iiinova — where your digital self keeps evolving

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Finally, thanks to the team! A huge shoutout to my friend and mentee @krithik-bs.bsky.social. Also infinitely grateful for #AlbertGu for his advice, and #MichaelMitzenmacher @pardissabeti.bsky.social for their mentorship and leadership. So much laughter while making this paper, can't wait for more.

010

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

This work shows that principled mathematical insights, like approximation of epistatic interactions, can provide an accessible and performant alternative to large foundation models—suggesting broader applicability beyond biological sequences.

120

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

We are excited about Lyra's potential to accelerate discoveries in molecular biology, therapeutic development, and protein engineering.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Lyra makes cutting-edge biological modeling accessible to labs without extensive compute resources. Instead of relying on massive GPU clusters, Lyra empowers researchers to train state-of-the-art models directly on their own laptops.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Lyra’s subquadratic O(N log N) complexity dramatically reduces memory (125x–2600x less than Evo and ESM-1b) and accelerates inference—up to 239x faster than ESM-1b, processing sequences up to 1M length.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

RNA-dependent RNA polymerases (RDRPs) are essential markers for RNA virus detection. Lyra achieves a near-perfect 0.998 true positive rate, matching LucaProt-ESM with over 60,000x fewer parameters, accelerating pathogen discovery without needing large-scale GPU infrastructure.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Lyra achieves SOTA results in 6 out of 7 intrinsically disordered protein region tasks, with an average AUC of 0.89, outperforming a ProtT5-based model (avg AUC 0.86). Lyra accomplishes this using only 55K parameters, compared to ProtT5’s 3 billion parameters—a >50,000-fold reduction in model size.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Lyra’s consistently strong performance across different tasks using orders of magnitude fewer parameters allows researchers to spend less time optimizing models and more time generating biological insights.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Lyra sets records in 5/9 RNA BEACON benchmarking tasks tested, including nearly solving the splice-site prediction dataset (98.89% accuracy vs previous best 50.55%) and almost doubling performance on structural score imputation (0.73 vs 0.42).

120

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

We tested Lyra on 101 diverse biological tasks spanning: 1. Proteomics 2. Genomics 3. CRISPR guide efficacy Lyra set new performance records in 79 out of 101 tasks, w/ substantially smaller models than competing architectures.

120

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

We designed Lyra with two simple components: Projected Gated Convolutions (PGC), which enhance local feature extraction, and diagonalized State Space Models (S4D), which capture global epistatic interactions. In doing so, Lyra efficiently captures both global and local epistatic relationships.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

We drew a mathematical connection between State Space Models (SSMs) and polynomial approximation, showing how their hidden states can naturally approximate the polynomial terms that govern epistatic relationships. This makes SSMs ideal for modeling biological functions as multilinear polynomials.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

This perspective provides a principled mathematical framework for modeling sequence-function relationships.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

To unify biological sequence modeling across DNA, RNA, and proteins into a single computational framework, we revisited epistasis—the phenomenon where mutations influence each other—which can be characterized by multilinear polynomials.

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

Breaking down how biological sequences encode molecular functions remains a central challenge in computational biology. For example, given a GFP sequence, can we predict its fluorescence brightness?

110

Sameed Siddiqui @sameedms.bsky.social · 21/03/2025

🧬 Meet Lyra, a new paradigm for accessible, powerful modeling of biological sequences. Lyra is a lightweight SSM achieving SOTA performance across DNA, RNA, and protein tasks—yet up to 120,000x smaller than foundation models (ESM, Evo). Bonus: you can train it on your Mac. arxiv.org/abs/2503.16351

12012