An official website of the United States government
Abstract MotivationNeural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet). ResultsWe evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications. Availability and implementationSource code of CFNet is available at: https://github.com/bchidest/CFNet. Supplementary informationSupplementary data are available at Bioinformatics online.
more »
« less
Amino acid encoding for deep learning applications
Abstract BackgroundThe number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. ResultsBy using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. ConclusionOur study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.
more »
« less
- Award ID(s):
- 1553289
- PAR ID:
- 10526561
- Publisher / Repository:
- BMC
- Date Published:
- Journal Name:
- BMC Bioinformatics
- Volume:
- 21
- Issue:
- 1
- ISSN:
- 1471-2105
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching. We consider two of the most popular random embeddings, namely, Gaussian embeddings and the Subsampled Randomized Hadamard Transform (SRHT). While current randomized solvers for least-squares optimization prescribe an embedding dimension at least greater than the data dimension, we show that the embedding dimension can be reduced to the effective dimension of the optimization problem, and still preserve high-probability convergence guarantees. In this regard, we derive sharp matrix deviation inequalities over ellipsoids for both Gaussian and SRHT embeddings. Specifically, we improve on the constant of a classical Gaussian concentration bound whereas, for SRHT embeddings, our deviation inequality involves a novel technical approach. Leveraging these bounds, we are able to design a practical and adaptive algorithm which does not require to know the effective dimension beforehand. Our method starts with an initial embedding dimension equal to 1 and, over iterations, increases the embedding dimension up to the effective one at most. Hence, our algorithm improves the state-of-the-art computational complexity for solving regularized least-squares problems. Further, we show numerically that it outperforms standard iterative solvers such as the conjugate gradient method and its pre-conditioned version on several standard machine learning datasets.more » « less
-
null (Ed.)We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching. We consider two of the most popular random embeddings, namely, Gaussian embeddings and the Subsampled Randomized Hadamard Transform (SRHT). While current randomized solvers for least-squares optimization prescribe an embedding dimension at least greater than the data dimension, we show that the embedding dimension can be reduced to the effective dimension of the optimization problem, and still preserve high-probability convergence guarantees. In this regard, we derive sharp matrix deviation inequalities over ellipsoids for both Gaussian and SRHT embeddings. Specifically, we improve on the constant of a classical Gaussian concentration bound whereas, for SRHT embeddings, our deviation inequality involves a novel technical approach. Leveraging these bounds, we are able to design a practical and adaptive algorithm which does not require to know the effective dimension beforehand. Our method starts with an initial embedding dimension equal to 1 and, over iterations, increases the embedding dimension up to the effective one at most. Hence, our algorithm improves the state-of-the-art computational complexity for solving regularized least-squares problems. Further, we show numerically that it outperforms standard iterative solvers such as the conjugate gradient method and its pre-conditioned version on several standard machine learning datasets.more » « less
-
Abstract BackgroundAlzheimer’s Disease (AD) is a widespread neurodegenerative disease with Mild Cognitive Impairment (MCI) acting as an interim phase between normal cognitive state and AD. The irreversible nature of AD and the difficulty in early prediction present significant challenges for patients, caregivers, and the healthcare sector. Deep learning (DL) methods such as Recurrent Neural Networks (RNN) have been utilized to analyze Electronic Health Records (EHR) to model disease progression and predict diagnosis. However, these models do not address some inherent irregularities in EHR data such as irregular time intervals between clinical visits. Furthermore, most DL models are not interpretable. To address these issues, we developed a novel DL architecture called Time‐Aware RNN (TA‐RNN) to predict MCI to AD conversion at the next clinical visit. MethodTA‐RNN comprises of a time embedding layer, attention‐based RNN, and prediction layer based on multi‐layer perceptron (MLP) (Figure 1). For interpretability, a dual‐level attention mechanism within the RNN identifies significant visits and features impacting predictions. TA‐RNN addresses irregular time intervals by incorporating time embedding into longitudinal cognitive and neuroimaging data based on attention weights to create a patient embedding. The MLP, trained on demographic data and the patient embedding predicts AD conversion. TA‐RNN was evaluated on Alzheimer’s Disease Neuroimaging Initiative (ADNI) and National Alzheimer’s Coordinating Center (NACC) datasets based on F2 score and sensitivity. ResultMultiple TA‐RNN models were trained with two, three, five, or six visits to predict the diagnosis at the next visit. In one setup, the models were trained and tested on ADNI. In another setup, the models were trained on the entire ADNI dataset and evaluated on the entire NACC dataset. The results indicated superior performance of TA‐RNN compared to state‐of‐the‐art (SOTA) and baseline approaches for both setups (Figure 2A and 2B). Based on attention weights, we also highlighted significant visits (Figure 3A) and features (Figure 3B) and observed that CDRSB and FAQ features and the most recent visit had highest influence in predictions. ConclusionWe propose TA‐RNN, an interpretable model to predict MCI to AD conversion while handling irregular time intervals. TA‐RNN outperformed SOTA and baseline methods in multiple experiments.more » « less
-
Abstract MotivationDespite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Providing computational tools for the exploration of the enzyme–substrate interaction space can expedite experimentation and benefit applications such as constructing synthesis pathways for novel biomolecules, identifying products of metabolism on ingested compounds, and elucidating xenobiotic metabolism. Recommender systems (RS), which are currently unexplored for the enzyme–substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) RSs; however, hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g. hierarchical, pairwise or groupings), remains a challenge. ResultsWe propose an innovative general RS framework, termed Boost-RS that enhances RS performance by ‘boosting’ embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme–substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors. Availability and implementationA Python implementation for Boost-RS is provided at https://github.com/HassounLab/Boost-RS. The enzyme-substrate interaction data is available from the KEGG database (https://www.genome.jp/kegg/).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1186/s12859-020-03546-x
