masster 0.2.4__py3-none-any.whl → 0.2.5__py3-none-any.whl

masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.2.4"
+__version__ = "0.5.1"
 
 
 def get_version():

masster/sample/save.py

@@ -168,7 +168,7 @@ def export_mgf(
     q1_ratio_max=None,
     eic_corr_min=None,
     deisotope=True,
-    precursor_trim=-(-10.0),
+    precursor_trim=10.0,
     centroid_algo=None,
 ):
     """
@@ -354,81 +354,98 @@ def export_mgf(
             elif use_cache:
                 spect = row["ms2_specs"]
                 if spect is None:
-                    print(f"No MS2 spectrum for feature {row['fid']} is cached.")
-                    continue
-                # check if spec is a list of spectra
-                if isinstance(spect, list):
-                    if selection == "best":
-                        s = spect[0]
-                        scan_uid = row["ms2_scans"][0]
-                        s.energy = self.get_spectrum(scan_uid).energy
-                        spect = [s]
-                        scan_uids = [scan_uid]
-                    else:
-                        scan_uids = row["ms2_scans"]
-
-                    for i, s in enumerate(spect):
-                        if s is None:
-                            print(
-                                f"No MS2 spectrum for feature {row['fid']} is cached.",
+                    # No cached spectra, fall through to fetch from scan_uid
+                    use_cache = False
+                else:
+                    # check if spec is a list of spectra
+                    if isinstance(spect, list):
+                        if selection == "best":
+                            s = spect[0]
+                            scan_uid = row["ms2_scans"][0]
+                            s.energy = self.get_spectrum(scan_uid).energy
+                            spect = [s]
+                            scan_uids = [scan_uid]
+                        else:
+                            scan_uids = row["ms2_scans"]
+
+                        for i, s in enumerate(spect):
+                            if s is None:
+                                print(
+                                    f"No MS2 spectrum for feature {feature_uid} is cached.",
+                                )
+                                continue
+                            # check if s is a spectrum
+                            if type(s).__name__ == "Spectrum":
+                                s = filter_peaks(
+                                    s,
+                                    inty_min=inty_min,
+                                    q1_min=q1_ratio_min,
+                                    eic_min=eic_corr_min,
+                                    q1_max=q1_ratio_max,
+                                )
+                                # Get the corresponding scan_uid from the list
+                                current_scan_uid = scan_uids[i] if i < len(scan_uids) else "unknown"
+                                write_ion(
+                                    f,
+                                    f"fid:{feature_uid}, rt:{rt_str}, mz:{mz_str}, scan_uid:{current_scan_uid}",
+                                    feature_uid,
+                                    mz,
+                                    rt,
+                                    charge,
+                                    s,
+                                )
+                                c += 1
+                        continue  # Skip the rest of the processing for this feature
+            
+            # If we reach here, either use_cache=False or no cached spectra were available
+            if split_energy:
+                # get energy of all scans with scan_uid in ms2_scans by fetching them
+                ms2_scan_uids = row["ms2_scans"]
+                if isinstance(ms2_scan_uids, list) and len(ms2_scan_uids) > 0:
+                    # Fetch spectra to get energy information
+                    spectra_with_energy = []
+                    for scan_uid in ms2_scan_uids:
+                        spec = self.get_spectrum(scan_uid)
+                        if spec is not None:
+                            spectra_with_energy.append((scan_uid, spec.energy if hasattr(spec, 'energy') else 0))
+                    
+                    # Group by energy
+                    energy_groups: dict[float, list[int]] = {}
+                    for scan_uid, energy in spectra_with_energy:
+                        if energy not in energy_groups:
+                            energy_groups[energy] = []
+                        energy_groups[energy].append(scan_uid)
+                    
+                    for energy, scan_uids_for_energy in energy_groups.items():
+                        if selection == "best":
+                            # Keep only the first scan for this energy
+                            scan_uids_for_energy = [scan_uids_for_energy[0]]
+                        
+                        for scan_uid in scan_uids_for_energy:
+                            spect = self.get_spectrum(
+                                scan_uid,
+                                centroid=centroid,
+                                deisotope=deisotope,
+                                precursor_trim=precursor_trim,
+                                centroid_algo=centroid_algo,
                             )
-                            continue
-                        # check if s is a spectrum
-                        if type(s).__name__ == "spec":
-                            s = filter_peaks(
-                                s,
+                            spect = filter_peaks(
+                                spect,
                                 inty_min=inty_min,
                                 q1_min=q1_ratio_min,
                                 eic_min=eic_corr_min,
                                 q1_max=q1_ratio_max,
                             )
-                            # Get the corresponding scan_uid from the list
-                            current_scan_uid = scan_uids[i] if i < len(scan_uids) else "unknown"
                             write_ion(
                                 f,
-                                f"fid:{feature_uid}, rt:{rt_str}, mz:{mz_str}, scan_uid:{current_scan_uid}",
+                                f"fid:{feature_uid}, rt:{rt_str}, mz:{mz_str}, scan_uid:{scan_uid}, energy:{energy}",
                                 feature_uid,
                                 mz,
                                 rt,
                                 charge,
-                                s,
+                                spect,
                             )
                             c += 1
-            elif split_energy:
-                # get energy of all scans with scan_uid in ms2_scans
-                energy = [s.energy for s in row["ms2_specs"]]
-                # find unique energies
-                unique_energies = list(set(energy))
-                for e in unique_energies:
-                    ms2_scans = [row["ms2_scans"][i] for i, s in enumerate(row["ms2_specs"]) if s.energy == e]
-                    if selection == "best":
-                        # Keep as list with single element
-                        ms2_scans = [ms2_scans[0]]
-                    for scan_uid in ms2_scans:
-                        spect = self.get_spectrum(
-                            scan_uid,
-                            centroid=centroid,
-                            deisotope=deisotope,
-                            precursor_trim=precursor_trim,
-                            centroid_algo=centroid_algo,
-                        )
-                        spect = filter_peaks(
-                            spect,
-                            inty_min=inty_min,
-                            q1_min=q1_ratio_min,
-                            eic_min=eic_corr_min,
-                            q1_max=q1_ratio_max,
-                        )
-                        write_ion(
-                            f,
-                            f"fid:{feature_uid}, rt:{rt_str}, mz:{mz_str}, scan_uid:{scan_uid}, energy:{e}",
-                            feature_uid,
-                            mz,
-                            rt,
-                            charge,
-                            spect,
-                        )
-                        c += 1
             else:
                 if selection == "best":
                     ms2_scans = row["ms2_scans"][0]

{masster-0.2.4.dist-info → masster-0.2.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.2.4
+Version: 0.2.5
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.2.4.dist-info → masster-0.2.5.dist-info}/RECORD

@@ -1,5 +1,5 @@
 masster/__init__.py,sha256=xeh-hwR_2umE0CpRXn8t22wbkt4IT-FBEzeJknL8J6c,670
-masster/_version.py,sha256=WHz92m1tRN92ku0H9xVvQmdlLPlnlBvBEJkpDBTz-eQ,239
+masster/_version.py,sha256=XwisdBCXGK6Rlum0rwaZ6ZBJxS8eMw72i3m-LXgksaY,239
 masster/chromatogram.py,sha256=f25rMrNvCQN0A93wp9QPdG3H4FiOlYPbRY3H4yd7Q5Y,18910
 masster/logger.py,sha256=9uzuVEPwQkVlnsqT_eVvh33FZY_FIm3Wn2TaJcGhZP8,10674
 masster/spectrum.py,sha256=XiClDcN1uiG-_2TIr7Bqp7x8gWvHPbC5oh3zUu3fr6Y,46789
@@ -17,7 +17,7 @@ masster/sample/plot.py,sha256=7iyBddUa8-4OAcNhbgNUR_mNJgh5KKLwIlIL0s14g9w,58110
 masster/sample/processing.py,sha256=-kWNWTYpyqlD2adF5uQ3laGZ9Zg8h79RgL5DY6qEoxM,56972
 masster/sample/sample.py,sha256=uTsLmm7aWvRZO1mIGD_9sYDlKO3Ws74aLp7fIeLn9Eo,15282
 masster/sample/sample5_schema.json,sha256=pnQMOM4z0P6BdrXGOovVoVZwt-1gS-v8KkhTgbSH8R8,3405
-masster/sample/save.py,sha256=begTBO8aSrneV44ncmb5bwlNLFuFoPJMg7xBBXpBkzA,29977
+masster/sample/save.py,sha256=LCWYYhlq8K98eUB6EZIGep_RLujQ39ayqgbPHPuNYec,31198
 masster/sample/defaults/__init__.py,sha256=aNVdfpiJnyQQ9Jm5KCaJm-ySsi6S4aPEWFglVdKYnag,432
 masster/sample/defaults/find_adducts_def.py,sha256=dhk_F-cAd1lc39mmC7Xt5sZF20LmLugR8JS2hu0DHYE,11305
 masster/sample/defaults/find_features_def.py,sha256=LoIc2qDSiw9tsSyDJyjn6I3GSbatdkuzYY_14QkTFxQ,13512
@@ -43,8 +43,8 @@ masster/study/defaults/find_consensus_def.py,sha256=artvErq4w07SfHB0WHi68ZjxGg0X
 masster/study/defaults/find_ms2_def.py,sha256=k-GmnCKgQuVO6M-EAjzGOqgdFrqZviRaNAdiFmwVujY,4907
 masster/study/defaults/integrate_chrom_def.py,sha256=FY9QdJpdWe18sYucrwNKoZYY0eoOo0a_hcdkZHm_W00,7107
 masster/study/defaults/study_def.py,sha256=SzUzd2YTGDGCHNMR-Dw57j5PprEnPhpITonv7wx6HQA,9035
-masster-0.2.4.dist-info/METADATA,sha256=6lb1cYuf6QSAp_kpI7kTfR3N6Q9D5m-vegaw_vr_094,44324
-masster-0.2.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-masster-0.2.4.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
-masster-0.2.4.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-masster-0.2.4.dist-info/RECORD,,
+masster-0.2.5.dist-info/METADATA,sha256=TtRzNj321SMax7E0IiDAUPd-En2lmQST8nEqSwTr_mw,44324
+masster-0.2.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+masster-0.2.5.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
+masster-0.2.5.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+masster-0.2.5.dist-info/RECORD,,