Example #1
0
def papers_with_orhpan_sequences():
    title = "Papers with orphan sequences"

    activity_enzyme_names = list(
        set(Activity.objects().distinct('enzyme_name')))
    paper_ids = []
    for name in activity_enzyme_names:
        if len(Sequence.objects(enzyme_name=name)) == 0:
            act = Activity.objects(enzyme_name=name)[0]
            paper_ids.append(act.paper)

    papers_data = list(
        Paper.objects(id__in=paper_ids).only(
            *papers_table.PAPERS_TABLE_FIELDS).order_by(
                '-status').as_pymongo())
    papers_data = papers_table.process_papers_dict(papers_data,
                                                   show_owner=False)

    return render_template('edit_tables/edit_papers.html',
                           papers_data=papers_data,
                           papers_table_height='80vh',
                           papers_button_columns=['delete', 'edit'],
                           show_owner=True,
                           title=title,
                           row_click_modal=False)
Example #2
0
def clear_databases():
    EnzymeType.drop_collection()
    Sequence.drop_collection()
    Paper.drop_collection()
    Reaction.drop_collection()
    Activity.drop_collection()
    Molecule.drop_collection()
Example #3
0
 def set_choices(self):
     self.enzymes.choices = [
         (c, c) for c in ['All'] +
         (list(Activity.objects().distinct('enzyme_type')))
     ]
     self.reactions.choices = [
         (c, c)
         for c in ['All'] + (list(Activity.objects().distinct('reaction')))
     ]
Example #4
0
def task_search_for_orphan_enzymes():
    activity_enzyme_names = list(
        set(Activity.objects().distinct('enzyme_name')))
    for name in activity_enzyme_names:
        if len(Sequence.objects(enzyme_name=name)) == 0:
            enzyme_type = Activity.objects(enzyme_name=name)[0].enzyme_type
            new_seq = Sequence(enzyme_name=name, enzyme_type=enzyme_type)
            new_seq.save()
            print(
                f"found orphan enzyme, added sequence entry for {name} - {enzyme_type}"
            )
Example #5
0
def merge_sequences():
    to_merge = request.form['to_merge']
    merge_with = request.form['merge_with']
    status = 'success'
    msg = 'Sequences merged'
    issues = []

    if to_merge != merge_with:
        seq = Sequence.objects(enzyme_name=to_merge)[0]
        seq_merge = Sequence.objects(enzyme_name=merge_with)[0]
        if seq.enzyme_type == seq_merge.enzyme_type:
            for paper in seq.papers:
                seq_merge.papers.append(paper)

            acts = Activity.objects(enzyme_name=to_merge)
            for act in acts:
                act.enzyme_name = seq_merge.enzyme_name
                act.save()
            seq.delete()
            seq_merge.other_names.append(to_merge)
            seq_merge.save()
            update_seq_papers_status(merge_with)
        else:
            status = 'danger'
            msg = 'Could not merge sequences'
            issues.append('Enzyme types must be the same')
    else:
        status = 'danger'
        msg = 'Could not merge sequences'
        issues.append('Cannot merge with self')

    result = {'status': status, 'msg': msg, 'issues': issues}

    return jsonify(result=result)
Example #6
0
def delete_sequence():
    to_delete = request.form['to_delete']

    seq = Sequence.objects(enzyme_name=to_delete)[0]
    acts = Activity.objects(enzyme_name=to_delete)

    status = 'success'
    msg = 'Sequence deleted'
    issues = []

    if len(acts) != 0:
        status = 'danger'
        msg = 'Could not delete'
        papers = []
        for act in acts:
            if act.short_citation not in papers:
                papers.append(act.short_citation)
        for paper in papers:
            issues.append(f"Sequence is recorded in activity data for {paper}")

    mutants = Sequence.objects(mutant_of=to_delete)
    if len(mutants) != 0:
        status = 'danger'
        msg = 'Could not delete'
        for mut in mutants:
            issues.append(f"Sequence is a parent of mutant {mut.enzyme_name}")

    if status == 'success':
        seq.delete()

    result = {'status': status, 'msg': msg, 'issues': issues}

    return jsonify(result=result)
Example #7
0
def raise_activity_data_issue():

    user = user_datastore.get_user(current_user.id)
    activity_id = request.form['activity_id']
    comment = request.form['comment']
    activity = Activity.objects(id=activity_id)[0].select_related()

    comment_obj = Comment(owner=user, text=comment)
    comment_obj.save()

    if len(ActivityIssue.objects(activity=activity)) == 0:
        new_issue = ActivityIssue(activity=activity,
                                  raised_by=user,
                                  comments=[comment_obj])
        new_issue.save()
        result = {
            'status': 'success',
            'msg': 'Issue has been created',
            'issues': []
        }
        return jsonify(result=result)

    else:
        result = {
            'status':
            'danger',
            'msg':
            'An issue has already been raised for this data',
            'issues':
            ['Please see the activity data issues page for more information']
        }
        return jsonify(result=result)
Example #8
0
    def delete_old_autoprocessed(self, paper):
        pq = db.Q(paper=paper)
        ap = db.Q(auto_generated=True)

        acts = Activity.objects(pq & ap)
        for act in acts:
            act.delete()
Example #9
0
    def add_to_db(self, new_df, paper):
        if len(new_df) != 0:
            self.log(f"..adding {len(new_df)} new activity rows")

        for i, row in new_df.iterrows():
            if row['binary'] == 1:
                binary = True
            else:
                binary = False

            if row['auto_generated'] == 1:
                auto_gen = True
            else:
                auto_gen = False

            activity = Activity(
                enzyme_type=check_is_nan(row['enzyme_type']),
                enzyme_name=check_is_nan(row['enzyme_name']),
                reaction=check_is_nan(row['reaction']),
                short_citation=check_is_nan(row['short_citation']),
                html_doi=check_is_nan(row['html_doi']),
                added_by_string=str(row['added_by_string']),
                paper=paper,
                substrate_1_smiles=get_smile(row['substrate_1_smiles']),
                substrate_2_smiles=get_smile(row['substrate_2_smiles']),
                product_1_smiles=get_smile(row['product_1_smiles']),
                temperature=check_is_nan(row['temperature']),
                ph=check_is_nan(row['ph']),
                solvent=check_is_nan(row['solvent']),
                other_conditions=check_is_nan(row['other_conditions']),
                notes=check_is_nan(row['notes']),
                reaction_vol=check_is_nan(row['reaction_vol']),
                formulation=check_is_nan(row['formulation']),
                biocat_conc=check_is_nan(row['biocat_conc']),
                kcat=check_is_float(row['kcat']),
                km=check_is_float(row['km']),
                mw=check_is_float(row['mw']),
                substrate_1_conc=check_is_nan(row['substrate_1_conc']),
                substrate_2_conc=check_is_nan(row['substrate_2_conc']),
                specific_activity=check_is_float(row['specific_activity']),
                conversion=check_is_float(row['conversion']),
                conversion_time=check_is_float(row['conversion_time']),
                categorical=check_is_nan(row['categorical']),
                binary=binary,
                selectivity=check_is_nan(row['selectivity']),
                auto_generated=auto_gen)
            activity.save()
Example #10
0
def clear_autoprocessed_activity_data():
    activity_data = Activity.objects(auto_generated=True)

    for act in activity_data:
        act.delete()

    result = {
        'status': 'success',
        'msg': f'Autoprocessed data deleted',
        'issues': []
    }

    return jsonify(result=result)
def admin_activity_to_owner():
    paper = Paper.objects(id=request.form['paper_id']).select_related()[0]
    activities = Activity.objects(paper=paper)

    for activity in activities:
        activity.added_by = paper.owner
        activity.save()

    result = {
        'status': 'success',
        'msg': 'Activity added by updated',
        'issues': []
    }

    return jsonify(result=result)
def submission_main_page(paper_id):
    user = user_datastore.get_user(current_user.id)
    paper_query = Paper.objects(id=paper_id).select_related()
    if len(paper_query) == 0:
        flash('Paper has not been added yet, please add to the database first', 'fail')
        return redirect(url_for("biocatdb.launch_add_paper"))

    paper = paper_query[0]

    if not check_permission.check_paper_permission(current_user.id, paper):
        flash('No access to edit this entry', 'fail')
        return redirect(url_for("biocatdb.launch_add_paper"))

    paper_data = get_paper_data(paper, user)
    activity_data = get_activity_data(paper)
    reactions = list(Reaction.objects().distinct('name'))
    enzyme_names = list(Sequence.objects(papers=paper).distinct('enzyme_name'))
    enzyme_types = list(EnzymeType.objects().distinct('enzyme_type'))
    enzyme_data = sequence_table.get_enzyme_data(db.Q(papers=paper))
    enzyme_types_in_paper = list(Sequence.objects(papers=paper).distinct('enzyme_type'))
    reactions_in_paper = list(Reaction.objects(enzyme_types__in=enzyme_types_in_paper).distinct('name'))
    reactions_in_activity = list(Activity.objects(paper=paper).distinct('reaction'))
    status_dict = get_status(paper, user)
    comments = get_comments(paper, user)
    paper_molecules = get_paper_molecules(paper)
    admin_panel = False
    admin_dict = {}
    if current_user.has_role('admin'):
        admin_panel = True
        admin_dict = get_admin_dict(paper)

    reactions_ordered = reactions_in_activity + [r for r in reactions_in_paper if r not in reactions_in_activity]
    reactions_ordered += [r for r in reactions_in_paper if r not in reactions_ordered]
    reactions_ordered += [r for r in reactions if r not in reactions_ordered]

    return render_template('data_submission/submission_main_page.html',
                           paper=paper_data,
                           activity_data=activity_data,
                           seq_data=enzyme_data, seq_button_columns=['edit', 'remove', 'papers'],
                           status=status_dict,
                           seq_table_height='60vh', enzyme_types=enzyme_types, show_header_filters=False, include_owner=True, lock_enz_type='false',
                           reactions=reactions_ordered, enzyme_names=enzyme_names+['Chemical'],
                           doi=paper.doi,
                           comments=comments,
                           paper_molecules=paper_molecules,
                           admin_panel=admin_panel,
                           admin_dict=admin_dict,
                           enzyme_reactions=reactions_in_paper)
Example #13
0
def enzyme_substrate_specificity(enzyme_name):
    title = f"{enzyme_name} substrate specificity"
    args = request.args.to_dict()
    if 'reviewed' in args:
        revQ = db.Q(reviewed=True)
    else:
        revQ = db.Q()
        title += " (including not reviewed)"

    enzNameQ = db.Q(enzyme_name=enzyme_name)

    activity_data = list(Activity.objects(enzNameQ & revQ).only(*process_activity_data.mongo_cols).as_pymongo())
    activity_data = process_activity_data.process_activity_data(activity_data)
    activity_data = process_activity_data.smiles_to_svg(activity_data)

    return render_template('substrate_specificity/table_result_specificity.html', substrate_specificity_data=activity_data, title=title)
Example #14
0
def paper_substrate_specificity(paper_id):
    paper = Paper.objects(id=paper_id)[0]
    title = f"{paper.short_citation} activity data"

    args = request.args.to_dict()
    if 'reviewed' in args:
        revQ = db.Q(reviewed=True)
    else:
        revQ = db.Q()

    paper_Q = db.Q(paper=paper)

    activity_data = list(Activity.objects(paper_Q & revQ).only(*process_activity_data.mongo_cols).as_pymongo())
    activity_data = process_activity_data.process_activity_data(activity_data)
    activity_data = process_activity_data.smiles_to_svg(activity_data)

    return render_template('substrate_specificity/table_result_specificity.html', substrate_specificity_data=activity_data, title=title)
Example #15
0
def activity_status(paper):
    progress = 5
    progress_text = "Please add activity data"

    activity = Activity.objects(paper=paper)

    if len(activity) != 0:
        progress = 90
        progress_text = "Activity data added, please ensure all activity data (including negative data) is included.  Awaiting review."

        if paper.reviewed == True:
            progress = 100
            progress_text = 'Complete'

        return progress_text, str(progress) + '%'

    else:
        return progress_text, str(progress) + '%'
Example #16
0
def change_enzyme_type_name(enz_type, new_name):

    print("Updating enzyme types..")

    old_name = enz_type.enzyme_type
    for seq in Sequence.objects(enzyme_type=old_name):
        seq.enzyme_type = new_name
        seq.save()
    for reaction in Reaction.objects(enzyme_types=old_name):
        reaction.enzyme_types.remove(old_name)
        reaction.enzyme_types.append(new_name)
        reaction.cofactors[new_name] = reaction.cofactors.pop(old_name)
        reaction.save()
    for activity in Activity.objects(enzyme_type=old_name):
        activity.enzyme_type = new_name
        activity.save()

    print('..done')
def get_activity_data(paper):
    include = ['id', "reaction", "enzyme_name", "substrate_1_smiles", "substrate_2_smiles",
               "product_1_smiles", "temperature", "ph", "solvent", "other_conditions",
               "notes", "reaction_vol", "formulation", "biocat_conc", "kcat", "km",
               "mw", "substrate_1_conc", "substrate_2_conc", "specific_activity",
               "conversion", "conversion_time", "selectivity", "categorical", "binary",
               ]
    q_paper = db.Q(paper=paper)
    q_not_automated = db.Q(auto_generated__ne=True)

    activity_data = list(Activity.objects(q_paper & q_not_automated).only(*include).as_pymongo())
    for i, data in enumerate(activity_data):
        activity_data[i]['_id'] = str(activity_data[i]['_id'])
        if activity_data[i]['binary']:
            activity_data[i]['binary'] = 1
        else:
            activity_data[i]['binary'] = 0

    return activity_data
Example #18
0
def delete_enzyme_types():
    to_delete = request.form['to_delete']

    enz_type = EnzymeType.objects(enzyme_type=to_delete)[0]
    seqs = Sequence.objects(enzyme_type=to_delete)
    reacs = Reaction.objects(enzyme_types=to_delete)
    acts = Activity.objects(enzyme_type=to_delete)

    status = 'success'
    msg = 'Enzyme type deleted'
    issues = []

    if len(seqs) != 0:
        status = 'danger'
        msg = 'Could not delete'
        for seq in seqs:
            issues.append(
                f'Enzyme type is present in sequence: {seq.enzyme_name}')

    if len(reacs) != 0:
        status = 'danger'
        msg = 'Could not delete'
        for reac in reacs:
            issues.append(f'Enzyme type is present in reaction: {reac.name}')

    if len(acts) != 0:
        status = 'danger'
        msg = 'Could not delete'
        papers = []
        for act in acts:
            if act.short_citation not in papers:
                papers.append(act.short_citation)
        for paper in papers:
            issues.append(
                f"Enzyme type is recorded in activity data for {paper}")

    if status == 'success':
        enz_type.delete()

    result = {'status': status, 'msg': msg, 'issues': issues}

    return jsonify(result=result)
Example #19
0
def update_reviewed_status():
    papers = Paper.objects(reviewed=True)
    for paper in papers:
        acts = Activity.objects(paper=paper)
        seqs = Sequence.objects(papers=paper)
        for act in acts:
            act.reviewed = True
            act.save()
        for seq in seqs:
            seq.reviewed = True
            seq.save()

    result = {
        'status': 'success',
        'msg':
        f'Updated activity and sequence data to reviewed = True, if paper has been reviewed',
        'issues': []
    }

    return jsonify(result=result)
Example #20
0
def enzyme_substrate_specificity_type(enzyme_type):
    title = f"Substrate scope for all {enzyme_type} enzymes"

    if enzyme_type == 'All':
        enz_type_q = db.Q()
        title += " (including not reviewed)"
    else:
        enz_type_q = db.Q(enzyme_type=enzyme_type)

    args = request.args.to_dict()
    if 'reviewed' in args:
        revQ = db.Q(reviewed=True)
    else:
        revQ = db.Q()

    activity_data = list(Activity.objects(enz_type_q & revQ).only(*process_activity_data.mongo_cols).as_pymongo())
    activity_data = process_activity_data.process_activity_data(activity_data)
    activity_data = process_activity_data.smiles_to_svg(activity_data)

    return render_template('substrate_specificity/table_result_specificity.html', substrate_specificity_data=activity_data,
                           title=title)
Example #21
0
def review_paper():
    user = user_datastore.get_user(current_user.id)
    paper = Paper.objects(id=request.form['paper_id'])[0]
    acts = Activity.objects(paper=paper)
    seqs = Sequence.objects(papers=paper).select_related()
    if check_permission.check_seq_permissions(current_user.id, paper):
        reviewed = bool(strtobool(request.form['reviewed']))
        paper.reviewed = reviewed
        if reviewed == True:
            paper.reviewed_by = user
        else:
            paper.reviewed_by = None
        paper.save()

        for act in acts:
            act.reviewed = reviewed
            act.save()

        if reviewed == True:
            for seq in seqs:
                seq.reviewed = True
                seq.save()
        else:
            for seq in seqs:
                has_reviewed_paper = False
                for paper in seq.papers:
                    if paper.reviewed == True:
                        has_reviewed_paper = True
                        break
                if has_reviewed_paper == False:
                    seq.reviewed = False
                    seq.save()

        result = {
            'status': 'success',
            'msg': 'Review status updated',
            'issues': []
        }

        return jsonify(result=result)
Example #22
0
def task_assign_papers():
    users = User.objects()
    papers = Paper.objects()

    for paper in papers:
        paper_status.update_status(paper)

    for user in users:
        usernames = get_usernames(user)
        for paper in papers:
            if paper.added_by is None or paper.added_by == '':
                activities = Activity.objects(paper=paper)
                for activity in activities:
                    if does_username_match(usernames,
                                           activity.added_by_string):
                        activity.added_by = user
                        activity.save()

                        if paper.added_by is None or paper.added_by == '':
                            paper.added_by = user
                            paper.owner = user
                            paper.save()
Example #23
0
def remove_sequence():
    user = user_datastore.get_user(current_user.id)
    paper = Paper.objects(id=request.form['paper_id'])[0]

    enzyme_name = request.form['enzyme_name']
    seq = Sequence.objects(enzyme_name=enzyme_name)[0]

    if len(
            Activity.objects(
                db.Q(enzyme_name=seq.enzyme_name) & db.Q(paper=paper))) != 0:
        result = {
            'status':
            'danger',
            'msg':
            'Can not remove sequence - activity data still attached',
            'issues': [
                'Please remove references to this sequence in the activity section before removing'
            ]
        }
        return jsonify(result=result)

    else:
        if paper in seq.papers:
            seq.papers.remove(paper)
            seq.save()
        if len(seq.papers) == 0 and (seq.sequence == ''
                                     or seq.sequence is None):
            seq.delete()

    papers_functions.tag_paper_with_enzyme_types(paper)

    result = {
        'status': 'success',
        'msg': 'Sequence removed from paper',
        'issues': []
    }
    flash("Sequence removed from paper", 'success')
    return jsonify(result=result)
Example #24
0
def query_specificity_data(listReactions, listEnzymes, only_reviewed=False):
    if "All" in listEnzymes or len(listEnzymes) == 0 or listEnzymes == ['']:
        enzQ = Q()
    else:
        enzQ = Q(enzyme_type__in=listEnzymes)

    if "All" in listReactions or len(listReactions) == 0 or listReactions == [
            ''
    ]:
        reacQ = Q()
    else:
        reacQ = Q(reaction__in=listReactions)

    if only_reviewed == True:
        revQ = Q(reviewed=True)
    else:
        revQ = Q()

    result = Activity.objects(enzQ & reacQ & revQ).as_pymongo()
    spec_df = pd.DataFrame(list(result))
    spec_df = organise_mongo_columns(spec_df)

    return spec_df
Example #25
0
def delete_paper():
    user = user_datastore.get_user(current_user.id)
    paper = Paper.objects(id=request.form['paper_id'])[0]

    if not check_permission.check_paper_permission(current_user.id, paper):
        result = {
            'status': 'danger',
            'msg': 'You are not the owner of this paper',
            'issues': ['Assign this paper to yourself in order to delete it']
        }
        return jsonify(result=result)

    elif len(Sequence.objects(papers=paper)) != 0:
        result = {
            'status': 'danger',
            'msg': 'Paper still contains sequences',
            'issues':
            ['Please remove any sequences from paper before deleting']
        }
        return jsonify(result=result)

    elif len(Activity.objects(paper=paper)) != 0:
        result = {
            'status':
            'danger',
            'msg':
            'Paper still contains activity data',
            'issues':
            ['Please remove any activity data from paper before deleting']
        }
        return jsonify(result=result)

    else:
        paper.delete()

        result = {'status': 'success', 'msg': 'Paper deleted', 'issues': []}
        return jsonify(result=result)
def save_reaction():
    rxn_selection = request.form['rxn_selection']
    rxn_name = request.form['rxn_name']
    smarts_yaml = request.form['smarts_yaml']
    cofactors = request.form['cofactors']
    positive_tests = request.form['positive_tests']
    negative_tests = request.form['negative_tests']
    rxn_type = request.form['rxn_type']
    experimental = request.form['experimental']
    two_step = request.form['two_step']
    requires_absence_of_water = request.form['requires_absence_of_water']

    if experimental == 'false':
        experimental = False
    elif experimental == 'true':
        experimental = True

    if two_step == 'false':
        two_step = False
    elif two_step == 'true':
        two_step = True

    if requires_absence_of_water == 'false':
        requires_absence_of_water = False
    elif requires_absence_of_water == 'true':
        requires_absence_of_water = True

    if rxn_selection == 'Empty template':
        if len(Reaction.objects(name=rxn_name)) == 0 and rxn_name != '':
            reaction = Reaction(name=rxn_name)
        else:
            result = {
                'status': 'failed',
                'msg': "Could not create new reaction - name already exists",
                'issues': []
            }
            return jsonify(result=result)
    else:
        reaction = Reaction.objects(name=rxn_selection)[0]

    if len(Reaction.objects(name=rxn_name)) == 0:
        reaction.name = rxn_name
    reaction.smarts = yaml.load(smarts_yaml, Loader=yaml.FullLoader)
    reaction.enzyme_types = list(
        yaml.load(cofactors, Loader=yaml.FullLoader).keys())
    reaction.cofactors = yaml.load(cofactors, Loader=yaml.FullLoader)
    reaction.positive_tests = yaml.load(positive_tests, Loader=yaml.FullLoader)
    reaction.negative_tests = yaml.load(negative_tests, Loader=yaml.FullLoader)
    reaction.type = rxn_type
    reaction.experimental = experimental
    reaction.two_step = two_step
    reaction.requires_absence_of_water = requires_absence_of_water

    reaction.save()

    refresh = 'False'
    if rxn_selection != reaction.name:
        refresh = 'True'
        activities = Activity.objects(reaction=rxn_selection)
        for act in activities:
            act.reaction = reaction.name
            act.save()

    print("reaction saved")
    result = {
        'status': 'info',
        'msg': "Reaction saved",
        'issues': [],
        'refresh': refresh
    }
    return jsonify(result=result)
Example #27
0
def get_enzymes_in_db():
    enzymes = Activity.objects().distinct('enzyme_type')
    return enzymes
Example #28
0
def get_reactions_in_db():
    reactions = Activity.objects().distinct('reaction')
    return reactions
Example #29
0
def init_db():
    form = InitDB()

    if form.validate_on_submit() == True:
        if form.rxns.data != None:
            rxns_data = form.rxns.data
            filename = secure_filename(rxns_data.filename)
            try:
                rxns_data.save(filename)
                yaml_dict = rxn_rules_to_db.load_yaml_dict(filename)
                Reaction.drop_collection()
                current_app.db_queue.enqueue(rxn_rules_to_db.load_into_mongo,
                                             yaml_dict)
                flash("Yaml loaded ok, reactions_to_db in queue", 'success')
            except:
                flash("Failed to load reactions", 'fail')
            os.remove(filename)

        if form.biocatdb.data != None:
            filename = secure_filename(form.biocatdb.data.filename)
            form.biocatdb.data.save(filename)
            try:
                df = biocatdb_excel_to_db.load_df(filename)

                Paper.drop_collection()
                Activity.drop_collection()
                Molecule.drop_collection()
                Sequence.drop_collection()
                current_app.db_queue.enqueue(biocatdb_excel_to_db.df_to_db, df)
                current_app.db_queue.enqueue(make_molecule_db.make_fp_db)
                flash("Biocatdb excel loaded ok, added to queue", "success")
            except:
                flash("Problem loading biocatdb_2 excel", "fail")
            os.remove(filename)

        if form.sequences.data != None:
            filename = secure_filename(form.sequences.data.filename)
            form.sequences.data.save(filename)
            try:

                if '.xlsx' in filename:
                    df = pd.read_excel(filename)
                elif '.csv' in filename:
                    df = pd.read_csv(filename)
                else:
                    df = None
                    Exception('File must be .csv or .xlsx')

                current_app.db_queue.enqueue(task_add_sequence_data, df)
                flash("Sequences excel loaded ok, added to queue", "success")
            except Exception as e:
                flash(f"Problem loading sequences excel - {e}", "fail")

            os.remove(filename)

        if form.mongo_dump.data != None:
            filename = secure_filename(form.mongo_dump.data.filename)
            form.mongo_dump.data.save(filename)

            try:
                if 'mongo_dump.gz' in filename:
                    execute_mongo_restore(filename)
                else:
                    Exception('File must be mongo_dump.gz')

                flash("mongo dump loaded ok", "success")
            except Exception as e:
                flash(f"Problem loading mongo dump - {e}", "fail")

    return render_template('init_db/init_db.html', form=form)
Example #30
0
def df_to_db(spec_df):
    #added_by_dict = make_added_by_user_dict()

    print('Saving biocatdb_2 excel to mongodb..')
    for i, row in spec_df.iterrows():
        html_doi = str(row['html_doi'])
        doi = str(row['html_doi'])
        added_by_string = str(row['added_by'])

        list_html_to_remove = [
            'https://doi.org/', 'http://doi.org/', 'http://dx.doi.org/'
        ]
        for to_remove in list_html_to_remove:
            if to_remove in doi:
                doi = html_doi.replace(to_remove, '')

        if len(Paper.objects(doi=doi)) == 0:
            paper = Paper(short_citation=str(row['short_citation']),
                          html=html_doi,
                          doi=doi)
            paper = paper.save()
            print(f"{row['short_citation']} added")
        else:
            paper = Paper.objects(doi=doi)[0]

        if row['enzyme_type'] is not None and row['enzyme_type'] != '' and type(
                row['enzyme_type']) == str:
            if len(EnzymeType.objects(enzyme_type=row['enzyme_type'])) == 0:
                enz_type = EnzymeType(enzyme_type=row['enzyme_type'],
                                      description='')
                enz_type.save()

        if row['enzyme_name'] is not None and row['enzyme_name'] != '' and type(
                row['enzyme_name']) == str:
            if len(Sequence.objects(enzyme_name=row['enzyme_name'])) == 0:
                seq = Sequence(enzyme_name=check_is_nan(row['enzyme_name']),
                               enzyme_type=check_is_nan(row['enzyme_type']),
                               papers=[paper])
                seq.save()
            else:
                seq = Sequence.objects(enzyme_name=row['enzyme_name'])[0]
                if paper not in seq.papers:
                    seq.papers.append(paper)
                    seq = seq.save()

        if row['binary'] == 1:
            binary = True
        else:
            binary = False

        if row['auto_generated'] == 1:
            auto_gen = True
        else:
            auto_gen = False

        activity = Activity(
            enzyme_type=check_is_nan(row['enzyme_type']),
            enzyme_name=check_is_nan(row['enzyme_name']),
            reaction=check_is_nan(row['reaction']),
            short_citation=check_is_nan(row['short_citation']),
            html_doi=check_is_nan(row['html_doi']),
            added_by_string=added_by_string,
            paper=paper,
            cascade_num=check_is_nan(row['cascade_num']),
            substrate_1_smiles=get_smile(row['substrate_1_smiles']),
            substrate_2_smiles=get_smile(row['substrate_2_smiles']),
            product_1_smiles=get_smile(row['product_1_smiles']),
            temperature=check_is_nan(row['temperature']),
            ph=check_is_nan(row['ph']),
            solvent=check_is_nan(row['solvent']),
            other_conditions=check_is_nan(row['other_conditions']),
            notes=check_is_nan(row['notes']),
            reaction_vol=check_is_nan(row['reaction_vol']),
            formulation=check_is_nan(row['formulation']),
            biocat_conc=check_is_nan(row['biocat_conc']),
            kcat=check_is_float(row['kcat']),
            km=check_is_float(row['km']),
            mw=check_is_float(row['mw']),
            substrate_1_conc=check_is_nan(row['substrate_1_conc']),
            substrate_2_conc=check_is_nan(row['substrate_2_conc']),
            specific_activity=check_is_float(row['specific_activity']),
            conversion=check_is_float(row['conversion']),
            conversion_time=check_is_float(row['conversion_time']),
            categorical=check_is_nan(row['categorical']),
            binary=binary,
            selectivity=check_is_nan(row['selectivity']),
            auto_generated=auto_gen)

        activity.save()
    print('..done')