Categorical scatterplots with R for biologists: a step-by-step guide

Benjamin Petre1, Aurore Coince2, Sophien Kamoun1

1 The Sainsbury Laboratory, Norwich, UK; 2 Earlham Institute, Norwich, UK

Weissgerber and colleagues (2015) recently stated that ‘as scientists, we urgently need to change our practices for presenting continuous data in small sample size studies’. They called for more scatterplot and boxplot representations in scientific papers, which ‘allow readers to critically evaluate continuous data’ (Weissgerber et al., 2015). In the Kamoun Lab at The Sainsbury Laboratory, we recently implemented a protocol to generate categorical scatterplots (Petre et al., 2016; Dagdas et al., 2016). Here we describe the three steps of this protocol: 1) formatting of the data set in a .csv file, 2) execution of the R script to generate the graph, and 3) export of the graph as a .pdf file.

Protocol

• Step 1: format the data set as a .csv file. Store the data in a three-column excel file as shown in Powerpoint slide. The first column ‘Replicate’ indicates the biological replicates. In the example, the month and year during which the replicate was performed is indicated. The second column ‘Condition’ indicates the conditions of the experiment (in the example, a wild type and two mutants called A and B). The third column ‘Value’ contains continuous values. Save the Excel file as a .csv file (File -> Save as -> in ‘File Format’, select .csv). This .csv file is the input file to import in R.

• Step 2: execute the R script (see Notes 1 and 2). Copy the script shown in Powerpoint slide and paste it in the R console. Execute the script. In the dialog box, select the input .csv file from step 1. The categorical scatterplot will appear in a separate window. Dots represent the values for each sample; colors indicate replicates. Boxplots are superimposed; black dots indicate outliers.

• Step 3: save the graph as a .pdf file. Shape the window at your convenience and save the graph as a .pdf file (File -> Save as). See Powerpoint slide for an example.

Notes

• Note 1: install the ggplot2 package. The R script requires the package ‘ggplot2’ to be installed. To install it, Packages & Data -> Package Installer -> enter ‘ggplot2’ in the Package Search space and click on ‘Get List’. Select ‘ggplot2’ in the Package column and click on ‘Install Selected’. Install all dependencies as well.

• Note 2: use a log scale for the y-axis. To use a log scale for the y-axis of the graph, use the command line below in place of command line #7 in the script.

7 Display the graph in a separate window. Dot colors indicate

replicates

graph + geom_boxplot(outlier.colour='black', colour='black') + geom_jitter(aes(col=Replicate)) + scale_y_log10() + theme_bw()

References

Dagdas YF, Belhaj K, Maqbool A, Chaparro-Garcia A, Pandey P, Petre B, et al. (2016) An effector of the Irish potato famine pathogen antagonizes a host autophagy cargo receptor. eLife 5:e10856.

Petre B, Saunders DGO, Sklenar J, Lorrain C, Krasileva KV, Win J, et al. (2016) Heterologous Expression Screens in Nicotiana benthamiana Identify a Candidate Effector of the Wheat Yellow Rust Pathogen that Associates with Processing Bodies. PLoS ONE 11(2):e0149035

Weissgerber TL, Milic NM, Winham SJ, Garovic VD (2015) Beyond Bar and Line Graphs: Time for a New Data Presentation Paradigm. PLoS Biol 13(4):e1002128

https://cran.r-project.org/

http://ggplot2.org/

* Distinct Flow Graphs and Data (Using Categories)
* *Distinct Flows by Malicious Category Using Full Flow Names* This graph depicts the frequency of flows appearing within each Malicious cateogry defined by the MalGenome project, and includes the popular applications we processed under the "Normal" category for comparison purposes. The frequency is defined by the number of applications within a category that use a particular flow, divided by the total number of applications in that category, and is represented by the size of the marks in the scatter plot.
* *Distinct Flow Categories by Malicious Category, Level 1* This graph, similar to the one described above, depicts the frequency of flow minus one level of distinction. For example, the flow sources android.location.Location:getLatitude and android.location.Location:getLongitude are now grouped under android.location.Location, as are their corresponding sinks.
* *Distinct Flow Categories by Malicious Category, Level 2* This graph, similar to the first one described above, depicts the frequency of flow minus two levels of distinction. For example, the flow sources android.location.Location:getLatitude and android.location.Location:getLongitude are now grouped under android.location, as are their corresponding sinks.
* *Distinct Flow Categories by Malicious Category, Level 3* This graph, similar to the first one described above, depicts the frequency of flow minus three levels of distinction. For example, the flow sources android.location.Location:getLatitude and android.location.Location:getLongitude are now grouped under android, as are their corresponding sinks.
* Distinct Flow Graphs and Data (General Malware Vs. Normal)
* *Distinct Flows Using Full Flow Names* This graph depicts the frequency of flows appearing within each Malicious cateogry defined by the MalGenome project, and includes the popular applications we processed under the "Normal" category for comparison purposes. The frequency is defined by the number of applications within a category that use a particular flow, divided by the total number of applications in that category, and is represented by the size of the marks in the scatter plot.
* *Distinct Flows Cateogories, Level 1* This graph, similar to the first graph, depicts the frequency of flow minus one level of distinction. For example, the flow sources android.location.Location:getLatitude and android.location.Location:getLongitude are now grouped under android.location.Location, as are their corresponding sinks.
* *Distinct Flows Cateogories, Level 2* This graph, similar to the first graph, depicts the frequency of flow minus one level of distinction. For example, the flow sources android.location.Location:getLatitude and android.location.Location:getLongitude are now grouped under android.location, as are their corresponding sinks.
* *Distinct Flows Categories, Level 3* This graph, similar to the first graph, depicts the frequency of flow minus one level of distinction. For example, the flow sources android.location.Location:getLatitude and android.location.Location:getLongitude are now grouped under android, as are their corresponding sinks.

Attribute info
1. Category
2. Flow Source
3. Flow Sink
4. Distinct APK count
5. Total Distinct APKs

Figures in scientific publications are critically important because they often show the data supporting key findings. Our systematic review of research articles published in top physiology journals (n = 703) suggests that, as scientists, we urgently need to change our practices for presenting continuous data in small sample size studies. Papers rarely included scatterplots, box plots, and histograms that allow readers to critically evaluate continuous data. Most papers presented continuous data in bar and line graphs. This is problematic, as many different data distributions can lead to the same bar or line graph. The full data may suggest different conclusions from the summary statistics. We recommend training investigators in data presentation, encouraging a more complete presentation of data, and changing journal editorial policies. Investigators can quickly make univariate scatterplots for small sample size studies using our Excel templates.

Additional file 6: Fig.S1 Gossypetin does not affect expression of β-, and γ-secretases and activity of β-secretase. (A to G) Time dependent β-secretase activity of mouse hippocampal lysate was measured with Relative Fluorescence Unit (RFU). Fluorescence excitation and emission wavelength was 335 nm and 495 nm respectively (A). Bar graph of RFU at each time point of 10 min (B), 20 min (C), 30 min (D), 40 min (E), 50 min (F), 60 min (G). (n = 10~12 mice per group) (H to L) Representative images of Western blot analysis for β-, γ-secretase subunits, and GAPDH (H). Bar graphs represent relative protein expression levels of BACE1 (I), Nicastrin (J), APH-1 (K), and PEN2 (L). (n = 12~15 mice per group) (M to P) Bar graphs represent relative mRNA expression level of β-, and γ-secretase subunits bace1 (M), ncstn (N), aph1 (O), pen2 (P). (n = 9~10 mice per group) Error bars represent the mean ± SD, p < 0.05, ns = not significant, two-way ANOVA followed by Tukey’s multiple comparisons test. Fig. S2 Cell type classification of brain samples. (A) UMAP plot showing all cells from the brain samples, colored by their cell types. (B) Heatmap illustrating the Z-scores of average normalized expressions of cell type markers. (C) Violin plots displaying the log-scaled number of detected genes (top), Unique Molecular Identifiers (UMIs) (middle), and the percentage of mitochondrial gene expressions (bottom) per cell for each cell type. (D) UMAP plots showing all cells from the brain samples, colored by their sampled region (left), mouse strain (middle), or drug administration (right) condition. Fig. S3 Detailed subtyping of the microglial population. (A) UMAP plots showing all microglial cells from cortex region. The cells are colored by their celltypes (left). Heatmap showing the Z-scores of average normalized expressions of representative DEGs for each cell type from cortex region (right). (B) UMAP plots showing microglial cells from cortex (left) or hippocampus (right), colored by combination of mouse strain and drug administration condition. (C) UMAP plots illustrating microglial cells from cortex (left) or hippocampus (right), colored by their inferred cell cycle. (D) Bar plots for the fraction of cortex (left) or hippocampus (right) microglial cells by sample conditions, which are the combination of mouse strain and drug administration, for each microglial subtype. Fig. S4 Differential gene expressions between vehicle- and gossypetin-treated microglia. (A) Scatter plot showing GOBP terms that are upregulated or downregulated by5xFAD construction or gossypetin administration for each microglial subtype from cortex. Significant (Fisher’s exact test, P < 0.01) terms associated with antigen presentation are colored by their biological keywords. (B) GSEA plots showing significant (P< 0.05) GOBP terms for gossypetin administration condition against vehicle treatment within 5xFAD homeostatic microglia from hippocampus region. Related to Fig. 3D. (C) Volcano plot illustrating the DEGs selected by the comparison between wild type and 5xFAD(left), or vehicle and gossypetin treated 5xFAD (right) from homeostatic microglial population of cortex region. Fig. S5 Transcriptomic transition in cortex microglia and measurement of DAM signature score. (A) Volcano plot showing significant (p < 0.05) DEGs selected by the comparison between cortex homeostatic microglia in vehicle treated wild type and 5xFAD (top left), or vehicle and gossypetin treated 5xFAD (top right). Volcano plots illustrating comparison between gossypetin administration condition against vehicle treatment within 5xFAD stage 1 DAM (bottom left) or stage 2 DAM (bottom right) from cortex are also presented. (B) Violin plot illustrating module scores for the DAM-related genes from previous studies. Cells are grouped by the combination of their mouse strain and treatment condition. (P < 0.001) Fig. S6 Gossypetin ameliorates gliosis in microglia and astrocytes. (A to D) Representative images of hippocampus (A) and cortex (C) stained with Hoechst and Iba-1. Scale bar corresponds to 200μm. Bar graph represents quantification of Iba-1 positive area in dentate gyrus of hippocampus (n = 9~12 mice per group, 3~6 slices per brain) (B) and cortex (n = 9~12 mice per group, 3~6 slices per brain) (D). (E to H) Representative images of hippocampus (E) and cortex (G) stained with Hoechst and GFAP. Scale bar corresponds to 200μm. Bar graph represents quantification of GFAP positive area in dentate gyrus of hippocampus (n = 9~12 mice per group, 3~6 slices per brain) (F) and cortex (n = 9~12 mice per group, 3~5 slices per brain) (H). The error bars represent the mean ± SEM.**p <0.0001, ***p < 0.001, **p < 0.01, ns = not significant, two-way ANOVA followed by Tukey’s multiple comparisons test (B, D, F and H). Fig. S7 Gossypetin increases Aβ phagocytic capacity and dynamics of BV2 microglial cell line. (A) Representative images of BV2 cells treated with 488-Aβ and stained with Hoechst and Iba-1. Gossypetin (25μM) was pretreated for 24 h before 488-Aβ treatment. Scale bar corresponds to 100μm. (B). Bar graph represents quantification of area of internalized 488-Aβ in BV2 (n= 3 per group, 253~656 cells per sample). (C) Line graph represents quantification of fluorescent area generated by internalized 488-Aβ in BV2 in a time dependent manner (n = 3 per group, 107~347 cells per sample). The error bars represent the mean ± SEM. ****p <0.0001, *p < 0.05, two-way ANOVA followed by Tukey’s multiple comparisons test (C), Student’s t test (B).

Domestic Earnings, Ratings, Titles, and Franchises for Movies

An In-Depth Investigation

By Kiersten Rule [source]

About this dataset

This dataset provides insight into the performance of movie franchises, with detailed information on domestic earnings, ratings, and information on each movie. Featuring data from over a decade of films released in North America from 2005 - 2018, we've collected a wealth of data to help analyze the trends that have emerged over time. From film budgets to box-office grosses, vote averages to release dates - you can explore how various studios and movies have impacted the industry by mining this database. Analyze the success of your favorite franchises or compare different plots and themes across genres! So dive in and uncover what makes a movie franchise great!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

• Compare movie franchises within the same studio – Look at trends such as average runtime or budget over time or compare one franchise to another (e.g., Marvel vs DC).

• Analyze box office results by rating – It can be useful to compare which types of movies draw better audiences by looking at their respective box office totals per rating (e.g., R-rated vs PG-13). This can help you decide which genres do better within certain ratings systems that may be beneficial in targeting an audience with a similar demographic.

• Use data visualization techniques – Manipulate and visualize the data set with charts and graphs to gain valuable insights into how certain movie characteristics influence overall success (e.g., use bar graphs and scatter plots to look at relationships between release year/budget/runtime etc).

• Utilize release date analysis - This dataset gives you comprehensive information about when different movies were released, so you can use this information to analyze whether there are any benefits targeting particular months/seasons or avoiding them altogether (e.g., does Christmas offer greater success than summer for family films?).

With these tips in mind, this dataset should provide helpful insights into an understanding of what factors contribute most significantly towards the success of both individual films and major movie franchises!

Research Ideas

• Analyzing the correlation between movie budget and lifetime gross earnings to determine optimum budgets for certain types of movies.
• Tracking the average ratings and reviews over time to see if certain studios are consistently making quality films or if there is a decline in their ratings and reviews.
• Comparing movie release dates against viewer ratings, reviews and lifetime gross revenue over time to determine which months of the year are most lucrative for releasing movies

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

See the dataset description for more information.

Columns

File: MovieFranchises.csv | Column name | Description | |:-------------------|:-----------------------------------------------------------------------| | Title | The title of the movie. (String) | | Lifetime Gross | The total amount of money the movie has earned domestically. (Integer) | | Year | The year the movie was released. (Integer) | | Studio | The studio that produced the movie. (String) | | Rating | The rating of the movie e.g. PG-13, R etc. (String) | | Runtime | The length of the movie in minutes. (Integer) | | Budget | The budget of the movie. (Integer) | | ReleaseDate | The date that the movie was released. (Date) | | VoteAvg | Average rating from users. (Float) | | VoteCount | Total number of votes from users. (Integer) |

Acknowledgements

If you use this dataset in your research, please credit the original authors. If you use this dataset in your research, please credit Kiersten Rule.

Large-scale white matter pathways crisscrossing the cortex create a complex pattern of connectivity that underlies human cognitive function. Generative mechanisms for this architecture have been difficult to identify in part because little is known in general about mechanistic drivers of structured networks. Here we contrast network properties derived from diffusion spectrum imaging data of the human brain with 13 synthetic network models chosen to probe the roles of physical network embedding and temporal network growth. We characterize both the empirical and synthetic networks using familiar graph metrics, but presented here in a more complete statistical form, as scatter plots and distributions, to reveal the full range of variability of each measure across scales in the network. We focus specifically on the degree distribution, degree assortativity, hierarchy, topological Rentian scaling, and topological fractal scaling—in addition to several summary statistics, including the mean clustering coefficient, the shortest path-length, and the network diameter. The models are investigated in a progressive, branching sequence, aimed at capturing different elements thought to be important in the brain, and range from simple random and regular networks, to models that incorporate specific growth rules and constraints. We find that synthetic models that constrain the network nodes to be physically embedded in anatomical brain regions tend to produce distributions that are most similar to the corresponding measurements for the brain. We also find that network models hardcoded to display one network property (e.g., assortativity) do not in general simultaneously display a second (e.g., hierarchy). This relative independence of network properties suggests that multiple neurobiological mechanisms might be at play in the development of human brain network architecture. Together, the network models that we develop and employ provide a potentially useful starting point for the statistical inference of brain network structure from neuroimaging data.

Figure S1, Spatial similarity of ICA-derived RSFC maps. Group-level RSFC maps for session 1 and session 2 and their Pearson correlation are displayed in the first to third columns. Figures (A) to (C) correspond to the RSFC data derived from HbO, HbR, and HbT, respectively. High similarity between sessions was observed in both the qualitative visual inspection and quantitative correlational analysis. Figure S2, Reliability analysis of ICA-derived RSFC maps. The first to third columns correspond to the data derived from HbO, HbR, and HbT, respectively. (A, B) The TRT reliability of RSFC maps and their corresponding reliability distributions. The reliability displays approximately normal configuration for all 1035 (i.e., 46×45/2) connections. The connections exhibit good reliability across HbO (mean ICC values 0.63), HbR (0.68) and HbT (0.65). (C) The relationship between RSFC strength and reliability as assessed by scatterplots. Each dot represents the group-level RSFC strength and the corresponding ICC value at the same connections. The trend lines were obtained by a linear least-squares fit method. Significant (p<0.05) positive correlations were found for HbO signals, suggesting stronger RSFC leads to higher reliability for this signal. Figure S3, TRT reliability of ICA-derived global network metrics as a function of sparsity threshold. (A–C) The global metric reliability was derived from HbO, HbR, and HbT, respectively. Five colors correspond to five different reliability grades. The red, yellow, green, cyan, and blue colors represent excellent ( 0.75< ICC <1), good (0.6< ICC <0.75), fair (0.4< ICC <0.6), low (0.25< ICC <0.4), and poor (ICC<0.25) reliability of global network metrics, respectively. Cp, Lp, γ, λ, and σ denote the clustering coefficient, characteristic path length, normalized clustering coefficient, normalized characteristic path length, and small-world, respectively. Eloc and Eglob denote local efficiency and global efficiency, respectively. Q, β, and r denote modularity, hierarchy, and assortativity, respectively. Figure S4, TRT reliability of ICA-derived nodal centrality metrics as a function of sparsity threshold. (A–C) The nodal metric reliability was derived from HbO, HbR, and HbT, respectively. The five colors correspond to five different reliability grades: red, yellow, green, cyan, and blue represent excellent (0.75< ICC <1), good (0.6< ICC <0.75), fair (0.4< ICC <0.6), low (0.25< ICC <0.4), and poor (ICC<0.25) reliability of the nodal centrality metrics, respectively. Figure S5, Threshold-independent reliability analysis of ICA-derived nodal centrality metrics. The areas under the curves (AUCs) of each nodal metric were used to provide threshold-independent reliability evaluation. (A–C) The nodal reliability was derived from HbO, HbR, and HbT, respectively. Different colors in the nodes correspond to different reliability grades: red, yellow, green, cyan, and blue colors represent excellent ( 0.75< ICC <1), good (0.6< ICC <0.75), fair (0.4< ICC <0.6), low (0.25< ICC <0.4), and poor (ICC<0.25) reliability of the nodal centrality metrics, respectively. Table S1, Pearson correlations at individual-level ICA-derived RSFC maps between sessions. Table S2, Statistical comparisons of the ICA-derived global network metrics (across subjects) between sessions. (DOC)

Northern Flicker Divorce and Breeding

17 years of Reproductive Performance

By [source]

About this dataset

This dataset offers an extensive look into 17 years of the mating behavior and performance of 1793 breeding pairs of Northern Flickers (Colaptes auratus), a migratory woodpecker with a high annual mortality rate. It provides vital insight into how divorce affects the reproductive success of male and female Northern Flickers, as well as how these strategies can change over time as a result of environmental conditions or population dynamics.

By looking at this data, researchers can gain an understanding of the adaptive strategies employed by Northern Flickers to optimize their reproductive success. This may include finding a new mate quickly or using bet-hedging strategies intended to maximize their chances at successful breeding in spite of environmental obstacles they may face. Studying the divorce patterns uncovered in this dataset is essential for gaining an accurate picture of which strategies are most adaptive, effective and sustainable for these creatures over time.

In addition to important information on each breeding pair's ID, age, clutch size, hatch success and fledglings performance - columns included in this dataset provide another unique glimpse into post-divorce relationships with brand new mates taken in the season following separation from prior associates. The thorough coverage on multiple levels present here makes it perfect for researchers seeking further investigation into this fascinating species' role within broad ecosystems across North America by more effectively accounting for individual behavior differences among individuals within one local population system: that associated with reproduction success after dissolution or downsizing post partnership arrangements among flicker birds everywhere!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset contains 17 years of longitudinal data on the mating behavior and performance of more than 1700 breeding pairs of Northern Flickers. It includes information about each pair, such as their age, primary cavity area (PCA), adjusted laying date, clutch size and hatch success rate. This dataset can be used to study how divorce affects the reproductive success of male and female Northern Flickers and how these patterns may be changing over time.

Researchers can use this data to analyze the differences between retained and divorced pairs, as well as to understand a bird's adaptive strategies in order to optimize their reproductive success. This dataset also offers a wealth of information that could be useful for scientists studying the mating behavior and reproduction habits of Northern Flickers.

To use this dataset effectively:

• Make sure you understand what each column means - key columns are 'case' (the unique identifier for each individual breeding pair), 'maleage', 'femaleage', 'malePCA' (primary cavity area), 'femalePCA', 'adjustedlaydate', 'clutchsize' (number of eggs laid) & ‘hatchsuccess’ (percentage that hatched).
• Select relevant variables for your research question or hypothesis; exclude any irrelevant data points or columns which will not help answer your question or prove your hypothesis true/false
• Create visualisations & graphs from your selected variables – pie charts, bar graphs & scatter plots are all useful ways to present trends in the data

• Analyze clusters within these visuals: identify areas where trends tend differ meaningfully compared with other groups – is one age group faring better/worse than another? Compare time-series graphs involving different values over time – do certain variables reach a peak at certain times? Can you identify patterns in either outcome or nesting behaviour?

• Finally come up with conclusions based off both qualitative observations taken from the analysis process, valuable insights learned throughout it & any tangible inferences drawn from them

Research Ideas

• Analyzing the differences in reproductive success between retained and divorced pairs of Northern Flickers to gain insight into the adaptive strategies they employ.
• Studying how divorce patterns may change over time due to changing environmental conditions or population dynamics.
• Examining the impact of different factors, such as age and cavity size, on breeding success post-divorce in order to inform conservation initiatives aimed at protecting this species

Acknowledgements

If you use this dataset in your research, please credit the original aut...