Language Model Powered Digital Biology

• URL: http://arxiv.org/abs/2409.02864v2
• Date: Mon, 14 Oct 2024 01:07:54 GMT
• Title: Language Model Powered Digital Biology
• Authors: Joshua Pickard, Marc Andrew Choi, Natalie Oliven, Cooper Stansbury, Jillian Cwycyshyn, Nicholas Galioto, Alex Gorodetsky, Alvaro Velasquez, Indika Rajapakse,
• Abstract summary: We present a prototype Bioinformatics Retrieval Augmented Data (BRAD) digital assistant. BRAD is a robot and agentic system that integrates a suite of tools to handle bioinformatics tasks, from code execution to online search. We demonstrate its capabilities through (1) improved question-and-answering with retrieval augmented generation (RAG), (2) the ability to run complex software pipelines, and (3) the ability to organize and distribute tasks in agentic pipelines.
• Score: 5.309032614374711
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in Large Language Models (LLMs) are transforming biology, computer science, and many other research fields, as well as impacting everyday life. While transformer-based technologies are currently being deployed in biology, no available agentic system has been developed to tackle bioinformatics workflows. We present a prototype Bioinformatics Retrieval Augmented Data (BRAD) digital assistant. BRAD is a chatbot and agentic system that integrates a suite of tools to handle bioinformatics tasks, from code execution to online search. We demonstrate its capabilities through (1) improved question-and-answering with retrieval augmented generation (RAG), (2) the ability to run complex software pipelines, and (3) the ability to organize and distribute tasks in agentic workflows. We use BRAD for automation, performing tasks ranging from gene enrichment and searching the archive to automatic code generation for running biomarker identification pipelines. BRAD is a step toward autonomous, self-driving labs for digital biology.

Related papers

• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? [73.81908518992161]
  We introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering. Spider2-V features real-world tasks in authentic computer environments and incorporating 20 enterprise-level professional applications. These tasks evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems.
  arXiv  Detail & Related papers  (2024-07-15T17:54:37Z)
• BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments [112.25067497985447]
  We introduce BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions. BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model. It achieves an average of 21% improvement in predicting relevant genetic perturbations across six datasets.
  arXiv  Detail & Related papers  (2024-05-27T19:57:17Z)
• Empowering Biomedical Discovery with AI Agents [15.125735219811268]
  We envision "AI scientists" as systems capable of skeptical learning and reasoning. Biomedical AI agents combine human creativity and expertise with AI's ability to analyze large datasets. AI agents can impact areas ranging from virtual cell simulation, programmable control of phenotypes, and the design of cellular circuits to developing new therapies.
  arXiv  Detail & Related papers  (2024-04-03T16:08:01Z)
• An Evaluation of Large Language Models in Bioinformatics Research [52.100233156012756]
  We study the performance of large language models (LLMs) on a wide spectrum of crucial bioinformatics tasks. These tasks include the identification of potential coding regions, extraction of named entities for genes and proteins, detection of antimicrobial and anti-cancer peptides, molecular optimization, and resolution of educational bioinformatics problems. Our findings indicate that, given appropriate prompts, LLMs like GPT variants can successfully handle most of these tasks.
  arXiv  Detail & Related papers  (2024-02-21T11:27:31Z)
• LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day [85.19963303642427]
  We propose a cost-efficient approach for training a vision-language conversational assistant that can answer open-ended research questions of biomedical images. The model first learns to align biomedical vocabulary using the figure-caption pairs as is, then learns to master open-ended conversational semantics. This enables us to train a Large Language and Vision Assistant for BioMedicine in less than 15 hours (with eight A100s)
  arXiv  Detail & Related papers  (2023-06-01T16:50:07Z)
• BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining [140.61707108174247]
  We propose BioGPT, a domain-specific generative Transformer language model pre-trained on large scale biomedical literature. We get 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks respectively, and 78.2% accuracy on PubMedQA.
  arXiv  Detail & Related papers  (2022-10-19T07:17:39Z)
• When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Development [3.687740185234604]
  Machine learning (ML) has significantly contributed to the development of bioprocess engineering, but its application is still limited. This review provides a comprehensive overview of ML-based automation in bioprocess development.
  arXiv  Detail & Related papers  (2022-09-02T14:30:49Z)
• BIOS: An Algorithmically Generated Biomedical Knowledge Graph [4.030892610300306]
  We introduce the Biomedical Informatics Ontology System (BIOS), the first large scale publicly available BioMedKG that is fully generated by machine learning algorithms. BIOS contains 4.1 million concepts, 7.4 million terms in two languages, and 7.3 million relation triplets. Results suggest that machine learning-based BioMedKG development is a totally viable solution for replacing traditional expert curation.
  arXiv  Detail & Related papers  (2022-03-18T14:09:22Z)
• Deep metric learning improves lab of origin prediction of genetically engineered plasmids [63.05016513788047]
  Genetic engineering attribution (GEA) is the ability to make sequence-lab associations. We propose a method, based on metric learning, that ranks the most likely labs-of-origin. We are able to extract key signatures in plasmid sequences for particular labs, allowing for an interpretable examination of the model's outputs.
  arXiv  Detail & Related papers  (2021-11-24T16:29:03Z)
• Pre-trained Language Models in Biomedical Domain: A Systematic Survey [33.572502204216256]
  Pre-trained language models (PLMs) have been the de facto paradigm for most natural language processing (NLP) tasks. This paper summarizes the recent progress of pre-trained language models in the biomedical domain and their applications in biomedical downstream tasks.
  arXiv  Detail & Related papers  (2021-10-11T05:30:30Z)
• GenoML: Automated Machine Learning for Genomics [3.2739205123864945]
  GenoML is a Python package automating machine learning for genomics (genetics and multi-omics) GenoML's mission is to bring machine learning for genomics and clinical data to non-experts.
  arXiv  Detail & Related papers  (2021-03-04T18:48:40Z)

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.