Skip to main content

Mimic

PyPI version Python versions License bioRxiv preprint

Mimic is a configurable neural-network architecture for genomic sequence modeling. It separates a model into k-mer embedding, sequence embedding, and output mapping, making it possible to compare sequence-embedding strategies within a shared architecture.

Part of the Poseigen ecosystem.

See the Mimic preprint. The study evaluates recurrent and convolutional sequence-embedding strategies on protein-DNA interaction and enhancer-activity datasets. It reports that Mimic significantly outperformed BiChrom on protein-DNA interactions and DeepSTARR on enhancer activity in the evaluated datasets.

Installation

Requires Python 3.12 or newer. Install from PyPI:

python -m pip install poseigen_mimic

Package

  • Mimic is a single-input architecture with three configurable stages: a convolutional k-mer embedding, a sequence-embedding component, and an output mapping. The sequence-embedding component uses Trident's Prong_W by default and can also use recurrent layers such as GRU or LSTM, convolutional layers, or compatible custom pooling modules.
  • Dual_Mimic applies separate Mimic branches to two inputs. The branches can have different input dimensions and k-mer settings. With late_comb=True, their outputs are summed; with late_comb=False, their sequence representations are concatenated before a shared output mapping.

Mimic's neural-network components are built with poseigen_trident.

Case studies

Usage

For the default input dimensions, Mimic expects a batch shaped (batch, 1, sequence_length, 4). This example uses a GRU for sequence embedding:

import torch
import torch.nn as nn
from poseigen_mimic import Mimic

model = Mimic(dim_i=(1, 249, 4), PR_layer=nn.GRU)
sequence_batch = torch.randn(8, 1, 249, 4)
predictions = model(sequence_batch)

Metadata

Release files for poseigen-mimic 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for poseigen-mimic 0.1.1
File Size Uploaded Provenance Actions
poseigen_mimic-0.1.1.tar.gz 5.7 kB With provenance Details for poseigen_mimic-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for poseigen-mimic 0.1.1
File Interpreter ABI Platform Actions
poseigen_mimic-0.1.1-py3-none-any.whl Python 3 none any Details for poseigen_mimic-0.1.1-py3-none-any.whl

Total release size: 11.6 kB

Release files / poseigen_mimic-0.1.1.tar.gz

Download URL poseigen_mimic-0.1.1.tar.gz
Size 5.7 kB
Tags Source
SHA-256 checksum
How to use checksums
553c70a41c5faf1e9e7cceef8c87d4fb9b43b9c77cace30e306abf6b87184d13
BLAKE2b-256 checksum
How to use checksums
138a94727cc7406533303fdc7836c0c062fd9ad1e0a4acbb70d0364f2f39e69f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

Release files / poseigen_mimic-0.1.1-py3-none-any.whl

Download URL poseigen_mimic-0.1.1-py3-none-any.whl
Size 5.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3923d047bfe8cbeed5e35b29aa795487c41b7f0b56aee4cdf22ae0f3b43a00f1
BLAKE2b-256 checksum
How to use checksums
9294d07f1e5a36bc846f03135c8b01a425badbdb846a3182bbaa2cee53589a0c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

Security for poseigen-mimic 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for poseigen_mimic-0.1.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 1, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page