +
+        xlab("Difference to theoretical ion") +
+        theme_bw() 
+
+    if (file == "fragment_y") {
+        plot = plot + geom_vline(xintercept=0, linetype="dashed") + geom_vline(xintercept=+18.011-0.984, linetype="dashed") + geom_vline(xintercept=-25.979+18.011, linetype="dashed")
+    }
+
+    ggsave(paste(file, ".png", sep=""), plot)
+}
+
+for (file in c("comparison_b_N_N[U:Deamidated]", "comparison_y_N_N[U:Deamidated]")) {
+    data = read.csv(paste(file, ".csv", sep=""), header=TRUE);
+    data = data[data$count_a > 20 | data$count_b > 20,];
+    max_a = max(data$avg_intensity_a);
+    max_b = max(data$avg_intensity_b);
+
+    ggplot(data, aes(x=mz, y=log2(count_a/count_b), colour=rgb(avg_intensity_a / max_a, 0, avg_intensity_b / max_b), size=avg_intensity_a)) +
+        geom_point() +
+        scale_size_continuous(range = c(0.25, 3)) +
+        theme_bw() +
+        guides(colour="none")
+
+    ggsave(paste(file, ".png", sep=""))
+}