Scholarlink

<p>Generative modeling of genomic sequences presents a stringent test for deep learning, requiring the capture of long-range dependencies and functional constraints beyond local nucleotide statistics. Existing architectures frequently collapse to limited modes or reproduce shallow nucleotide distributions without encoding functional semantics. We introduce the Multi-Task Adversarial Autoencoder (MT-AAE), a hybrid generative framework that integrates adversarial regularization with auxiliary functional and biophysical objectives to enforce structured latent representations. Evaluated on an empirical human gene corpus, MT-AAE achieved a Train-on-Synthetic-Test-on-Real (TRTS) accuracy of 74.7%, compared with 41.0% for a standard GAN baseline. Stratified analysis further showed that functional discriminability increased to 89.3% when sequence lengths aligned with the model’s architectural window. Importantly, the learned representations exhibited emergent biological structure: synthetic sequences spontaneously preserved <i>cis</i>-regulatory syntax, including canonical TATA-box motifs recovered across 100% of generated promoter sequences without explicit rule encoding, though positional placement relative to the TSS was not statistically significant (KS <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(p=0.90\)</EquationSource></InlineEquation>), and the high occurrence rate is partly attributable to the AT-rich composition of the generated sequences. Representation-level validation using frozen DNABERT-2 and DNABERT-S embeddings confirmed that the generated sequences retained functional information beyond shallow k-mer statistics. Cross-species evaluation on <i>Mus musculus</i> sequences further demonstrated species-specific learning consistent with known human–mouse regulatory divergence. The framework also mitigated mode collapse, maintaining near-uniform generation across functional classes (<InlineEquation ID="IEq2"><EquationSource Format="TEX">\(R_g \approx 1.0\)</EquationSource></InlineEquation>), including rare categories such as tRNAs (<InlineEquation ID="IEq3"><EquationSource Format="TEX">\( &lt; 2\%\)</EquationSource></InlineEquation> of the dataset). These findings position MT-AAE as an effective framework for biologically constrained genomic sequence generation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-task adversarial autoencoder for functional genomic element generation with preserved biophysical properties

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月3日

查看全文
  • Shamsuddeen Adamu,
  • Hitham Alhussian,
  • Said Jadid Abdulkadir,
  • Majdy Mohamed Eltayeb Eltahir,
  • Sallam O. F. Khairy,
  • Ibrahim Hayatu Hassan,
  • Ibrahim Muhammad Kurah,
  • Abubakar Mukhtar,
  • Vijayakanthan Ganesalingam,
  • Vaishali Ravi,
  • Yahaya Saidu

摘要

Generative modeling of genomic sequences presents a stringent test for deep learning, requiring the capture of long-range dependencies and functional constraints beyond local nucleotide statistics. Existing architectures frequently collapse to limited modes or reproduce shallow nucleotide distributions without encoding functional semantics. We introduce the Multi-Task Adversarial Autoencoder (MT-AAE), a hybrid generative framework that integrates adversarial regularization with auxiliary functional and biophysical objectives to enforce structured latent representations. Evaluated on an empirical human gene corpus, MT-AAE achieved a Train-on-Synthetic-Test-on-Real (TRTS) accuracy of 74.7%, compared with 41.0% for a standard GAN baseline. Stratified analysis further showed that functional discriminability increased to 89.3% when sequence lengths aligned with the model’s architectural window. Importantly, the learned representations exhibited emergent biological structure: synthetic sequences spontaneously preserved cis-regulatory syntax, including canonical TATA-box motifs recovered across 100% of generated promoter sequences without explicit rule encoding, though positional placement relative to the TSS was not statistically significant (KS \(p=0.90\)), and the high occurrence rate is partly attributable to the AT-rich composition of the generated sequences. Representation-level validation using frozen DNABERT-2 and DNABERT-S embeddings confirmed that the generated sequences retained functional information beyond shallow k-mer statistics. Cross-species evaluation on Mus musculus sequences further demonstrated species-specific learning consistent with known human–mouse regulatory divergence. The framework also mitigated mode collapse, maintaining near-uniform generation across functional classes (\(R_g \approx 1.0\)), including rare categories such as tRNAs (\( < 2\%\) of the dataset). These findings position MT-AAE as an effective framework for biologically constrained genomic sequence generation.