Prediction of DNA methylation-based tumor types from histopathology in central nervous system tumors with deep learning.

Precision in the diagnosis of diverse central nervous system (CNS) tumor types is crucial for optimal treatment. DNA methylation profiles, which capture the methylation status of thousands of individual CpG sites, are state-of-the-art data-driven means to enhance diagnostic accuracy but are also time consuming and not widely available. Here, to address these limitations, we developed Deep lEarning from histoPathoLOgy and methYlation (DEPLOY), a deep learning model that classifies CNS tumors to ten major categories from histopathology. DEPLOY integrates three distinct components: the first classifies CNS tumors directly from slide images ('direct model'), the second initially generates predictions for DNA methylation beta values, which are subsequently used for tumor classification ('indirect model'), and the third classifies tumor types directly from routinely available patient demographics. First, we find that DEPLOY accurately predicts beta values from histopathology images. Second, using a ten-class model trained on an internal dataset of 1,796 patients, we predict the tumor categories in three independent external test datasets including 2,156 patients, achieving an overall accuracy of 95% and balanced accuracy of 91% on samples that are predicted with high confidence. These results showcase the potential future use of DEPLOY to assist pathologists in diagnosing CNS tumors within a clinically relevant short time frame.

Prediction of cancer treatment response from histopathology images through imputed transcriptomics.

Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin (H&E)-stained tumor slides for precision oncology. We present ENLIGHT-DeepPT, an approach for predicting response to multiple targeted and immunotherapies from H&E-slides. In difference from existing approaches that aim to predict treatment response directly from the slides, ENLIGHT-DeepPT is an indirect two-step approach consisting of (1) DeepPT, a new deep-learning framework that predicts genome-wide tumor mRNA expression from slides, and (2) ENLIGHT, which predicts response based on the DeepPT inferred expression values. DeepPT successfully predicts transcriptomics in all 16 TCGA cohorts tested and generalizes well to two independent datasets. Our key contribution is showing that ENLIGHT-DeepPT successfully predicts true responders in five independent patients' cohorts involving four different treatments spanning six cancer types with an overall odds ratio of 2.44, increasing the baseline response rate by 43.47% among predicted responders, without the need for any treatment data for training. Furthermore, its prediction accuracy on these datasets is comparable to a supervised approach predicting the response directly from the images, which needs to be trained and tested on the same cohort. ENLIGHT-DeepPT future application could provide clinicians with rapid treatment recommendations to an array of different therapies and importantly, may contribute to advancing precision oncology in developing countries.

Clinically oriented prediction of patient response to targeted and immunotherapies from the tumor transcriptome.

BACKGROUND: Precision oncology is gradually advancing into mainstream clinical practice, demonstrating significant survival benefits. However, eligibility and response rates remain limited in many cases, calling for better predictive biomarkers. METHODS: We present ENLIGHT, a transcriptomics-based computational approach that identifies clinically relevant genetic interactions and uses them to predict a patient's response to a variety of therapies in multiple cancer types without training on previous treatment response data. We study ENLIGHT in two translationally oriented scenarios: personalized oncology (PO), aimed at prioritizing treatments for a single patient, and clinical trial design (CTD), selecting the most likely responders in a patient cohort. FINDINGS: Evaluating ENLIGHT's performance on 21 blinded clinical trial datasets in the PO setting, we show that it can effectively predict a patient's treatment response across multiple therapies and cancer types. Its prediction accuracy is better than previously published transcriptomics-based signatures and is comparable with that of supervised predictors developed for specific indications and drugs. In combination with the interferon-γ signature, ENLIGHT achieves an odds ratio larger than 4 in predicting response to immune checkpoint therapy. In the CTD scenario, ENLIGHT can potentially enhance clinical trial success for immunotherapies and other monoclonal antibodies by excluding non-responders while overall achieving more than 90% of the response rate attainable under an optimal exclusion strategy. CONCLUSIONS: ENLIGHT demonstrably enhances the ability to predict therapeutic response across multiple cancer types from the bulk tumor transcriptome. FUNDING: This research was supported in part by the Intramural Research Program, NIH and by the Israeli Innovation Authority.

Erasure machine: Inverse Ising inference from reweighting of observation frequencies.

Maximum likelihood estimation (MLE) is fundamental to system inference for stochastic systems. In some generality, MLE will converge to the correct model in the infinite data limit. In the context of physical approaches to system inference, such as Boltzmann machines, MLE requires the arduous computation of partition functions summing over all configurations, both observed and unobserved. We present a conceptually transparent data-driven inference computation based on a reweighting of observed configuration frequencies that allows us to recast the inference problem as a simpler calculation. Modeling our approach on the high-temperature limit of statistical physics, we reweight the frequencies of observed configurations by multiplying with reciprocals of Boltzmann weights and update the Boltzmann weights iteratively to make these products close to the high-temperature limit of the Boltzmann weights. This converts the required partition function computation in the reweighted MLE to a tractable leading-order high-temperature term. We show that this is a convex optimization at each step. Then, for systems with a large number of degrees of freedom where other approaches are intractable, we demonstrate that this data-driven algorithm gives accurate inference with both synthetic data and two real-world examples.

Data-driven inference of hidden nodes in networks.

The explosion of activity in finding interactions in complex systems is driven by availability of copious observations of complex natural systems. However, such systems, e.g., the human brain, are rarely completely observable. Interaction network inference must then contend with hidden variables affecting the behavior of the observed parts of the system. We present an effective approach for model inference with hidden variables. From configurations of observed variables, we identify the observed-to-observed, hidden-to-observed, observed-to-hidden, and hidden-to-hidden interactions, the configurations of hidden variables, and the number of hidden variables. We demonstrate the performance of our method by simulating a kinetic Ising model, and show that our method outperforms existing methods. Turning to real data, we infer the hidden nodes in a neuronal network in the salamander retina and a stock market network. We show that predictive modeling with hidden variables is significantly more accurate than that without hidden variables. Finally, an important hidden variable problem is to find the number of clusters in a dataset. We apply our method to classify MNIST handwritten digits. We find that there are about 60 clusters which are roughly equally distributed among the digits.

Network inference in stochastic systems from neurons to currencies: Improved performance at small sample size.

The fundamental problem in modeling complex phenomena such as human perception using probabilistic methods is that of deducing a stochastic model of interactions between the constituents of a system from observed configurations. Even in this era of big data, the complexity of the systems being modeled implies that inference methods must be effective in the difficult regimes of small sample sizes and large coupling variability. Thus, model inference by means of minimization of a cost function requires additional assumptions such as sparsity of interactions to avoid overfitting. In this paper, we completely divorce iterative model updates from the value of a cost function quantifying goodness of fit. This separation enables the use of goodness of fit as a natural rationale for terminating model updates, thereby avoiding overfitting. We do this within the mathematical formalism of statistical physics by defining a formal free energy of observations from a partition function with an energy function chosen precisely to enable an iterative model update. Minimizing this free energy, we demonstrate coupling strength inference in nonequilibrium kinetic Ising models, and show that our method outperforms other existing methods in the regimes of interest. Our method has no tunable learning rate, scales to large system sizes, and has a systematic expansion to obtain higher-order interactions. As applications, we infer a functional connectivity network in the salamander retina and a currency exchange rate network from time-series data of neuronal spiking and currency exchange rates, respectively. Accurate small sample size inference is critical for devising a profitable currency hedging strategy.

A Local Counter-Regulatory Motif Modulates the Global Phase of Hormonal Oscillations.

Counter-regulatory elements maintain dynamic equilibrium ubiquitously in living systems. The most prominent example, which is critical to mammalian survival, is that of pancreatic α and ß cells producing glucagon and insulin for glucose homeostasis. These cells are not found in a single gland but are dispersed in multiple micro-organs known as the islets of Langerhans. Within an islet, these two reciprocal cell types interact with each other and with an additional cell type: the δ cell. By testing all possible motifs governing the interactions of these three cell types, we found that a unique set of positive/negative intra-islet interactions between different islet cell types functions not only to reduce the superficially wasteful zero-sum action of glucagon and insulin but also to enhance/suppress the synchronization of hormone secretions between islets under high/normal glucose conditions. This anti-symmetric interaction motif confers effective controllability for network (de)synchronization.

Scaling Law for Irreversible Entropy Production in Critical Systems.

We examine the Jarzynski equality for a quenching process across the critical point of second-order phase transitions, where absolute irreversibility and the effect of finite-sampling of the initial equilibrium distribution arise in a single setup with equal significance. We consider the Ising model as a prototypical example for spontaneous symmetry breaking and take into account the finite sampling issue by introducing a tolerance parameter. The initially ordered spins become disordered by quenching the ferromagnetic coupling constant. For a sudden quench, the deviation from the Jarzynski equality evaluated from the ideal ensemble average could, in principle, depend on the reduced coupling constant ε0 of the initial state and the system size L. We find that, instead of depending on ε0 and L separately, this deviation exhibits a scaling behavior through a universal combination of ε0 and L for a given tolerance parameter, inherited from the critical scaling laws of second-order phase transitions. A similar scaling law can be obtained for the finite-speed quench as well within the Kibble-Zurek mechanism.

Design Principles of Pancreatic Islets: Glucose-Dependent Coordination of Hormone Pulses.

Pancreatic islets are functional units involved in glucose homeostasis. The multicellular system comprises three main cell types; ß and α cells reciprocally decrease and increase blood glucose by producing insulin and glucagon pulses, while the role of δ cells is less clear. Although their spatial organization and the paracrine/autocrine interactions between them have been extensively studied, the functional implications of the design principles are still lacking. In this study, we formulated a mathematical model that integrates the pulsatility of hormone secretion and the interactions and organization of islet cells and examined the effects of different cellular compositions and organizations in mouse and human islets. A common feature of both species was that islet cells produced synchronous hormone pulses under low- and high-glucose conditions, while they produced asynchronous hormone pulses under normal glucose conditions. However, the synchronous coordination of insulin and glucagon pulses at low glucose was more pronounced in human islets that had more α cells. When ß cells were selectively removed to mimic diabetic conditions, the anti-synchronicity of insulin and glucagon pulses was deteriorated at high glucose, but it could be partially recovered when the re-aggregation of remaining cells was considered. Finally, the third cell type, δ cells, which introduced additional complexity in the multicellular system, prevented the excessive synchronization of hormone pulses. Our computational study suggests that controllable synchronization is a design principle of pancreatic islets.

Traveling wave in a three-dimensional array of conformist and contrarian oscillators.

We consider a system of conformist and contrarian oscillators coupled locally in a three-dimensional cubic lattice and explore collective behavior of the system. The conformist oscillators attractively interact with the neighbor oscillators and therefore tend to be aligned with the neighbors' phase. The contrarian oscillators interact repulsively with the neighbors and therefore tend to be out of phase with them. In this paper, we investigate whether many peculiar dynamics that have been observed in the mean-field system with global coupling can emerge even with local coupling. In particular, we pay attention to the possibility that a traveling wave may arise. We find that the traveling wave occurs due to coupling asymmetry and not by global coupling; this observation confirms that the global coupling is not essential to the occurrence of a traveling wave in the system. The traveling wave can be a mechanism for the coherent rhythm generation of the circadian clock or of hormone secretion in biological systems under local coupling.

A conserved rule for pancreatic islet organization.

Morphogenesis, spontaneous formation of organism structure, is essential for life. In the pancreas, endocrine α, ß, and δ cells are clustered to form islets of Langerhans, the critical micro-organ for glucose homeostasis. The spatial organization of endocrine cells in islets looks different between species. Based on the three-dimensional positions of individual cells in islets, we computationally inferred the relative attractions between cell types, and found that the attractions between homotypic cells were slightly, but significantly, stronger than the attractions between heterotypic cells commonly in mouse, pig, and human islets. The difference between α-ß cell attraction and ß-ß cell attraction was minimal in human islets, maximizing the plasticity of islet structures. Our result suggests that although the cellular composition and attractions of pancreatic endocrine cells are quantitatively different between species, the physical mechanism of islet morphogenesis may be evolutionarily conserved.

Phase transition in dimer liquids.

We study the phase transition in a system composed of dimers interacting with each other via a nearest-neighbor (NN) exchange J and competing interactions taken from a truncated dipolar coupling. Each dimer occupies a link between two nearest sites of a simple cubic lattice. We suppose that dimers are self-avoiding and can have only three orientations, which coincide with the x, y or z direction. The interaction J is attractive if the two dimers are parallel to each other at the NN distance, zero otherwise. The truncated dipolar interaction is characterized by two parameters: its amplitude D and the cutoff distance rc. Using the steepest descent method, we determine the ground-state (GS) configuration as functions of D and rc. We then use Monte Carlo simulations to investigate the nature of the low-temperature phase and to determine characteristics of the phase transition from the ordered phase to the disordered phase at high temperatures at a given dimer concentration. We show that as the temperature increases, dimers remain in the compact state and the transition from the low-T compact phase to the disordered phase where dimers occupy the whole space is of second order when D is small, but becomes of first order for large enough D, for both polarized and nonpolarized dimers. This transition has a resemblance to the unfolding polymer transition. The effect of rc is discussed.

Re-orientation transition in molecular thin films: Potts model with dipolar interaction.

We study the low-temperature behavior and the phase transition of a thin film by Monte Carlo simulation. The thin film has a simple cubic lattice structure where each site is occupied by a Potts parameter which indicates the molecular orientation of the site. We take only three molecular orientations in this paper, which correspond to the three-state Potts model. The Hamiltonian of the system includes (i) the exchange interaction J(ij) between nearest-neighbor sites i and j, (ii) the long-range dipolar interaction of amplitude D truncated at a cutoff distance r(c), and (iii) a single-ion perpendicular anisotropy of amplitude A. We allow J(ij) = J(s) between surface spins, and J(ij) = J otherwise. We show that the ground state depends on the ratio D/A and r(c). For a single layer, for a given A, there is a critical value D(c) below (above) which the ground-state (GS) configuration of molecular axes is perpendicular (parallel) to the film surface. When the temperature T is increased, a re-orientation transition occurs near D(c): the low-T in-plane ordering undergoes a transition to the perpendicular ordering at a finite T, below the transition to the paramagnetic phase. The same phenomenon is observed in the case of a film with a thickness. Comparison with the Fe/Gd experiment is given. We show that the surface phase transition can occur below or above the bulk transition depending on the ratio J(s)/J. Surface and bulk order parameters as well as other physical quantities are shown and discussed.

Partial mixing phase of binary cells in finite systems.

We study the self-organization of binary cell mixtures in finite cubic lattices. Depending on the relative attractions between cell types, the binary mixture model generates four distinct cellular associations: complete sorting, shell-core sorting, partial mixing, and complete mixing of heterotypic cells. At the boundaries between these four phases, the cellular associations show large variations, representing phase transitions. We find that the partial mixing phase is highly tolerant to thermal fluctuations. Interestingly, human pancreatic islets, the micro-organs for glucose homeostasis, adapt the partial mixing phase consisting of α and ß cells.

Effect of dipolar interaction in molecular crystals.

In this paper we investigate the ground state and the nature of the transition from an orientational ordered phase at low temperature to the disordered state at high temperature in a molecular crystal. Our model is a Potts model which takes into account the exchange interaction J between nearest-neighbor molecules and a dipolar interaction between molecular axes in three dimensions. The dipolar interaction is characterized by two parameters: its amplitude D and the cutoff distance r(c). If the molecular axis at a lattice site has three orientations, say the x, y or z axes, then when D = 0, the system is equivalent to the 3-state Potts model: the transition to the disordered phase is known to be of first order. When D ≠ 0, the ground-state configuration is shown to be composed of two independent interpenetrating layered subsystems which form a sandwich whose periodicity depends on D and r(c). We show by extensive Monte Carlo simulation with a histogram method that the phase transition remains of first order at relatively large values of r(c).

Hexagonal-close-packed lattice: Ground state and phase transition.

We study the ground state (GS) and the phase transition in a hexagonal-close-packed lattice with both XY and Ising models by using extensive Monte Carlo simulation. We suppose the in-plane interaction J1 and interplane interaction J2, both antiferromagnetic. The system is frustrated with two kinds of GS configuration below and above a critical value of η=J1/J2 (ηc). For the Ising case, one has ηc=0.5 which separates in-plane ferromagnetic and antiferromagnetic states, while for the XY case ηc=1/3 separates the collinear and noncollinear spin configurations. The phase transition is shown to be of first (second) order for η>(<)ηc. The phase diagram in the space (η,T) is shown for both cases.