OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Deepconsensus

DeepConsensus is a Python research tool that uses gap-aware sequence transformers to correct errors in PacBio Circular Consensus Sequencing subreads and generate corrected FASTQ reads for downstream genomic analysis.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Deepconsensus — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it after a PacBio sequencing run when you want to correct subreads before downstream analysis. Follow the project’s `ccs` parameter guidance so that low-predicted-quality reads are not filtered before DeepConsensus can process them.

Who it is for

  • Bioinformatics teams processing PacBio CCS sequencing data.
  • Researchers preparing corrected reads for downstream assembly or variant-calling workflows.

Documented uses

  • Correct errors in PacBio CCS subreads.
  • Produce FASTQ reads for downstream genomic analysis.
  • Shard SMRT Cell data for parallel processing across compute workers.
Before you choose

Requirements & limits

The repository is public source code under the BSD-3-Clause license. The project documents pip, Docker, and source installation paths, with CPU and GPU options.

  • The input workflow is specific to PacBio CCS data.
  • The project recommends at least 500 shards per SMRT Cell and up to 16 CPUs per shard as a compute-planning guide.
  • Installation options include CPU and GPU packages or Docker images, alongside source setup.
  • The repository identifies the software as research code and excludes clinical use and medical-device use.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install DeepConsensus from pip

Install the documented CPU or GPU package and make its command-line tool available on PATH.

Before you start

  • A CPU or GPU machine.
  • Python package installation with pip.

Steps

  1. For a GPU machine, install deepconsensus[gpu]==1.2.0; for a CPU machine, install deepconsensus[cpu]==1.2.0.

  2. Add /home/${USER}/.local/bin to PATH so the deepconsensus CLI can be found.

Expected outcome

The version 1.2.0 package is installed for the selected compute type, with the documented CLI path configured.

Guide limitations

  • The installation instructions do not by themselves describe a complete run; consult the project quick start for execution and input preparation.
  • The project states that the research code is not intended for clinical use or as a medical device.
Documentation 1 ↗
Source-based practical guide

Install DeepConsensus from source

Set up the repository using its documented CPU or GPU installation script.

Before you start

  • Git and a Linux environment.
  • A CPU or GPU machine.

Steps

  1. Clone https://github.com/google/deepconsensus.git and change into the repository directory.

  2. For CPU installation, run source install.sh; for GPU installation, run source install-gpu.sh.

Expected outcome

The repository's documented installation script is run for the selected compute type.

Guide limitations

  • The repository instructions describe installation, not a complete data-processing run.
  • The project states that the research code is not intended for clinical use or as a medical device.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
google/deepconsensus · Official homepage title · retained in its source language
How we review sourcesSuggest a correction