Dataset Information

DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models.

ABSTRACT: Bacteriophages (phages) are viruses that infect bacteria. Many of them produce specific enzymes called depolymerases to break down external polysaccharide structures. Accurate annotation and domain identification of these depolymerases are challenging due to their inherent sequence diversity. Hence, we present DepoScope, a machine learning tool that combines a fine-tuned ESM-2 model with a convolutional neural network to identify depolymerase sequences and their enzymatic domains precisely. To accomplish this, we curated a dataset from the INPHARED phage genome database, created a polysaccharide-degrading domain database, and applied sequential filters to construct a high-quality dataset, which is subsequently used to train DepoScope. Our work is the first approach that combines sequence-level predictions with amino-acid-level predictions for accurate depolymerase detection and functional domain identification. In that way, we believe that DepoScope can greatly enhance our understanding of phage-host interactions at the level of depolymerases.

SUBMITTER: Concha-Eloko R

PROVIDER: S-EPMC11326577 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models.

Concha-Eloko Robby R Stock Michiel M De Baets Bernard B Briers Yves Y Sanjuán Rafael R Domingo-Calap Pilar P Boeckaerts Dimitri D

PLoS computational biology 20240805 8

Bacteriophages (phages) are viruses that infect bacteria. Many of them produce specific enzymes called depolymerases to break down external polysaccharide structures. Accurate annotation and domain identification of these depolymerases are challenging due to their inherent sequence diversity. Hence, we present DepoScope, a machine learning tool that combines a fine-tuned ESM-2 model with a convolutional neural network to identify depolymerase sequences and their enzymatic domains precisely. To a ...[more]

PMID: 39102416

Similar Datasets

Project description:ImportanceOver the past decade, the leadership of the National Institute of Mental Health (NIMH) has emphasized the importance of a transdiagnostic approach to psychiatric investigation using Research Domain Criteria (RDoC) mapping more closely to neurobiology.ObjectiveTo investigate whether research support from the NIMH for individual RDoC domains and for transdiagnostic investigation has changed over time and has had differential impact in terms of publication, citations, or patent filings.Design, setting, and participantsIn this longitudinal cohort study, all R01, R21, and R03 studies funded by the NIMH between January 2003 and December 2023 were identified via the National Institutes of Health RePORTER database. Their abstracts were characterized in terms of RDoC domains (negative valence, positive valence, cognition, social, arousal, and sensorimotor) using a large language model.Main outcomes and measuresPrimary outcomes were publications, citation impact estimated at 5 years from the index year of funding, and patents, examined using regression models adjusted for other grant characteristics.ResultsAmong 8897 R01, R03, and R21 projects, reflecting $17.7 billion of investment, abstracts of 3141 (35.3%) reflected negative valence; 1344 (15.1%), positive valence; 2781 (31.3%), cognition; 1607 (18.1%), social; 343 (3.9%), arousal; and 571 (6.4%), sensorimotor domains. A total of 1793 (20.2%) incorporated a transdiagnostic perspective. Positive and social domains were associated with fewer publications (difference, -1.13 [95% CI, -2.11 to -0.15] and -2.23 [95% CI, -3.15 to -1.30], respectively) and lesser citation impact (difference, -0.47 [95% CI, -0.75 to -0.18] and -1.19 [95% CI, -1.46 to -0.91], respectively) at 5 years. Social (adjusted odds ratio [AOR], 0.11; 95% CI, 0.04-0.23) and cognitive (AOR, 0.66; 95% CI, 0.48-0.89) domains and transdiagnostic proposals (AOR, 0.37; 95% CI, 0.21-0.60) were associated with lower likelihood of patent filing.Conclusions and relevanceIn this study of NIMH funding, grants reflecting different RDoC domains differed substantially in their scientific impact in terms of publications, citations, and patent generation. The findings suggest that large language models represent a promising approach to characterizing research proposals at scale, which may be useful in guiding resource allocation to maximize scientific return on investment.

Project description:BackgroundRecent advancements in large language models (LLMs) have accelerated their use across various domains. Psychiatric interviews, which are goal-oriented and structured, represent a significantly underexplored area where LLMs can provide substantial value. In this study, we explore the application of LLMs to enhance psychiatric interviews by analyzing counseling data from North Korean defectors who have experienced traumatic events and mental health issues.ObjectiveThis study aims to investigate whether LLMs can (1) delineate parts of the conversation that suggest psychiatric symptoms and identify those symptoms, and (2) summarize stressors and symptoms based on the interview dialogue transcript.MethodsGiven the interview transcripts, we align the LLMs to perform 3 tasks: (1) extracting stressors from the transcripts, (2) delineating symptoms and their indicative sections, and (3) summarizing the patients based on the extracted stressors and symptoms. These 3 tasks address the 2 objectives, where delineating symptoms is based on the output from the second task, and generating the summary of the interview incorporates the outputs from all 3 tasks. In this context, the transcript data were labeled by mental health experts for the training and evaluation of the LLMs.ResultsFirst, we present the performance of LLMs in estimating (1) the transcript sections related to psychiatric symptoms and (2) the names of the corresponding symptoms. In the zero-shot inference setting using the GPT-4 Turbo model, 73 out of 102 transcript segments demonstrated a recall mid-token distance d<20 for estimating the sections associated with the symptoms. For evaluating the names of the corresponding symptoms, the fine-tuning method demonstrates a performance advantage over the zero-shot inference setting of the GPT-4 Turbo model. On average, the fine-tuning method achieves an accuracy of 0.82, a precision of 0.83, a recall of 0.82, and an F1-score of 0.82. Second, the transcripts are used to generate summaries for each interviewee using LLMs. This generative task was evaluated using metrics such as Generative Evaluation (G-Eval) and Bidirectional Encoder Representations from Transformers Score (BERTScore). The summaries generated by the GPT-4 Turbo model, utilizing both symptom and stressor information, achieve high average G-Eval scores: coherence of 4.66, consistency of 4.73, fluency of 2.16, and relevance of 4.67. Furthermore, it is noted that the use of retrieval-augmented generation did not lead to a significant improvement in performance.ConclusionsLLMs, using either (1) appropriate prompting techniques or (2) fine-tuning methods with data labeled by mental health experts, achieved an accuracy of over 0.8 for the symptom delineation task when measured across all segments in the transcript. Additionally, they attained a G-Eval score of over 4.6 for coherence in the summarization task. This research contributes to the emerging field of applying LLMs in psychiatric interviews and demonstrates their potential effectiveness in assisting mental health practitioners.

Dataset Information

DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models.

Publications

DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets