SEARCH · PubMed Health

Results for “Deep Learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3Linked to original sources

PubMed2025

Harnessing deep learning for proteome-scale detection of amyloid signaling motifs.

MOTIVATION: Amyloid signaling sequences adopt the cross-β fold that is capable of self-replication in the templating process. Propagation of the amyloid fold from the receptor to the effector protein is used for signal transduction in the immune response pathways in animals, fungi, and bacteria. So far, a dozen of families of amyloid signaling motifs (ASMs) have been classified. Unfortunately, due to the wide variety of ASMs it is difficult to identify them in large protein databases available, which limits the possibility of conducting experimental studies. To date, various deep learning (DL) models have been applied across a range of protein-related tasks, including domain family classification and the prediction of protein structure and protein-protein interactions. RESULTS: In this study, we develop tailor-made bidirectional LSTM and BERT-based architectures to model ASM, and compare their performance against a state-of-the-art machine learning grammatical model. Our research is focused on developing a discriminative model of generalized ASMs, capable of detecting ASMs in large datasets. The DL-based models are trained on a diverse set of motif families and a global negative set, and used to identify ASMs from remotely related families. We analyze how both models represent the data and demonstrate that the DL-based approaches effectively detect ASMs, including novel motifs, even at the genome scale. AVAILABILITY AND IMPLEMENTATION: The models are provided as a Python package, asmscan-bilstm, and a Docker image at https://github.com/chrispysz/asmscan-proteinbert-run. The source code can be accessed at https://github.com/jakub-galazka/asmscan-bilstm and https://github.com/chrispysz/asmscan-proteinbert. Data and results are at https://github.com/wdyrka-pwr/ASMscan.

Deep Learning↗

PubMed2025

Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology.

Characterizing cancer presents a delicate challenge as it involves deciphering complex biological interactions within the tumor's microenvironment. Clinical trials often provide histology images and molecular profiling of tumors, which can help understand these interactions. Despite recent advances in representing multimodal data for weakly supervised tasks in the medical domain, achieving a coherent and interpretable fusion of whole slide images and multi-omics data is still a challenge. Each modality operates at distinct biological levels, introducing substantial correlations between and within data sources. In response to these challenges, we propose a novel deep-learning-based approach designed to represent multi-omics & histopathology data for precision medicine in a readily interpretable manner. While our approach demonstrates superior performance compared to state-of-the-art methods across multiple test cases, it also deals with incomplete and missing data in a robust manner. It extracts various scores characterizing the activity of each modality and their interactions at the pathway and gene levels. The strength of our method lies in its capacity to unravel pathway activation through multimodal relationships and to extend enrichment analysis to spatial data for supervised tasks. We showcase its predictive capacity and interpretation scores by extensively exploring multiple TCGA datasets and validation cohorts. The method opens new perspectives in understanding the complex relationships between multimodal pathological genomic data in different cancer types and is publicly available on Github.

Deep Learning↗

PubMed2025

G4STAB: a multi-input deep learning model to predict G-quadruplex thermodynamic stability based on sequence and salt concentration.

MOTIVATION: G-quadruplexes (G4s) are non-canonical nucleic acid structures formed in guanine-rich regions that modulate gene regulation and genomic stability. The thermodynamic stability of G4s directly influences their biological functions and potential as therapeutic targets. However, current quantitative frameworks for predicting G4 stability rely on predetermined structural features, limiting their effectiveness for diverse G4 topologies, and fail to account for environmental factors such as ion concentration and pH that significantly modulate G4 stability in cellular contexts. RESULTS: We present G4STAB, a multi-input deep learning neural network that accurately predicts DNA G4 melting temperatures based on sequence features, salt concentration, and pH. Trained on 2382 diverse DNA G4 sequences, our model achieves high accuracy (R 2=0.8) without relying on predetermined G4 structural features. G4STAB successfully captures established G4 stability determinants and proposes previously unobserved sequence-stability relationships. Analysis of 391 502 experimentally validated G4s reveals that cancer-like ionic environments alter G4 stability profiles, with a 13.5-fold increase in the number of structures exhibiting physiological melting temperatures (36-42°C). These findings suggest systematic genomic patterns in G4 stability responses across chromosomes and gene types. AVAILABILITY AND IMPLEMENTATION: G4STAB is available at https://github.com/donn-liew/G4STAB; G4STAB web database interface is available at https://donn-liew.github.io/g4stab-web-database/.

G-Quadruplexes↗

PubMed2026

Exploring the use of machine and deep learning in genome-wide association studies: a comprehensive review.

The advent of high-throughput sequencing technologies has generated increasingly large and complex genomic datasets, necessitating analytical approaches capable of capturing high-dimensional and potentially nonlinear genetic interactions. This situation has significantly impacted the entire field of Genome-Wide Association Study (GWAS), whose primary goal is the identification of genomic traits and variants that are statistically associated with the risk of a disease. However, traditional GWAS methods may show reduced performance when applied to highly polygenic and nonlinear genetic architectures. Computational strategies from Artificial Intelligence (AI) and, in particular, from machine- and deep-learning may provide a powerful tool to overcome such limitations, especially by capturing nonlinear interactions and complex hidden regularities in large-scale data, which traditional GWAS approaches might overlook. To date, only a few approaches have been introduced and systematically assessed. In this review, we describe the main characteristics and limitations of standard statistical approaches for GWAS, the main uses of AI methods in computational genomics, and recent attempts to leverage AI strategies in GWAS. Particular attention will be devoted to key issues, such as the interpretability of methods and results, and the curse of dimensionality. More specifically, the review presents 30 methods designed to leverage AI in GWAS, as well as presenting a comprehensive set of evaluation metrics for their performance, also providing references to the most frequently used databases, and biobanks. Overall, this work may serve as a starting point for both dry- and wet-lab researchers, aiming to extract deeper insights from genomic data by moving beyond traditional linear additive assumptions, and leveraging large-scale datasets through AI-driven approaches.

Artificial intelligence↗

PubMed2025

Soffritto: a deep learning model for predicting high-resolution replication timing.

MOTIVATION: Replication timing (RT) refers to the order in which DNA loci are replicated during S phase. RT is cell-type specific and implicated in cellular processes including transcription, differentiation, and disease. RT is typically quantified genome-wide using two-fraction assays (e.g. Repli-Seq) which sort cells into early and late S phase fractions followed by DNA sequencing, yielding a ratio as the RT signal. While two-fraction RT data are widely available in multiple cell lines, it is limited in its ability to capture high-resolution RT features. To address this, high-resolution Repli-Seq, which quantifies RT across 16 fractions, was developed, but it is costly and technically challenging with very limited data generated to date. RESULTS: Here, we developed Soffritto, a deep learning model that predicts high-resolution RT data using two-fraction RT data, histone ChIP-seq data, GC content, and gene density as input. Soffritto is composed of a Long Short-Term Memory (LSTM) module and a prediction module. The LSTM module learns long- and short-range interactions between genomic bins, while the prediction module is composed of a fully connected layer that outputs a 16-fraction probability vector for each bin using the LSTM module's embeddings as input. By performing both within cell line and cross-cell line training and testing for five human and mouse cell lines, we show that Soffritto is able to capture experimental 16-fraction RT signals with high accuracy, and the predicted signals allow detection of high-resolution RT patterns. AVAILABILITY AND IMPLEMENTATION: Soffritto is available at https://github.com/ay-lab/Soffritto.

Deep Learning↗

PubMed2025

SetBERT: the deep learning platform for contextualized embeddings and explainable predictions from high-throughput sequencing.

MOTIVATION: High-throughput sequencing (HTS) is a modern sequencing technology used to profile microbiomes by sequencing thousands of short genomic fragments from the microorganisms within a given sample. This technology presents a unique opportunity for artificial intelligence to comprehend the underlying functional relationships of microbial communities. However, due to the unstructured nature of HTS data, nearly all computational models are limited to processing DNA sequences individually. This limitation causes them to miss out on key interactions between microorganisms, significantly hindering our understanding of how these interactions influence the microbial communities as a whole. Furthermore, most computational methods rely on post-processing of samples which could inadvertently introduce unintentional protocol-specific bias. RESULTS: Addressing these concerns, we present SetBERT, a robust pre-training methodology for creating generalized deep learning models for processing HTS data to produce contextualized embeddings and be fine-tuned for downstream tasks with explainable predictions. By leveraging sequence interactions, we show that SetBERT significantly outperforms other models in taxonomic classification with genus-level classification accuracy of 95%. Furthermore, we demonstrate that SetBERT is able to accurately explain its predictions autonomously by confirming the biological-relevance of taxa identified by the model. AVAILABILITY AND IMPLEMENTATION: All source code is available at https://github.com/DLii-Research/setbert. SetBERT may be used through the q2-deepdna QIIME 2 plugin whose source code is available at https://github.com/DLii-Research/q2-deepdna.

Deep Learning↗

PubMed2026

shinyDeepGxP: a user-friendly R shiny app for predicting surface protein abundance from scRNA-seq expression using deep learning in blood cells.

MOTIVATION: Understanding accurate immune cell heterogeneity and function in single-cell datasets requires access to protein-level information, which is often unavailable due to experimental limitations. RESULTS: We present shinyDeepGxP, an interactive web application featuring our deep learning model, DeepGxP, for predicting surface protein abundance from single-cell RNA-sequencing (scRNA-seq) data. This platform makes DeepGxP accessible to researchers without programming skills. Users can upload scRNA-seq count matrices and use "Predict Protein" to predict the abundance of 224 biologically relevant surface proteins. shinyDeepGxP provides visualizations to help identify distinct cell populations based on predicted protein profiles. Moreover, users can choose "Explore Model" to reveal key RNA predictors and their associated biological pathways for each protein. Overall, shinyDeepGxP is a user-friendly, freely available web tool that provides protein-level detail for RNA-only single-cell datasets, enabling multimodal discovery without additional experiments. AVAILABILITY AND IMPLEMENTATION: shinyDeepGxP can be launched on https://shiny.crc.pitt.edu/deepgxp/.

Journal Article↗

PubMed2026

IQ-NET: fast and accurate quartet phylogenetic inference using deep learning trained on empirical DNA alignments.

Phylogenetic inference is fundamental to modern biology, with many applications including evolutionary biology, epidemiology, and comparative genomics. While maximum likelihood and Bayesian methods remain the gold standard for phylogenetic analysis, they rely on simplifying assumptions and are computationally intensive. Recent machine learning approaches for phylogenetics offer speed advantages, but have several limitations: exclusive reliance on simulated data for training, inadequate handling of gaps, and sensitivity to input sequence order. Here, we introduce IQ-NET (Intelligent Quartet NETwork), a deep learning framework that solves these limitations to infer four-taxon trees. IQ-NET estimates both tree topology and branch lengths directly from gapped alignments. IQ-NET outperforms existing machine learning methods in terms of accuracy, and obtained a 24-fold speedup compared with the widely used maximum likelihood software, IQ-TREE. We finally introduce a pipeline using IQ-NET and the ASTRAL software to reconstruct a larger species tree, i.e., with more than four taxa.

Empirical data training↗

PubMed2026

An interpretable deep learning framework uncovers features governing CRISPR-Cas9 genome-editing efficiency.

MOTIVATION: CRISPR-Cas9 genome-editing efficiency is strongly influenced by the sequence composition and positional context of single-guide RNAs (sgRNAs). Although numerous deep learning-based models have been developed to predict Cas9 efficiency from sgRNA sequences, most operate as black boxes, offering limited insight into the sequence determinants underlying Cas9 activity. In addition, previous studies often overlook how the positional context of sequence motifs within sgRNAs influences their effects on Cas9 binding or cleavage. RESULTS: We introduce DeepCC9, an interpretable machine learning framework that combines explicit sequence feature extraction with a residual block-based deep architecture to improve interpretability and identify composition- and position-based motifs governing Cas9 genome-editing efficiency. We applied this method to multiple Cas9 variant datasets, achieving superior predictive performance compared with existing methods while enabling direct interpretation of sequence motifs and their positional effects. Our analysis uncovered 74 sequence motifs enriched or depleted at specific positions within sgRNAs and strongly associated with Cas9 efficiency, providing mechanistic insight into sequence features that influence guide performance. Together, these results establish DeepCC9 as a generalizable and interpretable framework for modeling sequence-function relationships and advancing the understanding of the sequence determinants underlying CRISPR-Cas9 genome editing. AVAILABILITY AND IMPLEMENTATION: The authors have implemented their algorithm in the Python programming language (version 3.X), which is accessible using (https://zenodo.org/records/20073890).

Deep Learning↗

PubMed2026

High-accuracy SNV calling for bacterial isolates using deep learning with AccuSNV.

Accurate detection of mutations within bacterial species is critical for fundamental studies of microbial evolution, reconstruction of transmission events, and identification of antimicrobial resistance mutations. Although many tools have been developed to identify single-nucleotide variants (SNVs) from whole-genome sequencing, they often suffer from high false-positive rates owing to the complexity of bacterial genomes and the need for different filtering cutoffs across sample types and sequencing depths. As data sets increase in size, the manual filtering required for high accuracy presents a significant obstacle. Here, we present AccuSNV, a novel deep learning-based tool for high-precision and automated bacterial SNV calling. Unlike traditional methods that process one sample at a time, AccuSNV leverages a convolutional neural network (CNN) that integrates alignment information across multiple samples, enhancing precision through learned across-sample patterns. We evaluate AccuSNV against seven popular SNV-calling tools using simulated data from six bacterial species with varied sequencing depths, numbers of isolates, mutations, and divergence levels. To further validate its real-world utility, we test AccuSNV on multiple curated bacterial data sets containing reported SNVs. In both simulated and real-world scenarios, AccuSNV consistently achieves the best performance. Moreover, AccuSNV provides comprehensive user-friendly downstream analysis modules and outputs, including mutation annotation information, phylogenetic inference, d N/d S calculations, and optional manual filtering. Together with the automated deep learning-based calling, these features make AccuSNV broadly accessible to users with different levels of computational expertise.

Deep Learning↗

PubMed2026

Deep learning reveals genomic regions introgressed between two recurrently hybridizing lynx species.

Recently, diverged species with overlapping distributional ranges have high chances of hybridizing and if hybrids are viable, genomic material can be transferred between species in a process called introgression. To characterize the patterns and consequences of introgression in species with historically low population sizes and recent steep declines resulting in genetic erosion, we analyze the Iberian and Eurasian lynx (EL) as an illustrative and relevant case study. While genome-wide introgression was already detected, here we apply a method using a deep convolutional neural network to detect specific regions of the genome with signals of introgression in three populations of these two species. Over 6% of the genome of both Iberian lynx and ELw shows introgression from the other species, compared with only 2% in the ELs. This observation, along with the results from demographic modeling, suggests that the ELw population is genetically closest to the source of EL introgression, a probably now extinct group that coexisted with the Iberian lynx in Southern Europe and Northern Iberia until recently. As predicted by theory, introgression was generally higher in populations with smaller effective sizes and in genomic regions of high recombination. However, the Iberian lynx did not show higher overall introgression than the more abundant ELw, and coding regions introgressed as frequently as intergenic regions. Local genetic diversity is boosted approximately 3-fold in genomic windows where introgression occurs, potentially including the adaptively relevant and highly diverse MHC region of the Iberian lynx.

Animals↗

PubMed2026

DeepMASS v.2: An enhanced deep learning platform for large-scale discovery and structural annotation of unknown plant metabolites.

Determining the structures of unknown metabolites remains a fundamental bottleneck in plant metabolomics, as the vast chemical diversity of plant secondary metabolites far exceeds the coverage of existing spectral libraries. Here, we present DeepMASS v.2, a substantially enhanced platform for annotating unknown metabolites from liquid chromatography-tandem mass spectrometry data, designed to address this challenge at scale. DeepMASS v.2 leverages a semantic spectral representation model trained on millions of spectra from GNPS, NIST, and in-house resources. By integrating Spec2Vec-based embeddings with HNSW (hierarchical navigable small world) graph retrieval and a unified chemical space defined by molecular fingerprints, DeepMASS v.2 identifies structurally related neighbors of unknown spectra and ranks candidate structures according to their proximity to the predicted structural neighborhoods within chemical space. Benchmarking against Critical Assessment of Small Molecule Identification datasets and a curated natural product collection demonstrated that DeepMASS v.2 outperforms state-of-the-art in silico annotation tools, including SIRIUS, CFM-ID, MetFrag, and MS-Finder. Importantly, DeepMASS v.2 maintains strong performance for metabolites absent from spectral libraries, highlighting its capacity to annotate genuinely unknown compounds. Application of DeepMASS v.2 to large-scale plant metabolomics datasets demonstrated its ability to expand accessible metabolome coverage. Implemented as an intuitive web platform, DeepMASS v.2 provides the community with a scalable, interpretable, and high-throughput solution for structural annotation, enabling more comprehensive characterization of plant chemical diversity and accelerating natural product discovery in molecular plant science. The DeepMASS v.2 web server is publicly available at http://deepmass.cn.

Metabolomics↗

PubMed2025

Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control.

Core promoters are essential regulatory elements that control transcription initiation, but accurately predicting and designing their strength remains challenging due to complex sequence-function relationships and the limited generalizability of existing AI-based approaches. To address this, we developed a modular platform integrating rational library design, predictive modelling, and generative optimization into a closed-loop workflow for end-to-end core promoter engineering. Conserved and spacer region of core promoters exert distinct effects on transcriptional strength, with the former driving large-scale variation and the latter enabling finer gradation. Based on this insight, Mutation-Barcoding-Reverse Sequencing approach was used and constructed a synthetic promoter library comprising 112 955 variants with minimal redundancy and a 16 226-fold expression range. A Transformer-based model trained on this dataset achieved a Pearson correlation of 0.87 with experimentally measured promoter strengths. When combined with a conditional diffusion model, the system enabled de novo generation of promoter sequences with defined strengths, achieving a design-to-measurement correlation of 0.95 and maintaining high accuracy (R = 0.93) across varied sequence contexts. The designed promoters consistently preserved their intended strength gradients, demonstrating robust plug-and-play functionality. This work establishes a scalable and extensible platform (www.yudenglab.com) for deep learning-guided programmable design of Escherichia coli core promoters, enabling precise transcriptional control.

Promoter Regions, Genetic↗

PubMed2025

Multimodal deep learning for immunotherapy response prediction and biomarker discovery in non-small cell lung cancer.

OBJECTIVE: Immunotherapy has emerged as a promising treatment for advanced non-small cell lung cancer (NSCLC), but accurately predicting which patients will benefit from it remains a major clinical challenge. To address this, we aim to develop a novel multimodal method, DeepAFM, that integrates histopathology, genomic features, and clinical information to predict patient responses to anti-PD-(L)1 immunotherapy. MATERIALS AND METHODS: A total of 93 patients with advanced NSCLC were included in this study. Histopathological whole-slide images were processed using a self-supervised VQVAE2 for representation learning. PCA and K-means clustering were then applied for dimensionality reduction and feature grouping. Key regions of interest were visualized through permutation importance evaluation and color-coding techniques. The extracted histopathological features, along with genomic alterations and clinical variables, were integrated into the DeepAFM multimodal prediction model. RESULTS: The DeepAFM achieved a high predictive performance with an area under the curve (AUC) of 0.77 (95% confidence interval: 0.69-1.00). Attention-based heatmaps revealed that the model could identify critical pathological patterns, genomic mutations, and clinical indicators associated with patient responses to immunotherapy. DISCUSSION: The integration of multimodal data enabled the model to capture complex interactions among pathology, genomics, and clinical characteristics, enhancing the interpretability and predictive power of immunotherapy response prediction. The visualization techniques facilitated the identification of biologically meaningful features and potential biomarkers. CONCLUSION: This study demonstrates the effectiveness of the DeepAFM in predicting responses to immunotherapy in advanced NSCLC. The approach not only improves prediction accuracy but also provides valuable insights for personalized treatment strategies and biomarker discovery.

Humans↗

PubMed2025

N6-methyladenine identification using deep learning and discriminative feature integration.

N6-methyladenine (6 mA) is a pivotal DNA modification that plays a crucial role in epigenetic regulation, gene expression, and various biological processes. With advancements in sequencing technologies and computational biology, there is an increasing focus on developing accurate methods for 6 mA site identification to enhance early detection and understand its biological significance. Despite the rapid progress of machine learning in bioinformatics, accurately detecting 6 mA sites remains a challenge due to the limited generalizability and efficiency of existing approaches. In this study, we present Deep-N6mA, a novel Deep Neural Network (DNN) model incorporating optimal hybrid features for precise 6 mA site identification. The proposed framework captures complex patterns from DNA sequences through a comprehensive feature extraction process, leveraging k-mer, Dinucleotide-based Cross Covariance (DCC), Trinucleotide-based Auto Covariance (TAC), Pseudo Single Nucleotide Composition (PseSNC), Pseudo Dinucleotide Composition (PseDNC), and Pseudo Trinucleotide Composition (PseTNC). To optimize computational efficiency and eliminate irrelevant or noisy features, an unsupervised Principal Component Analysis (PCA) algorithm is employed, ensuring the selection of the most informative features. A multilayer DNN serves as the classification algorithm to identify N6-methyladenine sites accurately. The robustness and generalizability of Deep-N6mA were rigorously validated using fivefold cross-validation on two benchmark datasets. Experimental results reveal that Deep-N6mA achieves an average accuracy of 97.70% on the F. vesca dataset and 95.75% on the R. chinensis dataset, outperforming existing methods by 4.12% and 4.55%, respectively. These findings underscore the effectiveness of Deep-N6mA as a reliable tool for early 6 mA site detection, contributing to epigenetic research and advancing the field of computational biology.

Deep Learning↗

PubMed2024

Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data.

UNLABELLED: Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor-type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole-genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a data set of 39,787 solid tumors sequenced using a clinically targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivaling the performance of WGS-based methods. GDD-ENS can also guide diagnoses of rare type and cancers of unknown primary and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows could provide clinically relevant tumor-type predictions to guide treatment decisions in real time. SIGNIFICANCE: We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.

Humans↗

PubMed2024

PredIL13: Stacking a variety of machine and deep learning methods with ESM-2 language model for identifying IL13-inducing peptides.

Interleukin (IL)-13 has emerged as one of the recently identified cytokine. Since IL-13 causes the severity of COVID-19 and alters crucial biological processes, it is urgent to explore novel molecules or peptides capable of including IL-13. Computational prediction has received attention as a complementary method to in-vivo and in-vitro experimental identification of IL-13 inducing peptides, because experimental identification is time-consuming, laborious, and expensive. A few computational tools have been presented, including the IL13Pred and iIL13Pred. To increase prediction capability, we have developed PredIL13, a cutting-edge ensemble learning method with the latest ESM-2 protein language model. This method stacked the probability scores outputted by 168 single-feature machine/deep learning models, and then trained a logistic regression-based meta-classifier with the stacked probability score vectors. The key technology was to implement ESM-2 and to select the optimal single-feature models according to their absolute weight coefficient for logistic regression (AWCLR), an indicator of the importance of each single-feature model. Especially, the sequential deletion of single-feature models based on the iterative AWCLR ranking (SDIWC) method constructed the meta-classifier consisting of the top 16 single-feature models, named PredIL13, while considering the model's accuracy. The PredIL13 greatly outperformed the-state-of-the-art predictors, thus is an invaluable tool for accelerating the detection of IL13-inducing peptide within the human genome.

Humans↗

PubMed2026

RP3Net: a deep learning model for predicting recombinant protein production in Escherichia coli.

MOTIVATION: Recombinant protein expression can be a limiting step in the production of protein reagents for drug discovery and other biotechnology applications. We introduce RP3Net (Recombinant Protein Production Prediction Network), an AI model of small-scale heterologous soluble protein expression in Escherichia coli. RP3Net utilizes the most recent protein and genomic foundational models. A curated dataset of internal experimental results from AstraZeneca and publicly available data from the Structural Genomics Consortium was used for training, validation and testing of RP3Net. RESULTS: RP3Net achieves an increase in area under the receiver operator curve (AUROC) of 0.15, compared to a baseline model. When experimentally validated on an independent, prospective, manually selected set of 97 constructs, RP3Net outperformed currently available models, with an AUROC of 0.83, delivering accurate predictions in 77% of the cases, and correctly identifying successfully expressing constructs in 92% of cases. AVAILABILITY AND IMPLEMENTATION: The model, along with installation and running instructions, is available under an MIT licence at https://github.com/RP3Net/RP3Net, DOI 10.5281/zenodo.17243498.

Escherichia coli↗