Search

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional approaches typically assume that data variations are random, which makes it difficult to adjust the model parameters accurately to remove patterns and characteristics from unlearned data. In this work, we present Unlearning Information Bottleneck (UIB), a novel information-theoretic framework designed to enhance the process of machine unlearning that effectively leverages the influence of systematic patterns and biases for parameter adjustment. By proposing a variational upper bound, we recalibrate the model parameters through a dynamic prior that integrates changes in data distribution with an affordable computational cost, allowing efficient and accurate removal of outdated or unwanted data patterns and biases. Our experiments across various datasets, models, and unlearning methods demonstrate that our approach effectively removes systematic patterns and biases while maintaining the performance of models post-unlearning.

Recent advancements in immune sequencing and experimental techniques are generating extensive T cell receptor (TCR) repertoire data, enabling the development of models to predict TCR binding specificity. Despite the computational challenges due to the vast diversity of TCRs and epitopes, significant progress has been made. This paper discusses the evolution of the computational models developed for this task, with a focus on machine learning efforts, including the early unsupervised clustering approaches, supervised models, and the more recent applications of Protein Language Models (PLMs). We critically assess the most prominent models in each category, and discuss recurrent challenges, such as the lack of generalization to new epitopes, dataset biases, and biases in the validation design of the models. Furthermore, our paper discusses the transformative role of transformer-based protein models in bioinformatics. These models, pretrained on extensive collections of unlabeled protein sequences, can convert amino acid sequences into vectorized embeddings that capture important biological properties. We discuss recent attempts to leverage PLMs to deliver very competitive performances in TCR-related tasks. Finally, we address the pressing need for improved interpretability in these often opaque models, proposing strategies to amplify their impact in the field.

Protein interactions and assembly formation are fundamental to most biological processes. Predicting the assembly structure from constituent proteins -- referred to as the protein docking task -- is thus a crucial step in protein design applications. Most traditional and deep learning methods for docking have focused mainly on binary docking, following either a search-based, regression-based, or generative modeling paradigm. In this paper, we focus on the less-studied multimeric (i.e., two or more proteins) docking problem. We introduce DockGame, a novel game-theoretic framework for docking -- we view protein docking as a cooperative game between proteins, where the final assembly structure(s) constitute stable equilibria w.r.t. the underlying game potential. Since we do not have access to the true potential, we consider two approaches - i) learning a surrogate game potential guided by physics-based energy functions and computing equilibria by simultaneous gradient updates, and ii) sampling from the Gibbs distribution of the true potential by learning a diffusion generative model over the action spaces (rotations and translations) of all proteins. Empirically, on the Docking Benchmark 5.5 (DB5.5) dataset, DockGame has much faster runtimes than traditional docking methods, can generate multiple plausible assembly structures, and achieves comparable performance to existing binary docking baselines, despite solving the harder task of coordinating multiple protein chains., Comment: Under Review

We introduce two new extensions to the beam search algorithm based on conformal predictions (CP) to produce sets of sequences with theoretical coverage guarantees. The first method is very simple and proposes dynamically-sized subsets of beam search results but, unlike typical CP procedures, has an upper bound on the achievable guarantee depending on a post-hoc calibration measure. Our second algorithm introduces the conformal set prediction procedure as part of the decoding process, producing a variable beam width which adapts to the current uncertainty. While more complex, this procedure can achieve coverage guarantees selected a priori. We provide marginal coverage bounds for each method, and evaluate them empirically on a selection of tasks drawing from natural language processing and chemistry., Comment: 11 pages, 4 figures

Conformal regression provides prediction intervals with global coverage guarantees, but often fails to capture local error distributions, leading to non-homogeneous coverage. We address this with a new adaptive method based on rescaling conformal scores with an estimate of local score distribution, inspired by the Jackknife+ method, which enables the use of calibration data in conformal scores without breaking calibration-test exchangeability. Our approach ensures formal global coverage guarantees and is supported by new theoretical results on local coverage, including an a posteriori bound on any calibration score. The strength of our approach lies in achieving local coverage without sacrificing calibration set size, improving the applicability of conformal prediction intervals in various settings. As a result, our method provides prediction intervals that outperform previous methods, particularly in the low-data regime, making it especially relevant for real-world applications such as healthcare and biomedical domains where uncertainty needs to be quantified accurately despite low sample data., Comment: 24 pages, 7 figures

Diffusion Schr\"odinger bridges (DSB) have recently emerged as a powerful framework for recovering stochastic dynamics via their marginal observations at different time points. Despite numerous successful applications, existing algorithms for solving DSBs have so far failed to utilize the structure of aligned data, which naturally arises in many biological phenomena. In this paper, we propose a novel algorithmic framework that, for the first time, solves DSBs while respecting the data alignment. Our approach hinges on a combination of two decades-old ideas: The classical Schr\"odinger bridge theory and Doob's $h$-transform. Compared to prior methods, our approach leads to a simpler training procedure with lower variance, which we further augment with principled regularization schemes. This ultimately leads to sizeable improvements across experiments on synthetic and real data, including the tasks of predicting conformational changes in proteins and temporal evolution of cellular differentiation processes.

Discrete stochastic processes are widespread in natural systems with many applications across physics, biochemistry, epidemiology, sociology, and finance. While analytic solutions often cannot be derived, existing simulation frameworks can generate stochastic trajectories compatible with the dynamical laws underlying the random phenomena. However, most simulation algorithms assume the system dynamics are memoryless (Markovian assumption), under which assumption, future occurrences only depend on the present state of the system. Mathematically, the Markovian assumption models inter-event times as exponentially distributed variables, which enables the exact simulation of stochastic trajectories using the seminal Gillespie algorithm. Unfortunately, the majority of stochastic systems exhibit properties of memory, an inherently non-Markovian attribute. Non-Markovian systems are notoriously difficult to investigate analytically, and existing numerical methods are computationally costly or only applicable under strong simplifying assumptions, often not compatible with empirical observations. To address these challenges, we have developed the Rejection-based Gillespie algorithm for non-Markovian Reactions (REGIR), a general and scalable framework to simulate non-Markovian stochastic systems with arbitrary inter-event time distributions. REGIR can achieve arbitrary user-defined accuracy while maintaining the same asymptotic computational complexity as the Gillespie algorithm. We illustrate REGIR's modeling capabilities in three important biochemical systems, namely microbial growth dynamics, stem cell differentiation, and RNA transcription. In all three cases, REGIR efficiently models the underlying stochastic processes and demonstrates its utility to accurately investigate complex non-Markovian systems. The algorithm is implemented as a python library REGIR.

Interpretability of deep learning is widely used to evaluate the reliability of medical imaging models and reduce the risks of inaccurate patient recommendations. For models exceeding human performance, e.g. predicting RNA structure from microscopy images, interpretable modelling can be further used to uncover highly non-trivial patterns which are otherwise imperceptible to the human eye. We show that interpretability can reveal connections between the microscopic appearance of cancer tissue and its gene expression profiling. While exhaustive profiling of all genes from the histology images is still challenging, we estimate the expression values of a well-known subset of genes that is indicative of cancer molecular subtype, survival, and treatment response in colorectal cancer. Our approach successfully identifies meaningful information from the image slides, highlighting hotspots of high gene expression. Our method can help characterise how gene expression shapes tissue morphology and this may be beneficial for patient stratification in the pathology unit. The code is available on GitHub., Comment: Github Repo: https://github.com/maragraziani/interpretableWSItoRNAseq

The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-components of data. We propose to study the interpretability of attention in the context of set machine learning, where each data point is composed of an unordered collection of instances with a global label. For classical multiple-instance-learning problems and simple extensions, there is a well-defined "importance" ground truth that can be leveraged to cast interpretation as a binary classification problem, which we can quantitatively evaluate. By building synthetic datasets over several data modalities, we perform a systematic assessment of attention-based interpretations. We find that attention distributions are indeed often reflective of the relative importance of individual instances, but that silent failures happen where a model will have high classification performance but attention patterns that do not align with expectations. Based on these observations, we propose to use ensembling to minimize the risk of misleading attention-based explanations., Comment: 11 pages, 20 figures. Presented at the XKDD 2022 workshop

Interpretability has become a necessary feature for machine learning models deployed in critical scenarios, e.g. legal system, healthcare. In these situations, algorithmic decisions may have (potentially negative) long-lasting effects on the end-user affected by the decision. In many cases, the representational power of deep learning models is not needed, therefore simple and interpretable models (e.g. linear models) should be preferred. However, in high-dimensional and/or complex domains (e.g. computer vision), the universal approximation capabilities of neural networks are required. Inspired by linear models and the Kolmogorov-Arnold representation theorem, we propose a novel class of structurally-constrained neural networks, which we call FLANs (Feature-wise Latent Additive Networks). Crucially, FLANs process each input feature separately, computing for each of them a representation in a common latent space. These feature-wise latent representations are then simply summed, and the aggregated representation is used for prediction. These constraints (which are at the core of the interpretability of linear models) allow a user to estimate the effect of each individual feature independently from the others, enhancing interpretability. In a set of experiments across different domains, we show how without compromising excessively the test performance, the structural constraints proposed in FLANs indeed facilitates the interpretability of deep learning models. We quantitatively compare FLANs interpretability to post-hoc methods using recently introduced metrics, discussing the advantages of natively interpretable models over a post-hoc analysis.

Motivation: The activity of the adaptive immune system is governed by T-cells and their specific T-cell receptors (TCR), which selectively recognize foreign antigens. Recent advances in experimental techniques have enabled sequencing of TCRs and their antigenic targets (epitopes), allowing to research the missing link between TCR sequence and epitope binding specificity. Scarcity of data and a large sequence space make this task challenging, and to date only models limited to a small set of epitopes have achieved good performance. Here, we establish a k-nearest-neighbor (K-NN) classifier as a strong baseline and then propose TITAN (Tcr epITope bimodal Attention Networks), a bimodal neural network that explicitly encodes both TCR sequences and epitopes to enable the independent study of generalization capabilities to unseen TCRs and/or epitopes. Results: By encoding epitopes at the atomic level with SMILES sequences, we leverage transfer learning and data augmentation to enrich the input data space and boost performance. TITAN achieves high performance in the prediction of specificity of unseen TCRs (ROC-AUC 0.87 in 10-fold CV) and surpasses the results of the current state-of-the-art (ImRex) by a large margin. Notably, our Levenshtein-distance-based K-NN classifier also exhibits competitive performance on unseen TCRs. While the generalization to unseen epitopes remains challenging, we report two major breakthroughs. First, by dissecting the attention heatmaps, we demonstrate that the sparsity of available epitope data favors an implicit treatment of epitopes as classes. This may be a general problem that limits unseen epitope performance for sufficiently complex models. Second, we show that TITAN nevertheless exhibits significantly improved performance on unseen epitopes and is capable of focusing attention on chemically meaningful molecular structures., Comment: 9 pages, 5 figures, to be published in ISMB 2021 conference proceedings

Less than 1% of protein sequences are structurally and functionally annotated. Natural Language Processing (NLP) community has recently embraced self-supervised learning as a powerful approach to learn representations from unlabeled text, in large part due to the attention-based context-aware Transformer models. In this work we present a modification to the RoBERTa model by inputting during pre-training a mixture of binding and non-binding protein sequences (from STRING database). However, the sequence pairs have no label to indicate their binding status, as the model relies solely on Masked Language Modeling (MLM) objective during pre-training. After fine-tuning, such approach surpasses models trained on single protein sequences for protein-protein binding prediction, TCR-epitope binding prediction, cellular-localization and remote homology classification tasks. We suggest that the Transformer's attention mechanism contributes to protein binding site discovery. Furthermore, we compress protein sequences by 64% with the Byte Pair Encoding (BPE) vocabulary consisting of 10K subwords, each around 3-4 amino acids long. Finally, to expand the model input space to even larger proteins and multi-protein assemblies, we pre-train Longformer models that support 2,048 tokens. Further work in token-level classification for secondary structure prediction is needed. Code available at: https://github.com/PaccMann/paccmann_proteomics, Comment: 20 pages, 12 figures, accepted to Machine Learning for Structural Biology (MLSB) workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS)

We propose to learn model invariances as a means of interpreting a model. This is motivated by a reverse engineering principle. If we understand a problem, we may introduce inductive biases in our model in the form of invariances. Conversely, when interpreting a complex supervised model, we can study its invariances to understand how that model solves a problem. To this end we propose a supervised form of variational auto-encoders (VAEs). Crucially, only a subset of the dimensions in the latent space contributes to the supervised task, allowing the remaining dimensions to act as nuisance parameters. By sampling solely the nuisance dimensions, we are able to generate samples that have undergone transformations that leave the classification unchanged, revealing the invariances of the model. Our experimental results show the capability of our proposed model both in terms of classification, and generation of invariantly transformed samples. Finally we show how combining our model with feature attribution methods it is possible to reach a more fine-grained understanding about the decision process of the model.

Despite the growing body of work in interpretable machine learning, it remains unclear how to evaluate different explainability methods without resorting to qualitative assessment and user-studies. While interpretability is an inherently subjective matter, previous works in cognitive science and epistemology have shown that good explanations do possess aspects that can be objectively judged apart from fidelity), such assimplicity and broadness. In this paper we propose a set of metrics to programmatically evaluate interpretability methods along these dimensions. In particular, we argue that the performance of methods along these dimensions can be orthogonally imputed to two conceptual parts, namely the feature extractor and the actual explainability method. We experimentally validate our metrics on different benchmark tasks and show how they can be used to guide a practitioner in the selection of the most appropriate method for the task at hand.

With the fast development of COVID-19 into a global pandemic, scientists around the globe are desperately searching for effective antiviral therapeutic agents. Bridging systems biology and drug discovery, we propose a deep learning framework for conditional de novo design of antiviral candidate drugs tailored against given protein targets. First, we train a multimodal ligand--protein binding affinity model on predicting affinities of antiviral compounds to target proteins and couple this model with pharmacological toxicity predictors. Exploiting this multi-objective as a reward function of a conditional molecular generator (consisting of two VAEs), we showcase a framework that navigates the chemical space toward regions with more antiviral molecules. Specifically, we explore a challenging setting of generating ligands against unseen protein targets by performing a leave-one-out-cross-validation on 41 SARS-CoV-2-related target proteins. Using deep RL, it is demonstrated that in 35 out of 41 cases, the generation is biased towards sampling more binding ligands, with an average increase of 83% comparing to an unbiased VAE. We present a case-study on a potential Envelope-protein inhibitor and perform a synthetic accessibility assessment of the best generated molecules is performed that resembles a viable roadmap towards a rapid in-vitro evaluation of potential SARS-CoV-2 inhibitors., Comment: 5 pages, 6 figures

In this work we perform a study of various unsupervised methods to identify mental stress in firefighter trainees based on unlabeled heart rate variability data. We collect RR interval time series data from nearly 100 firefighter trainees that participated in a drill. We explore and compare three methods in order to perform unsupervised stress detection: 1) traditional K-Means clustering with engineered time and frequency domain features 2) convolutional autoencoders and 3) long short-term memory (LSTM) autoencoders, both trained on the raw RRI measurements combined with DBSCAN clustering and K-Nearest-Neighbors classification. We demonstrate that K-Means combined with engineered features is unable to capture meaningful structure within the data. On the other hand, convolutional and LSTM autoencoders tend to extract varying structure from the data pointing to different clusters with different sizes of clusters. We attempt at identifying the true stressed and normal clusters using the HRV markers of mental stress reported in the literature. We demonstrate that the clusters produced by the convolutional autoencoders consistently and successfully stratify stressed versus normal samples, as validated by several established physiological stress markers such as RMSSD, Max-HR, Mean-HR and LF-HF ratio.

Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance. This is especially true when there is interest in deploying data-driven models to make high-stakes decisions, e.g. in healthcare. While recent years have seen an increasing interest in interpretable machine learning research, this field is currently lacking an agreed-upon definition of interpretability, and some researchers have called for a more active conversation towards a rigorous approach to interpretability. Joining this conversation, we claim in this paper that the difficulty of interpreting a complex model stems from the existing interactions among features. We argue that by enforcing monotonicity between features and outputs, we are able to reason about the effect of a single feature on an output independently from other features, and consequently better understand the model. We show how to structurally introduce this constraint in deep learning models by adding new simple layers. We validate our model on benchmark datasets, and compare our results with previously proposed interpretable models.

With the advent of deep generative models in computational chemistry, in silico anticancer drug design has undergone an unprecedented transformation. While state-of-the-art deep learning approaches have shown potential in generating compounds with desired chemical properties, they disregard the genetic profile and properties of the target disease. Here, we introduce the first generative model capable of tailoring anticancer compounds for a specific biomolecular profile. Using a RL framework, the transcriptomic profiles of cancer cells are used as a context for the generation of candidate molecules. Our molecule generator combines two separately pretrained variational autoencoders (VAEs) - the first VAE encodes transcriptomic profiles into a smooth, latent space which in turn is used to condition a second VAE to generate novel molecular structures on the given transcriptomic profile. The generative process is optimized through PaccMann, a previously developed drug sensitivity prediction model to obtain effective anticancer compounds for the given context (i.e., transcriptomic profile). We demonstrate how the molecule generation can be biased towards compounds with high predicted inhibitory effect against individual cell lines or specific cancer sites. We verify our approach by investigating candidate drugs generated against specific cancer types and find the highest structural similarity to existing compounds with known efficacy against these cancer types. We envision our approach to transform in silico anticancer drug design by leveraging the biomolecular characteristics of the disease in order to increase success rates in lead compound discovery., Comment: 18 pages total (12 pages main text, 4 pages references, 11 pages appendix) 8 figures

In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds' structure in the form of a SMILES sequence, gene expression profiles of tumors and prior knowledge on intracellular interactions from protein-protein interaction networks. We demonstrate that our multiscale convolutional attention-based (MCA) encoder significantly outperforms a baseline model trained on Morgan fingerprints, a selection of encoders based on SMILES as well as previously reported state of the art for multimodal drug sensitivity prediction (R2 = 0.86 and RMSE = 0.89). Moreover, the explainability of our approach is demonstrated by a thorough analysis of the attention weights. We show that the attended genes significantly enrich apoptotic processes and that the drug attention is strongly correlated with a standard chemical structure similarity index. Finally, we report a case study of two receptor tyrosine kinase (RTK) inhibitors acting on a leukemia cell line, showcasing the ability of the model to focus on informative genes and submolecular regions of the two compounds. The demonstrated generalizability and the interpretability of our model testify its potential for in-silico prediction of anticancer compound efficacy on unseen cancer cells, positioning it as a valid solution for the development of personalized therapies as well as for the evaluation of candidate compounds in de novo drug design., Comment: 11 pages, 5 figures, 1 table, Workshop on Computational Biology at the International Conference on Machine Learning (ICML), Long Beach, CA, 2019

The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler-Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN., Comment: Representation Learning on Graphs and Manifolds @ ICLR19

Understanding the three-dimensional (3D) structure of the genome is essential for elucidating vital biological processes and their links to human disease. To determine how the genome folds within the nucleus, chromosome conformation capture methods such as HiC have recently been employed. However, computational methods that exploit the resulting high-throughput, high-resolution data are still suffering from important limitations. In this work, we explore the idea of manifold learning for the 3D chromatin structure inference and present a novel method, REcurrent Autoencoders for CHromatin 3D structure prediction (REACH-3D). Our framework employs autoencoders with recurrent neural units to reconstruct the chromatin structure. In comparison to existing methods, REACH-3D makes no transfer function assumption and permits dynamic analysis. Evaluating REACH-3D on synthetic data indicated high agreement with the ground truth. When tested on real experimental HiC data, REACH-3D recovered most faithfully the expected biological properties and obtained the highest correlation coefficient with microscopy measurements. Last, REACH-3D was applied to dynamic HiC data, where it successfully modeled chromatin conformation during the cell cycle., Comment: 10 pages, 7 figures, 1 algorithm. Neural Information Processing Systems, Machine Learning for Molecules and Materials, 2018

We present a novel approach for the prediction of anticancer compound sensitivity by means of multi-modal attention-based neural networks (PaccMann). In our approach, we integrate three key pillars of drug sensitivity, namely, the molecular structure of compounds, transcriptomic profiles of cancer cells as well as prior knowledge about interactions among proteins within cells. Our models ingest a drug-cell pair consisting of SMILES encoding of a compound and the gene expression profile of a cancer cell and predicts an IC50 sensitivity value. Gene expression profiles are encoded using an attention-based encoding mechanism that assigns high weights to the most informative genes. We present and study three encoders for SMILES string of compounds: 1) bidirectional recurrent 2) convolutional 3) attention-based encoders. We compare our devised models against a baseline model that ingests engineered fingerprints to represent the molecular structure. We demonstrate that using our attention-based encoders, we can surpass the baseline model. The use of attention-based encoders enhance interpretability and enable us to identify genes, bonds and atoms that were used by the network to make a prediction., Comment: 10 pages, 5 figures, 2 tables. NIPS MLMM 2018

We present the Network-based Biased Tree Ensembles (NetBiTE) method for drug sensitivity prediction and drug sensitivity biomarker identification in cancer using a combination of prior knowledge and gene expression data. Our devised method consists of a biased tree ensemble that is built according to a probabilistic bias weight distribution. The bias weight distribution is obtained from the assignment of high weights to the drug targets and propagating the assigned weights over a protein-protein interaction network such as STRING. The propagation of weights, defines neighborhoods of influence around the drug targets and as such simulates the spread of perturbations within the cell, following drug administration. Using a synthetic dataset, we showcase how application of biased tree ensembles (BiTE) results in significant accuracy gains at a much lower computational cost compared to the unbiased random forests (RF) algorithm. We then apply NetBiTE to the Genomics of Drug Sensitivity in Cancer (GDSC) dataset and demonstrate that NetBiTE outperforms RF in predicting IC50 drug sensitivity, only for drugs that target membrane receptor pathways (MRPs): RTK, EGFR and IGFR signaling pathways. We propose based on the NetBiTE results, that for drugs that inhibit MRPs, the expression of target genes prior to drug administration is a biomarker for IC50 drug sensitivity following drug administration. We further verify and reinforce this proposition through control studies on, PI3K/MTOR signaling pathway inhibitors, a drug category that does not target MRPs, and through assignment of dummy targets to MRP inhibiting drugs and investigating the variation in NetBiTE accuracy., Comment: 36 pages, 5 figures, 3 supplementary figures

Reliable identification of molecular biomarkers is essential for accurate patient stratification. While state-of-the-art machine learning approaches for sample classification continue to push boundaries in terms of performance, most of these methods are not able to integrate different data types and lack generalization power, limiting their application in a clinical setting. Furthermore, many methods behave as black boxes, and we have very little understanding about the mechanisms that lead to the prediction. While opaqueness concerning machine behaviour might not be a problem in deterministic domains, in health care, providing explanations about the molecular factors and phenotypes that are driving the classification is crucial to build trust in the performance of the predictive system. We propose Pathway Induced Multiple Kernel Learning (PIMKL), a novel methodology to reliably classify samples that can also help gain insights into the molecular mechanisms that underlie the classification. PIMKL exploits prior knowledge in the form of a molecular interaction network and annotated gene sets, by optimizing a mixture of pathway-induced kernels using a Multiple Kernel Learning (MKL) algorithm, an approach that has demonstrated excellent performance in different machine learning applications. After optimizing the combination of kernels for prediction of a specific phenotype, the model provides a stable molecular signature that can be interpreted in the light of the ingested prior knowledge and that can be used in transfer learning tasks.

In recent years, the number of biomedical publications has steadfastly grown, resulting in a rich source of untapped new knowledge. Most biomedical facts are however not readily available, but buried in the form of unstructured text, and hence their exploitation requires the time-consuming manual curation of published articles. Here we present INtERAcT, a novel approach to extract protein-protein interactions from a corpus of biomedical articles related to a broad range of scientific domains in a completely unsupervised way. INtERAcT exploits vector representation of words, computed on a corpus of domain specific knowledge, and implements a new metric that estimates an interaction score between two molecules in the space where the corresponding words are embedded. We demonstrate the power of INtERAcT by reconstructing the molecular pathways associated to 10 different cancer types using a corpus of disease-specific articles for each cancer type. We evaluate INtERAcT using STRING database as a benchmark, and show that our metric outperforms currently adopted approaches for similarity computation at the task of identifying known molecular interactions in all studied cancer types. Furthermore, our approach does not require text annotation, manual curation or the definition of semantic rules based on expert knowledge, and hence it can be easily and efficiently applied to different scientific domains. Our findings suggest that INtERAcT may increase our capability to summarize the understanding of a specific disease using the published literature in an automated and completely unsupervised fashion.

Background: MicroRNAs (miRNAs) play multiple roles in tumor biology [1]. Interestingly, reports from multiple groups suggest that miRNA targets may be coupled through competitive stoichiometric sequestration [2]. Specifically, computational models predicted [3, 4] and experimental assays confirmed [5, 6] that miRNA activity is dependent on miRNA target abundance, and consequently, changes to the abundance of some miRNA targets lead to changes to the regulation and abundance of their other targets. The resulting indirect regulatory influence between miRNA targets resembles competition and has been dubbed competitive endogenous RNA (ceRNA) [5, 7, 8]. Recent studies have questioned the physiological relevance of ceRNA interactions [9], researchers ability to accurately predict these interactions [10], and the number of genes that are impacted by ceRNA interactions in specific cellular contexts [11]. Results: To address these concerns, we reverse engineered ceRNA networks (ceRNETs) in breast and prostate adenocarcinomas using context-specific TCGA profiles [12-14], and tested whether ceRNA interactions can predict the effects of RNAi-mediated gene silencing perturbations in PC3 and MCF7 cells. Our results, based on tests of thousands of inferred ceRNA interactions that are predicted to alter hundreds of cancer genes in each of the two tumor contexts, confirmed statistically significant effects for half of the predicted targets. Conclusions: Our results suggest that the expression of a significant fraction of cancer genes may be regulated by ceRNA interactions in each of the two tumor contexts.

Explicit accounting for copy number alterations can dramatically improve mutation frequency estimates, leading to more accurate phylogeny reconstructions and subclone characterizations.

In this follow-up to our paper from 2005, we briefly discuss the implications of the apparent detection of B modes in the Cosmic Microwave Background for the issues raised in that paper. We argue that under the assumptions of eternal inflation, there is now stronger support for the detectability of a Coleman-De Luccia bubble nucleation event in our past. In particular, the odds that the spatial curvature of the universe is large enough to be detectable by near future experiments are increased., Comment: 13 pages, 5 figures

Cooperative effects in neural networks appear because a neuron fires only if a minimal number $m$ of its inputs are excited. The multiple inputs requirement leads to a percolation model termed {\it quorum percolation}. The connectivity undergoes a phase transition as $m$ grows, from a network--spanning cluster at low $m$ to a set of disconnected clusters above a critical $m$. Both numerical simulations and the model reproduce the experimental results well. This allows a robust quantification of biologically relevant quantities such as the average connectivity $\kbar$ and the distribution of connections $p_k$, Comment: 87.19.L-: Neuroscience 87.19.ll: Models of single neurons and networks 64.60.ah: Percolation http://iopscience.iop.org/0295-5075/89/1/18008 http://www.weizmann.ac.il/complex/tlusty/papers/EuroPhysLett2010.pdf

Single cell experiments of simple regulatory networks can markedly differ from cell population experiments. Such differences arise from stochastic events in individual cells that are averaged out in cell populations. For instance, while individual cells may show sustained oscillations in the concentrations of some proteins, such oscillations may appear damped in the population average. In this paper we investigate the role of RNA stochastic fluctuations as a leading force to produce a sustained excitatory behavior at the single cell level. Opposed to some previous models, we build a fully stochastic model of a negative feedback loop that explicitly takes into account the RNA stochastic dynamics. We find that messenger RNA random fluctuations can be amplified during translation and produce sustained pulses of protein expression. Motivated by the recent appreciation of the importance of non--coding regulatory RNAs in post--transcription regulation, we also consider the possibility that a regulatory RNA transcript could bind to the messenger RNA and repress translation. Our findings show that the regulatory transcript helps reduce gene expression variability both at the single cell level and at the cell population level., Comment: 87.18.Vf --> Systems biology 87.10.Mn --> Stochastic models in biological systems 87.18.Tt --> Noise in biological systems http://www.ncbi.nlm.nih.gov/pubmed/20365787 http://www.weizmann.ac.il/complex/tlusty/papers/PhysRevE2010.pdf

Various approaches to quantum gravity suggest the possibility of violation of Lorentz symmetry at very high energies. In these cases we expect a modification at low energies of the dispersion relation of photons that contains extra powers of the momentum suppressed by a high energy scale. These terms break boost invariance and can be tested even at relatively low energies. We use the light curves of the very bright short Gamma-Ray Burst GRB 051221A and compare the arrival times of photons at different energies with the expected time delay due to a modified dispersion relation. As no time delay was observed, we set a lower bound of 0.0066 E_{pl} \sim 0.66 10^{17} GeV on the scale of Lorentz invariance violation., Comment: 9 pages, 2 figures

Gamma ray bursts are excellent candidates to constrain physical models which break Lorentz symmetry. We consider deformed dispersion relations which break the boost invariance and lead to an energy-dependent speed of light. In these models, simultaneously emitted photons from cosmological sources reach Earth with a spectral time delay that depends on the symmetry breaking scale. We estimate the possible bounds which can be obtained by comparing the spectral time delays with the time resolution of available telescopes. We discuss the best strategy to reach the strongest bounds. We compute the probability of detecting bursts that improve the current bounds. The results are encouraging. Depending on the model, it is possible to build a detector that within several years will improve the present limits of 0.015 m_pl., Comment: 16 pages, 4 figures; reference added

In this paper we consider the implications of the "landscape" paradigm for the large scale properties of the universe. The most direct implication of a rich landscape is that our local universe was born in a tunnelling event from a neighboring vacuum. This would imply that we live in an open FRW universe with negative spatial curvature. We argue that the "overshoot" problem, which in other settings would make it difficult to achieve slow roll inflation, actually favors such a cosmology. We consider anthropic bounds on the value of the curvature and on the parameters of inflation. When supplemented by statistical arguments these bounds suggest that the number of inflationary efolds is not very much larger than the observed lower bound. Although not statistically favored, the likelihood that the number of efolds is close to the bound set by observations is not negligible. The possible signatures of such a low number of efolds are briefly described., Comment: 21 pages, 4 figures v2: references added