Canabinoid Cytokine Analysis

In [2]:

    

from __future__ import division
import os, os.path
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import sys
sys.path.append('/home/will/PySeqUtils/')
sys.path.append('/home/will/PatientPicker/')
os.chdir('/home/will/HIVSystemsBio/MoreCytokineAnalysis/')


    

In [3]:

    

raw_cyto_data = pd.read_csv('../NewCytokineAnalysis/CytoRawData.csv', sep = '\t')


    

In [7]:

    

import LoadingTools
redcap_data = LoadingTools.load_redcap_data()
redcap_data = redcap_data.groupby(['Patient ID', 'VisitNum']).first()


    

In [99]:

    

def count_with_skips(inser, nskips):
    skips = 0
    for row in inser.values:
        if row:
            skips = 0
        else:
            skips += 1
        if skips > nskips:
            return False
    return True

name_mappings = {'Test-Benzodiazepine':'SBe', 
                'Test-Cannabinoid':'SCa', 
                'Test-Cocaine':'PC',
                'Test-Opiates':'PO',
                'Test-Amphetamines':np.nan,
                'Test-Barbiturates':np.nan,
                'Test-Phencyclidine':np.nan
                }

def niz_groupings(indf):
    
    inds = [v for p, v in indf.index]
    
    if len(indf.index) < 3:
        return pd.Series(np.nan, index=inds)
    indf = indf.dropna()
    ever_used = indf.any(axis = 0)
    if not ever_used.any():
        return pd.Series('PN', index=inds)
    all_used = indf.all(axis = 0)
    if all_used.sum() == 1:
        return pd.Series(name_mappings[all_used.idxmax()], index=inds)
    elif all_used.sum() > 1:
        return pd.Series('MDU', index=inds)
    
    pure_cols = []
    non_pure_cols = []
    for col in indf.columns:
        if count_with_skips(indf[col], 1):
            pure_cols.append(col)
        else:
            non_pure_cols.append(col)
    if ever_used[non_pure_cols].any():
        return pd.Series(np.nan, index=inds)
            
    if len(pure_cols) == 1:
        return pd.Series(name_mappings[pure_cols[0]], index=inds)
    else:
        return pd.Series('MDU', index=inds)

admit_cols = [col for col in redcap_data.columns if col.startswith('Admit')]
admit_data = redcap_data[admit_cols].any(axis = 1).groupby(level = 'Patient ID').transform('any')
drug_names = ['Test-Benzodiazepine', 'Test-Cannabinoid', 'Test-Cocaine', 'Test-Opiates']
niz_groupings = redcap_data[drug_names].groupby(level = 'Patient ID').apply(niz_groupings)
niz_groupings[(niz_groupings == 'PN') & (admit_data)] = np.nan


    

In [100]:

    

def safe_days(val):
    try:
        return val/np.timedelta64(1, 'D')
    except:
        return np.nan


def get_days_since_bl(ser):
    
    fdate = ser.dropna().min()
    diff_dates = (ser-fdate).apply(safe_days)
    return diff_dates


def guess_race(indf):
    race_cols = [col for col in indf.columns if col.startswith('Race-')]
    race = indf[race_cols].sum().idxmax()
    vnums = [v for _, v in indf.index]
    rser = pd.Series([race]*len(indf), index = vnums)
    return rser

def convert_haart(inval):
    tdict = {'on': 'cH',
             'non-adherent': 'dH',
             'off': 'dH',
             'naive': 'nH'}
    return tdict.get(inval, np.nan)


cols = {'Age':redcap_data.groupby(level = 0)['Age'].transform('min'),
        'NumTotalVisits': redcap_data.groupby(level = 0)['Age'].transform(len),
        'Latest CD4 count': redcap_data['Latest CD4 count (cells/uL)'],
        'Current Alcohol use': redcap_data['Current Alcohol Use'],
        'Current Tobacco use': redcap_data['Current Tobacco Use'],
        'Days since baseline': redcap_data.groupby(level = 0)['Date Of Visit'].transform(get_days_since_bl),
        'Gender': redcap_data['Gender'],
        'Grouping': niz_groupings,
        'Race': redcap_data.groupby(level=0).apply(guess_race),
        'HAART': redcap_data['Current ART status'].map(convert_haart),
        'Hepatitis C status (HCV)': redcap_data.groupby(level=0)['Hepatitis C status (HCV)'].transform(pd.expanding_max),
        'HIVD score': redcap_data['TMHDS'],
        'HIVD.I': redcap_data['TMHDS']<10,
        'Hepatitis B status (HBV)': redcap_data.groupby(level=0)['Hepatitis B status (HBV)'].transform(pd.expanding_max),
        'Latest CD8 count': redcap_data['Latest CD8 count (cells/uL)'],
        'Nadir CD4 count': redcap_data.groupby(level=0)['Nadir CD4 count (cells/uL)'].transform(pd.expanding_min),
        'Nadir CD8 count': redcap_data.groupby(level=0)['Nadir CD8 count (cells/uL)'].transform(pd.expanding_min),
        'Peak viral load': redcap_data.groupby(level=0)['Peak viral load (copies/mL)'].transform(pd.expanding_max),
        'Latest Viral load': redcap_data['Latest viral load'],
        'Years Seropositive': redcap_data['Years Seropositive'],
        'TOSample.Benzodiazepines': redcap_data.groupby(level=0)['Test-Benzodiazepine'].transform(pd.expanding_mean),
        'TOSample.Cannabinoid': redcap_data.groupby(level=0)['Test-Cannabinoid'].transform(pd.expanding_mean),
        'TOSample.Cocaine': redcap_data.groupby(level=0)['Test-Cocaine'].transform(pd.expanding_mean),
        'TOSample.Opiates': redcap_data.groupby(level=0)['Test-Opiates'].transform(pd.expanding_mean),
        'ALL.Benzodiazepines': redcap_data.groupby(level=0)['Test-Benzodiazepine'].transform('mean'),
        'ALL.Cannabinoid': redcap_data.groupby(level=0)['Test-Cannabinoid'].transform('mean'),
        'ALL.Cocaine': redcap_data.groupby(level=0)['Test-Cocaine'].transform('mean'),
        'ALL.Opiates': redcap_data.groupby(level=0)['Test-Opiates'].transform('mean'),
        'ATSample.Benzodiazepines': redcap_data['Test-Benzodiazepine'],
        'ATSample.Cannabinoid': redcap_data['Test-Cannabinoid'],
        'ATSample.Cocaine': redcap_data['Test-Cocaine'],
        'ATSample.Opiates': redcap_data['Test-Opiates']}

known_pat_data = pd.DataFrame(cols)


    

In [101]:

    

known_pat_data


    

    
Out[101]:




&ltclass 'pandas.core.frame.DataFrame'>
MultiIndex: 1419 entries, (A0001, R00) to (A0514, R00)
Data columns (total 32 columns):
ALL.Benzodiazepines         1371  non-null values
ALL.Cannabinoid             1371  non-null values
ALL.Cocaine                 1371  non-null values
ALL.Opiates                 1371  non-null values
ATSample.Benzodiazepines    774  non-null values
ATSample.Cannabinoid        774  non-null values
ATSample.Cocaine            774  non-null values
ATSample.Opiates            774  non-null values
Age                         1415  non-null values
Current Alcohol use         1381  non-null values
Current Tobacco use         1381  non-null values
Days since baseline         1247  non-null values
Gender                      1398  non-null values
Grouping                    354  non-null values
HAART                       1383  non-null values
HIVD score                  1223  non-null values
HIVD.I                      1419  non-null values
Hepatitis B status (HBV)    1236  non-null values
Hepatitis C status (HCV)    1321  non-null values
Latest CD4 count            1348  non-null values
Latest CD8 count            1092  non-null values
Latest Viral load           1335  non-null values
Nadir CD4 count             1343  non-null values
Nadir CD8 count             1243  non-null values
NumTotalVisits              1419  non-null values
Peak viral load             1316  non-null values
Race                        1419  non-null values
TOSample.Benzodiazepines    1371  non-null values
TOSample.Cannabinoid        1371  non-null values
TOSample.Cocaine            1371  non-null values
TOSample.Opiates            1371  non-null values
Years Seropositive          1371  non-null values
dtypes: bool(1), float64(9), object(22)

In [14]:

    

list(redcap_data.columns)


    

    
Out[14]:





['Event Name',
 'Patient Visit Number',
 'Date Of Visit',
 'Year Of Birth',
 'Age',
 'Gender',
 'Transgender Designation',
 'Ethnicity',
 'Race-Asian',
 'Race-Indian',
 'Race-Black',
 'Race-Hawaiian',
 'Race-White',
 'Race-Multiple',
 'Race-Unknown',
 'Height',
 'Weight',
 'Abdominal Girth',
 'Highest education level completed',
 'Exposure-MSM',
 'Exposure-IDU',
 'Exposure-Ttransfusion',
 'Exposure-Heterosexual',
 'Exposure-Hemophilia',
 'Exposure-Perinatal',
 'Exposure-MSM+IDU',
 'Exposure-Heterosexual+IDU',
 'Exposure-Other',
 'Exposure-ND',
 'Exposure-Explanation',
 'Current Tobacco Use',
 'Date Stopped Tobacco Use',
 'Tobacco-Cigarettes',
 'Tobacco-Cigars',
 'Tobacco-Pipes',
 'Tobacco-Chewing+Tobacco',
 'Tobacco Uses Per Day',
 'Number Years Used',
 'Current Alcohol Use',
 'Date Stopped Alcohol Use',
 'Number Of Beers Consumed Per Week',
 'Number Of Glasses Of Wine Consumed Per Week',
 'Number Of Liquor Based Drinks Consumed Per Eeek',
 'Current Drug use',
 'Date Stopped Drug Use',
 'Age First Used Drugs',
 'Date Last Used Drugs',
 'Drug Use And HIV Status',
 'Admit-Cannabinoid',
 'Admit-Cocaine',
 'Admit-Heroin',
 'Admit-Amphetamines',
 'Admit-Benzodiazapine',
 'Admit-Narcotics',
 'Admit-Ecstasy',
 'Admit-PCP',
 'Admit-Ritalin',
 'Admit-Other',
 'Admit-None',
 'Designation Of Other Drug Use',
 'Specimen-Collection-Urine',
 'Specimen-Collection-Hair-Follicles',
 'Specimen-Collection-Blood',
 'Test-Amphetamines',
 'Test-Barbiturates',
 'Test-Benzodiazepine',
 'Test-Cannabinoid',
 'Test-Cocaine',
 'Test-Opiates',
 'Test-Phencyclidine',
 'Drug User Designation',
 'Pregnant',
 'Estimated Due Date',
 'HIV Seropositive Date',
 'Years Seropositive',
 'Seropositive Date Verbal',
 'Seropositive Date Medical Records',
 'Likely location of infection',
 'DSG lowest',
 'DSG today',
 'Initial CD4 count (cells/uL)',
 'Date of initial CD4 count',
 'Nadir CD4 count (cells/uL)',
 'Date of nadir CD4 count',
 'Latest CD4 count (cells/uL)',
 'Date of latest CD4 count',
 'Initial CD8 count (cells/uL)',
 'Date of initial CD8 count',
 'Nadir CD8 count (cells/uL)',
 'Date of nadir CD8 count',
 'Latest CD8 count (cells/uL)',
 'Date of latest CD8 count',
 'Initial viral load (copies/mL)',
 'Date of initial viral load',
 'Peak viral load (copies/mL)',
 'Date of peak viral load',
 'Latest viral load',
 'Date of latest viral load',
 'Current ART status',
 'Date first began HAART',
 "Current ART (choice='AZT')",
 "Current ART (choice='ABC')",
 "Current ART (choice='DVL')",
 "Current ART (choice='ATV')",
 "Current ART (choice='T-20')",
 "Current ART (choice='3TC')",
 "Current ART (choice='TDF')",
 "Current ART (choice='SAQ')",
 "Current ART (choice='AMP')",
 "Current ART (choice='FPV')",
 "Current ART (choice='DDI')",
 "Current ART (choice='FTC')",
 "Current ART (choice='RTV')",
 "Current ART (choice='LPV/r')",
 "Current ART (choice='DDC')",
 "Current ART (choice='EFV')",
 "Current ART (choice='NFL')",
 "Current ART (choice='TPV')",
 "Current ART (choice='D4T')",
 "Current ART (choice='NVP')",
 "Current ART (choice='IDV')",
 "Current ART (choice='DRV')",
 "Current ART (choice='Combivir')",
 "Current ART (choice='Trizivir')",
 "Current ART (choice='Kaletra')",
 "Current ART (choice='Epzicom')",
 "Current ART (choice='Truvada')",
 "Current ART (choice='Atripla')",
 "Current ART (choice='Other')",
 "Current ART (choice='none')",
 "Current ART (choice='ND')",
 "Define 'other' selection for current ART",
 "Past ART (choice='AZT')",
 "Past ART (choice='ABC')",
 "Past ART (choice='DVL')",
 "Past ART (choice='ATV')",
 "Past ART (choice='T-20')",
 "Past ART (choice='3TC')",
 "Past ART (choice='TDF')",
 "Past ART (choice='SAQ')",
 "Past ART (choice='AMP')",
 "Past ART (choice='FPV')",
 "Past ART (choice='DDI')",
 "Past ART (choice='FTC')",
 "Past ART (choice='RTV')",
 "Past ART (choice='LPV/r')",
 "Past ART (choice='DDC')",
 "Past ART (choice='EFV')",
 "Past ART (choice='NFL')",
 "Past ART (choice='TPV')",
 "Past ART (choice='D4T')",
 "Past ART (choice='NVP')",
 "Past ART (choice='IDV')",
 "Past ART (choice='DRV')",
 "Past ART (choice='Combivir')",
 "Past ART (choice='Trizivir')",
 "Past ART (choice='Kaletra')",
 "Past ART (choice='Epzicom')",
 "Past ART (choice='Truvada')",
 "Past ART (choice='Atripla')",
 "Past ART (choice='Other')",
 "Past ART (choice='none')",
 "Past ART (choice='ND')",
 "Define 'other' selection for past ART",
 'List any drug resistance',
 'Date of patients most recent CBC test',
 'Red blood cell count date',
 'Red blood cell count result',
 'Hemoglobin date',
 'Hemoglobin results',
 'Hematocrit date',
 'Hematocrit results',
 'Red blood cell indices date',
 'Red blood cells indices results',
 'Mean corpuscular hemoglobin date',
 'Mean corpuscular hemoglobin results',
 'Mean corpuscular hemoglobin concentration date',
 'Mean corpuscular hemoglobin concentration results',
 'Red blood cell distribution date',
 'Red blood cell distribution results',
 'White blood cell count date',
 'White blood cell count results',
 'Differential count date',
 'Differential count results',
 'Platelet count date',
 'Platelet count results',
 'Creatinine date',
 'Creatinine results',
 'BUN date',
 'BUN results',
 'Bilirubin date',
 'Bilirubin results',
 'Hepatitis B status (HBV)',
 'Year diagnosed HBV positive',
 'Hepatitis C status (HCV)',
 'Year diagnosed HCV positive',
 'Cytomegalovirus (CMV)',
 'Year diagnosed CMV positive',
 'Human Papillomavirus (HPV)',
 'Year diagnosed HPV positive',
 'Herpes Simplex Virus Type 1 (HSV 1)',
 'Year diagnosed HSV 1 positive',
 'Herpes Simplex Virus Type 2 (HSV 2)',
 'Year diagnosed HSV 2 positive',
 'Tuberculosis',
 'Year diagnosed tuberculosis positive',
 'Hypertension',
 'Year diagnosed with hypertension',
 'Diabetes',
 'Year diagnosed with diabetes',
 'Elevated lipids',
 'Year diagnosed with elevated lipids',
 'Asthma',
 'Year diagnosed with asthma',
 'Chronic obstructive pulmonary disease (COPD)',
 'Year diagnosed with COPD',
 "Current AIDS defining indicators (choice='Candidiasis of bronchi, trachea, or lungs')",
 "Current AIDS defining indicators (choice='Candidiasis, esophageal')",
 "Current AIDS defining indicators (choice='Cervical cancer, invasive')",
 "Current AIDS defining indicators (choice='Coccidioidomycosis, disseminated')",
 "Current AIDS defining indicators (choice='Cryptococcosis, extrapulmonary')",
 "Current AIDS defining indicators (choice='Cryptosporidiosis, chronic intestinal (>1 month duration)')",
 "Current AIDS defining indicators (choice='Cytomegalovirus disease- other than liver, spleen, or lymph nodes')",
 "Current AIDS defining indicators (choice='Cytomegalovirus retinitis (with loss of vision)')",
 "Current AIDS defining indicators (choice='Encephalopathy, HIV-related')",
 "Current AIDS defining indicators (choice='Herpes simplex: chronic ulcer(s) (>1 mo. duration) or bronchitis, pneumonitis, or esophagitis')",
 "Current AIDS defining indicators (choice='Histoplasmosis, disseminated')",
 "Current AIDS defining indicators (choice='Isosporiasis, chronic intestinal (>1 month duration)')",
 "Current AIDS defining indicators (choice='Kaposi's sarcoma')",
 "Current AIDS defining indicators (choice='Lymphoma, Burkitt's')",
 "Current AIDS defining indicators (choice='Lymphoma, immunoblastic')",
 "Current AIDS defining indicators (choice='Lymphoma, primary, of brain (primary central nervous system lymphoma)')",
 "Current AIDS defining indicators (choice='Mycobacterium avium complex or disease caused by M. Kansasii, disseminated')",
 "Current AIDS defining indicators (choice='Disease caused by Mycobacterium tuberculosis, any site (pulmonary or extrapulmonary)')",
 "Current AIDS defining indicators (choice='Disease caused by Mycobacterium, other species or unidentified species, disseminated')",
 "Current AIDS defining indicators (choice='Pneumocystis carinii pneumonia')",
 "Current AIDS defining indicators (choice='Pneumonia, recurrent')",
 "Current AIDS defining indicators (choice='Progressive multifocal leukoencephalopathy')",
 "Current AIDS defining indicators (choice='Salmonella septicemia, recurrent')",
 "Current AIDS defining indicators (choice='Toxoplasmosis of brain (encephalitis)')",
 "Current AIDS defining indicators (choice='Wasting syndrome caused by HIV infection')",
 "Current AIDS defining indicators (choice='Other')",
 "Current AIDS defining indicators (choice='none')",
 'Date diagnosed: Candidiasis of bronchi, trachea, or lungs',
 'Date diagnosed: Candidiasis, esophageal',
 'Date diagnosed: Cervical Cancer, invasive',
 'Date diagnosed: Coccidioidomycosis, disseminated',
 'Date diagnosed: Cryptococcosis, extrapulmonary',
 'Date diagnosed: Crypotosporidiosis, chronic intestinal (>1 month duration)',
 'Date diagnosed: Cytomegalovirus disease- other than liver, spleen, or lymph nodes',
 'Date diagnosed: Cytomegalovirus retinitis (with loss of vision)',
 'Date diagnosed: Encephalopathy, HIV-related',
 'Date diagnosed: Herpes simplex, chronic ulcer(s) (>1 mo. duration) or bronchitis, pneumonitis, or esophagitis',
 'Date diagnosed: Histoplasmosis, disseminated',
 'Date diagnosed: Isosporiasis, chronic intestinal (>1month duration)',
 "Date diagnosed: Kaposi's sarcoma",
 "Date diagnosed: Lymphoma, Burkitt's",
 'Date diagnosed: Lymphoma, immunoblastic',
 'Date diagnosed: Lymphoma, primary, of brain (primary central nervous system lymphoma)',
 'Date diagnosed: Mycobacterium avium complex or disease caused by M. Kansasii, disseminated',
 'Date diagnosed: Disease caused by Mycobacterium tuberculosis, any site (pulmonary or extrapulmonary)',
 'Date diagnosed: Disease caused by Mycobacterium, other species or unidentified species, disseminated',
 'Date diagnosed: Pneumocystis carinii pneumonia',
 'Date diagnosed: Pneumonia, recurrent',
 'Date diagnosed: Progressive multifocal leukoencephalopathy',
 'Date diagnosed: Salmonella septicemia, recurrent',
 'Date diagnosed: Toxoplasmosis of brain (encephalitis)',
 'Date diagnosed: Wasting syndrome caused by HIV infection',
 "Define 'other' designation for AIDS defining indicators.  Include date diagnosed.",
 "Past AIDS defining indicators (choice='Candidiasis of bronchi, trachea, or lungs')",
 "Past AIDS defining indicators (choice='Candidiasis, esophageal')",
 "Past AIDS defining indicators (choice='Cervical cancer, invasive')",
 "Past AIDS defining indicators (choice='Coccidioidomycosis, disseminated')",
 "Past AIDS defining indicators (choice='Cryptococcosis, extrapulmonary')",
 "Past AIDS defining indicators (choice='Cryptosporidiosis, chronic intestinal (>1 month duration)')",
 "Past AIDS defining indicators (choice='Cytomegalovirus disease- other than liver, spleen, or lymph nodes')",
 "Past AIDS defining indicators (choice='Cytomegalovirus retinitis (with loss of vision)')",
 "Past AIDS defining indicators (choice='Encephalopathy, HIV-related')",
 "Past AIDS defining indicators (choice='Herpes simplex: chronic ulcer(s) (>1 mo. duration) or bronchitis, pneumonitis, or esophagitis')",
 "Past AIDS defining indicators (choice='Histoplasmosis, disseminated')",
 "Past AIDS defining indicators (choice='Isosporiasis, chronic intestinal (>1 month duration)')",
 "Past AIDS defining indicators (choice='Kaposi's sarcoma')",
 "Past AIDS defining indicators (choice='Lymphoma, Burkitt's')",
 "Past AIDS defining indicators (choice='Lymphoma, immunoblastic')",
 "Past AIDS defining indicators (choice='Lymphoma, primary, of brain (primary central nervous system lymphoma)')",
 "Past AIDS defining indicators (choice='Mycobacterium avium complex or disease caused by M. Kansasii, disseminated')",
 "Past AIDS defining indicators (choice='Disease caused by Mycobacterium tuberculosis, any site (pulmonary or extrapulmonary)')",
 "Past AIDS defining indicators (choice='Disease caused by Mycobacterium, other species or unidentified species, disseminated')",
 "Past AIDS defining indicators (choice='Pneumocystis carinii pneumonia')",
 "Past AIDS defining indicators (choice='Pneumonia, recurrent')",
 "Past AIDS defining indicators (choice='Progressive multifocal leukoencephalopathy')",
 "Past AIDS defining indicators (choice='Salmonella septicemia, recurrent')",
 "Past AIDS defining indicators (choice='Toxoplasmosis of brain (encephalitis)')",
 "Past AIDS defining indicators (choice='Wasting syndrome caused by HIV infection')",
 "Past AIDS defining indicators (choice='Other')",
 "Past AIDS defining indicators (choice='none')",
 'Date resolved: Candidiasis of bronchi, trachea, or lungs',
 'Date resolved: Candidiasis, esophageal',
 'Date resolved: Cervical Cancer, invasive',
 'Date resolved: Coccidioidomycosis, disseminated',
 'Date resolved: Cryptococcosis, extrapulmonary',
 'Date resolved: Crypotosporidiosis, chronic intestinal (>1 month duration)',
 'Date resolved: Cytomegalovirus disease- other than liver, spleen, or lymph nodes',
 'Date resolved: Cytomegalovirus retinitis (with loss of vision)',
 'Date resolved: Encephalopathy, HIV-related',
 'Date resolved: Herpes simplex, chronic ulcer(s) (>1 mo. duration) or bronchitis, pneumonitis, or esophagitis',
 'Date resolved: Histoplasmosis, disseminated',
 'Date resolved: Isosporiasis, chronic intestinal (>1month duration)',
 "Date resolved: Kaposi's sarcoma",
 "Date resolved: Lymphoma, Burkitt's",
 'Date resolved: Lymphoma, immunoblastic',
 'Date resolved: Lymphoma, primary, of brain (primary central nervous system lymphoma)',
 'Date resolved: Mycobacterium avium complex or disease caused by M. Kansasii, disseminated',
 'Date resolved: Disease caused by Mycobacterium tuberculosis, any site (pulmonary or extrapulmonary)',
 'Date resolved: Disease caused by Mycobacterium, other species or unidentified species, disseminated',
 'Date resolved: Pneumocystis carinii pneumonia',
 'Date resolved: Pneumonia, recurrent',
 'Date resolved: Progressive multifocal leukoencephalopathy',
 'Date diagnosed: Salmonella septicemia, recurrent.1',
 'Date resolved: Toxoplasmosis of brain (encephalitis)',
 'Date resolved: Wasting syndrome caused by HIV infection',
 "Define 'other' designation for AIDS defining indicators. Include date resolved.",
 'Neurocognitive test',
 'MSK Score',
 'Psychomotor Speed Score',
 'Memory Recall Score',
 'Constructional Score',
 'TMHDS',
 'Mental health history (including inpatient stay for MH) / Hospitalizations for medical/surgical reasons)',
 'Other diagnoses or complicating conditions relating to HIV-1 infection including all sexually transmitted diseases',
 'Other comments or observations',
 "Mental Health Issues (choice='Depression')",
 "Mental Health Issues (choice='Bipolar')",
 "Mental Health Issues (choice='Schizophrenia')",
 "Mental Health Issues (choice='ADHD')",
 "Mental Health Issues (choice='Anxiety')",
 "Mental Health Issues (choice='Dementia')",
 "Mental Health Issues (choice='Epilepsy/Seizures')",
 "Mental Health Issues (choice='Diagnosed HIVD')",
 "Mental Health Issues (choice='Head trauma or spinal injury')",
 "Mental Health Issues (choice='MS')",
 "Mental Health Issues (choice='Paranoia')",
 "Mental Health Issues (choice='PTSD')",
 "Mental Health Issues (choice='Stroke')",
 "Mental Health Issues (choice='Peripheral neuropathy')",
 "Mental Health Issues (choice='Other neurological problems')",
 "Mental Health Issues (choice='No neurological problems')",
 "Clarification of 'other neurological problems' under mental health issues",
 'Complete?',
 'PBMC isolation complete',
 'Date of PBMC isolation',
 'Number of tubes of PBMCs collected',
 'Serum collected',
 'Number of tubes of serum collected',
 'Genomic DNA isolated',
 'Concentration of genomic DNA',
 'Successful PCR product collection',
 'Date of successful PCR product collection',
 'Name of person who completed successful PCR',
 'Lab notebook number of PCR collection',
 'Lab notebook page number of PCR collection',
 'PCR sequence obtained',
 'Company who completed PCR sequencing',
 'Date of successful PCR product sequencing',
 'Sequence sent to Brian Moldover',
 'Drop box folder title',
 'Date trace file sent to Brian Moldover',
 'Sequence passed quality control',
 'Date sequence passed quality control',
 'SNPs for trace file determined',
 'Date SNPs were called',
 '4.4kB fragment for this visit',
 'Date of 4.4kB fragment',
 'Name of person who successfully completed 4.4kB fragment',
 'Lab notebook number of 4.4kB fragment',
 'Lab notebook page number of 4.4kB fragment',
 "Sequence of 4.4kB obtained (choice='whole fragment')",
 "Sequence of 4.4kB obtained (choice='LTR')",
 "Sequence of 4.4kB obtained (choice='envelope')",
 "Sequence of 4.4kB obtained (choice='V3 only')",
 "Sequence of 4.4kB obtained (choice='other')",
 "Define 'other' for sequence of 4.4kB obtained ",
 'Deep sequencing for this visit',
 'Date of Deep sequencing',
 'Deep sequencing completed by which facility',
 'Lab notebook number for deep sequencing',
 'Lab notebook page number for deep sequencing',
 'RNA isolated',
 'Date of RNA isolation',
 'Name of person who isolated RNA',
 'Lab notebook number for RNA isolation',
 'Lab notebook page number for RNA isolation',
 'Microarray/RNA expression profiling completed',
 'Date microarray/RNA expression profiling completed',
 'Name of person/facitlity that completed microarray/RNA expression profiling',
 'Lab notebook number for microarray/RNA expression profiling',
 'Lab notebook page number for microarray/RNA expression profiling',
 'miRNA profiling completed',
 'Date miRNA profiling completed',
 'Name of person/facility that completed miRNA profiling',
 'Lab notebook number for miRNA profiling',
 'Lab notebook page number for miRNA profiling',
 'Cytokine profiling completed',
 'Date cytokine profiling completed',
 'Name of person/facility that completed cytokine profiling',
 'Lab notebook number for cytokine profiling',
 'Lab notebook page number for cytokine profiling',
 'Viral RNA from plasma isolated',
 'Date of vRNA isolation',
 'Name of person who isolated vRNA ',
 'Lab notebook number for vRNA isolation',
 'Lab notebook page number for vRNA isolation',
 'Envelope in silico prediction completed',
 'Date of envelope in silico prediction completion',
 'Name of person who completed envelope in silico prediction',
 'Lab notebook number of envelope in silico prediction',
 'Lab notebook page number of envelope in silico prediction',
 'Envelope functionality/tropism completed',
 'Date of envelope functionality/tropism completion',
 'Name of person who completed envelope functionality/tropism',
 'Lab notebook number of envelope functionality/tropism',
 'Lab notebook page number of envelope functionality/tropism',
 'Complete?.1',
 'HAART-Naive',
 'HAART-Non-Adherent',
 'HAART-Off',
 'HAART-On',
 'HAART-Missing']

In [ ]: