Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

DrugBank Drug Interaction Sentences Seem to Be of a Standard Type #383

Open
ecwood opened this issue Jun 26, 2024 · 6 comments
Open

DrugBank Drug Interaction Sentences Seem to Be of a Standard Type #383

ecwood opened this issue Jun 26, 2024 · 6 comments
Assignees

Comments

@ecwood
Copy link
Collaborator

ecwood commented Jun 26, 2024

We might be able to get more precise information from the DrugBank drug-interactions by mapping the standard sentence forms onto edge types.

@ecwood ecwood self-assigned this Jun 26, 2024
@ecwood
Copy link
Collaborator Author

ecwood commented Jun 27, 2024

Here are the most common phrases in the drug interaction sentences:

{
    "CNS": 295660,
    "CNS depression": 295614,
    "CNS depression can": 295568,
    "CNS depression can be": 295568,
    "CNS depression can be increased": 295568,
    "CNS depression can be increased when": 295568,
    "The": 2091852,
    "The metabolism": 405067,
    "The metabolism of": 405067,
    "The risk": 1211679,
    "The risk or": 1209578,
    "The risk or severity": 1209578,
    "The risk or severity of": 1209578,
    "The risk or severity of CNS": 289998,
    "The risk or severity of CNS depression": 289998,
    "The risk or severity of CNS depression can": 289952,
    "The risk or severity of CNS depression can be": 289952,
    "The risk or severity of CNS depression can be increased": 289952,
    "The risk or severity of CNS depression can be increased when": 289952,
    "The risk or severity of adverse": 331153,
    "The risk or severity of adverse effects": 331153,
    "The risk or severity of adverse effects can": 331153,
    "The risk or severity of adverse effects can be": 331153,
    "The risk or severity of adverse effects can be increased": 330711,
    "The risk or severity of adverse effects can be increased when": 330711,
    "The serum": 171392,
    "The serum concentration": 171392,
    "The serum concentration of": 171392,
    "The therapeutic": 277690,
    "The therapeutic efficacy": 277690,
    "The therapeutic efficacy of": 277690,
    "a": 544436,
    "a higher": 352172,
    "a higher serum": 352172,
    "a higher serum level.": 352172,
    "activities": 310627,
    "activities of": 310627,
    "adverse": 331710,
    "adverse effects": 331153,
    "adverse effects can": 331153,
    "adverse effects can be": 331153,
    "adverse effects can be increased": 330711,
    "adverse effects can be increased when": 330711,
    "and": 157490,
    "be": 2089751,
    "be decreased": 594552,
    "be decreased when": 594552,
    "be decreased when combined": 320819,
    "be decreased when combined with": 320819,
    "be decreased when used": 232489,
    "be decreased when used in": 232489,
    "be decreased when used in combination": 232489,
    "be decreased when used in combination with": 232489,
    "be increased": 1494993,
    "be increased when": 1494993,
    "be increased when combined": 110272,
    "be increased when combined with": 110272,
    "be increased when it": 129870,
    "be increased when it is": 129870,
    "be increased when it is combined": 129870,
    "be increased when it is combined with": 129870,
    "can": 2112673,
    "can be": 2089751,
    "can be decreased": 594552,
    "can be decreased when": 594552,
    "can be decreased when combined": 320819,
    "can be decreased when combined with": 320819,
    "can be decreased when used": 232489,
    "can be decreased when used in": 232489,
    "can be decreased when used in combination": 232489,
    "can be decreased when used in combination with": 232489,
    "can be increased": 1494993,
    "can be increased when": 1494993,
    "can be increased when combined": 110272,
    "can be increased when combined with": 110272,
    "can be increased when it": 129870,
    "can be increased when it is": 129870,
    "can be increased when it is combined": 129870,
    "can be increased when it is combined with": 129870,
    "combination": 279108,
    "combination with": 279108,
    "combined": 1812744,
    "combined with": 1812744,
    "concentration": 194314,
    "concentration of": 171392,
    "could": 412560,
    "could result": 412560,
    "could result in": 412560,
    "could result in a": 412560,
    "could result in a higher": 352172,
    "could result in a higher serum": 352172,
    "could result in a higher serum level.": 352172,
    "decrease": 488133,
    "decrease the": 441894,
    "decrease the excretion": 352172,
    "decrease the excretion rate": 352172,
    "decrease the excretion rate of": 352172,
    "decreased": 594552,
    "decreased when": 594552,
    "decreased when combined": 320819,
    "decreased when combined with": 320819,
    "decreased when used": 232489,
    "decreased when used in": 232489,
    "decreased when used in combination": 232489,
    "decreased when used in combination with": 232489,
    "depression": 297436,
    "depression can": 297390,
    "depression can be": 297390,
    "depression can be increased": 297390,
    "depression can be increased when": 297390,
    "effects": 332463,
    "effects can": 332463,
    "effects can be": 332463,
    "effects can be increased": 332021,
    "effects can be increased when": 332021,
    "efficacy": 277690,
    "efficacy of": 277690,
    "excretion": 433102,
    "excretion rate": 412560,
    "excretion rate of": 412560,
    "higher": 352172,
    "higher serum": 352172,
    "higher serum level.": 352172,
    "in": 820804,
    "in a": 435133,
    "in a higher": 352172,
    "in a higher serum": 352172,
    "in a higher serum level.": 352172,
    "in combination": 279108,
    "in combination with": 279108,
    "increase": 281868,
    "increase the": 281293,
    "increased": 1497663,
    "increased when": 1497094,
    "increased when combined": 110272,
    "increased when combined with": 110272,
    "increased when it": 131971,
    "increased when it is": 131971,
    "increased when it is combined": 131971,
    "increased when it is combined with": 131971,
    "is": 1384692,
    "is combined": 1381653,
    "is combined with": 1381653,
    "it": 172075,
    "it is": 172075,
    "it is combined": 172075,
    "it is combined with": 172075,
    "level.": 352172,
    "may": 724712,
    "may decrease": 443399,
    "may decrease the": 441894,
    "may decrease the excretion": 352172,
    "may decrease the excretion rate": 352172,
    "may decrease the excretion rate of": 352172,
    "may increase": 281313,
    "may increase the": 281293,
    "metabolism": 405067,
    "metabolism of": 405067,
    "of": 2841473,
    "of CNS": 289998,
    "of CNS depression": 289998,
    "of CNS depression can": 289952,
    "of CNS depression can be": 289952,
    "of CNS depression can be increased": 289952,
    "of CNS depression can be increased when": 289952,
    "of adverse": 331708,
    "of adverse effects": 331153,
    "of adverse effects can": 331153,
    "of adverse effects can be": 331153,
    "of adverse effects can be increased": 330711,
    "of adverse effects can be increased when": 330711,
    "or": 1209578,
    "or severity": 1209578,
    "or severity of": 1209578,
    "or severity of CNS": 289998,
    "or severity of CNS depression": 289998,
    "or severity of CNS depression can": 289952,
    "or severity of CNS depression can be": 289952,
    "or severity of CNS depression can be increased": 289952,
    "or severity of CNS depression can be increased when": 289952,
    "or severity of adverse": 331153,
    "or severity of adverse effects": 331153,
    "or severity of adverse effects can": 331153,
    "or severity of adverse effects can be": 331153,
    "or severity of adverse effects can be increased": 330711,
    "or severity of adverse effects can be increased when": 330711,
    "rate": 412560,
    "rate of": 412560,
    "result": 412560,
    "result in": 412560,
    "result in a": 412560,
    "result in a higher": 352172,
    "result in a higher serum": 352172,
    "result in a higher serum level.": 352172,
    "risk": 1211679,
    "risk or": 1209578,
    "risk or severity": 1209578,
    "risk or severity of": 1209578,
    "risk or severity of CNS": 289998,
    "risk or severity of CNS depression": 289998,
    "risk or severity of CNS depression can": 289952,
    "risk or severity of CNS depression can be": 289952,
    "risk or severity of CNS depression can be increased": 289952,
    "risk or severity of CNS depression can be increased when": 289952,
    "risk or severity of adverse": 331153,
    "risk or severity of adverse effects": 331153,
    "risk or severity of adverse effects can": 331153,
    "risk or severity of adverse effects can be": 331153,
    "risk or severity of adverse effects can be increased": 330711,
    "risk or severity of adverse effects can be increased when": 330711,
    "serum": 606876,
    "serum concentration": 194314,
    "serum concentration of": 171392,
    "serum level.": 352172,
    "severity": 1209578,
    "severity of": 1209578,
    "severity of CNS": 289998,
    "severity of CNS depression": 289998,
    "severity of CNS depression can": 289952,
    "severity of CNS depression can be": 289952,
    "severity of CNS depression can be increased": 289952,
    "severity of CNS depression can be increased when": 289952,
    "severity of adverse": 331153,
    "severity of adverse effects": 331153,
    "severity of adverse effects can": 331153,
    "severity of adverse effects can be": 331153,
    "severity of adverse effects can be increased": 330711,
    "severity of adverse effects can be increased when": 330711,
    "the": 747047,
    "the excretion": 412560,
    "the excretion rate": 412560,
    "the excretion rate of": 412560,
    "therapeutic": 277690,
    "therapeutic efficacy": 277690,
    "therapeutic efficacy of": 277690,
    "used": 279108,
    "used in": 279108,
    "used in combination": 279108,
    "used in combination with": 279108,
    "when": 2091852,
    "when combined": 431091,
    "when combined with": 431091,
    "when it": 172075,
    "when it is": 172075,
    "when it is combined": 172075,
    "when it is combined with": 172075,
    "when used": 278170,
    "when used in": 278170,
    "when used in combination": 278170,
    "when used in combination with": 278170,
    "which": 412560,
    "which could": 412560,
    "which could result": 412560,
    "which could result in": 412560,
    "which could result in a": 412560,
    "which could result in a higher": 352172,
    "which could result in a higher serum": 352172,
    "which could result in a higher serum level.": 352172,
    "with": 2091852
}

@ecwood
Copy link
Collaborator Author

ecwood commented Jun 27, 2024

The risk/severity items can be decoded with this code. This maps 1,209,578 of the 2,839,486 drug interaction sentences (roughly 43%):

def risk_or_severity_matches(sentence):
    start = "The risk or severity of "
    increased = " can be increased when "
    decreased = " can be decreased when "
    middle2 = " is combined with "

    if sentence.startswith(start):
        sentence_cut1 = sentence.replace(start, '')

        dir_flag = ""
        middle1 = ""
        if increased in sentence_cut1:
            dir_flag = "increased"
            middle1 = increased
        elif decreased in sentence_cut1:
            dir_flag = "decreased"
            middle1 = decreased
        else:
            return None, None

        sentence_div1 = sentence_cut1.split(middle1)
        risk_item = sentence_div1[0]

        sentence_cut2 = sentence_cut1.replace(risk_item + middle1, "")
        sentence_div2 = sentence_cut2.split(middle2)

        comb_item1 = sentence_div2[0]
        comb_item2 = sentence_div2[1].strip('.')

        return risk_item, (risk_item, dir_flag, comb_item1, comb_item2)

    return None, None

These are the different risk/severity items, which we will need to map:

{
    "Anticonvulsant Toxicity": 4,
    "CNS depression": 289952,
    "CNS depression and hypotonia": 46,
    "Cardiac Arrhythmia": 2592,
    "Cardiac Arrhythmia and CNS stimulation": 46,
    "Cardiovascular Impairment": 36,
    "Hypertrichosis": 2,
    "QTc prolongation": 91758,
    "QTc prolongation and Cardiac Arrhythmia": 6,
    "QTc prolongation and hypotension": 30,
    "QTc prolongation and serotonin syndrome": 2,
    "QTc prolongation and torsade de pointes": 878,
    "QTc prolongation and ventricular arrhythmias": 648,
    "QTc prolongation, torsade de pointes, and Cardiac Arrhythmia": 2,
    "QTc prolongation, torsade de pointes, and cardiotoxicity": 62,
    "QTc prolongation, torsade de pointes, hypokalemia, hypomagnesemia, and cardiac arrest": 14,
    "QTc prolongation, ventricular arrhythmias, torsade de pointes, and convulsion": 4,
    "Reye's syndrome": 78,
    "Stevens-Johnson syndrome": 2,
    "Tachycardia": 23486,
    "Tachycardia and drowsiness": 2140,
    "Thrombosis": 4566,
    "adverse effects": 331153,
    "anemia": 12,
    "angioedema": 3388,
    "bleeding": 51614,
    "bleeding and bruising": 1890,
    "bleeding and gastrointestinal bleeding": 64,
    "bleeding and hemorrhage": 24140,
    "bleeding and thrombocytopenia": 88,
    "bleeding, nephrotoxicity, and gastrointestinal bleeding": 152,
    "bradycardia": 2634,
    "bronchospasm, shortness of breath, and dyspnea": 14,
    "cardiac arrest": 2,
    "cardiotoxicity": 590,
    "cardiovascular complications": 26,
    "confusion, irritability, and sleep disorders": 12,
    "congestive heart failure": 26,
    "congestive heart failure and hypotension": 70,
    "congestive heart failure, bleeding, hypotension, and Tachycardia": 20,
    "constipation": 656,
    "cytopenia": 40,
    "cytotoxicity": 2,
    "death": 2,
    "dehydration": 7532,
    "drowsiness and CNS depression": 2,
    "edema formation": 4617,
    "electrolyte abnormality": 38,
    "electrolyte imbalance": 2028,
    "elevated intracranial pressure": 772,
    "extrapyramidal symptoms": 1682,
    "extrapyramidal symptoms and CNS depression": 60,
    "fluid retention": 612,
    "gastrointestinal bleeding": 10504,
    "gastrointestinal bleeding and gastrointestinal ulceration": 18,
    "gastrointestinal bleeding and peptic ulcer": 206,
    "gastrointestinal bleeding and thrombocytopenia": 36,
    "gastrointestinal irritation": 13120,
    "gastrointestinal ulceration": 240,
    "gastrointestinal ulceration and gastrointestinal irritation": 125,
    "generalized seizure": 4,
    "generalized seizure and bradycardia": 2,
    "gouty arthritis": 2,
    "granulocytopenia": 28,
    "hemorrhage": 3006,
    "hemorrhage, gastrointestinal bleeding, and gastrointestinal ulceration": 2,
    "hemorrhagic cystitis": 2,
    "hyperbilirubinemia": 2,
    "hypercalcemia": 484,
    "hypercoagulability": 4,
    "hyperglycemia": 15498,
    "hyperkalemia": 26786,
    "hyperkalemia and metabolic acidosis": 2,
    "hyperkinetic symptoms": 6,
    "hypersensitivity reaction": 74,
    "hypertension": 77781,
    "hypertension and Tachycardia": 18,
    "hypertension and cardiovascular complications": 62,
    "hypertension and tardive dyskinesia": 46,
    "hypertension, hyponatremia, and water intoxication": 208,
    "hyperthermia and oligohydrosis": 240,
    "hypocalcemia": 210,
    "hypoglycemia": 28220,
    "hypokalemia": 7720,
    "hyponatremia": 644,
    "hyponatremia and water intoxication": 46,
    "hypotension": 8968,
    "hypotension and CNS depression": 2242,
    "hypotension and hyperkalemia": 8,
    "hypotension and orthostatic hypotension": 728,
    "hypotension and priapism": 20,
    "hypotension and sinus node depression": 24,
    "hypotension and syncope": 780,
    "hypotension, bradycardia, and Cardiac Arrhythmia": 2,
    "hypotension, hyperglycemia, and hyperuricemia": 8,
    "hypotension, hyperkalemia, and nephrotoxicity": 54,
    "hypotension, hyperkalemia, and reduced intravascular volume": 30,
    "hypotension, nitritoid reactions, facial flushing, nausea, and vomiting": 54,
    "hypotension, sedation, death, somnolence, and respiratory depression": 1296,
    "immunosuppression": 1909,
    "increased glucose": 2,
    "increased serum creatinine": 2,
    "increased transaminases": 10,
    "infection": 6150,
    "infection and neutropenia": 12,
    "intraocular pressure": 2,
    "jaw osteonecrosis": 2,
    "jaw osteonecrosis and anti-angiogenesis": 428,
    "lactic acidosis": 64,
    "leukopenia": 2,
    "liver damage": 312,
    "liver enzyme elevations": 212,
    "metabolic acidosis": 38,
    "methemoglobinemia": 66658,
    "mucosal ulceration and ischemic colitis": 16,
    "myelosuppression": 1120,
    "myelosuppression, anemia, and severe leukopenia": 54,
    "myocardial depression": 32,
    "myopathy": 34,
    "myopathy and rhabdomyolysis": 292,
    "myopathy and weakness": 2218,
    "myopathy, rhabdomyolysis, and myoglobinuria": 6864,
    "nephrotoxicity": 23358,
    "nephrotoxicity and hypocalcemia": 1672,
    "neuromuscular blockade": 2742,
    "neuropsychiatric effects": 1310,
    "neutropenia": 820,
    "neutropenia and thrombocytopenia": 2050,
    "orthostatic hypotension": 224,
    "orthostatic hypotension and dizziness": 326,
    "orthostatic hypotension and syncope": 312,
    "osteomalacia": 16,
    "ototoxicity": 14,
    "ototoxicity and nephrotoxicity": 106,
    "peripheral neuropathy": 264,
    "progressive multifocal leukoencephalopathy and immunosuppression": 2,
    "pseudotumor cerebri": 396,
    "psychotic reaction": 2,
    "pulmonary toxicity": 50,
    "rash": 1,
    "rash, hypersensitivity reaction, Stevens-Johnson syndrome, and Cutaneous drug reaction": 2,
    "reduced gastrointestinal motility": 504,
    "renal failure": 1172,
    "renal failure and hypertension": 404,
    "renal failure and hypotension": 82,
    "renal failure, hyperkalemia, and hypertension": 9398,
    "renal failure, hypotension, and hyperkalemia": 1360,
    "respiratory depression": 468,
    "rhabdomyolysis": 20,
    "rhabdomyolysis, myoglobinuria, and elevated creatine kinase (CPK)": 14,
    "sedation": 3094,
    "sedation and CNS depression": 1086,
    "sedation and extrapyramidal symptoms": 2,
    "sedation and orthostatic hypotension": 36,
    "sedation and somnolence": 400,
    "sedation, somnolence, and CNS depression": 2226,
    "seizure": 918,
    "seizure and encephalopathy": 2,
    "serotonin syndrome": 12086,
    "serotonin syndrome and hypomania": 58,
    "serotonin syndrome and neuroleptic malignant syndrome": 4,
    "serotonin syndrome and opioid toxicity": 62,
    "serotonin syndrome and seizure": 70,
    "sinus node depression": 2,
    "somnolence and peripheral neuropathy": 4,
    "tendinopathy": 4053,
    "thrombocytopenia": 316,
    "thromboembolism": 158,
    "torsade de pointes": 10,
    "torsade de pointes and Cardiac Arrhythmia": 4,
    "tumor lysis syndrome": 2,
    "ulceration": 125,
    "urinary retention": 238,
    "urinary retention and constipation": 176,
    "urinary retention, reduced gastrointestinal motility, and constipation": 168,
    "vasospastic reactions": 120,
    "ventricular arrhythmias": 2,
    "ventricular arrhythmias and Cardiac Arrhythmia": 490,
    "ventricular arrhythmias and torsade de pointes": 2,
    "ventricular arrhythmias, bradycardia, and heart block": 270,
    "visual accommodation disturbances": 2,
    "water intoxication": 2,
    "weight gain and edema formation": 16
}

@ecwood
Copy link
Collaborator Author

ecwood commented Jun 27, 2024

The increase/decrease activity items were extracted with this code. These sentences account for about 310,627 of the total 2,839,486 (about 10%).

def may_impact_activities(sentence):
    increased = " may increase the "
    decreased = " may decrease the "
    dir_flag = ""
    middle1 = ""

    middle2 = " activities of "

    if increased in sentence and middle2 in sentence:
        dir_flag = "increased"
        middle1 = increased
    elif decreased in sentence and middle2 in sentence:
        dir_flag = "decreased"
        middle1 = decreased
    else:
        return None, None

    sentence_div1 = sentence.split(middle1)
    item1 = sentence_div1[0]


    sentence_cut1 = sentence.replace(item1 + middle1, "")
    sentence_div2 = sentence_cut1.split(middle2)
    activity = sentence_div2[0]
    item2 = sentence_div2[1]

    return activity, (item1, dir_flag, activity, item2)

These are the different increase/decrease activity of items that will need to be mapped:

{
    "Change in thyroid function": 120,
    "Decreased alertness": 2,
    "Pseudotumor Cerebri": 28,
    "QTc-prolonging": 2344,
    "QTc-prolonging and arrhythmogenic": 4,
    "alpha-adrenergic": 62,
    "analgesic": 2158,
    "anticholinergic": 1546,
    "anticoagulant": 16507,
    "antihypertensive": 71674,
    "antiplatelet": 1630,
    "antipsychotic": 360,
    "arrhythmogenic": 21434,
    "arrhythmogenic and cardiotoxic": 366,
    "atrioventricular blocking (AV block)": 110,
    "atrioventricular blocking (AV block) and arrhythmogenic": 26,
    "atrioventricular blocking (AV block) and tachycardic": 2,
    "bradycardic": 9552,
    "bradycardic, atrioventricular blocking (AV block), and arrhythmogenic": 26,
    "bronchoconstrictory": 74,
    "bronchodilatory": 862,
    "cardiodepressant": 206,
    "cardiotoxic": 1046,
    "central nervous system depressant (CNS depressant)": 27016,
    "constipating": 2,
    "dermatologic adverse": 2,
    "diuretic": 138,
    "fluid retaining and vasopressor": 112,
    "gastrointestinal motility reducing": 242,
    "hepatotoxic": 500,
    "hepatotoxic and myelosuppressive": 2,
    "hypercalcemic": 38,
    "hyperkalemic": 10156,
    "hypertensive": 3852,
    "hypertensive and vasoconstricting": 3246,
    "hypoglycemic": 17592,
    "hypokalemic": 1019,
    "hypolipidaemic": 18,
    "hypotensive": 42649,
    "hypotensive and Electrolyte Disturbance": 118,
    "hypotensive and central nervous system depressant (CNS depressant)": 28,
    "hypotensive and hyperkalemic": 2,
    "hypotensive and vasodilatory": 24,
    "hypothyroid": 6,
    "immunosuppressive": 3064,
    "myelosuppressive": 246,
    "myopathic rhabdomyolysis": 52,
    "nephrotoxic": 1818,
    "nephrotoxic and neuromuscular blocking": 2,
    "nephrotoxic and ototoxic": 2,
    "neuroexcitatory": 6288,
    "neuromuscular blocking": 5790,
    "neurotoxic": 5686,
    "neutropenic": 4,
    "opioid antagonism": 78,
    "orthostatic hypotensive": 5302,
    "orthostatic hypotensive and hypotensive": 24,
    "orthostatic hypotensive, hypotensive, and antihypertensive": 2138,
    "ototoxic": 54,
    "pancreatitis": 2,
    "photosensitizing": 220,
    "sedative": 9548,
    "serotonergic": 3074,
    "serotonergic and central nervous system depressant (CNS depressant)": 118,
    "skeletal muscle relaxing": 4,
    "smooth muscle relaxing": 29,
    "stimulatory": 2594,
    "sympathomimetic": 272,
    "tachycardic": 1242,
    "teratogenic": 2,
    "thrombogenic": 21546,
    "uterotonic": 19,
    "vasoconstricting": 1758,
    "vasodilatory": 1916,
    "vasopressor": 834
}

@ecwood
Copy link
Collaborator Author

ecwood commented Jun 27, 2024

This map covers all of the sentence types in the DrugBank drug interaction field: (the keys are placeholders for the fields that change with each entry)

"risk_or_severity_increase": ["The risk or severity of ", DISEASE_KEY, " can be increased when ", MAIN_DRUG_KEY " is combined with ", INTERACTION_DRUG_KEY]
"risk_or_severity_decrease": ["The risk or severity of ", DISEASE_KEY, " can be decreased when ", MAIN_DRUG_KEY " is combined with ", INTERACTION_DRUG_KEY]
"may_impact_activity_increase": [MAIN_DRUG_KEY, " may increase the ", ACTIVITY_KEY, " activities of ", INTERACTION_DRUG_KEY]
"may_impact_activity_decrease": [MAIN_DRUG_KEY, " may decrease the ", ACTIVITY_KEY, " activities of ", INTERACTION_DRUG_KEY]
"therapeutic_efficacy_increase": ["The therapeutic efficacy of ", INTERACTION_DRUG_KEY, " can be increased when used in combination with ", MAIN_DRUG_KEY]
"therapeutic_efficacy_decrease": ["The therapeutic efficacy of ", INTERACTION_DRUG_KEY, " can be decreased when used in combination with ", MAIN_DRUG_KEY]
"higher_serum_level": [MAIN_DRUG_KEY, " may decrease the excretion rate of ", INTERACTION_DRUG_KEY, " which could result in a higher serum level"]
"metabolism_increase": ["The metabolism of ", MAIN_DRUG_KEY, " can be increased when combined with ", INTERACTION_DRUG_KEY]
"metabolism_decrease": ["The metabolism of ", MAIN_DRUG_KEY, " can be decreased when combined with ", INTERACTION_DRUG_KEY]
"serum_concentration_increase": ["The serum concentration of ", MAIN_DRUG_KEY, " can be increased when it is combined with ", INTERACTION_DRUG_KEY]
"serum_concentration_decrease": ["The serum concentration of ", MAIN_DRUG_KEY, " can be decreased when it is combined with ", INTERACTION_DRUG_KEY]
"excretion_rate_increase": [INTERACTION_DRUG_KEY, " may increase the excretion rate of ", MAIN_DRUG_KEY, " which could result in a lower serum level and potentially a reduction in efficacy"]
"absorption_decrease": [INTERACTION_DRUG_KEY, " can cause a decrease in the absorption of ", MAIN_DRUG_KEY, " resulting in a reduced serum concentration and potentially a decrease in efficacy"]
"excretion_increase": ["The excretion of ", MAIN_DRUG_KEY, " can be increased when combined with ", INTERACTION_DRUG_KEY]
"excretion_decrease": ["The excretion of ", MAIN_DRUG_KEY, " can be decreased when combined with ", INTERACTION_DRUG_KEY]
"active_metabolites_increase": ["The serum concentration of the active metabolites of ", INTERACTION_DRUG_KEY, " can be increased when ", INTERACTION_DRUG_KEY, " is used in combination with ", MAIN_DRUG_KEY]
"active_metabolites_decrease": ["The serum concentration of the active metabolites of ", INTERACTION_DRUG_KEY, " can be decreased when ", INTERACTION_DRUG_KEY, " is used in combination with ", MAIN_DRUG_KEY]
"bioavailibility_decrease": ["The bioavailability of ", MAIN_DRUG_KEY, " can be decreased when combined with ", INTERACTION_DRUG_KEY]
"bioavailibility_increase": ["The bioavailability of ", MAIN_DRUG_KEY, " can be increased when combined with ", INTERACTION_DRUG_KEY]
"diagnostic_agent_effectiveness_decrease": [INTERACTION_DRUG_KEY, " may decrease effectiveness of ", MAIN_DRUG_KEY, " as a diagnostic agent"]
"absorption_increase": [MAIN_DRUG_KEY, " can cause an increase in the absorption of ", INTERACTION_DRUG_KEY, " resulting in an increased serum concentration and potentially a worsening of adverse effects"]
"diagnostic_agent_effectiveness_increase": [INTERACTION_DRUG_KEY, " may increase effectiveness of ", MAIN_DRUG_KEY, " as a diagnostic agent"]
"absorption_of_decreased": ["The absorption of ", INTERACTION_DRUG_KEY, " can be decreased when combined with ", MAIN_DRUG_KEY]
"protein_binding_decrease": ["The protein binding of ", INTERACTION_DRUG_KEY, " can be decreased when combined with ", MAIN_DRUG_KEY]
"hypersensitivity_reaction_increase": ["The risk of a hypersensitivity reaction to ", INTERACTION_DRUG_KEY, " is increased when it is combined with ", MAIN_DRUG_KEY]
"serum_concentration_of_active_metabolites": ["The serum concentration of the active metabolites of ", MAIN_DRUG_KEY, " can be reduced when ", MAIN_DRUG_KEY, " is used in combination with ", INTERACTION_DRUG_KEY, " resulting in a loss in efficacy"]
"serum_concentration_increased_in_combination": ["The serum concentration of ", INTERACTION_DRUG_KEY, ", an active metabolite of ", MAIN_DRUG_KEY, ", can be increased when used in combination with ", MAIN_DRUG_KEY]
"serum_concentration_decreased_in_combination": ["The serum concentration of ", INTERACTION_DRUG_KEY, ", an active metabolite of ", MAIN_DRUG_KEY, ", can be decreased when used in combination with ", MAIN_DRUG_KEY]

Here are the counts for each sentence type:

{
    "absorption_decrease": 22367,
    "absorption_increase": 555,
    "absorption_of_decreased": 648,
    "active_metabolites_decrease": 154,
    "active_metabolites_increase": 578,
    "bioavailibility_decrease": 1844,
    "bioavailibility_increase": 170,
    "diagnostic_agent_effectiveness_decrease": 1505,
    "diagnostic_agent_effectiveness_increase": 20,
    "excretion_decrease": 19972,
    "excretion_increase": 570,
    "excretion_rate_increase": 60388,
    "higher_serum_level": 352172,
    "hypersensitivity_reaction_increase": 2101,
    "may_impact_activity_decrease": 89722,
    "may_impact_activity_increase": 220905,
    "metabolism_decrease": 295535,
    "metabolism_increase": 109532,
    "protein_binding_decrease": 2820,
    "risk_or_severity_decrease": 986,
    "risk_or_severity_increase": 1208592,
    "serum_concentration_decrease": 40104,
    "serum_concentration_decreased_in_combination": 44,
    "serum_concentration_increase": 129870,
    "serum_concentration_increased_in_combination": 436,
    "serum_concentration_of_active_metabolites": 206,
    "therapeutic_efficacy_decrease": 232445,
    "therapeutic_efficacy_increase": 45245
}

@ecwood
Copy link
Collaborator Author

ecwood commented Jun 27, 2024

02f1cbb contains the code for identifying and extracting information from the different sentence types. A few disclaimers:

  • I tried to verify places where interaction drug vs main drug occur, but sometimes it didn't seem standardized. Hopefully, the cases where it isn't standard will use symmetric predicates. Otherwise, we will need to figure that out.
  • We don't actually need the names of the drugs (we have the IDs for that), but it is helpful to extract them for verification purposes.
  • We do need the names of the diseases and activities, because we will have to map those ourselves.

@ecwood
Copy link
Collaborator Author

ecwood commented Jun 27, 2024

This should hopefully be a good stepping stone towards #369 (to include other free text information from DrugBank in KG2).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant