Gemcitabine Hydrochloride and Cisplatin With or Without Veliparib or Veliparib Alone in Treating Patients With Locally Advanced or Metastatic Pancreatic Cancer

Prior treatment

• Patients who have had chemotherapy or radiotherapy within 3 weeks (6 weeks for nitrosoureas or mitomycin C) prior to entering the study or those who have not recovered from adverse events due to agents administered more than 3 weeks earlier
  • For part I, prior adjuvant therapy with gemcitabine or a fluoropyrimidine therapy is permitted if completed \> 6 months prior to recurrence; no prior PARP inhibitor therapy is allowed
  • For part II, no prior PARP inhibitor therapy is permitted and up to two prior treatment regimens are permitted as follows: 1 adjuvant and 1 metastatic; 1 locally advanced and 1 metastatic; or 2 metastatic, or a variation thereof
• Patients may not be receiving any other investigational agents
• Pregnant women are excluded from this study because veliparib is a PARP inhibitor with the potential for teratogenic or abortifacient effects; because there is an unknown but potential risk for adverse events in nursing infants secondary to treatment of the mother with veliparib, breastfeeding should be discontinued if the mother is treated with veliparib; these potential risks may also apply to other agents used in this study
• Patients with uncontrolled central nervous system (CNS) metastasis are not eligible; patients with CNS metastases are to be stable for \> 3 months after treatment and off steroid treatment prior to study enrollment
• Patients with prior allogeneic bone marrow transplant or double umbilical cord blood transplantation are ineligible

Other illness

• History of allergic reactions attributed to compounds of similar chemical or biologic composition to veliparib or other agents used in study
• Uncontrolled intercurrent illness including, but not limited to, ongoing or active infection, symptomatic congestive heart failure, unstable angina pectoris, cardiac arrhythmia, or psychiatric illness/social situations that would limit compliance with study requirements
• Patients with a known active infection, e.g., hepatitis B virus or hepatitis C virus; human immunodeficiency virus (HIV)-positive patients who are otherwise well and who do not have evidence of significant immune compromise are eligible
• Patients with active seizure or history of seizure are not eligible
• Patients with prior malignancy successfully treated who are currently stable and on no active treatment are eligible
• Patients with treatment-related acute myeloid leukemia (AML) (t-AML)/myelodysplastic syndrome (MDS) or with features suggestive of AML/MDS are ineligible

Other

• For part I: patients with known contraindications to platinum agents are excluded
• Patients who are unable to swallow pills/capsules are ineligible

• Male or female patients with cytologically or histologically confirmed locally advanced or metastatic pancreas adenocarcinoma with a BRCA1 or 2 or PALB2 mutation confirmed by report from Myriad Genetics (United States of America \[USA\]); reports from other molecular diagnostic companies can be used to confirm mutations as well; BRCA 1 or 2 or PALB2 mutation can be confirmed locally for all international sites
  • For part I, non-randomized, lead-in portion, patients with a known BRCA 1 or 2 or PALB2 mutation are eligible along with patients who potentially may have a likelihood of having a BRCA mutation (e.g., personal or family history of breast, pancreas, ovary, endometrial, prostate or other likely related malignancy)
  • For part I, randomized portion, a known BRCA 1 or 2 or PALB2 mutation is required
• For part I (arms A, B): Patients can have either locally advanced or metastatic pancreas adenocarcinoma for which no prior therapy has been administered for either locally advanced or metastatic disease; prior adjuvant therapy is permissible if gemcitabine or a fluoropyrimidine was administered with or without radiation and if disease recurrence has been documented at least 6 months after completion of adjuvant therapy
• For part II (arm C): Patients can have either locally advanced or metastatic pancreas adenocarcinoma; up to two prior treatment regimens are permissible (excluding a prior PARP inhibitor) for either localized or metastatic pancreas adenocarcinoma; prior combined chemotherapy and radiotherapy is permissible provided the patient has measurable disease outside the radiation port; prior therapy must have been completed at least 3 weeks prior to starting therapy
• Age \> 18 years. No dosing or adverse event data are currently available on the use of veliparib in patients \< 18 years of age, therefore children are excluded from this study
• Eastern Cooperative Oncology Group (ECOG) performance status:
  • For part I (arm A, B): 0-1 (Karnofsky \> 70%)
  • For part II (arm C): 0-2 (Karnofsky \>= 60%)
• Life expectancy of greater than 3 months
• Absolute neutrophil count \>= 1,500/mcL (measured within 14 days prior to administration of ABT-888)
• Hemoglobin \>= 9.0 g/dl (measured within 14 days prior to administration of ABT-888)
• Platelets \>= 100,000/mcL (measured within 14 days prior to administration of ABT-888)
• Total bilirubin =\< 2 x institutional upper limit of normal (measured within 14 days prior to administration of ABT-888)
• Aspartate aminotransferase(AST)/serum glutamic oxaloacetic transaminase (SGOT) and alanine aminotransferase(ALT)/serum glutamate pyruvate transaminase (SGPT) =\< 2.5 x institutional upper limit of normal unless there is evidence of liver metastases in which case the AST (SGOT)/ALT (SGPT) must be =\< 5 x institutional upper limit of normal (measured within 14 days prior to administration of ABT-888)
• Creatinine =\< 1.5 x upper limit of normal (ULN) (measured within 14 days prior to administration of ABT-888)
• Measurable disease by RECIST criteria
  • For the lead-in, non-randomized portion of part I, either measurable or evaluable disease is acceptable
  • For part I, randomized portion, measurable disease is required
• If a woman is of child-bearing potential a negative blood or urine pregnancy test is required; (the effects of veliparib on the developing human fetus are unknown; for this reason and because other therapeutic agents or modalities used in this trial are known to be teratogenic, women of child-bearing potential and men must agree to use adequate contraception \[hormonal or barrier method of birth control; abstinence\] prior to study entry and for the duration of study participation; should a woman become pregnant or suspect she is pregnant while participating in this study, she should inform her treating physician immediately)
• Ability to understand and the willingness to sign a written informed consent document