Federated learning for predicting histological response to neoadjuvant chemotherapy in triple-negative breast cancer

Triple-negative breast cancer (TNBC) is a rare cancer, characterized by high metastatic potential and poor prognosis, and has limited treatment options. The current standard of care in nonmetastatic settings is neoadjuvant chemotherapy (NACT), but treatment efficacy varies substantially across patients. This heterogeneity is still poorly understood, partly due to the paucity of curated TNBC data. Here we investigate the use of machine learning (ML) leveraging whole-slide images and clinical information to predict, at diagnosis, the histological response to NACT for early TNBC women patients. To overcome the biases of small-scale studies while respecting data privacy, we conducted a multicentric TNBC study using federated learning, in which patient data remain secured behind hospitals' firewalls. We show that local ML models relying on whole-slide images can predict response to NACT but that collaborative training of ML models further improves performance, on par with the best current approaches in which ML models are trained using time-consuming expert annotations. Our ML model is interpretable and is sensitive to specific histological patterns. This proof of concept study, in which federated learning is applied to real-world datasets, paves the way for future biomarker discovery using unprecedentedly large datasets.

External control arm analysis: an evaluation of propensity score approaches, G-computation, and doubly debiased machine learning

BACKGROUND

An external control arm is a cohort of control patients that are collected from data external to a single-arm trial. To provide an unbiased estimation of efficacy, the clinical profiles of patients from single and external arms should be aligned, typically using propensity score approaches. There are alternative approaches to infer efficacy based on comparisons between outcomes of single-arm patients and machine-learning predictions of control patient outcomes. These methods include G-computation and Doubly Debiased Machine Learning (DDML) and their evaluation for External Control Arms (ECA) analysis is insufficient.

METHODS

We consider both numerical simulations and a trial replication procedure to evaluate the different statistical approaches: propensity score matching, Inverse Probability of Treatment Weighting (IPTW), G-computation, and DDML. The replication study relies on five type 2 diabetes randomized clinical trials granted by the Yale University Open Data Access (YODA) project. From the pool of five trials, observational experiments are artificially built by replacing a control arm from one trial by an arm originating from another trial and containing similarly-treated patients.

RESULTS

Among the different statistical approaches, numerical simulations show that DDML has the smallest bias followed by G-computation. In terms of mean squared error, G-computation usually minimizes mean squared error. Compared to other methods, DDML has varying Mean Squared Error performances that improves with increasing sample sizes. For hypothesis testing, all methods control type I error and DDML is the most conservative. G-computation is the best method in terms of statistical power, and DDML has comparable power at [Formula: see text] but inferior ones for smaller sample sizes. The replication procedure also indicates that G-computation minimizes mean squared error whereas DDML has intermediate performances in between G-computation and propensity score approaches. The confidence intervals of G-computation are the narrowest whereas confidence intervals obtained with DDML are the widest for small sample sizes, which confirms its conservative nature.

CONCLUSIONS

For external control arm analyses, methods based on outcome prediction models can reduce estimation error and increase statistical power compared to propensity score approaches.

An artificial intelligence model predicts the survival of solid tumour patients from imaging and clinical data

BACKGROUND

The need for developing new biomarkers is increasing with the emergence of many targeted therapies. Artificial Intelligence (AI) algorithms have shown great promise in the medical imaging field to build predictive models. We developed a prognostic model for solid tumour patients using AI on multimodal data.

PATIENTS AND METHODS

Our retrospective study included examinations of patients with seven different cancer types performed between 2003 and 2017 in 17 different hospitals. Radiologists annotated all metastases on baseline computed tomography (CT) and ultrasound (US) images. Imaging features were extracted using AI models and used along with the patients' and treatments' metadata. A Cox regression was fitted to predict prognosis. Performance was assessed on a left-out test set with 1000 bootstraps.

RESULTS

The model was built on 436 patients and tested on 196 patients (mean age 59, IQR: 51-6, 411 men out of 616 patients). On the whole, 1147 US images were annotated with lesions delineation, and 632 thorax-abdomen-pelvis CTs (total of 301,975 slices) were fully annotated with a total of 9516 lesions. The developed model reaches an average concordance index of 0.71 (0.67-0.76, 95% CI). Using the median predicted risk as a threshold value, the model is able to significantly (log-rank test P value < 0.001) isolate high-risk patients from low-risk patients (respective median OS of 11 and 31 months) with a hazard ratio of 3.5 (2.4-5.2, 95% CI).

CONCLUSION

AI was able to extract prognostic features from imaging data, and along with clinical data, allows an accurate stratification of patients' prognoses.

Abstract 1924: PULS-AI: A multimodal artificial intelligence model to predict survival of solid tumor patients treated with antiangiogenics

The need for developing new biomarkers is increasing with the emergence of many targeted therapies. In this study, we used artificial intelligence (AI) to develop a multimodal model (PULS-AI) predicting the survival of solid tumor patients treated with antiangiogenic treatments.

Our retrospective, multicentric study included 616 patients with 7 different cancer types: renal cell carcinoma, colorectal carcinoma, hepatocellular carcinoma, gastrointestinal carcinoma, melanoma, breast cancer, and sarcoma. A set of 196 patients was left out of the study for validation. Clinical data including patient, treatment, and cancer metadata were collected at baseline for all patients, as well as computed tomography (CT) and ultrasound (US) images. Radiologists annotated all metastases on the CT images and the visible tumor lesion on the US images. AI models were used to extract relevant features from the regions of interest on CT and US images. In addition, handcrafted features related to the tumor burden were extracted from the annotations of all lesions on CT such as the number of lesions and the tumor burden volume per organ (lungs, liver, skull, bone, other). Finally, a Cox regression model was fitted to the set of imaging features and clinical features.

The annotation process led to 1147 annotated US images with lesions delineation and 4564 reviewed CTs, of which 989 were selected and fully annotated with a total of 9516 annotated lesions.The developed model reaches an average concordance index of 0.71 (0.67-0.75, 95% CI). Using a risk threshold of 50%, PULS-AI model is able to significantly isolate (log-rank test P-value &lt; 0.001) high-risk patients from low-risk patients (respective median OS of 12 and 32 months) with a hazard ratio of 3.52 (2.35-5.28, 95% CI).

The results of this study show that AI algorithms are able to extract relevant information from radiology images and to aggregate data from multiple modalities to build powerful prognostic tools. Such tools may provide assistance to oncology clinicians in therapeutic decision-making.

Citation Format: Kathryn Schutte, Fabien Brulport, Sana Harguem-Zayani, Jean-Baptiste Schiratti, Ridouane Ghermi, Paul Jehanno, Alexandre Jaeger, Talal Alamri, Raphael Naccache, Leila Haddag-Miliani, Teresa Orsi, Jean-Philippe Lamarque, Isaline Hoferer, Littisha Lawrance, Baya Benatsou, Imad Bousaid, Mickael Azoulay, Antoine Verdon, François Bidault, Corinne Balleyguier, Victor Aubert, Etienne Bendjebbar, Charles Maussion, Nicolas Loiseau, Benoit Schmauch, Meriem Sefta, Gilles Wainrib, Thomas Clozel, Samy Ammari, Nathalie Lassau. PULS-AI: A multimodal artificial intelligence model to predict survival of solid tumor patients treated with antiangiogenics [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1924.

Collaborative federated learning behind hospitals’ firewalls for predicting histological complete response to neoadjuvant chemotherapy in triple-negative breast cancer

590

Background: Triple-Negative Breast Cancer (TNBC) is characterized by high metastatic potential and poor prognosis with limited treatment options. Neoadjuvant chemotherapy (NACT) is the standard of care in non-metastastic setting due to the ability to assess pathologic responses providing important prognostic information and guidance in adjuvant therapy decisions. However, the histological response heterogeneity is still poorly understood. We investigate the use of Machine Learning (ML) to predict from diagnosis Whole-Slide Images (WSI) of early TNBC the positive histological Complete Response (pCR) to NACT on surgical specimens. To overcome the known biases of small scale studies while respecting data privacy, we conduct a study in a multi-centric fashion behind hospitals’ firewalls using collaborative Federated Learning (FL). Thereby allowing access to enough TNBC data to sustain a complete response heterogeneity investigation. Methods: We collected in both comprehensive cancer centers: Centre Léon Bérard (A)(n=99) and Institut Curie (B) (n=420), WSI of biopsies performed at diagnosis and relevant clinical variables. We use traditional Multiple Instance Learning pipelines by tiling the matter on each WSI with a pre-trained Neural Network (NN). We train a second NN to predict the NACT pCR using the mean feature of each WSI. ML trainings are performed using either one cohort in isolation (NN Local) or both cohorts using FL. We compare the performance of this federated WSI based model to the best clinical model (Clin.) simulating clinical practice (using grade and Tumor-Infiltrating Lymphocytes (TILs) percentage) on both centers. Results: Performance of models to predict NACT pCR (AUC). All results are evaluated in 5 repeated 4-folds cross validations. Conclusions: The final ML model, that was trained in a privacy preserving fashion on both hospitals, provides better prediction of NACT pCR than current clinical standards. This study shows that 1. Not all relevant information is routinely extracted from WSI and 2. Non simulated FL is possible in Healthcare and gives better results than siloed studies on open medical questions. Additional interpretability results of the model show that it has re-discovered known biomarkers such as TILs and apocrine tumor cells without any tile-level annotation, and hints at potential new biomarkers. [Table: see text]

A deep learning method for predicting knee osteoarthritis radiographic progression from MRI

Background

The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs.

Methods

Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OAI) database , we implemented a deep learning method to predict, from MR images and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months.

Results

Using COR IW TSE images, our classification model achieved a ROC AUC score of 65%. On a similar task, trained radiologists obtained a ROC AUC score of 58.7% highlighting the difficulty of the classification task. Additional analyses conducted in parallel to predict pain grade evaluated by the WOMAC pain index achieved a ROC AUC score of 72%. Attention maps provided evidence for distinct specific areas as being relevant in those two predictive models, including the medial joint space for JSN progression and the intra-articular space for pain prediction.

Conclusions

This feasibility study demonstrates the interest of deep learning applied to OA, with a potential to support even trained radiologists in the challenging task of identifying patients with a high-risk of disease progression.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13075-021-02634-4.

Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients

The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, and chest CT scan data, from 1003 coronavirus-infected patients from two French hospitals. We train a deep learning model based on CT scans to predict severity. We then construct the multimodal AI-severity score that includes 5 clinical and biological variables (age, sex, oxygenation, urea, platelet) in addition to the deep learning model. We show that neural network analysis of CT-scans brings unique prognosis information, although it is correlated with other markers of severity (oxygenation, LDH, and CRP) explaining the measurable but limited 0.03 increase of AUC obtained when adding CT-scan information to clinical variables. Here, we show that when comparing AI-severity with 11 existing severity scores, we find significantly improved prognosis performance; AI-severity can therefore rapidly become a reference scoring approach.

Predicting Survival After Hepatocellular Carcinoma Resection Using Deep Learning on Histological Slides

BACKGROUND AND AIMS

Standardized and robust risk-stratification systems for patients with hepatocellular carcinoma (HCC) are required to improve therapeutic strategies and investigate the benefits of adjuvant systemic therapies after curative resection/ablation.

APPROACH AND RESULTS

In this study, we used two deep-learning algorithms based on whole-slide digitized histological slides (whole-slide imaging; WSI) to build models for predicting survival of patients with HCC treated by surgical resection. Two independent series were investigated: a discovery set (Henri Mondor Hospital, n = 194) used to develop our algorithms and an independent validation set (The Cancer Genome Atlas [TCGA], n = 328). WSIs were first divided into small squares ("tiles"), and features were extracted with a pretrained convolutional neural network (preprocessing step). The first deep-learning-based algorithm ("SCHMOWDER") uses an attention mechanism on tumoral areas annotated by a pathologist whereas the second ("CHOWDER") does not require human expertise. In the discovery set, c-indices for survival prediction of SCHMOWDER and CHOWDER reached 0.78 and 0.75, respectively. Both models outperformed a composite score incorporating all baseline variables associated with survival. Prognostic value of the models was further validated in the TCGA data set, and, as observed in the discovery series, both models had a higher discriminatory power than a score combining all baseline variables associated with survival. Pathological review showed that the tumoral areas most predictive of poor survival were characterized by vascular spaces, the macrotrabecular architectural pattern, and a lack of immune infiltration.

CONCLUSIONS

This study shows that artificial intelligence can help refine the prediction of HCC prognosis. It highlights the importance of pathologist/machine interactions for the construction of deep-learning algorithms that benefit from expert knowledge and allow a biological understanding of their output.

Abstract 2105: HE2RNA: A deep learning model for transcriptomic learning from digital pathology

Today, pathology imaging is one of the most common and inexpensive diagnostic/prognostic tools used in oncology, while more sophisticated methods such as next generation sequencing (NGS) remain relatively expensive and not routinely used in a clinical setting. Deep convolutional neural networks (CNNs) have emerged as an important image analysis technology enhancing the workflow of pathologists and improving the prediction of patient prognosis and response to treatment​​. Recently, a few attempts have been made to predict molecular features from tissue imaging using CNNs. While these preliminary results are encouraging, there have been no systematic attempts to link Whole Slide Images (WSIs) to transcriptomic profiles. In this study, we developed a cutting-edge deep learning model named HE2RNA, specifically customized for the direct prediction of gene expression from H&E-stained WSIs without need for annotation from pathologists. Our model was trained and tested on 8,725 patients from 28 different cancer types available at The Cancer Genome Atlas (TCGA).

HE2RNA accurately predicted the expression of six gene signatures related to well known cancer hallmarks (angiogenesis, hypoxia, DNA repair, cell cycle and immunity) and performed particularly well for signalling pathways involved in immune cell activation. This indicates that suitably designed deep learning models can recognize subtle structures in tissue imaging and relate them to molecular portraits.

Moreover, HE2RNA is designed to generate a spatial representation (virtual map) of any well-predicted gene expression overlaying the H&E slide. Such a virtual map was validated on a double-stained H&E/CD3 slide obtained from an independent hepatocellular carcinoma sample. This spatialization could be useful in augmenting the pathologists' workflow by providing a virtual multiplexed staining for each H&E slide while overcoming the technical issues associated with immunohistochemistry.

Various important prognostic factors, such as microsatellite instability (MSI), are derived from molecular features. Microsatellite instability refers to the hypermutability of short repetitive genomic sequences caused by impaired DNA mismatch repair. These mutations frequently observed in gastric and colorectal cancer are associated with better response to immunotherapy. We show that the transcriptomic representation learned by our model can be used to improve the performance of MSI status prediction for small datasets of WSI. This type of setting is common since large databases of matched RNA-Seq profiles and WSI are widely available, while databases of matched MSI status and WSI are more scarce. In the future, such technologies could therefore facilitate universal screening of molecular biomarkers and improved identification of patients that could benefit from new therapeutic strategies.

Citation Format: Elodie Pronier, Benoît Schmauch, Alberto Romagnoni, Charlie Saillard, Pascale Maillé, Julien Calderaro, Meriem Sefta, Sylvain Toldo, Mikhail Zaslavskiy, Thomas Clozel, Matahi Moarii, Pierre Courtiol, Gilles Wainrib. HE2RNA: A deep learning model for transcriptomic learning from digital pathology [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2105.

A deep learning model to predict RNA-Seq expression of tumours from whole slide images

Deep learning methods for digital pathology analysis are an effective way to address multiple clinical questions, from diagnosis to prediction of treatment outcomes. These methods have also been used to predict gene mutations from pathology images, but no comprehensive evaluation of their potential for extracting molecular features from histology slides has yet been performed. We show that HE2RNA, a model based on the integration of multiple data modes, can be trained to systematically predict RNA-Seq profiles from whole-slide images alone, without expert annotation. Through its interpretable design, HE2RNA provides virtual spatialization of gene expression, as validated by CD3- and CD20-staining on an independent dataset. The transcriptomic representation learned by HE2RNA can also be transferred on other datasets, even of small size, to increase prediction performance for specific molecular phenotypes. We illustrate the use of this approach in clinical diagnosis purposes such as the identification of tumors with microsatellite instability.

RNA-sequencing of tumour tissue can provide important diagnostic and prognostic information but this is costly and not routinely performed in all clinical settings. Here, the authors show that whole slide histology slides—part of routine care—can be used to predict RNA-sequencing data and thus reduce the need for additional analyses.

Comprehensive Molecular and Pathologic Evaluation of Transitional Mesothelioma Assisted by Deep Learning Approach: A Multi-Institutional Study of the International Mesothelioma Panel from the MESOPATH Reference Center

INTRODUCTION

Histologic subtypes of malignant pleural mesothelioma are a major prognostic indicator and decision denominator for all therapeutic strategies. In an ambiguous case, a rare transitional mesothelioma (TM) pattern may be diagnosed by pathologists either as epithelioid mesothelioma (EM), biphasic mesothelioma (BM), or sarcomatoid mesothelioma (SM). This study aimed to better characterize the TM subtype from a histological, immunohistochemical, and molecular standpoint. Deep learning of pathologic slides was applied to this cohort.

METHODS

A random selection of 49 representative digitalized sections from surgical biopsies of TM was reviewed by 16 panelists. We evaluated BAP1 expression and CDKN2A (p16) homozygous deletion. We conducted a comprehensive, integrated, transcriptomic analysis. An unsupervised deep learning algorithm was trained to classify tumors.

RESULTS

The 16 panelists recorded 784 diagnoses on the 49 cases. Even though a Kappa value of 0.42 is moderate, the presence of a TM component was diagnosed in 51%. In 49% of the histological evaluation, the reviewers classified the lesion as EM in 53%, SM in 33%, or BM in 14%. Median survival was 6.7 months. Loss of BAP1 observed in 44% was less frequent in TM than in EM and BM. p16 homozygous deletion was higher in TM (73%), followed by BM (63%) and SM (46%). RNA sequencing unsupervised clustering analysis revealed that TM grouped together and were closer to SM than to EM. Deep learning analysis achieved 94% accuracy for TM identification.

CONCLUSION

These results revealed that the TM pattern should be classified as non-EM or at minimum as a subgroup of the SM type.

Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data

Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural networks (NN). The main score used to compare the methods was the Area Under the ROC Curve (AUC) statistics. The impact of quality control (QC), imputing and coding methods on LR results showed that QC methods and imputation of missing genotypes may artificially increase the scores. At the opposite, neither the patient/control ratio nor marker preselection or coding strategies significantly affected the results. LR methods, including Lasso, Ridge and ElasticNet provided similar results with a maximum AUC of 0.80. GBT methods like XGBoost, LightGBM and CatBoost, together with dense NN with one or more hidden layers, provided similar AUC values, suggesting limited epistatic effects in the genetic architecture of the trait. ML methods detected near all the genetic variants previously identified by GWAS among the best predictors plus additional predictors with lower effects. The robustness and complementarity of the different methods are also studied. Compared to LR, non-linear models such as GBT or NN may provide robust complementary approaches to identify and classify genetic markers.

A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series

Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a sleep expert who assigns to each 30 s of the signal of a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEGs), electrooculograms (EOGs), electrocardiograms, and electromyograms (EMGs). We introduce here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data. For each modality, the first layer learns linear spatial filters that exploit the array of sensors to increase the signal-to-noise ratio, and the last layer feeds the learnt representation to a softmax classifier. Our model is compared to alternative automatic approaches based on convolutional networks or decisions trees. Results obtained on 61 publicly available PSG records with up to 20 EEG channels demonstrate that our network architecture yields the state-of-the-art performance. Our study reveals a number of insights on the spatiotemporal distribution of the signal of interest: a good tradeoff for optimal classification performance measured with balanced accuracy is to use 6 EEG with 2 EOG (left and right) and 3 EMG chin channels. Also exploiting 1 min of data before and after each data segment offers the strongest improvement when a limited number of channels are available. As sleep experts, our system exploits the multivariate and multimodal nature of PSG signals in order to deliver the state-of-the-art classification performance with a small computational cost.

Integrative Network-based Analysis of Colonic Detoxification Gene Expression in Ulcerative Colitis According to Smoking Status

BACKGROUNDS AND AIMS

The effect of cigarette smoking [CS] is ambivalent since smoking improves ulcerative colitis [UC] while it worsens Crohn's disease [CD]. Although this clinical relationship between inflammatory bowel disease [IBD] and tobacco is well established, only a few experimental works have investigated the effect of smoking on the colonic barrier homeostasis focusing on xenobiotic detoxification genes.

METHODS

A comprehensive and integrated comparative analysis of the global xenobiotic detoxification capacity of the normal colonic mucosa of healthy smokers [n = 8] and non-smokers [n = 9] versus the non-affected colonic mucosa of UC patients [n = 19] was performed by quantitative real-time polymerase chain reaction [qRT PCR]. The detoxification gene expression profile was analysed in CD patients [n = 18], in smoking UC patients [n = 5], and in biopsies from non-smoking UC patients cultured or not with cigarette smoke extract [n = 8].

RESULTS

Of the 244 detoxification genes investigated, 65 were dysregulated in UC patients in comparison with healthy controls or CD patients. The expression of ≥ 45/65 genes was inversed by CS in biopsies of smoking UC patients in remission and in colonic explants of UC patients exposed to cigarette smoke extract. We devised a network-based data analysis approach for differentially assessing changes in genetic interactions, allowing identification of unexpected regulatory detoxification genes that may play a major role in the beneficial effect of smoking on UC.

CONCLUSIONS

Non-inflamed colonic mucosa in UC is characterised by a specifically altered detoxification gene network, which is partially restored by tobacco. These mucosal signatures could be useful for developing new therapeutic strategies and biomarkers of drug response in UC.

Mathematical modeling of lymphocytes selection in the germinal center

Lymphocyte selection is a fundamental process of adaptive immunity. In order to produce B-lymphocytes with a target antigenic profile, mutation selection and division occur in the germinal center, a specific part of lymph nodes. We introduce in this article a simplified mathematical model of this phenomenon, taking into account the main mechanisms. This model is written as a non-linear, non-local, inhomogeneous second order partial differential equation, for which we develop a mathematical analysis. We assess, mathematically and numerically, in the case of piecewise-constant coefficients, the performance of the biological function by evaluating the duration of this production process as a function of several parameters such as the mutation rate or the selection profile, in various asymptotic regimes.

Fluid limit theorems for stochastic hybrid systems with application to neuron models

In this paper we establish limit theorems for a class of stochastic hybrid systems (continuous deterministic dynamics coupled with jump Markov processes) in the fluid limit (small jumps at high frequency), thus extending known results for jump Markov processes. We prove a functional law of large numbers with exponential convergence speed, derive a diffusion approximation, and establish a functional central limit theorem. We apply these results to neuron models with stochastic ion channels, as the number of channels goes to infinity, estimating the convergence to the deterministic model. In terms of neural coding, we apply our central limit theorems to numerically estimate the impact of channel noise both on frequency and spike timing coding.

Network Modeling of Crohn's Disease Incidence

Background

Numerous genetic and environmental risk factors play a role in human complex genetic disorders (CGD). However, their complex interplay remains to be modelled and explained in terms of disease mechanisms.

Methods and findings

Crohn's Disease (CD) was modeled as a modular network of patho-physiological functions, each summarizing multiple gene-gene and gene-environment interactions. The disease resulted from one or few specific combinations of module functional states. Network aging dynamics was able to reproduce age-specific CD incidence curves as well as their variations over the past century in Western countries. Within the model, we translated the odds ratios (OR) associated to at-risk alleles in terms of disease propensities of the functional modules. Finally, the model was successfully applied to other CGD including ulcerative colitis, ankylosing spondylitis, multiple sclerosis and schizophrenia.

Conclusion

Modeling disease incidence may help to understand disease causative chains, to delineate the potential of personalized medicine, and to monitor epidemiological changes in CGD.

Regular graphs maximize the variability of random neural networks

In this work we study the dynamics of systems composed of numerous interacting elements interconnected through a random weighted directed graph, such as models of random neural networks. We develop an original theoretical approach based on a combination of a classical mean-field theory originally developed in the context of dynamical spin-glass models, and the heterogeneous mean-field theory developed to study epidemic propagation on graphs. Our main result is that, surprisingly, increasing the variance of the in-degree distribution does not result in a more variable dynamical behavior, but on the contrary that the most variable behaviors are obtained in the regular graph setting. We further study how the dynamical complexity of the attractors is influenced by the statistical properties of the in-degree distribution.

Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes

A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate modeling approaches, Echo State Networks (ESN) and Linear Inverse Modeling (LIM), under the common principle of relative entropy minimization. The power of the new method is demonstrated on a stochastic approximation of the El Niño phenomenon studied in climate research.

Optimal system size for complex dynamics in random neural networks near criticality

In this article, we consider a model of dynamical agents coupled through a random connectivity matrix, as introduced by Sompolinsky et al. [Phys. Rev. Lett. 61(3), 259-262 (1988)] in the context of random neural networks. When system size is infinite, it is known that increasing the disorder parameter induces a phase transition leading to chaotic dynamics. We observe and investigate here a novel phenomenon in the sub-critical regime for finite size systems: the probability of observing complex dynamics is maximal for an intermediate system size when the disorder is close enough to criticality. We give a more general explanation of this type of system size resonance in the framework of extreme values theory for eigenvalues of random matrices.

Synchronization in random balanced networks

Characterizing the influence of network properties on the global emerging behavior of interacting elements constitutes a central question in many areas, from physical to social sciences. In this article we study a primary model of disordered neuronal networks with excitatory-inhibitory structure and balance constraints. We show how the interplay between structure and disorder in the connectivity leads to a universal transition from trivial to synchronized stationary or periodic states. This transition cannot be explained only through the analysis of the spectral density of the connectivity matrix. We provide a low-dimensional approximation that shows the role of both the structure and disorder in the dynamics.

A biological gradient descent for prediction through a combination of STDP and homeostatic plasticity

Identifying, formalizing, and combining biological mechanisms that implement known brain functions, such as prediction, is a main aspect of research in theoretical neuroscience. In this letter, the mechanisms of spike-timing-dependent plasticity and homeostatic plasticity, combined in an original mathematical formalism, are shown to shape recurrent neural networks into predictors. Following a rigorous mathematical treatment, we prove that they implement the online gradient descent of a distance between the network activity and its stimuli. The convergence to an equilibrium, where the network can spontaneously reproduce or predict its stimuli, does not suffer from bifurcation issues usually encountered in learning in recurrent neural networks.

Topological and dynamical complexity of random neural networks

Random neural networks are dynamical descriptions of randomly interconnected neural units. These show a phase transition to chaos as a disorder parameter is increased. The microscopic mechanisms underlying this phase transition are unknown and, similar to spin glasses, shall be fundamentally related to the behavior of the system. In this Letter, we investigate the explosion of complexity arising near that phase transition. We show that the mean number of equilibria undergoes a sharp transition from one equilibrium to a very large number scaling exponentially with the dimension on the system. Near criticality, we compute the exponential rate of divergence, called topological complexity. Strikingly, we show that it behaves exactly as the maximal Lyapunov exponent, a classical measure of dynamical complexity. This relationship unravels a microscopic mechanism leading to chaos which we further demonstrate on a simpler disordered system, suggesting a deep and underexplored link between topological and dynamical complexity.

Multiscale analysis of slow-fast neuronal learning models with noise

This paper deals with the application of temporal averaging methods to recurrent networks of noisy neurons undergoing a slow and unsupervised modification of their connectivity matrix called learning. Three time-scales arise for these models: (i) the fast neuronal dynamics, (ii) the intermediate external input to the system, and (iii) the slow learning mechanisms. Based on this time-scale separation, we apply an extension of the mathematical theory of stochastic averaging with periodic forcing in order to derive a reduced deterministic model for the connectivity dynamics. We focus on a class of models where the activity is linear to understand the specificity of several learning rules (Hebbian, trace or anti-symmetric learning). In a weakly connected regime, we study the equilibrium connectivity which gathers the entire 'knowledge' of the network about the inputs. We develop an asymptotic method to approximate this equilibrium. We show that the symmetric part of the connectivity post-learning encodes the correlation structure of the inputs, whereas the anti-symmetric part corresponds to the cross correlation between the inputs and their time derivative. Moreover, the time-scales ratio appears as an important parameter revealing temporal correlations.

Noise-controlled dynamics through the averaging principle for stochastic slow-fast systems

The effect of noise on nonlinear systems is analyzed, considering the case of slow-fast systems. It is known that small noise perturbations can induce a deterministic limit cycle in excitable systems when a specific scaling between the noise strength and the time-scale separation is achieved, a mechanism called self-induced stochastic resonance (SISR). The present study is focused on the impact of order 1 noise using the stochastic averaging principle. We introduce an elementary system of two coupled FitzHugh-Nagumo equations, which display the following nontrivial noise-induced behavior: (i) in the noise-free case, or for very small noise, the system fluctuates around its resting state; (ii) for small noise, oscillations appear due to SISR; (iii) for intermediate noise, the system fluctuates again around its resting state; (iv) for larger noise, new oscillations are observed and their explanation requires the application of the stochastic averaging principle. It is suggested that in the perspective of biological systems, time-scale separation may act as a "noise averager," enabling a noise-controlled dynamical behavior through the averaging principle.

Intrinsic variability of latency to first-spike

The assessment of the variability of neuronal spike timing is fundamental to gain understanding of latency coding. Based on recent mathematical results, we investigate theoretically the impact of channel noise on latency variability. For large numbers of ion channels, we derive the asymptotic distribution of latency, together with an explicit expression for its variance. Consequences in terms of information processing are studied with Fisher information in the Morris-Lecar model. A competition between sensitivity to input and precision is responsible for favoring two distinct regimes of latencies.