An official website of the United States government
Abstract Protein language models, like the popular ESM2, are widely used tools for extracting evolution-based protein representations and have achieved significant success on downstream biological tasks. Representations based on sequence and structure models, however, show significant performance differences depending on the downstream task. A major open problem is to obtain representations that best capture both the evolutionary and structural properties of proteins in general. Here we introduceImplicitStructureModel(ISM), a sequence-only input model with structurally-enriched representations that outperforms state-of-the-art sequence models on several well-studied benchmarks including mutation stability assessment and structure prediction. Our key innovations are a microenvironment-based autoencoder for generating structure tokens and a self-supervised training objective that distills these tokens into ESM2’s pre-trained model. We have madeISM’s structure-enriched weights easily available: integrating ISM into any application using ESM2 requires changing only a single line of code. Our code is available athttps://github.com/jozhang97/ISM.
more »
« less
A refined reweighing technique for nondiscriminatory classification
Discrimination-aware classification methods remedy socioeconomic disparities exacerbated by machine learning systems. In this paper, we propose a novel data pre-processing technique that assigns weights to training instances in order to reduce discrimination without changing any of the inputs or labels. While the existing reweighing approach only looks into sensitive attributes, we refine the weights by utilizing both sensitive and insensitive ones. We formulate our weight assignment as a linear programming problem. The weights can be directly used in any classification model into which they are incorporated. We demonstrate three advantages of our approach on synthetic and benchmark datasets. First, discrimination reduction comes at a small cost in accuracy. Second, our method is more scalable than most other pre-processing methods. Third, the trade-off between fairness and accuracy can be explicitly monitored by model users. Code is available athttps://github.com/frnliang/refined_reweighing.
more »
« less
- PAR ID:
- 10535313
- Publisher / Repository:
- PLOS
- Date Published:
- Journal Name:
- PLOS ONE
- Volume:
- 19
- Issue:
- 8
- ISSN:
- 1932-6203
- Page Range / eLocation ID:
- e0308661
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Protein–peptide interactions play a crucial role in various cellular processes and are implicated in abnormal cellular behaviors leading to diseases such as cancer. Therefore, understanding these interactions is vital for both functional genomics and drug discovery efforts. Despite a significant increase in the availability of protein–peptide complexes, experimental methods for studying these interactions remain laborious, time-consuming, and expensive. Computational methods offer a complementary approach but often fall short in terms of prediction accuracy. To address these challenges, we introduce PepCNN, a deep learning-based prediction model that incorporates structural and sequence-based information from primary protein sequences. By utilizing a combination of half-sphere exposure, position specific scoring matrices from multiple-sequence alignment tool, and embedding from a pre-trained protein language model, PepCNN outperforms state-of-the-art methods in terms of specificity, precision, and AUC. The PepCNN software and datasets are publicly available athttps://github.com/abelavit/PepCNN.git.more » « less
-
Abstract Galaxies are biased tracers of the underlying cosmic web, which is dominated by dark matter (DM) components that cannot be directly observed. Galaxy formation simulations can be used to study the relationship between DM density fields and galaxy distributions. However, this relationship can be sensitive to assumptions in cosmology and astrophysical processes embedded in galaxy formation models, which remain uncertain in many aspects. In this work, we develop a diffusion generative model to reconstruct DM fields from galaxies. The diffusion model is trained on the CAMELS simulation suite that contains thousands of state-of-the-art galaxy formation simulations with varying cosmological parameters and subgrid astrophysics. We demonstrate that the diffusion model can predict the unbiased posterior distribution of the underlying DM fields from the given stellar density fields while being able to marginalize over uncertainties in cosmological and astrophysical models. Interestingly, the model generalizes to simulation volumes ≈500 times larger than those it was trained on and across different galaxy formation models. The code for reproducing these results can be found athttps://github.com/victoriaono/variational-diffusion-cdm✎.more » « less
-
Zhu, Shanfeng (Ed.)We present TIPP3 and TIPP3-fast, new tools for abundance profiling in metagenomic datasets. Like its predecessor, TIPP2, the TIPP3 pipeline uses a maximum likelihood approach to place reads into labeled taxonomies using marker genes, but it achieves superior accuracy to TIPP2 by enabling the use of much larger taxonomies through improved algorithmic techniques. We show that TIPP3 is generally more accurate than leading methods for abundance profiling in two important contexts: when reads come from genomes not already in a public database (i.e., novel genomes) and when reads contain sequencing errors. We also show that TIPP3-fast has slightly lower accuracy than TIPP3, but is also generally more accurate than other leading methods and uses a small fraction of TIPP3’s runtime. Additionally, we highlight the potential benefits of restricting abundance profiling methods to those reads that map to marker genes (i.e., using a filtered marker-gene based analysis), which we show typically improves accuracy. TIPP3 is freely available athttps://github.com/c5shen/TIPP3.more » « less
-
Abstract The widespread misuse of antibiotics has escalated antibiotic resistance into a critical global public health concern. Beyond antibiotics, metals function as antibacterial agents. Metal resistance genes (MRGs) enable bacteria to tolerate metal-based antibacterials and may also foster antibiotic resistance within bacterial communities through co-selection. Thus, predicting bacterial MRGs is vital for elucidating their involvement in antibiotic resistance and metal tolerance mechanisms. The “best hit” approach is mainly utilized to identify and annotate MRGs. This method is sensitive to cutoff values and produces a high false negative rate. Other than the best hit approach, only a few antimicrobial resistance (AMR) detection tools exist for predicting MRGs. However, these tools lack comprehensive annotation for MRGs conferring resistance to multiple metals. To address such limitations, we introduce DeepMRG, a deep learning-based multi-label classifier, to predict bacterial MRGs. Because a bacterial MRG can confer resistance to multiple metals, DeepMRG is designed as a multi-label classifier capable of predicting multiple metal labels associated with an MRG. It leverages bit score-based similarity distribution of sequences with experimentally verified MRGs. To ensure unbiased model evaluation, we employed a clustering method to partition our dataset into six subsets, five for cross-validation and one for testing, with non-homologous sequences, mitigating the impact of sequence homology. DeepMRG consistently achieved high overall F1-scores and significantly reduced false negative rates across a wide range of datasets. It can be used to predict bacterial MRGs in metagenomic or isolate assemblies. The web server of DeepMRG can be accessed athttps://deepmrg.cs.vt.edu/deepmrgand the source code is available athttps://github.com/muhit-emon/DeepMRGunder the MIT license.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1371/journal.pone.0308661
