Merge pull request #34 from marbl/develop

v0.8.6 release

CITATION.cff

@@ -1,14 +1,15 @@
-
-@article{Sweeten2024.04.15.589623,
-	abstract = {Motivation A common method for analyzing genomic repeats is to produce a sequence similarity matrix visualized via a dot plot. Innovative approaches such as StainedGlass have improved upon this classic visualization by rendering dot plots as a heatmap of sequence identity, enabling researchers to better visualize multi-megabase tandem repeat arrays within centromeres and other heterochromatic regions of the genome. However, computing the similarity estimates for heatmaps requires high computational overhead and can suffer from decreasing accuracy. Results In this work we introduce ModDotPlot, an interactive and alignment-free dot plot viewer. By approximating average nucleotide identity via a k-mer-based containment index, ModDotPlot produces accurate plots orders of magnitude faster than StainedGlass. We accomplish this through the use of a hierarchical modimizer scheme that can visualize the full 128 Mbp genome of Arabidopsis thaliana in under 5 minutes on a laptop. ModDotPlot is implemented in Python with a graphical user interface supporting real-time interactive navigation of entire chromosomes. Availability and Implementation ModDotPlot is available at https://github.com/marbl/ModDotPlot.Competing Interest StatementThe authors have declared no competing interest.},
-	author = {Alexander P. Sweeten and Michael C. Schatz and Adam M. Phillippy},
-	doi = {10.1101/2024.04.15.589623},
-	elocation-id = {2024.04.15.589623},
-	eprint = {https://www.biorxiv.org/content/early/2024/04/19/2024.04.15.589623.full.pdf},
-	journal = {bioRxiv},
-	publisher = {Cold Spring Harbor Laboratory},
-	title = {ModDotPlot - Rapid and interactive visualization of complex repeats},
-	url = {https://www.biorxiv.org/content/early/2024/04/19/2024.04.15.589623},
-	year = {2024},
-	bdsk-url-1 = {https://www.biorxiv.org/content/early/2024/04/19/2024.04.15.589623},
-	bdsk-url-2 = {https://doi.org/10.1101/2024.04.15.589623}}
+@article{10.1093/bioinformatics/btae493,
+    author = {Sweeten, Alexander P and Schatz, Michael C and Phillippy, Adam M},
+    title = "{ModDotPlot—rapid and interactive visualization of tandem repeats}",
+    journal = {Bioinformatics},
+    volume = {40},
+    number = {8},
+    pages = {btae493},
+    year = {2024},
+    month = {08},
+    abstract = "{A common method for analyzing genomic repeats is to produce a sequence similarity matrix visualized via a dot plot. Innovative approaches such as StainedGlass have improved upon this classic visualization by rendering dot plots as a heatmap of sequence identity, enabling researchers to better visualize multi-megabase tandem repeat arrays within centromeres and other heterochromatic regions of the genome. However, computing the similarity estimates for heatmaps requires high computational overhead and can suffer from decreasing accuracy.In this work, we introduce ModDotPlot, an interactive and alignment-free dot plot viewer. By approximating average nucleotide identity via a k-mer-based containment index, ModDotPlot produces accurate plots orders of magnitude faster than StainedGlass. We accomplish this through the use of a hierarchical modimizer scheme that can visualize the full 128 Mb genome of Arabidopsis thaliana in under 5 min on a laptop. ModDotPlot is bundled with a graphical user interface supporting real-time interactive navigation of entire chromosomes.ModDotPlot is available at https://github.com/marbl/ModDotPlot.}",
+    issn = {1367-4811},
+    doi = {10.1093/bioinformatics/btae493},
+    url = {https://doi.org/10.1093/bioinformatics/btae493},
+    eprint = {https://academic.oup.com/bioinformatics/article-pdf/40/8/btae493/58809824/btae493.pdf},
+}

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ModDotPlot"
-version = "0.8.5"
+version = "0.8.6"
 requires-python = ">= 3.7"
 dependencies = [
   "pysam",

src/moddotplot/const.py

@@ -1,4 +1,4 @@
-VERSION = "0.8.5"
+VERSION = "0.8.6"
 COLS = [
     "#query_name",
     "query_start",

src/moddotplot/moddotplot.py

@@ -950,7 +950,7 @@ def main():
                     smaller_length = len(smaller_seq)
                     larger_seq_name = sequences[i][0]
                     smaller_seq_name = sequences[j][0]
-                    # Houston we have a problem
+
                     if larger_length < smaller_length:
                         smaller_seq = sequences[i][1]
                         larger_seq = sequences[j][1]
@@ -1000,15 +1000,25 @@ def main():
                             seq_list[j],
                             False,
                         )
+                        if args.grid:
+                            grid_vals.append(bed)
 
                         if not args.no_bed:
                             # Log saving bed file
                             if not args.output_dir:
-                                bedfile_output = sequences[i][0] + ".bed"
+                                bedfile_output = (
+                                    smaller_seq_name
+                                    + "_"
+                                    + larger_seq_name
+                                    + "_COMPARE.bed"
+                                )
                             else:
                                 bedfile_output = os.path.join(
                                     args.output_dir,
-                                    sequences[i][0] + "_" + sequences[j][0] + ".bed",
+                                    smaller_seq_name
+                                    + "_"
+                                    + larger_seq_name
+                                    + "_COMPARE.bed",
                                 )
                             with open(bedfile_output, "w") as bedfile:
                                 for row in bed:
@@ -1019,8 +1029,8 @@ def main():
                             create_plots(
                                 sdf=[bed],
                                 directory=args.output_dir if args.output_dir else ".",
-                                name_x=sequences[i][0],
-                                name_y=sequences[j][0],
+                                name_x=smaller_seq_name,
+                                name_y=larger_seq_name,
                                 palette=args.palette,
                                 palette_orientation=args.palette_orientation,
                                 no_hist=args.no_hist,
@@ -1035,6 +1045,9 @@ def main():
                                 axes_labels=args.axes_ticks,
                             )
 
+            """if args.grid:
+                print(grid_vals)"""
+
 
 if __name__ == "__main__":
     main()

src/moddotplot/static_plots.py

@@ -574,7 +574,7 @@ def create_plots(
             height=9,
             dpi=dpi,
             format="pdf",
-            filename=f"{plot_filename}.pdf",
+            filename=f"{plot_filename}_COMPARE.pdf",
             verbose=False,
         )
         ggsave(
@@ -583,11 +583,13 @@ def create_plots(
             height=9,
             dpi=dpi,
             format="png",
-            filename=f"{plot_filename}.png",
+            filename=f"{plot_filename}_COMPARE.png",
             verbose=False,
         )
         if no_hist:
-            print(f"{plot_filename}.pdf and {plot_filename}.png saved sucessfully. \n")
+            print(
+                f"{plot_filename}_COMPARE.pdf and {plot_filename}_COMPARE.png saved sucessfully. \n"
+            )
         else:
             ggsave(
                 histy,
@@ -608,7 +610,7 @@ def create_plots(
                 verbose=False,
             )
             print(
-                f"{plot_filename}.pdf, {plot_filename}.png, {plot_filename}_HIST.pdf and {plot_filename}_HIST.png saved sucessfully. \n"
+                f"{plot_filename}_COMPARE.pdf, {plot_filename}_COMPARE.png, {plot_filename}_HIST.pdf and {plot_filename}_HIST.png saved sucessfully. \n"
             )
     # Self-identity plots: Output _TRI, _FULL, and _HIST
     else: