Biology subjects

Praljak, N.

Publications and source records attributed to Praljak, N..

4 recordsLinked to original sources

bioRxiv2024

Natural Language Prompts Guide the Design of Novel Functional Protein Sequences

The advent of natural language interaction with machines has ushered in new innovations in text-guided generation of images, audio, video, and more. In this arena, we introduce Biological Multi-Modal Model (BioM3), as a novel framework for designing functional proteins via natural language prompts. This framework integrates natural language with protein design through a three-stage process: aligning protein and text representations in a joint embedding space learned using contrastive learning, refinement of the text embeddings, and conditional generation of protein sequences via a discrete autoregressive diffusion model. BioM3 synthe-sizes protein sequences with detailed descriptions of the protein structure, lineage, and function from text annotations to enable the conditional generation of novel sequences with desired attributes through natural language prompts. We present in silico validation of the model predictions for subcellular localization prediction, reaction classification, remote homology detection, scaffold in-painting, and structural plausibility, and in vivo and in vitro experimental tests of natural language prompt-designed synthetic analogs of Src-homology 3 (SH3) domain proteins that mediate signaling in the Sho1 osmotic stress response pathway in bakers yeast. BioM3 possesses state-of-the-art performance in zero-shot prediction and homology detection tasks, and generates proteins with native-like tertiary folds and wild-type levels of experimentally assayed function.

synthetic biology↗

bioRxiv2023

ProtWave-VAE: Integrating autoregressive sampling with latent-based inference for data-driven protein design

Deep generative models (DGMs) have shown great success in the understanding of data-driven design of proteins. Variational autoencoders (VAEs) are a popular DGM approach that can learn the correlated patterns of amino acid mutations within a multiple sequence alignment (MSA) of protein sequences and distill this information into a low-dimensional latent space to expose phylogenetic and functional relationships and guide generative protein design. Autoregressive (AR) models are another popular DGM approach that typically lack a low-dimensional latent embedding but do not require training sequences to be aligned into an MSA and enable the design of variable length proteins. In this work, we propose ProtWave-VAE as a novel and lightweight DGM employing an information maximizing VAE with a dilated convolution encoder and autoregressive WaveNet decoder. This architecture blends the strengths of the VAE and AR paradigms in enabling training over unaligned sequence data and the conditional generative design of variable length sequences from an interpretable low-dimensional learned latent space. We evaluate the models ability to infer patterns and design rules within alignment-free homologous protein family sequences and to design novel synthetic proteins in four diverse protein families. We show that our model can infer meaningful functional and phylogenetic embeddings within latent spaces and make highly accurate predictions within semi-supervised downstream fitness prediction tasks. In an application to the C-terminal SH3 domain in the Sho1 transmembrane osmosensing receptor in bakers yeast, we subject ProtWave-VAE designed sequences to experimental gene synthesis and select-seq assays for osmosensing function to show that the model enables de novo generative design, conditional C-terminus diversification, and engineering of osmosensing function into SH3 paralogs.

synthetic biology↗

bioRxiv2022

Deep learning-enabled design of synthetic orthologs of a signaling protein

Evolution-based deep generative models represent an exciting direction in understanding and designing proteins. An open question is whether such models can represent the constraints underlying specialized functions that are necessary for organismal fitness in specific biological contexts. Here, we examine the ability of three different models to produce synthetic versions of SH3 domains that can support function in a yeast stress signaling pathway. Using a select-seq assay, we show that one form of a variational autoencoder (VAE) recapitulates the functional characteristics of natural SH3 domains and classifies fungal SH3 homologs hierarchically by function and phylogeny. Locality in the latent space of the model predicts and extends the function of natural orthologs and exposes amino acid constraints distributed near and far from the SH3 ligand-binding site. The ability of deep generative models to specify orthologous function in vivo opens new avenues for probing and engineering protein function in specific cellular environments.

molecular biology↗

bioRxiv2020

Integrating deep learning with microfluidics for biophysical classification of sickle red blood cells

Sickle cell disease (SCD), a group of inherited blood disorders with significant morbidity and early mortality, affects a sizeable global demographic largely of African and Indian descent. It is manifested in a mutated form of hemoglobin that distorts the red blood cells into a characteristic sickle shape with altered biophysical properties. Sickle red blood cells (sRBCs) show heightened adhesive interactions with inflamed endothelium, triggering obstruction of blood vessels and painful vaso-occlusive crisis events. Numerous studies have reported microfluidic-assay-based disease monitoring tools which rely on quantifying adhesion characteristics of adhered sRBCs from high resolution channel images. The current workflow for analyzing images from these assays relies on manual cell counting and detailed morphological characterization by a specially trained worker, which is time and labor intensive. Moreover manual counts by different individuals are prone to artifacts due to user bias. We present here a standardized and reproducible image analysis workflow designed to tackle these issues, using a two part deep neural network architecture that works in tandem for automatic, fast and reliable segmentation and classification into subtypes of adhered cell images. Our training utilized an exhaustive data set of images generated by the SCD BioChip, a microfluidic assay which injects clinical whole blood samples into protein-functionalized microchannels, mimicking physiological conditions in the microvasculature. The automated image analysis performs robustly in comparison to human classification: accuracies were similar to or better than those of the trained personnel, while the overall analysis time was improved by two orders of magnitude.Competing Interest StatementThe authors have declared no competing interest.View Full Text

biophysics↗