Use of Artificial Intelligence and Machine Learning Algorithms with Gene Expression Profiling to Predict Recurrent Nonmuscle Invasive Urothelial Carcinoma of the Bladder.

PURPOSE: Due to the high recurrence risk of nonmuscle invasive urothelial carcinoma it is crucial to distinguish patients at high risk from those with indolent disease. In this study we used a machine learning algorithm to identify the genes in patients with nonmuscle invasive urothelial carcinoma at initial presentation that were most predictive of recurrence. We used the genes in a molecular signature to predict recurrence risk within 5 years after transurethral resection of bladder tumor. MATERIALS AND METHODS: Whole genome profiling was performed on 112 frozen nonmuscle invasive urothelial carcinoma specimens obtained at first presentation on Human WG-6 BeadChips (Illumina®). A genetic programming algorithm was applied to evolve classifier mathematical models for outcome prediction. Cross-validation based resampling and gene use frequencies were used to identify the most prognostic genes, which were combined into rules used in a voting algorithm to predict the sample target class. Key genes were validated by quantitative polymerase chain reaction. RESULTS: The classifier set included 21 genes that predicted recurrence. Quantitative polymerase chain reaction was done for these genes in a subset of 100 patients. A 5-gene combined rule incorporating a voting algorithm yielded 77% sensitivity and 85% specificity to predict recurrence in the training set, and 69% and 62%, respectively, in the test set. A singular 3-gene rule was constructed that predicted recurrence with 80% sensitivity and 90% specificity in the training set, and 71% and 67%, respectively, in the test set. CONCLUSIONS: Using primary nonmuscle invasive urothelial carcinoma from initial occurrences genetic programming identified transcripts in reproducible fashion, which were predictive of recurrence. These findings could potentially impact nonmuscle invasive urothelial carcinoma management.

Generation and external validation of a tumor-derived 5-gene prognostic signature for recurrence of lymph node-negative, invasive colorectal carcinoma.

BACKGROUND: One in 4 patients with lymph node-negative, invasive colorectal carcinoma (CRC) develops recurrent disease after undergoing curative surgery, and most die of advanced disease. Predicting which patients will develop a recurrence is a significantly growing, unmet medical need. METHODS: Archival formalin-fixed, paraffin-embedded (FFPE) primary adenocarcinoma tissues obtained at surgery were retrieved from 74 patients with CRC (15 with stage I disease and 59 with stage II disease) for Training/Test Sets. In addition, FFPE tissues were retrieved from 49 patients with stage I CRC and 215 patients with stage II colon cancer for an External Validation (EV) Set (n = 264) from 18 hospitals in 4 countries. No patients had received neoadjuvant/adjuvant therapy. Proprietary genetic programming analysis of expression profiles for 225 prespecified tumor genes was used to create a 36-month recurrence risk signature. RESULTS: Using reverse transcriptase-polymerase chain reaction, a 5-gene rule correctly classified 62 of 92 recurrent patients and 87 of 172 nonrecurrent patients in the EV Set (sensitivity, 0.67; specificity, 0.51). "High-risk" patients had a greater probability of 36-month recurrence (42%) than "low-risk" patients (26%; hazard ratio, 1.80; 95% confidence interval, 1.19-2.71; P = .007; Cox regression) independent of T-classification, the number of lymph nodes examined, histologic grade/subtype, anatomic location, age, sex, or race. The rule outperformed (P = .021) current National Comprehensive Cancer Network Guidelines (hazard ratio, 0.897). The same rule also differentiated the risk of recurrence (hazard ratio, 1.63; P = .031) in a subset of patients from the EV Set who had stage I/II colon cancer only (n = 251). CONCLUSIONS: To the authors' knowledge, the 5-gene rule (OncoDefender-CRC) is the first molecular prognostic that has been validated in both stage I CRC and stage II colon cancer. It outperforms standard clinicopathologic prognostic criteria and obviates the need to retrieve ≥12 lymph nodes for accurate prognostication. It identifies those patients most likely to develop recurrent disease within 3 years after curative surgery and, thus, those most likely to benefit from adjuvant treatment.

Multicenter, randomized, phase II trial of CI-1033, an irreversible pan-ERBB inhibitor, for previously treated advanced non small-cell lung cancer.

PURPOSE: To evaluate the efficacy of the pan-ERBB inhibitor, CI-1033, in platinum-refractory or recurrent advanced-stage non-small-cell lung cancer (NSCLC). PATIENTS AND METHODS: This open-label, randomized phase II trial evaluated CI-1033 in patients with advanced-stage NSCLC who experienced treatment failure after or were refractory to platinum-based chemotherapy. Three oral CI-1033 doses were evaluated in 21-day dosing cycles: 50 mg daily for 21 consecutive days, 150 mg daily for 21 consecutive days, and 450 mg daily for 14 consecutive days followed by 7 days of no treatment. The primary efficacy end point was the 1-year survival rate. RESULTS: One hundred sixty-six patients were randomly assigned to treatment. Baseline patient demographics were well balanced. The most common drug-related adverse events were rash and diarrhea. The 450-mg arm (14 days on/7 days off) was closed early due to an excessive rate of adverse events. The 1-year survival rates were 29%, 26%, and 29%, respectively, in the three arms. The response rates were 2%, 2%, and 4%, and stable disease was confirmed in 16%, 23%, and 18% of patients, respectively, in the three study arms. Exploratory analyses demonstrated a prolonged survival in patients who developed a rash and in those with baseline tumor ERBB-2 expression. CONCLUSION: CI-1033 had modest activity in unselected NSCLC patients but did not meet its primary end point. Future studies should focus on identifying methods of patient selection.

Phase I clinical and pharmacodynamic evaluation of oral CI-1033 in patients with refractory cancer.

PURPOSE: To determine the tolerability and pharmacokinetics of CI-1033 given daily for 7 days of a 21-day cycle. Tumor response and changes in erbB receptor tyrosine kinase activity in tumor and skin tissue were examined, and modulation of potential biomarkers in plasma was explored. DESIGN: This was a dose-finding phase I study in patients with advanced solid malignancies. Patients were evaluated for safety, pharmacokinetics, and tumor response. Pharmacodynamic markers, such as Ki67, p27, and erbB receptor status, were assessed in tumor and skin tissue using immunohistochemical and immunoprecipitation methodologies. Plasma biomarkers HER2, vascular endothelial growth factor, interleukin-8, and matrix metalloproteinase-9 were evaluated using immunologic techniques. RESULTS: Fifty-three patients were enrolled in the study. Dose-limiting toxicity (emesis, persistent rash, and mouth ulcer) was observed at 750 mg. The maximum tolerated dose was 650 mg. There were no confirmed objective responses. CI-1033 treatment showed down-regulation of epidermal growth factor receptor, HER2, and Ki67 in a variety of tumor tissues and up regulation of p27 in skin tissue. Plasma HER2 was reduced following CI-1033 administration, but no consistent change in vascular endothelial growth factor, interleukin-8, or matrix metalloproteinase-9 was noted. CI-1033 plasma concentrations were proportional to dose. CONCLUSION: The safety and pharmacokinetic profile of CI-1033 was favorable for multidose oral administration. Evidence of modulation of erbB receptor activity in tumor and skin tissue was accompanied by changes in markers of proliferation and cell cycle inhibition. Additional clinical trials are warranted in defining the role of CI-1033 in the treatment of cancer and further assessing the utility of antitumor markers.

Intestinal mucosa remodeling by recombinant human epidermal growth factor(1-48) in neonates with severe necrotizing enterocolitis.

BACKGROUND AND AIMS: Neonatal necrotizing enterocolitis (NEC) is a common and serious acquired gastrointestinal tract condition. This clinical study assessed the potential clinical efficacy and microscopic effects of recombinant human epidermal growth factor 1-48 (EGF(1-48)) in neonates with NEC. METHODS: This prospective, double-blind, randomized controlled study included 8 neonates with NEC. The study compared the effects of a 6-day continuous intravenous infusion of EGF(1-48) at 100 ng kg(-1) h(-1) against placebo. Clinical outcomes and morphological evaluation of serial rectal mucosal biopsies were assessed at baseline and 4, 7, and 14 days after starting EGF infusions. RESULTS: There was no difference between the clinical safety outcomes recorded for EGF(1-48) or placebo patients. Quantitative morphologic differences in the rectal mucosa biopsies were noted with EGF(1-48) treatment compared with baseline or placebo and included a statistically significant increase in the number of mitoses per mucosal crypt on study day 4, significantly increased thickness of rectal mucosa from baseline on study days 4 and 7, and increased crypt surface area of rectal mucosa in parallel with increased mucosa thickness on day 14. CONCLUSION: This study of EGF(1-48) in neonates with severe NEC showed that growth factor treatment was well tolerated and produced positive and measurable remodeling trophic effects on the gastrointestinal mucosa.

Increased bioavailability of intravenous versus oral CI-1033, a pan erbB tyrosine kinase inhibitor: results of a phase I pharmacokinetic study.

PURPOSE: In phase I studies with oral CI-1033, dose-limiting toxicities were primarily gastrointestinal, supporting the exploration of i.v. dosing to achieve optimal drug exposures by increasing bioavailability. EXPERIMENTAL DESIGN: Fifty-three patients with advanced nonhematologic malignancies received i.v. CI-1033 via 30-minute infusions (10-500 mg) on a thrice-weekly schedule. Pharmacokinetic samples were collected on days 1 and 8 and evaluated using noncompartmental analysis. RESULTS: Dose levels evaluated were 10, 20, 30, 45, 67.5, 100, 150, 225, 337.5, and 500 mg. The maximum administered dose was 500 mg, whereas the maximum tolerated dose was 225 mg. The most common treatment-related grade 1 to 2 adverse events were rashes (38% of patients), nausea (17%), vomiting (17%), stomatitis (14%), and diarrhea (13%). Most common grade 3 adverse events were hypersensitivity reactions (7.5%), rashes (3.8%), and diarrhea (3.8%). No grade 4 toxicities were observed. Ten of the 53 (19%) patients had disease stabilization at their first efficacy evaluation visit (including two with minor responses). A 5- to 10-fold increase in i.v. C(max) was noted with a 3-fold increase in AUC compared with oral CI-1033 at equivalent doses. Treatment-related gastrointestinal adverse events were notably less frequent with this i.v. regimen. CONCLUSIONS: CI-1033 was safely given i.v. up to 225 mg/dose on a thrice-weekly schedule, with evidence of antitumor activity. At equivalent doses, the bioavailability of i.v. CI-1033 is thrice that of the oral formulation. Treatment with i.v. CI-1033 is feasible and may be warranted when increased drug exposures are desired.

A phase I clinical and pharmacokinetic study of oral CI-1033 in combination with docetaxel in patients with advanced solid tumors.

PURPOSE: CI-1033 is an orally available 4-anilinoquinazolone irreversible tyrosine kinase inhibitor of erbB-1, erbB-2, and erbB-4. We conducted a dose escalation study of CI-1033 with docetaxel to assess the safety profile and pharmacokinetics of the combination and to establish the maximum tolerated dose. EXPERIMENTAL DESIGN: Twenty-six patients with advanced solid tumors were treated on four dosing cohorts starting at CI-1033 (50 mg/d) + docetaxel (75 mg/m2). An intermittent dosing schedule avoided concurrent drug dosing. RESULTS: CI-1033 alone was escalated from 50 to 75 mg/d (dose level 2), where diarrhea was dose limiting; a 38% incidence of cycle 1 febrile neutropenia prompted dose de-escalation of both CI-1033 and docetaxel for dose level 3, where dose-limiting toxicities prompted further de-escalation of CI-1033 to 45 mg/d. Given equivalent safety profiles for dose level 1 [CI-1033 (50 mg/d) + docetaxel (75 mg/m2)] and dose level 4 [CI-1033 (45 mg/d) + docetaxel (60 mg/m2)], the former was determined to be the recommended phase II dose, given greater dose intensity of both drugs. Antitumor activity was noted in three patients, including a complete response in a patient with cervix uteri cancer. Pharmacokinetic analysis showed a possible effect of docetaxel on CI-1033 pharmacokinetics. CONCLUSIONS: It is feasible to combine the irreversible pan-erbB tyrosine kinase inhibitor CI-1033 with docetaxel on an intermittent dosing schedule in advanced cancer patients. We established the maximum tolerated dose and recommended phase II dose for the combination. Further investigation of this combination should include a rigorous analysis of the effect of docetaxel on CI-1033 pharmacokinetics.

The use of genetic programming in the analysis of quantitative gene expression profiles for identification of nodal status in bladder cancer.

BACKGROUND: Previous studies on bladder cancer have shown nodal involvement to be an independent indicator of prognosis and survival. This study aimed at developing an objective method for detection of nodal metastasis from molecular profiles of primary urothelial carcinoma tissues. METHODS: The study included primary bladder tumor tissues from 60 patients across different stages and 5 control tissues of normal urothelium. The entire cohort was divided into training and validation sets comprised of node positive and node negative subjects. Quantitative expression profiling was performed for a panel of 70 genes using standardized competitive RT-PCR and the expression values of the training set samples were run through an iterative machine learning process called genetic programming that employed an N-fold cross validation technique to generate classifier rules of limited complexity. These were then used in a voting algorithm to classify the validation set samples into those associated with or without nodal metastasis. RESULTS: The generated classifier rules using 70 genes demonstrated 81% accuracy on the validation set when compared to the pathological nodal status. The rules showed a strong predilection for ICAM1, MAP2K6 and KDR resulting in gene expression motifs that cumulatively suggested a pattern ICAM1 > MAP2K6 > KDR for node positive cases. Additionally, the motifs showed CDK8 to be lower relative to ICAM1, and ANXA5 to be relatively high by itself in node positive tumors. Rules generated using only ICAM1, MAP2K6 and KDR were comparably robust, with a single representative rule producing an accuracy of 90% when used by itself on the validation set, suggesting a crucial role for these genes in nodal metastasis. CONCLUSION: Our study demonstrates the use of standardized quantitative gene expression values from primary bladder tumor tissues as inputs in a genetic programming system to generate classifier rules for determining the nodal status. Our method also suggests the involvement of ICAM1, MAP2K6, KDR, CDK8 and ANXA5 in unique mathematical combinations in the progression towards nodal positivity. Further studies are needed to identify more class-specific signatures and confirm the role of these genes in the evolution of nodal metastasis in bladder cancer.

Multicenter, randomized phase II trial of oral CI-1033 for previously treated advanced ovarian cancer.

PURPOSE: To evaluate the antitumor activity and toxicity of two doses of CI-1033 in patients with platinum-refractory or recurrent ovarian cancer, and to determine baseline expression of epidermal growth factor receptor in tumor cells. PATIENTS AND METHODS: This phase II, open-label clinical trial evaluated CI-1033 in patients with ovarian cancer who failed prior platinum-based therapy. Two oral doses of CI-1033 were evaluated--a 50-mg and a 200--mg oral dose administered daily for 21 days in a 28-day cycle. Patients were evaluated for tumor response and toxicity; in addition, archival baseline tumor samples were analyzed by immunohistochemistry for erbB1 to erbB4 status. RESULTS: One hundred five eligible patients were treated. Baseline demographic characteristics were balanced in this heavily pretreated patient population. The median number of prior chemotherapy regimens received was four. The most commonly encountered drug-related adverse events for both dose arms were gastrointestinal (diarrhea, nausea, stomatitis) toxicity, asthenia, and rash. No responses were observed. Stable disease was confirmed in 34% and 26% of patients in the 200-mg and 50-mg arms, respectively, and 1-year survival rates were 38.5% and 37.7%, respectively. Baseline erbB3 and erbB4 revealed the highest frequencies of expression, while erbB2 was the lowest. CONCLUSION: CI-1033 did not show activity in unscreened patients with advanced ovarian cancer. At 50 mg/d, CI-1033 had a more favorable adverse events profile than at 200 mg/d. erbB3 and erbB4 receptors showed the highest expression in tumor samples while erbB2 revealed the least. There appears to be no association between baseline erbB expression and disease stability.

Phase 1 clinical and pharmacokinetics evaluation of oral CI-1033 in patients with refractory cancer.

PURPOSE: To determine the tolerability and pharmacokinetics of oral CI-1033, a pan-erbB tyrosine kinase inhibitor, administered over 14 consecutive days of a 21-day cycle. DESIGN: Phase 1, multicenter trial involving patients with solid tumors that are refractory to standard therapy. CI-1033 was administered initially at 300 mg/day to a minimum cohort of three patients. Dose escalation proceeded at

Administration of CI-1033, an irreversible pan-erbB tyrosine kinase inhibitor, is feasible on a 7-day on, 7-day off schedule: a phase I pharmacokinetic and food effect study.

PURPOSE: To determine the maximum tolerated dose of administrating CI-1033, an oral 4-anilinoquinazoline that irreversibly inhibits the tyrosine kinase domain of all erbB subfamilies, on an intermittent schedule, and assess the interaction of CI-1033 with food on the pharmacokinetic behavior. EXPERIMENTAL DESIGN: Escalating doses of CI-1033 from a dose level of 300 mg/day for 7 days every other week were administered to patients with advanced solid malignancies. Plasma concentration-time data sets from all evaluable patients were used to develop a population pharmacokinetic model. Noncompartmental methods were used to independently assess the effect of a high-fat meal on CI-1033 absorption and bioavailability. RESULTS: Twenty-four patients were treated with 69 twenty-eight day courses. The incidence of unacceptable toxicity, principally diarrhea and skin rash, was observed at the 300 mg/day dose level. At the 250 mg/day level, toxicity was manageable, and protracted administration was feasible. A one-compartment linear model with first-order absorption and elimination adequately described the pharmacokinetic disposition. CL/F, apparent volume of distribution (Vd/F), and ka (mean +/- relative SD) were 280 L/hour +/- 33%, 684 L +/- 20%, and 0.35 hour(-1)+/- 69%, respectively. Cmax values were achieved in 2 to 4 hours. Systemic CI-1033 exposure was largely unaffected by administration of a high-fat meal. At 250 mg, concentration values exceeded IC50 values required for prolonged pan-erbB tyrosine kinase inhibition in preclinical assays. CONCLUSIONS: The recommended dose on this schedule is 250 mg/day. Its tolerability and the biological relevance of concentrations achieved at the maximal tolerated dose warrant consideration of disease-directed evaluations. This intermittent treatment schedule can be used without regard to meals.

CI-1033, an irreversible pan-erbB receptor inhibitor and its potential application for the treatment of breast cancer.

The erbB family of cell surface receptor proteins consists of four members, all of which play a role in the development and growth of the normal breast. The activity of this signaling pathway is normally tightly controlled, and dysregulation has been shown to play a significant role in the pathogenesis and progression of breast and other cancers. The potent transforming potential of these receptors is further enhanced by the coexpression of multiple members of this receptor family, which worsens prognosis. Therapeutic blockade of erbB-2 receptor signaling has to date been shown to be effective in only a subset of chemotherapy-resistant breast cancer patients. CI-1033 is a highly potent and selective pan-erbB inhibitor that efficiently blocks signal transduction through all four members of the erbB receptor family. In addition, it covalently binds to these receptors, irreversibility inhibiting them, and thereby provides for prolonged suppression of erbB receptor-mediated signaling. Clinically, it has been shown to have an acceptable side effect profile at potentially therapeutic doses and schedules. Biomarker studies have shown target inhibition in patients, and evidence of antitumor activity has also been observed in phase I studies. Given the broad expression pattern of the erbB family of receptors in solid tumors, and the important proliferative effect of co-expression of multiple erbB receptors, CI-1033, as an irreversible, pan-erbB inhibitor, has the potential to have an important role in the future treatment of breast and other cancers.

Potential benefits of the irreversible pan-erbB inhibitor, CI-1033, in the treatment of breast cancer.

Transmembrane receptor tyrosine kinases have been shown to play an important role in the modulation of growth factor signaling and regulation of key cellular processes. The erbB receptor family is part of the receptor tyrosine kinase superfamily and consists of four members, erbB-1, erbB-2, erbB-3, and erbB-4. A majority of solid tumors express one or more members of this receptor family, and coexpression of multiple erbB receptors leads to an enhanced transforming potential and worsened prognosis. The erbB receptor family has been shown to play an important role in both the development of the normal breast and in the pathogenesis and progression of breast cancer. Receptor overexpression has also been shown to be a negative prognostic indicator and to correlate with both tumor invasiveness and a lack of responsiveness to standard treatment. Clinically, blockade of the erbB-2 receptor has recently been shown to provide benefit in a subset of chemotherapy-resistant breast cancer patients. CI-1033 is an orally available pan-erbB receptor tyrosine kinase inhibitor that, unlike the majority of receptor inhibitors, effectively blocks signal transduction through all four members of the erbB family. In addition, it blocks the highly tumorigenic, constitutively activated variant of erbB-1, EGFRvIII, and inhibits downstream signaling through both the Ras/MAP kinase, and PI-3 kinase/AKT pathways. CI-1033 is also unique in that it is an irreversible inhibitor, thereby providing prolonged suppression of erbB receptor-mediated signaling. Preclinical data have shown CI-1033 to be efficacious against a variety of human tumors in mouse xenograft models, including breast carcinomas. In a phase I study, CI-1033 has been shown to have an acceptable side effect profile at potentially therapeutic dose levels and demonstrates evidence of target biomarker modulation. Antitumor activity has also been observed in this study, including one partial clinical response and stable disease in over 30% of patients, including one patient with heavily pretreated breast cancer. By virtue of its pan-erbB receptor inhibition and potent interruption of downstream mitogenic signaling pathways, CI-1033 may have clinical activity for solid tumors that overexpress one erbB family member, coexpress multiple members of the erbB family, or express a constitutively activated, mutated form of these receptors. Given the important role of the erbB receptor family in the pathogenesis and progression of breast cancer, an irreversible pan-erbB inhibitor like CI-1033 could have an important role to play in the future treatment of breast cancer.