Neural computing in cancer drug development: predicting mechanism of action.

Described here are neural networks capable of predicting a drug's mechanism of action from its pattern of activity against a panel of 60 malignant cell lines in the National Cancer Institute's drug screening program. Given six possible classes of mechanism, the network misses the correct category for only 12 out of 141 agents (8.5 percent), whereas linear discriminant analysis, a standard statistical technique, misses 20 out of 141 (14.2 percent). The success of the neural net indicates several things. (i) The cell line response patterns are rich in information about mechanism. (ii) Appropriately designed neural networks can make effective use of that information. (iii) Trained networks can be used to classify prospectively the more than 10,000 agents per year tested by the screening program. Related networks, in combination with classical statistical tools, will help in a variety of ways to move new anticancer agents through the pipeline from in vitro studies to clinical application.

Preclinical antitumor activity of temozolomide in mice: efficacy against human brain tumor xenografts and synergism with 1,3-bis(2-chloroethyl)-1-nitrosourea.

Temozolomide, a methylating agent with clinical activity against brain tumors, demonstrated excellent antitumor activity following p.o. administration to athymic mice bearing human brain tumor xenografts. In the early stage s.c. implanted SNB-75 astrocytoma model, a 400-mg/kg dose administered on Day 5 produced 10 of 10 Day 54 tumor-free mice. In later staged s.c. U251 and SF-295 glioblastoma models, a single 600-mg/kg dose produced 9 of 10 Day 86 and 2 of 10 Day 40 tumor-free mice, respectively. In the latter group, a tumor growth delay of > 315% was attained. Similar levels of activity were attained with equal total doses on schedules of daily for 5 doses and every fourth day for 3 doses. A single 40-mg/kg i.v. dose of 1,3-bis(2-chloroethyl)-1-nitrosourea (BCNU) also demonstrated excellent activity, producing 9 of 10 tumor-free mice in the SNB-75 model and growth delays of 283 and 301% in the U251 and SF-295 models, respectively. Temozolomide was also highly effective against intracerebral implants of the U251 and SF-295 glioblastomas. Administration of either 600 mg/kg on Day 1 or 200 mg/kg on Days 1, 5, and 9 produced 7 of 9 Day 90 tumor-free mice in the U251 model. In the SF-295 model, a single 400-mg/kg dose or three 200-mg/kg doses produced 3 and 4 of 10 Day 90 tumor-free mice, respectively, and prolonged survival by 127%. A single 40-mg/kg i.v. dose of BCNU was more effective than temozolomide in the intracerebral SF-295 model, and less effective in the intracerebral U251 model. The synergistic potential of temozolomide and BCNU in combination was evaluated in an advanced stage s.c. implanted SF-295 model. When temozolomide was administered 2 h after BCNU on a single treatment day, a dramatic synergistic therapeutic effect was observed in two experiments. For example, single agent doses of temozolomide (600 mg/kg) and BCNU (60 mg/kg) and a combination (400 mg/kg + 27 mg/kg) demonstrating equivalent toxicity produced growth delays of 190, 258, and > 492% (includes 5 of 10 Day 51 tumor-free mice), respectively. Analysis of the data by a quadratic dose response model indicated synergism with significance at P = 0.0001 in both experiments. Synergism also was demonstrated by the isobole method. The reverse sequence was more toxic, but at lower combination doses a synergistic effect was still observed (P = 0.0001).(ABSTRACT TRUNCATED AT 400 WORDS)

Multidrug-resistant phenotype of disease-oriented panels of human tumor cell lines used for anticancer drug screening.

Disease-oriented panels of human tumor cell lines used by the National Cancer Institute for large-scale in vitro anticancer drug screening were evaluated for multidrug-resistant phenotype at the functional (in vitro drug sensitivity) and molecular levels. The cell line panels manifested a broad range of sensitivities to drugs typically associated with multidrug resistance (MDR) as well as to drugs not associated with MDR. Individual cell lines displayed unique and characteristic profiles of response. Patterns of correlated response were observed among, but not between, MDR and non-MDR drugs. Strong evidence of correlated response was limited to drugs sharing an intracellular mechanism of action. Several tumor cell lines exhibited a high degree of resistance to MDR drugs and relative sensitivity to non-MDR drugs, contained high levels of MDR-1 mRNA, and expressed cell surface P-glycoprotein detectable with one or more monoclonal antibodies. Parallel expression of all of these features representing the classic MDR phenotype was observed among members of the colon and renal tumor panels. Certain individual cell lines among other panels (lung, ovarian, melanoma, and central nervous system) also manifested some aspects of the MDR phenotype to various extents. Identification of MDR cell lines used for large-scale in vitro anticancer drug screening will facilitate interpretation of data in a way which may allow identification of new drug leads of potential value in treatment of MDR tumor cell populations.

Quality control of oncology clinical trials.

This article discusses issues that are essential to ensuring the reliability of the conclusions of oncology clinical trials. Though quality control is important at every stage of a well-run clinical trial, the authors focus on the quality of the data as evidenced by the results and conclusions of the study. Good quality control principles and practices are discussed for study planning, design, conduct, analysis, and interpretation.

An integrated analysis of five double-blind, randomized controlled trials evaluating the safety and efficacy of a hyaluronan product for intra-articular injection in osteoarthritis of the knee.

OBJECTIVE: Five double-blind, randomized, saline-controlled trials (RCTs) were included in the United States marketing application for an intra-articular hyaluronan (IA-HA) product for the treatment of osteoarthritis (OA) of the knee. We report an integrated analysis of the primary Case Report Form (CRF) data from these trials. METHOD: Trials were similar in design, patient population and outcome measures - all included the Lequèsne Algofunctional Index (LI), a validated composite index of pain and function, evaluating treatment over 3 months. Individual patient data were pooled; a repeated measures analysis of covariance was performed in the intent-to-treat (ITT) population. Analyses utilized both fixed and random effects models. Safety data from the five RCTs were summarized. RESULTS: A total of 1155 patients with radiologically confirmed knee OA were enrolled: 619 received three or five IA-HA injections; 536 received "placebo" saline injections. In the active and control groups, mean ages were 61.8 and 61.4 years; 62.4% and 58.8% were women; baseline total Lequèsne scores 11.03 and 11.30, respectively. Integrated analysis of the pooled data set found a statistically significant reduction (P < 0.001) in total Lequèsne score with hyaluronan (HA) (-2.68) vs placebo (-2.00); estimated difference -0.68 (95% CI: -0.56 to -0.79), effect size 0.20. Additional modeling approaches confirmed robustness of the analyses. CONCLUSIONS: This integrated analysis demonstrates that multiple design factors influence the results of RCTs assessing efficacy of intra-articular (IA) therapies, and that integrated analyses based on primary data differ from meta-analyses using transformed data.

Discrimination techniques applied to the NCI in vitro anti-tumour drug screen: predicting biochemical mechanism of action.

The National Cancer Institute currently tests approximately 400 compounds per week against a panel of human tumour cell lines in order to identify potential anti-cancer drugs. We describe several approaches, based on these in vitro data, to the problem of identifying the primary biochemical mechanism of action of a compound. Using linear and non-parametric discriminant procedures and cross-validation, we find that accurate identification of the mechanism of action is achieved for approximately 90 per cent of a diverse collection of 141 known compounds, representing six different mechanistic categories. We demonstrate that two-dimensional graphical displays of the compounds in terms of the initial three principal components (of the original data) result in suggestive visual clustering according to mechanism of action. Finally, we compare the classification accuracy of the statistical discrimination procedures with the accuracy obtained from a neural network approach and, for our example, we find that the results obtained from the various approaches are similar.

Predictive statistics and artificial intelligence in the U.S. National Cancer Institute's Drug Discovery Program for Cancer and AIDS.

The National Cancer Institute's drug discovery program screens more than 20,000 chemical compounds and natural products a year for activity against a panel of 60 tumor cell lines in vitro. The result is an information-rich database of patterns that form the basis for what we term an "information-intensive" approach to the process of drug discovery. The first step was a demonstration, both by statistical methods (including the program COMPARE) and by neural networks, that patterns of activity in the screen can be used to predict a compound's mechanism of action. Given this finding, the overall plan has been to develop three large matrices of information: the first (designated A) gives the pattern of activity for each compound tested against each cell line in the screen; the second (S) encodes any of a number of types of 2-D or 3-D structural motifs for each compound; the third (T) indicates each cell's expression of molecular targets (e.g., from 2-dimensional protein gel electrophoresis). Construction and updating of these matrices is an ongoing process. The matrices can be concatenated in various ways to test a variety of specific hypotheses about compounds screened, as well as to "prioritize" candidate compounds for testing. To aid in these efforts, we have developed the DISCOVERY program package, which integrates the matrix data for visual pattern recognition. The "information-intensive" approach summarized here in some senses serves to bridge the perceived gap between screening and structure-based drug design.