A Differentiable Model for Optimizing the Genetic Drivers of Synaptogenesis

• URL: http://arxiv.org/abs/2402.07242v2
• Date: Fri, 20 Dec 2024 12:49:57 GMT
• Title: A Differentiable Model for Optimizing the Genetic Drivers of Synaptogenesis
• Authors: Tommaso Boccato, Matteo Ferrante, Nicola Toschi,
• Abstract summary: We introduce SynaptoGen, a novel computational framework designed to bring the advent of synthetic biological intelligence closer. SynaptoGen is the first model in the family of Connectome Models (CMs) to offer a possible mechanistic explanation of synaptic multiplicity. Differentiability is a critical feature of the framework, enabling its integration with gradient-based optimization techniques.
• Score: 0.12289361708127873
• License:
• Abstract: There is a growing consensus among neuroscientists that many neural circuits critical for survival result from a process of genomic decompression, hence are constructed based on the information contained within the genome. Aligning with this perspective, we introduce SynaptoGen, a novel computational framework designed to bring the advent of synthetic biological intelligence closer, facilitating the development of neural biological agents through the precise control of genetic factors governing synaptogenesis. SynaptoGen represents the first model in the well-established family of Connectome Models (CMs) to offer a possible mechanistic explanation of synaptic multiplicity based on genetic expression and protein interaction probabilities, modeling connectivity with unprecedented granularity. Furthermore, SynaptoGen connects these genetic factors through a differentiable function, effectively working as a neural network in which each synaptic weight is computed as the average number of synapses between neurons, multiplied by its corresponding conductance, and derived from a specific genetic profile. Differentiability is a critical feature of the framework, enabling its integration with gradient-based optimization techniques. This allows SynaptoGen to generate patterns of genetic expression and/or genetic rules capable of producing pre-wired biological agents tailored to specific tasks. The framework is validated in simulated synaptogenesis scenarios with varying degrees of biological plausibility. It successfully produces biological agents capable of solving tasks in four different reinforcement learning benchmarks, consistently outperforming the state-of-the-art and a control baseline designed to represent populations of neurons where synapses form freely, i.e., without guided manipulations.

Related papers

• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters. The model adheres to the central dogma of molecular biology, accurately generating protein-coding sequences. It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of promoter sequences.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• Interpreting artificial neural networks to detect genome-wide association signals for complex traits [0.0]
  We trained artificial neural networks to predict complex traits using both simulated and real genotype-phenotype datasets. We detected multiple loci associated with schizophrenia.
  arXiv  Detail & Related papers  (2024-07-26T15:20:42Z)
• Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification [119.13058298388101]
  We develop a Biological-knowledge enhanced PathGenomic multi-label Transformer to improve genetic mutation prediction performances. BPGT first establishes a novel gene encoder that constructs gene priors by two carefully designed modules. BPGT then designs a label decoder that finally performs genetic mutation prediction by two tailored modules.
  arXiv  Detail & Related papers  (2024-06-05T06:42:27Z)
• Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity [7.479827648985631]
  In biological evolution complex neural structures grow from a handful of cellular ingredients. This self-organisation is hypothesized to play an important part in the generalisation, and robustness of biological neural networks. We present an algorithm for growing artificial neural networks that solve reinforcement learning tasks.
  arXiv  Detail & Related papers  (2024-05-14T11:21:52Z)
• Causal machine learning for single-cell genomics [94.28105176231739]
  We discuss the application of machine learning techniques to single-cell genomics and their challenges. We first present the model that underlies most of current causal approaches to single-cell biology. We then identify open problems in the application of causal approaches to single-cell data.
  arXiv  Detail & Related papers  (2023-10-23T13:35:24Z)
• MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data [22.938437500266847]
  We introduce a novel model called Multimodal Similarity Learning Graph Neural Network. It combines Multimodal Machine Learning and Deep Graph Neural Networks to learn gene representations from single-cell sequencing and spatial transcriptomic data. Our model efficiently produces unified gene representations for the analysis of gene functions, tissue functions, diseases, and species evolution.
  arXiv  Detail & Related papers  (2023-09-29T13:33:53Z)
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks [64.08042492426992]
  We introduce the Expressive Memory (ELM) neuron model, a biologically inspired model of a cortical neuron. Our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. We evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets.
  arXiv  Detail & Related papers  (2023-06-14T13:34:13Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Evolving spiking neuron cellular automata and networks to emulate in vitro neuronal activity [0.0]
  We produce spiking neural systems that emulate the patterns of behavior of biological neurons in vitro. Our models were able to produce a level of network-wide synchrony. The genomes of the top-performing models indicate the excitability and density of connections in the model play an important role in determining the complexity of the produced activity.
  arXiv  Detail & Related papers  (2021-10-15T17:55:04Z)
• Complexity-based speciation and genotype representation for neuroevolution [81.21462458089142]
  This paper introduces a speciation principle for neuroevolution where evolving networks are grouped into species based on the number of hidden neurons. The proposed speciation principle is employed in several techniques designed to promote and preserve diversity within species and in the ecosystem as a whole.
  arXiv  Detail & Related papers  (2020-10-11T06:26:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.