masster 0.5.28__py3-none-any.whl → 0.6.2__py3-none-any.whl

masster/study/plot.py

@@ -2955,6 +2955,203 @@ def plot_tic(
     return p
 
 
+def plot_heatmap(
+    self,
+    filename=None,
+    width=800,
+    height=600,
+    cmap="viridis",
+    title="Consensus Matrix Heatmap",
+    quant="chrom_area",
+    samples=None,
+):
+    """
+    Plot a heatmap of the consensus matrix data.
+
+    Samples are ordered from left to right, features are ordered by m/z from top to bottom.
+    Values are log10 transformed for better visualization.
+
+    Parameters:
+        filename (str, optional): Path to save the plot
+        width (int): Plot width in pixels (default: 800)
+        height (int): Plot height in pixels (default: 600)
+        cmap (str): Colormap name (default: "viridis")
+        title (str): Plot title (default: "Consensus Matrix Heatmap")
+        quant (str): Quantification method column name (default: "chrom_area")
+        samples: Sample identifier(s) to include. Can be:
+                - None: include all samples (default)
+                - int: single sample_uid
+                - str: single sample_name
+                - list: multiple sample_uids or sample_names
+    """
+    from bokeh.plotting import figure
+    from bokeh.models import LinearColorMapper, ColorBar, BasicTicker
+    from bokeh.transform import transform
+    import numpy as np
+    import pandas as pd
+
+    # Get consensus matrix
+    matrix_df = self.get_consensus_matrix(quant=quant, samples=samples)
+
+    if matrix_df is None or matrix_df.is_empty():
+        self.logger.error("No consensus matrix available for heatmap.")
+        return
+
+    # Get m/z values for each consensus_uid to sort by
+    if self.consensus_df is None or self.consensus_df.is_empty():
+        self.logger.error("No consensus_df available for sorting features by m/z.")
+        return
+
+    # Join with consensus_df to get m/z values
+    matrix_with_mz = matrix_df.join(
+        self.consensus_df.select(["consensus_uid", "mz"]),
+        on="consensus_uid",
+        how="left",
+    )
+
+    # Sort by m/z (ascending - lowest m/z at top)
+    matrix_with_mz = matrix_with_mz.sort("mz")
+
+    # Remove the m/z column after sorting
+    matrix_sorted = matrix_with_mz.drop("mz")
+
+    # Extract consensus_uid and sample columns
+    consensus_uids = matrix_sorted["consensus_uid"].to_list()
+    sample_cols = [col for col in matrix_sorted.columns if col != "consensus_uid"]
+
+    # Convert to pandas for easier heatmap processing
+    matrix_pd = matrix_sorted.select(sample_cols).to_pandas()
+
+    # Apply log10 transformation (add 1 to avoid log(0))
+    matrix_log = np.log10(matrix_pd.values + 1)
+
+    # Prepare data for Bokeh heatmap
+    # Create a list of (sample, feature, value) tuples
+    heatmap_data = []
+    for i, feature_idx in enumerate(range(len(consensus_uids))):
+        for j, sample in enumerate(sample_cols):
+            value = matrix_log[feature_idx, j]
+            heatmap_data.append({
+                "sample": sample,
+                "feature": str(consensus_uids[feature_idx]),
+                "feature_idx": str(i),  # Use string index for y-axis position
+                "value": value,
+            })
+
+    # Convert to DataFrame for Bokeh ColumnDataSource
+    heatmap_df = pd.DataFrame(heatmap_data)
+
+    from bokeh.models import ColumnDataSource
+
+    source = ColumnDataSource(heatmap_df)
+
+    # Handle colormap using cmap.Colormap
+    try:
+        # Get colormap palette using cmap
+        if isinstance(cmap, str):
+            colormap = Colormap(cmap)
+            # Generate 256 colors and convert to hex
+            import matplotlib.colors as mcolors
+
+            colors = colormap(np.linspace(0, 1, 256))
+            palette = [mcolors.rgb2hex(color) for color in colors]
+        else:
+            colormap = cmap
+            # Try to use to_bokeh() method first
+            try:
+                palette = colormap.to_bokeh()
+                # Ensure we got a color palette, not another mapper
+                if not isinstance(palette, (list, tuple)):
+                    # Fall back to generating colors manually
+                    import matplotlib.colors as mcolors
+
+                    colors = colormap(np.linspace(0, 1, 256))
+                    palette = [mcolors.rgb2hex(color) for color in colors]
+            except AttributeError:
+                # Fall back to generating colors manually
+                import matplotlib.colors as mcolors
+
+                colors = colormap(np.linspace(0, 1, 256))
+                palette = [mcolors.rgb2hex(color) for color in colors]
+    except (AttributeError, ValueError, TypeError) as e:
+        # Fallback to viridis if cmap interpretation fails
+        self.logger.warning(f"Could not interpret colormap '{cmap}': {e}, falling back to viridis")
+        from bokeh.palettes import viridis
+
+        palette = viridis(256)
+
+    # Create color mapper
+    color_mapper = LinearColorMapper(
+        palette=palette,
+        low=heatmap_df["value"].min(),
+        high=heatmap_df["value"].max(),
+    )
+
+    # Create figure with categorical ranges for both axes
+    p = figure(
+        width=width,
+        height=height,
+        title=title,
+        x_range=sample_cols,
+        y_range=[str(i) for i in range(len(consensus_uids))],
+        toolbar_location="above",
+        tools="pan,wheel_zoom,box_zoom,reset,save,hover",
+        tooltips=[
+            ("Sample", "@sample"),
+            ("Feature UID", "@feature"),
+            ("log10(Value+1)", "@value{0.00}"),
+        ],
+    )
+
+    # Draw rectangles for heatmap
+    p.rect(
+        x="sample",
+        y="feature_idx",
+        width=1,
+        height=1,
+        source=source,
+        fill_color=transform("value", color_mapper),
+        line_color=None,
+    )
+
+    # Add colorbar
+    color_bar = ColorBar(
+        color_mapper=color_mapper,
+        width=8,
+        location=(0, 0),
+        title=f"log10({quant}+1)",
+        ticker=BasicTicker(desired_num_ticks=8),
+    )
+    p.add_layout(color_bar, "right")
+
+    # Style the plot
+    p.axis.axis_line_color = None
+    p.axis.major_tick_line_color = None
+    p.grid.grid_line_color = None
+    p.xaxis.major_label_orientation = 45
+    p.yaxis.axis_label = "Features (sorted by m/z)"
+    p.xaxis.axis_label = "Samples"
+
+    # Apply consistent save/display behavior
+    if filename is not None:
+        # Convert relative paths to absolute paths using study folder as base
+        import os
+
+        if not os.path.isabs(filename):
+            filename = os.path.join(self.folder, filename)
+
+        # Convert to absolute path for logging
+        abs_filename = os.path.abspath(filename)
+
+        # Use isolated file saving
+        _isolated_save_plot(p, filename, abs_filename, self.logger, "Heatmap Plot")
+    else:
+        # Show in notebook when no filename provided
+        _isolated_show_notebook(p)
+
+    return p
+
+
 def plot_pca(self, *args, **kwargs):
     """Deprecated: Use plot_samples_pca instead."""
     import warnings

masster/study/study.py

@@ -14,8 +14,8 @@ Main class:
         consensus_select/filter/delete
     - Retrieval: get_consensus, get_chrom, get_samples, get_*_stats, get_*_matrix
     - Plotting: plot_alignment, plot_samples_pca/umap/2d, plot_tic/bpc/eic, plot_chrom,
-        plot_rt_correction, plot_consensus_2d/stats
-    - Export: export_mgf, export_mztab, export_xlsx, export_parquet
+        plot_rt_correction, plot_consensus_2d/stats, plot_heatmap
+    - Export: export_mgf, export_mztab, export_excel, export_parquet
     - Identification: lib_load, identify, get_id, id_reset, lib_reset
     - Parameters: get/update parameters, update_history
 
@@ -96,6 +96,7 @@ from masster.study.plot import plot_bpc
 from masster.study.plot import plot_tic
 from masster.study.plot import plot_eic
 from masster.study.plot import plot_rt_correction
+from masster.study.plot import plot_heatmap
 from masster.study.processing import align
 from masster.study.merge import merge
 from masster.study.processing import integrate
@@ -108,7 +109,7 @@ from masster.study.parameters import update_parameters
 from masster.study.parameters import get_parameters_property
 from masster.study.parameters import set_parameters_property
 from masster.study.save import save, save_consensus, save_samples
-from masster.study.export import export_mgf, export_mztab, export_xlsx, export_parquet
+from masster.study.export import export_mgf, export_mztab, export_excel, export_parquet
 from masster.study.id import lib_load, identify, get_id, id_reset, lib_reset, _get_adducts
 from masster.study.importers import import_oracle
 
@@ -429,6 +430,7 @@ class Study:
     plot_rt_correction = plot_rt_correction
     plot_tic = plot_tic
     plot_eic = plot_eic
+    plot_heatmap = plot_heatmap
 
     # === Analysis Operations ===
     analyze_umap = analyze_umap
@@ -436,7 +438,7 @@ class Study:
     # === Export Operations ===
     export_mgf = export_mgf
     export_mztab = export_mztab
-    export_xlsx = export_xlsx
+    export_excel = export_excel
     export_parquet = export_parquet
 
     # === Identification and Library Matching ===

masster/study/study5_schema.json

@@ -261,6 +261,21 @@
       },
       "ms1_spec": {
         "dtype": "pl.Object"
+      },
+      "id_top_name": {
+        "dtype": "pl.Utf8"
+      },
+      "id_top_class": {
+        "dtype": "pl.Utf8"
+      },
+      "id_top_adduct": {
+        "dtype": "pl.Utf8"
+      },
+      "id_top_score": {
+        "dtype": "pl.Float64"
+      },
+      "id_source": {
+        "dtype": "pl.Utf8"
       }
     }
   },

masster/wizard/wizard.py

@@ -200,12 +200,12 @@ class wizard_def:
         # Set default adducts based on polarity if not provided
         if not self.adducts:
             if self.polarity and self.polarity.lower() in ["positive", "pos"]:
-                self.adducts = ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"]
+                self.adducts = ["+H:1:0.8", "+Na:1:0.1", "+NH4:1:0.1"]
             elif self.polarity and self.polarity.lower() in ["negative", "neg"]:
-                self.adducts = ["H-1:-:1.0", "CH2O2:0:0.5"]
+                self.adducts = ["-H:-1:1.0", "+CH2O2:0:0.5"]
             else:
                 # Default to positive if polarity is None or unknown
-                self.adducts = ["H:+:0.8", "Na:+:0.1", "NH4:+:0.1"]
+                self.adducts = ["+H:1:0.8", "+Na:1:0.1", "+NH4:1:0.1"]
 
         # Validate num_cores
         max_cores = multiprocessing.cpu_count()
@@ -676,9 +676,7 @@ class Wizard:
             "        ",
             "        # Step 3: Create and configure study",
             '        print("\\nStep 3/7: Initializing study...")',
-            "        study = Study(folder=PARAMS['folder'])",
-            "        study.polarity = PARAMS['polarity']",
-            "        study.adducts = PARAMS['adducts']",
+            "        study = Study(folder=PARAMS['folder'], polarity=PARAMS['polarity'], adducts=PARAMS['adducts'])",
             "        ",
             "        # Step 4: Add sample5 files to study",
             '        print("\\nStep 4/7: Adding samples to study...")',
@@ -692,6 +690,12 @@ class Wizard:
             "            rt_tol=PARAMS['rt_tol']",
             "        )",
             "        ",
+            "        # Check that more than 1 file has been loaded",
+            "        if len(study.samples) <= 1:",
+            '            print("\\nWARNING: Study merging requires more than 1 sample file.")',
+            '            print(f"Only {len(study.samples)} sample(s) loaded. Terminating execution.")',
+            "            return False",
+            "        ",
             "        study.merge(",
             '            method="qt",',
             "            min_samples=PARAMS['min_samples_per_feature'],",
@@ -705,7 +709,7 @@ class Wizard:
             "        # Step 6/7: Saving results",
             '        print("\\nStep 6/7: Saving results...")',
             "        study.save()",
-            "        study.export_xlsx()",
+            "        study.export_excel()",
             "        study.export_mgf()",
             "        study.export_mztab()",
             "        ",
@@ -764,14 +768,9 @@ class Wizard:
             'app = marimo.App(width="medium")',
             "",
             "@app.cell",
-            "def __():",
-            "    import marimo as mo",
-            "    return (mo,)",
-            "",
-            "@app.cell",
             "def __(mo):",
             '    mo.md(r"""',
-            "    # MASSter Interactive Analysis",
+            "    ## MASSter Interactive Analysis",
             "    ",
             f"    **Source:** {source_info.get('number_of_files', 0)} files detected",
             f"    **Polarity:** {source_info.get('polarity', 'unknown')}",
@@ -1382,7 +1381,7 @@ class Wizard:
             "        # Step 6/7: Saving results",
             '        print("\\nStep 6/7: Saving results...")',
             "        study.save()",
-            "        study.export_xlsx()",
+            "        study.export_excel()",
             "        study.export_mgf()",
             "        study.export_mztab()",
             "        ",

{masster-0.5.28.dist-info → masster-0.6.2.dist-info}/METADATA

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.28
+Version: 0.6.2
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster
 Project-URL: documentation, https://github.com/zamboni-lab/masster#readme
 Project-URL: Third-Party Licenses, https://github.com/zamboni-lab/masster/blob/main/THIRD_PARTY_NOTICES.md
-Author: Zamboni Lab
+Author: Zamboni Lab, ETH Zurich
 License:                     GNU AFFERO GENERAL PUBLIC LICENSE
                                Version 3, 19 November 2007
         
@@ -734,19 +734,19 @@ Description-Content-Type: text/markdown
 
 ## Background and motivation
 
-MASSter is actively used, maintainted, and developed by the Zamboni Lab at ETH Zurich. The project started because many needs of were unmatched by the "usual" software packages (mzmine, msdial, W4M, ...), e.g. performance, scalability, sensitivity, robustness, speed, rapid implementation of new features, embedding in ETL systems, and so on. 
+MASSter is actively used, maintained, and developed by the Zamboni Lab at ETH Zurich. The project started because many needs were unmet by the "usual" software packages (mzMine, MS-DIAL, Workflow4Metabolomics (W4M), ...), for example performance, scalability, sensitivity, robustness, speed, rapid implementation of new features, and embedding in ETL systems.
 
-All methods include a long list of parameters, and might wrap alternative algorithms. These are only relevant for advanced users. We recommend running the processing methods with defaults, or using the Wizard.  
+All methods include many parameters and may wrap alternative algorithms. These options are primarily relevant for advanced users. We recommend running the processing methods with the defaults or using the Wizard.
 
 ## Content
 
 MASSter is designed to deal with DDA data, and hides functionalities for DIA and ZTScan DIA data. The sample-centric feature detection uses OpenMS, which is both accurate and fast, and it was wrapped with additional code to improve isotope and adduct detection. All other functionalities are own implementations: centroiding, RT alignment, adduct and isotopomer detection, merging of multiple samples, gap-filling, quantification, etc. 
 
-MASSter was engineered to maximize quality of results, sensitivity, scalability, and also speed. Yes, it's Python which is notoriously slower than other languages, but considerable time was spent in speeding up everything, including the systematic use of [polars](https://pola.rs/), numpy vectorization, multiprocessing, chunking, etc. MASSter was tested with studies with 3000+ LC-MS/MS samples (1 Mio MS2 spectra), and it autonomously completed analysis within a few hours. 
+MASSter was engineered to maximize result quality, sensitivity, scalability, and speed. Yes, it's Python, which can be slower than other languages, but considerable effort was spent on optimizations, including the systematic use of [Polars](https://pola.rs/), NumPy vectorization, multiprocessing, and chunking. MASSter has been tested on studies with 3,000+ LC–MS/MS samples (≈1 million MS2 spectra) and autonomously completed analyses within a few hours.
 
 ## Architecture
 
-MASSter defines own classes for Spectra, Chromatograms, Libraries, Samples, and Studies (= bunch of samples, i.e. a LC-MS sequence). Users will deal mostly with one Study() object at the time. Sample() objects are created when analyzing a batch - and saved for caching -, or will be used only for development, troubleshooting, or to generate illustrations. 
+MASSter defines classes for Spectra, Chromatograms, Libraries, Samples, and Studies (a Study is a collection of samples, i.e. an LC–MS sequence). Users will typically work with a single `Study` object at a time. `Sample` objects are created when analyzing a batch (and saved for caching), or used for development, troubleshooting, or generating illustrations.
 
 The analysis can be done in scripts (without user intervention, e.g. by the integrated Wizard), or interactively in notebooks, i.e. [marimo](https://marimo.io/) or [jupyter](https://jupyter.org/).
 
@@ -756,9 +756,9 @@ You'll need to install Python (3.10-3.13, 3.14 has not been tested yet).
 
 MASSter reads raw (Thermo), wiff (SCIEX), or mzML data. Reading vendor formats relies on .NET libraries, and is only possible in Windows. On Linux or MacOS, you'll be forced to use mzML data.
 
-**It's recommended to use data in either vendor's raw format (wiff and raw) or mzML in profile data.** MASSter includes a sophisticated and sufficiently fast centroiding algorithm that works well across the full dynamic range and will only act on the spectra that are relevant. In our tests with data from different vendors, the centroiding performed much better than most Vendor's implementations (that are primarily proteomics-centric). 
+**It's recommended to use data in either the vendor's raw formats (WIFF and Thermo RAW) or mzML in profile mode.** MASSter includes a sophisticated and sufficiently fast centroiding algorithm that works well across the full dynamic range and will only act on spectra that are relevant. In our tests with data from different vendors, the centroiding performed much better than most vendor implementations (which are primarily proteomics-centric).
 
-If still want to convert raw data to centroided mzML, please use (CentroidR)[https://github.com/Adafede/CentroidR/tree/0.0.0.9001]. 
+If you still want to convert raw data to centroided mzML, please use CentroidR: https://github.com/Adafede/CentroidR/tree/0.0.0.9001
 
 ## Installation
 
@@ -769,7 +769,7 @@ pip install masster
 ## Getting started
 **The quickest way to use, or learn how to use MASSter, is to use the Wizard** which we integrated and, ideally, takes care of everything automatically. 
 
-The Wizard only needs to know where to find the MS files and were the store the results.
+The Wizard only needs to know where to find the MS files and where to store the results.
 ```python
 from masster import Wizard
 wiz = Wizard(
@@ -780,15 +780,15 @@ wiz = Wizard(
 wiz.test_and_run()
 ```
 
-This will trigger the analysis of raw data, and the creation of a script to process all samples and then assemble the study. The whole processing will be stored as `1_masster_workflow.py` in the output folder. The wizard will test once and, if successull, run the full workflow using parallel processes. Once the processing is over you, navigate to `folder` to see what happened...
+This will trigger the analysis of raw data, and the creation of a script to process all samples and then assemble the study. The whole processing will be stored as `1_masster_workflow.py` in the output folder. The wizard will test once and, if successful, run the full workflow using parallel processes. Once the processing is over you, navigate to `folder` to see what happened...
 
 If you want to interact with your data, we recommend using [marimo](https://marimo.io/) or [jupyter](https://jupyter.org/) and open the `*.study5` file, for example:
 
 ```bash
-# use marimo to open the script created by marino
-marimo edit '..\..folder_to_store_results\2_interactive_analysis.py'
-# or, if you use uv to manage an environment with masster 
-uv run marimo edit '..\..folder_to_store_results\2_interactive_analysis.py'
+# use marimo to open the script created by marimo
+marimo edit '..\\..\\folder_to_store_results\\2_interactive_analysis.py'
+# or, if you use uv to manage an environment with masster
+uv run marimo edit '..\\..\\folder_to_store_results\\2_interactive_analysis.py'
 ```
 
 ### Basic Workflow for analyzing LC-MS study with 1-1000+ samples
@@ -833,6 +833,7 @@ study.save()
 study.plot_samples_pca()
 study.plot_samples_umap()
 study.plot_samples_2d()
+study.plot_heatmap()
 
 # To know more about the available methods...
 dir(study)
@@ -874,7 +875,7 @@ sample.plot_2d()
 sample.plot_features_stats()
 
 # explore methods
-dir(study)
+dir(sample)
 ```
 
 ## Disclaimer
@@ -885,11 +886,9 @@ dir(study)
 - **Backward compatibility**: We do not guarantee backward compatibility between versions. Breaking changes may occur as we improve the software
 - **Performance**: While optimized for our workflows, performance may vary depending on your data and system configuration
 - **Results**: We do our best to ensure accuracy, but you should validate results independently for your research
-- **Support**: This is an academic project with limited resources. Community support is available through GitHub issues, but we cannot guarantee response times
+- **Support**: This is an academic project with limited resources. At the moment, we do not provide external user support.
 - **Production use**: If you plan to use MASSter in production or critical workflows, thorough testing with your data is recommended
 
-We welcome feedback, bug reports, and contributions via GitHub!
-
 ## License
 GNU Affero General Public License v3
 

{masster-0.5.28.dist-info → masster-0.6.2.dist-info}/RECORD

@@ -1,53 +1,54 @@
 masster/__init__.py,sha256=B7zftzdElF2Wb5B7KvkD6TONnMIY-Jxeen3s49dgmzs,1029
-masster/_version.py,sha256=1ymsIuIjSvggBFAIWxPqWntiqdxjPZEjAmDJy3vRsLE,257
+masster/_version.py,sha256=F1HdyCdWIoQe5IvLkXjg59Gp9roKbCXkIP_h-VUp0ME,256
 masster/chromatogram.py,sha256=iYpdv8C17zVnlWvOFgAn9ns2uFGiF-GgoYf5QVVAbHs,19319
-masster/logger.py,sha256=oHEFPH1LzBHbmeP9WFaRZCWyqd14GasJjZMLI8a4O3I,19439
+masster/logger.py,sha256=MbQ3uLI3N0G3tnvtGIJZN_HEwjKRfIhBVZmIzUev7oc,18827
 masster/spectrum.py,sha256=LlmxrI5MFS3aPrGSdqUSKVY0rJnKeBh3Frdh6a4dPvA,49722
-masster/data/libs/aa.csv,sha256=Sja1DyMsiaM2NfLcct4kAAcXYwPCukJJW8sDkup9w_c,1924
-masster/data/libs/ccm.csv,sha256=Q6nylV1152uTpX-ydqWeGrc6L9kgv45xN_fBZ4f7Tvo,12754
-masster/data/libs/urine.csv,sha256=iRrR4N8Wzb8KDhHJA4LqoQC35pp93FSaOKvXPrgFHis,653736
+masster/data/libs/aa_nort.json,sha256=tadOrusSrcAIxTcvME-Vy_PVNQskCU4jN9XVDeYhq4o,6052
+masster/data/libs/ccm_nort.json,sha256=9Dq_JqLqQ700Nri6LDe7stBUQkiTGXukK2GqsFaOrTw,35425
 masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.timeseries.data,sha256=01vC6m__Qqm2rLvlTMZoeKIKowFvovBTUnrNl8Uav3E,24576
 masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.wiff,sha256=go5N9gAM1rn4PZAVaoCmdteY9f7YGEM9gyPdSmkQ8PE,1447936
 masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.wiff.scan,sha256=ahi1Y3UhAj9Bj4Q2MlbgPekNdkJvMOoMXVOoR6CeIxc,13881220
 masster/data/wiff/2025_01_14_VW_7600_LpMx_DBS_CID_2min_TOP15_030msecMS1_005msecReac_CE35_DBS-ON_3.wiff2,sha256=TFB0HW4Agkig6yht7FtgjUdbXax8jjKaHpSZSvuU5vs,3252224
 masster/lib/__init__.py,sha256=TcePNx3SYZHz6763TL9Sg4gUNXaRWjlrOtyS6vsu-hg,178
-masster/lib/lib.py,sha256=SGWuiCTHc65khmLndC2cFBCO1rk8-SS6BkG4C_nOf-o,44984
+masster/lib/lib.py,sha256=j3aFmS_xohvjgVi2XrfIOcNA5v3-slusDIOqHTij-Og,45016
 masster/sample/__init__.py,sha256=HL0m1ept0PMAYUCQtDDnkdOS12IFl6oLAq4TZQz83uY,170
-masster/sample/adducts.py,sha256=ALUSeY8fDf4oWl-g1wEffBDRk_apKTDwd_FOdxtP5Es,33511
-masster/sample/h5.py,sha256=uEbsfaMgRWgADLhw3j6rdXjHqRz4bmLQKjAzXXGA12M,109285
-masster/sample/helpers.py,sha256=opitF12aS3KNfwM0GFwiITX129AAi0HXvEW32oljTL4,43627
+masster/sample/adducts.py,sha256=kVsVZTUIQsVGDgmzvkhPn-9XdilGjuNe-xqUZG--Huc,33519
+masster/sample/h5.py,sha256=80ClWBCZH8eY5hLmUIy0GRvHshq0FvT4LWKmQ9Hn7L4,116017
+masster/sample/helpers.py,sha256=ldQ05ha4whONSB-5YouZEXf0E9v90AnAN7fePAc3Y4s,48094
+masster/sample/id.py,sha256=f2Y3JFn_0PPAscnfpllDR_82tiHH1j-SuxahiGsBjjU,46428
+masster/sample/importers.py,sha256=XLZ6kIjuJkmA6CklMH1JD-awBnpafqxRXYnx2qfew_Q,28794
 masster/sample/lib.py,sha256=YIeG9nBiSMllu3xkqcQXnMe6pXJ9sJSN7un8SORgVJ4,33968
 masster/sample/load.py,sha256=tpPqRZtmfOY1AibHBBqcYfPD8SoI8Uue-IiDOA20DYc,48402
 masster/sample/parameters.py,sha256=Gg2KcuNbV_wZ_Wwv93QlM5J19ji0oSIvZLPV1NoBmq0,4456
-masster/sample/plot.py,sha256=fQWWG-BeJz3XdtIVYTlV1_mM5xqZw5cYjQEmJU68t2U,105244
+masster/sample/plot.py,sha256=CHfsAIeTxxjXwCd4E6rAKTZdtjtq_cpDNoYAo0Gi0zs,110454
 masster/sample/processing.py,sha256=7FmlDO_vsVbUfI62QSoHXKkgGtfjMLHLRdvaB4KdmP4,56018
 masster/sample/quant.py,sha256=tHNjvUFTdehKR31BXBZnVsBxMD9XJHgaltITOjr71uE,7562
-masster/sample/sample.py,sha256=-xliZfE_6I0tRkMZa8yChiMtdbKXdLnF4xnD-LtIgZY,22078
-masster/sample/sample5_schema.json,sha256=H5e2T6rHIDzul2kp_yP-ILUUWUpW08wP2pEQjMR0nSk,3977
-masster/sample/save.py,sha256=RD3tRoTNy2ANKoU-oZSfu47nQ4ATSAB-Io2EN0RUZaI,37994
+masster/sample/sample.py,sha256=BJq9ArDe4mCOkwmW4yR5k7b_oPLJLu35cXXWzRYzf9o,22911
+masster/sample/sample5_schema.json,sha256=szuRsrs2o50jEjXOAT7T6zLQhZauN_0nc_605uQjgVA,5839
+masster/sample/save.py,sha256=E6dII0icr6kX3zrx7Uc0p52jBHXPmk8dQhpzmf3j3Ag,71334
 masster/sample/sciex.py,sha256=jzMrw5iKzbCFVgmgbU65eIr10eegzKng9WKx1Inl8Dg,21740
 masster/sample/thermo.py,sha256=zcH4aZg2hQnZp9rM618ZUiQXRuUqFRmVFdbCg0SnIOQ,27775
 masster/sample/defaults/__init__.py,sha256=A09AOP44cxD_oYohyt7XFUho0zndRcrzVD4DUaGnKH4,447
-masster/sample/defaults/find_adducts_def.py,sha256=bK05FcACdj0t-T8x6zWUbCzxRxbR7P0u8o8U23RIFrc,13552
+masster/sample/defaults/find_adducts_def.py,sha256=RFZGaP3VeVEnSxlqvUaHq6wl1m5mfr7yvyf7pHWgtJI,13553
 masster/sample/defaults/find_features_def.py,sha256=Bcd39uav1BniwKgrsB-I1maF3ljf4Wb1f5yv0pDYfts,17745
 masster/sample/defaults/find_ms2_def.py,sha256=mr_XtzlhYfXt7kYWVFPt1ReGqHZQDPXe-1pGND2VvV8,9844
 masster/sample/defaults/get_spectrum_def.py,sha256=o62p31PhGd-LiIkTOzKQhwPtnO2AtQDHcPu-O-YoQPs,11460
 masster/sample/defaults/sample_def.py,sha256=MWWeEexGG2Ahbs-id4uq2doIgH-Ja96GioXaSl2CxN8,15449
 masster/study/__init__.py,sha256=55axdFuqRX4aXtJ8ocnhcLB32fNtmmJpCi58moO0r4g,237
 masster/study/analysis.py,sha256=bf2o_ywvwdPz1mZAHPETCPjWbvhoL9eEl1rLaz46Rp4,82032
-masster/study/export.py,sha256=oRgM4F4hL3-nBRr_xd4KTin8WoH8QqCJnz3K_S1M14E,60258
+masster/study/export.py,sha256=fONBhPiLKGv8D3DGJNjL4uOLa41oPF7G66oeXinA2C8,69352
 masster/study/h5.py,sha256=gJRWNQxBTyFKD3qRmEbM24YZ-HdyUk-veYgwQbK0eoE,99104
 masster/study/helpers.py,sha256=pRcVvGmm6NX-GEvWfYZXZjGc_C0WyklqSQx1PdpYn2E,189694
-masster/study/id.py,sha256=dTMNdBE7eOQZdFSU0KZwd7vFpqOmNlQnLI0VGW98y8w,89570
-masster/study/importers.py,sha256=iOe9w6uEn39ShosRms8n_zIrsSBczb51CAMoMrxSUw4,13587
-masster/study/load.py,sha256=-qz9tAVYzI5is7_-z43FndcJJk95BmuMUOIxYzZoO_I,71314
-masster/study/merge.py,sha256=FEya_v2cMNvzNBtxzTv57KxfwNxT1R63LDrvnYIHORY,164557
+masster/study/id.py,sha256=iKMcxEzFpCKSBWWrBoOHWWM43tYJSRFvDqmYJTIQ1eU,92348
+masster/study/importers.py,sha256=5WhOWKOTuIX0IKAuhNIz7vYxKJ6tL0X2kvMtmfYuTRI,28946
+masster/study/load.py,sha256=GrdXuY7EFrmkqnzNk4gdqE41ufFE39pUvBrQaA7RPXA,70649
+masster/study/merge.py,sha256=6jZPaCFp4Z8lnG8ztgEeoOzoxRmULIS4SKBYoPnEaTc,171480
 masster/study/parameters.py,sha256=bTvmcwX9INxzcrEAmTiFH8qeWVhwkvMTZjuP394pz5o,3279
-masster/study/plot.py,sha256=HIz8GMxN988KDXP425cpYohCgrgMrMCWBQ2s5ncmLoI,113816
+masster/study/plot.py,sha256=2tRjZFViYq_I5ih1TruelzIdnGynKsOpnHyhTzGUr-k,120731
 masster/study/processing.py,sha256=oQGepG5-AXP9GGk8NTzl_i1ztgDp3TPwE2x15BmnpMw,57353
 masster/study/save.py,sha256=tF00anwwQDe2qxumv_4AP_1UOo0-f28Tkd2WXGyNHbI,9182
-masster/study/study.py,sha256=_IL6pCw29JI0p2ujdaMr_gsfaFkq3PFWO5NPuLpshYA,37867
-masster/study/study5_schema.json,sha256=uLA9TIb5loki87_BEdwSNyPYahwOanacYisXdIK0_Z0,8044
+masster/study/study.py,sha256=AJgIgxCXmp-hXp-4Vfuh6g-mQqVGWORRZq8NjUhiUAk,37963
+masster/study/study5_schema.json,sha256=tvlQZezS4bwRRxlUi8cpoiPIE3qTzk2WDQfZw8mE724,8359
 masster/study/defaults/__init__.py,sha256=m3Z5KXGqsTdh7GjYzZoENERt39yRg0ceVRV1DeCt1P0,610
 masster/study/defaults/align_def.py,sha256=Du0F592ej2einT8kOx8EUs610axSvur8_-6N19O-uJY,10209
 masster/study/defaults/export_def.py,sha256=eXl3h4aoLX88XkHTpqahLd-QZ2gjUqrmjq8IJULXeWo,1203
@@ -58,11 +59,11 @@ masster/study/defaults/identify_def.py,sha256=nFj-pv6q1eRgSgoRr78YEnqulPPMWo2Ju5
 masster/study/defaults/integrate_chrom_def.py,sha256=0MNIWGTjty-Zu-NTQsIweuj3UVqEY3x1x8pK0mPwYak,7264
 masster/study/defaults/integrate_def.py,sha256=Vf4SAzdBfnsSZ3IRaF0qZvWu3gMDPHdgPfMYoPKeWv8,7246
 masster/study/defaults/merge_def.py,sha256=99TJtIk7mSoq8NMJMJ4b-cy7gUUixQN69krxttBnkfA,12899
-masster/study/defaults/study_def.py,sha256=xXOAcb8hez0woWwA1_T3fcokjiLJkq3hwA3OS6elb6I,15965
+masster/study/defaults/study_def.py,sha256=kSvhiqpFp8b84vUsE8608LQsSXwz9lAPcU2BqK0T8z0,16095
 masster/wizard/__init__.py,sha256=L9G_datyGSFJjrBVklEVpZVLGXzUhDiWobtiygBH8vQ,669
-masster/wizard/wizard.py,sha256=11utDrZSt7R8D16Sl-NbRKHcgzhQEu8gW_q2V02-Qi0,66483
-masster-0.5.28.dist-info/METADATA,sha256=KbBVi4lzwtoxbw1ljv1FlxwyN3_YTs1VJcU9hvoD-_k,50869
-masster-0.5.28.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-masster-0.5.28.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
-masster-0.5.28.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-masster-0.5.28.dist-info/RECORD,,
+masster/wizard/wizard.py,sha256=e-jh8MfKIkbN9MrPh2B_OKKMexXXMFBlOFJpen2pYa0,66679
+masster-0.6.2.dist-info/METADATA,sha256=OcaQpmk_8lPnlm-SS2eMAhiIQ3BOo1yRcVjtYPMdulY,50818
+masster-0.6.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+masster-0.6.2.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
+masster-0.6.2.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+masster-0.6.2.dist-info/RECORD,,

masster/data/libs/aa.csv

@@ -1,22 +0,0 @@
-name,smiles,inchikey,formula,db_id,db
-L-Glutamic acid,N[C@@H](CCC(O)=O)C(O)=O,WHUUTDBJXJRKMK-VKHMYHEASA-N,C5H9NO4,CID:33032,pubchem
-L-Tyrosine,N[C@@H](CC1=CC=C(O)C=C1)C(O)=O,OUYCCCASQSFEME-QMMMGPOBSA-N,C9H11NO3,CID:6057,pubchem
-L-Phenylalanine,N[C@@H](CC1=CC=CC=C1)C(O)=O,COLNVLDHVKWLRT-QMMMGPOBSA-N,C9H11NO2,CID:6140,pubchem
-L-Alanine,C[C@H](N)C(O)=O,QNAYBMKLOCPYGJ-REOHCLBHSA-N,C3H7NO2,CID:5950,pubchem
-L-Proline,OC(=O)[C@@H]1CCCN1,ONIBWKKTOPOVIA-BYPYZUCNSA-N,C5H9NO2,CID:145742,pubchem
-L-Threonine,C[C@@H](O)[C@H](N)C(O)=O,AYFVYJQAPQTCCC-GBXIJSLDSA-N,C4H9NO3,CID:6288,pubchem
-L-Asparagine,N[C@@H](CC(N)=O)C(O)=O,DCXYFEDJOCDNAF-REOHCLBHSA-N,C4H8N2O3,CID:6267,pubchem
-L-Isoleucine,CC[C@H](C)[C@H](N)C(O)=O,AGPKZVBTJJNPAG-WHFBIAKZSA-N,C6H13NO2,CID:6306,pubchem
-L-Histidine,N[C@@H](CC1=CN=CN1)C(O)=O,HNDVDQJCIGZPNO-YFKPBYRVSA-N,C6H9N3O2,CID:6274,pubchem
-L-Lysine,NCCCC[C@H](N)C(O)=O,KDXKERNSBIXSRK-YFKPBYRVSA-N,C6H14N2O2,CID:5962,pubchem
-L-Serine,N[C@@H](CO)C(O)=O,MTCFGRXMJLQNBG-REOHCLBHSA-N,C3H7NO3,CID:5951,pubchem
-L-Aspartic acid,N[C@@H](CC(O)=O)C(O)=O,CKLJMWTZIZZHCS-REOHCLBHSA-N,C4H7NO4,CID:5960,pubchem
-L-Cystine,N[C@@H](CSSC[C@H](N)C(O)=O)C(O)=O,LEVWYRKDKASIDU-IMJSIDKUSA-N,C6H12N2O4S2,CID:67678,pubchem
-L-Arginine,N[C@@H](CCCNC(N)=N)C(O)=O,ODKSFYDXXFIFQN-BYPYZUCNSA-N,C6H14N4O2,CID:6322,pubchem
-L-Cysteine,N[C@@H](CS)C(O)=O,XUJNEKJLAYXESH-REOHCLBHSA-N,C3H7NO2S,CID:5862,pubchem
-L-Glutamine,N[C@@H](CCC(N)=O)C(O)=O,ZDXPYRJPNDTMRX-VKHMYHEASA-N,C5H10N2O3,CID:5961,pubchem
-L-Leucine,CC(C)C[C@H](N)C(O)=O,ROHFNLRQFUQHCH-YFKPBYRVSA-N,C6H13NO2,CID:6106,pubchem
-L-Methionine,CSCC[C@H](N)C(O)=O,FFEARJCKVFRZRR-BYPYZUCNSA-N,C5H11NO2S,CID:6137,pubchem
-L-Valine,CC(C)[C@H](N)C(O)=O,KZSNJWFQEVHDMF-BYPYZUCNSA-N,C5H11NO2,CID:6287,pubchem
-L-Tryptophan,N[C@@H](CC1=CNC2=C1C=CC=C2)C(O)=O,QIVBCDIJIAJPQS-VIFPVBQESA-N,C11H12N2O2,CID:6305,pubchem
-Glycine,NCC(O)=O,QNAYBMKLOCPYGJ-UHFFFAOYSA-N,C2H5NO2,CID:750,Glycine