DeepSeek and the future of drug discovery: a correspondence on AI integration

Intelligent Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

---

Large Language Models and Their Applications in Drug Discovery and Development: A Primer

Clinical and Translational Science, Journal Year: 2025, Volume and Issue: 18(4)

Published: April 1, 2025

ABSTRACT Large language models (LLMs) have emerged as powerful tools in many fields, including clinical pharmacology and translational medicine. This paper aims to provide a comprehensive primer on the applications of LLMs these disciplines. We will explore fundamental concepts LLMs, their potential drug discovery development processes ranging from facilitating target identification aiding preclinical research trial analysis, practical use cases such assisting with medical writing accelerating analytical workflows quantitative pharmacology. By end this paper, pharmacologists scientists clearer understanding how leverage enhance efforts.

Language: Английский

---

Foundation models for bioinformatics

Quantitative Biology, Journal Year: 2024, Volume and Issue: 12(4), P. 339 - 344

Published: July 24, 2024

Abstract Transformer‐based foundation models such as ChatGPTs have revolutionized our daily life and affected many fields including bioinformatics. In this perspective, we first discuss about the direct application of textual on bioinformatics tasks, focusing how to make most out canonical large language mitigate their inherent flaws. Meanwhile, go through transformer‐based, bioinformatics‐tailored for both sequence non‐sequence data. particular, envision further development directions well challenges models.

Language: Английский

---

EpiGePT: a pretrained transformer-based language model for context-specific human epigenomics

Genome biology, Journal Year: 2024, Volume and Issue: 25(1)

Published: Dec. 18, 2024

Abstract The inherent similarities between natural language and biological sequences have inspired the use of large models in genomics, but current struggle to incorporate chromatin interactions or predict unseen cellular contexts. To address this, we propose EpiGePT, a transformer-based model designed for predicting context-specific human epigenomic signals. By incorporating transcription factor activities 3D genome interactions, EpiGePT outperforms existing methods signal prediction tasks, especially cell-type-specific long-range interaction predictions genetic variant impacts, advancing our understanding gene regulation. A free online service is available at http://health.tsinghua.edu.cn/epigept .

Language: Английский

---

Comparative Molecular Docking of Apigenin and Luteolin Versus Conventional Ligands for TP-53, pRb, APOBEC3H, and HPV-16 E6: Potential Clinical Applications in Preventing Gy-necological Malignancies

Published: Aug. 26, 2024

This study presents a detailed comparative analysis of Molecular Docking data, focusing on the binding interactions conventional ligands and natural compounds, Apigenin Luteolin, with TP-53, pRb, APOBEC. Utilizing advanced bioinformatics techniques, coupled Ar-tificial Intelligence software High-Performance Computing (HPC), we measured con-trasted energies these interactions. Additionally, investigated protein-protein between HPV-16 oncoprotein E6 tumor suppressors TP-53 pRb. Our findings demonstrate that compounds Luteolin exhibit significantly higher affinities to APOBEC compared pharmacological ligands. The for were approximately -6.9 kcal/mol -6.6 kcal/mol, respectively, indicating their strong potential as therapeutic agents in inhibiting oncogenic functions HPV-16. In contrast, showed lower affinities, around -4.5 -5.5 kcal/mol. further revealed exhibited considerably en-ergies, -976.7 due multiple interaction sites complex nature protein interfaces. A conversion formula was developed translate high-energy inter-actions comparable scale non-protein-protein interactions, highlighting superior which, through same formula, shown be than These results underscore promise preventing HPV-16-related on-cogenesis. By demonstrating crucial suppressors, this supports development compound-based therapies. also em-phasize necessity experimental validation explore compounds' efficacy clinical settings. comprehensive provides robust framework understanding lays groundwork innovative strategies against

Language: Английский

---

Biomedical relation extraction method based on ensemble learning and attention mechanism

BMC Bioinformatics, Journal Year: 2024, Volume and Issue: 25(1)

Published: Oct. 18, 2024

Abstract Background Relation extraction (RE) plays a crucial role in biomedical research as it is essential for uncovering complex semantic relationships between entities textual data. Given the significance of RE informatics and increasing volume literature, there an urgent need advanced computational models capable accurately efficiently extracting these on large scale. Results This paper proposes novel approach, SARE, combining ensemble learning Stacking attention mechanisms to enhance performance relation extraction. By leveraging multiple pre-trained models, SARE demonstrates improved adaptability robustness across diverse domains. The enable model capture utilize key information text more accurately. achieved improvements 4.8, 8.7, 0.8 percentage points PPI, DDI, ChemProt datasets, respectively, compared original BERT variant domain-specific PubMedBERT model. Conclusions offers promising solution improving accuracy efficiency tasks research, facilitating advancements informatics. results suggest that with effective from texts. Our code data are publicly available at: https://github.com/GS233/Biomedical .

Language: Английский

---

Exploring the potential of large language model–based chatbots in challenges of ribosome profiling data analysis: a review

Briefings in Bioinformatics, Journal Year: 2024, Volume and Issue: 26(1)

Published: Nov. 22, 2024

Abstract Ribosome profiling (Ribo-seq) provides transcriptome-wide insights into protein synthesis dynamics, yet its analysis poses challenges, particularly for nonbioinformatics researchers. Large language model–based chatbots offer promising solutions by leveraging natural processing. This review explores their convergence, highlighting opportunities synergy. We discuss challenges in Ribo-seq and how mitigate them, facilitating scientific discovery. Through case studies, we illustrate chatbots’ potential contributions, including data result interpretation. Despite the absence of applied examples, existing software underscores value large model. anticipate pivotal role future analysis, overcoming limitations. Challenges such as model bias privacy require attention, but emerging trends promise. The integration models holds immense advancing translational regulation gene expression understanding.

Language: Английский

---

Steering veridical large language model analyses by correcting and enriching generated database queries: first steps toward ChatGPT bioinformatics

Briefings in Bioinformatics, Journal Year: 2024, Volume and Issue: 26(1)

Published: Nov. 22, 2024

Large language models (LLMs) leverage factual knowledge from pretraining. Yet this remains incomplete and sometimes challenging to retrieve-especially in scientific domains not extensively covered pretraining datasets where information is still evolving. Here, we focus on genomics bioinformatics. We confirm expand upon issues with plain ChatGPT functioning as a bioinformatics assistant. Poor data retrieval hallucination lead err, do incorrect sequence manipulations. To address this, propose system basing LLM outputs up-to-date, authoritative facts facilitating LLM-guided analysis. Specifically, introduce NagGPT, middleware tool insert between LLMs databases, designed bridge gaps usage of database application programming interfaces. NagGPT proxies LLM-generated queries, special handling queries. It acts gatekeeper query responses the prompt, redirecting large files but providing synthesized snippet injecting comments steer LLM. A companion OpenAI custom GPT, Genomics Fetcher-Analyzer, connects NagGPT. steers generate run Python code, performing tasks dynamically retrieved dozen common databases (e.g. NCBI, Ensembl, UniProt, WormBase, FlyBase). implement partial mitigations for encountered challenges: detrimental interactions code generation style analysis, confusion identifiers, both actions taken. Our results identify avenues augment assistant and, more broadly, improve accuracy instruction following unmodified LLMs.

Language: Английский

---

The Use of AI-Supported Chatbot in Psychology

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 20

Published: Dec. 27, 2024

Artificial intelligence has allowed programmers to create human-like meaningful texts. As a result, chatbots have recently gained great attention. Many people praised how novel chat applications can original and essays. However, few studies discuss the use of AI in psychology. The authors aimed field Psychology. Also, they summarize previous on ChatGPT. This chapter discusses be used this process. They ChatGPT brief literature review show progress OpenAI application. Studies Pubmed were searched. Overall, found eight using keyword “ChatGPT.” Most claim that write essays, it is hard distinguish from writing. no study discussing impact allow writing essays various topics many fields, including psychology, medicine, engineering, philosophy, medical education, literature, computer sciences.

Language: Английский

---