Systems biology has embraced computational modeling in response to the quantitative nature and increasing scale of contemporary data sets. The onslaught of data is accelerating as molecular profiling technology evolves. The Dialogue for Reverse Engineering Assessments and Methods (DREAM) is a community effort to catalyze discussion about the design, application, and assessment of systems biology models through annual reverse-engineering challenges. We describe our assessments of the four challenges associated with the third DREAM conference which came to be known as the DREAM3 challenges: signaling cascade identification, signaling response prediction, gene expression prediction, and the DREAM3 in silico network challenge. The challenges, based on anonymized data sets, tested participants in network inference and prediction of measurements. Forty teams submitted 413 predicted networks and measurement test sets. Overall, a handful of best-performer teams were identified, while a majority of teams made predictions that were equivalent to random. Counterintuitively, combining the predictions of multiple teams (including the weaker teams) can in some cases improve predictive power beyond that of any single method. DREAM provides valuable feedback to practitioners of systems biology modeling. Lessons learned from the predictions of the community provide much-needed context for interpreting claims of efficacy of algorithms described in the scientific literature.
Large‐scale protein signalling networks are useful for exploring complex biochemical pathways but do not reveal how pathways respond to specific stimuli. Such specificity is critical for understanding disease and designing drugs. Here we describe a computational approach—implemented in the free CNO software—for turning signalling networks into logical models and calibrating the models against experimental data. When a literature‐derived network of 82 proteins covering the immediate‐early responses of human cells to seven cytokines was modelled, we found that training against experimental data dramatically increased predictive power, despite the crudeness of Boolean approximations, while significantly reducing the number of interactions. Thus, many interactions in literature‐derived networks do not appear to be functional in the liver cells from which we collected our data. At the same time, CNO identified several new interactions that improved the match of model to data. Although missing from the starting network, these interactions have literature support. Our approach, therefore, represents a means to generate predictive, cell‐type‐specific models of mammalian signalling from generic protein signalling networks.
1 April 2006 in Annals of the New York Academy of Sciences
A major challenge in cancer treatment is predicting clinical response to anti-cancer drugs on a personalized basis. Using a pharmacogenomics database of 1,001 cancer cell lines, we trained deep neural networks for prediction of drug response and assessed their performance on multiple clinical cohorts. We demonstrate that deep neural networks outperform the current state in machine learning frameworks. We provide a proof of concept for the use of deep neural network-based frameworks to aid precision oncology strategies.
1 June 2003 in Journal of Biomechanical Engineering
In articular cartilage, chondrocytes are surrounded by a pericellular matrix (PCM), which together with the chondrocyte have been termed the “chondron.” While the precise function of the PCM is not known there has been considerable speculation that it plays a role in regulating the biomechanical environment of the chondrocyte. In this study, we measured the Young’s modulus of the PCM from normal and osteoarthritic cartilage using the micropipette aspiration technique, coupled with a newly developed axisymmetric elastic layered half-space model of the experimental configuration. Viable, intact chondrons were extracted from human articular cartilage using a new microaspiration-based isolation technique. In normal cartilage, the Young’s modulus of the PCM was similar in chondrons isolated from the surface zone (68.9±18.9 kPa) as compared to the middle and deep layers (62.0±30.5 kPa). However, the mean Young’s modulus of the PCM (pooled for the two zones) was significantly decreased in osteoarthritic cartilage (66.5±23.3 kPa versus 41.3±21.1 kPa, In combination with previous theoretical models of cell-matrix interactions in cartilage, these findings suggest that the PCM has an important influence on the stress-strain environment of the chondrocyte that potentially varies with depth from the cartilage surface. Furthermore, the significant loss of PCM stiffness that was observed in osteoarthritic cartilage may affect the magnitude and distribution of biomechanical signals perceived by the chondrocytes.