X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design
- URL: http://arxiv.org/abs/2402.07148v2
- Date: Sat, 30 Mar 2024 20:18:54 GMT
- Title: X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design
- Authors: Eric L. Buehler, Markus J. Buehler,
- Abstract summary: We report a mixture of expert strategy to create fine-tuned large language models using a deep layer-wise token-level approach based on low-rank adaptation (LoRA)
The design is inspired by the biological principles of universality and diversity, where neural network building blocks are reused in different hierarchical manifestations.
We develop a tailored X-LoRA model that offers scientific capabilities including forward/inverse analysis tasks and enhanced reasoning capability, focused on biomaterial analysis, protein mechanics and design.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: We report a mixture of expert strategy to create fine-tuned large language models using a deep layer-wise token-level approach based on low-rank adaptation (LoRA). Starting with a set of pre-trained LoRA adapters, our gating strategy uses the hidden states to dynamically mix adapted layers, allowing the resulting X-LoRA model to draw upon different capabilities and create never-before-used deep layer-wise combinations to solve tasks. The design is inspired by the biological principles of universality and diversity, where neural network building blocks are reused in different hierarchical manifestations. Hence, the X-LoRA model can be easily implemented for any existing large language model (LLM) without a need for modifications of the underlying structure. We develop a tailored X-LoRA model that offers scientific capabilities including forward/inverse analysis tasks and enhanced reasoning capability, focused on biomaterial analysis, protein mechanics and design. The impact of this work include access to readily expandable and adaptable models with strong domain knowledge and the capability to integrate across areas of knowledge. Featuring experts in biology, mathematics, reasoning, bio-inspired materials, mechanics and materials, chemistry, protein biophysics, mechanics and quantum-mechanics based molecular properties, we conduct a series of physics-focused case studies. We examine knowledge recall, protein mechanics forward/inverse tasks, protein design, adversarial agentic modeling including ontological knowledge graph construction, as well as molecular design. The model is capable not only of making quantitative predictions of nanomechanical properties of proteins or quantum mechanical molecular properties, but also reasons over the results and correctly predicts likely mechanisms that explain distinct molecular behaviors.
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) - Computational Protein Science in the Era of Large Language Models (LLMs) [54.35488233989787]
Computational protein science is dedicated to revealing knowledge and developing applications within the protein sequence-structure-function paradigm.
Recently, Language Models (pLMs) have emerged as a milestone in AI due to their unprecedented language processing & generalization capability.
arXiv Detail & Related papers (2025-01-17T16:21:18Z) - Biology Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models [51.316001071698224]
We introduce Biology-Instructions, the first large-scale multi-omics biological sequences-related instruction-tuning dataset.
This dataset can bridge the gap between large language models (LLMs) and complex biological sequences-related tasks.
We also develop a strong baseline called ChatMultiOmics with a novel three-stage training pipeline.
arXiv Detail & Related papers (2024-12-26T12:12:23Z) - Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model [49.64512917330373]
We introduce a multi-constraint molecular generation large language model, TSMMG, akin to a student.
To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers'
We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements.
arXiv Detail & Related papers (2024-03-20T02:15:55Z) - ProtAgents: Protein discovery via large language model multi-agent
collaborations combining physics and machine learning [0.0]
ProtAgents is a platform for de novo protein design based on Large Language Models (LLMs)
Multiple AI agents with distinct capabilities collaboratively address complex tasks within a dynamic environment.
The flexibility in designing the agents, on one hand, and their capacity in autonomous collaboration through the dynamic LLM-based multi-agent environment unleashes great potentials.
arXiv Detail & Related papers (2024-01-27T20:19:49Z) - MeLM, a generative pretrained language modeling framework that solves
forward and inverse mechanics problems [0.0]
We report a flexible multi-modal mechanics language model, MeLM, applied to solve various nonlinear forward and inverse problems.
The framework is applied to various examples including bio-inspired hierarchical honeycomb design and carbon nanotube mechanics.
arXiv Detail & Related papers (2023-06-30T10:28:20Z) - Generative Pretrained Autoregressive Transformer Graph Neural Network
applied to the Analysis and Discovery of Novel Proteins [0.0]
We report a flexible language-model based deep learning strategy, applied here to solve complex forward and inverse problems in protein modeling.
The model is applied to predict secondary structure content (per-residue level and overall content), protein solubility, and sequencing tasks.
We find that adding additional tasks yields emergent synergies that the model exploits in improving overall performance.
arXiv Detail & Related papers (2023-05-07T12:30:24Z) - Learning Geometrically Disentangled Representations of Protein Folding
Simulations [72.03095377508856]
This work focuses on learning a generative neural network on a structural ensemble of a drug-target protein.
Model tasks involve characterizing the distinct structural fluctuations of the protein bound to various drug molecules.
Results show that our geometric learning-based method enjoys both accuracy and efficiency for generating complex structural variations.
arXiv Detail & Related papers (2022-05-20T19:38:00Z) - Accurate Machine Learned Quantum-Mechanical Force Fields for
Biomolecular Simulations [51.68332623405432]
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes.
Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations.
This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
arXiv Detail & Related papers (2022-05-17T13:08:28Z) - Flexible dual-branched message passing neural network for quantum
mechanical property prediction with molecular conformation [16.08677447593939]
We propose a dual-branched neural network for molecular property prediction based on message-passing framework.
Our model learns heterogeneous molecular features with different scales, which are trained flexibly according to each prediction target.
arXiv Detail & Related papers (2021-06-14T10:00:39Z) - Hierarchical, rotation-equivariant neural networks to select structural
models of protein complexes [6.092214762701847]
We introduce a machine learning method that learns directly from the 3D positions of all atoms to identify accurate models of protein complexes.
Our network substantially improves the identification of accurate structural models among a large set of possible models.
arXiv Detail & Related papers (2020-06-05T20:17:12Z)
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.