Patterns最新文献

The UN Convention on Biological Diversity adopted new rules for sharing benefits from publicly available genetic sequence data, also known as digital sequence information (DSI). In this Opinion, the authors describe the key elements researchers need to be aware of, address real-life questions, and explain the practical implications of these rules for research and development.

High-throughput molecular profiling technologies have revolutionized molecular biology research in the past decades. One important use of molecular data is to make predictions of phenotypes and other features of the organisms using machine learning algorithms. Deep learning models have become increasingly popular for this task due to their ability to learn complex non-linear patterns. Applying deep learning to molecular profiles, however, is challenging due to the very high dimensionality of the data and relatively small sample sizes, causing models to overfit. A solution is to incorporate biological prior knowledge to guide the learning algorithm for processing the functionally related input together. This helps regularize the models and improve their generalizability and interpretability. Here, we describe three major strategies proposed to use prior knowledge in deep learning models to make predictions based on molecular profiles. We review the related deep learning architectures, including the major ideas in relatively new graph neural networks.

The concept of dignity is proliferating in ethical, legal, and policy discussions of AI, yet dignity is an elusive concept with multiple philosophical interpretations. The authors argue that the unspecific and uncritical employment of the notion of dignity can be counterproductive for AI ethics.

The burgeoning landscape of text-to-image models, exemplified by innovations such as Midjourney and DALL·E 3, has revolutionized content creation across diverse sectors. However, these advances bring forth critical ethical concerns, particularly with the misuse of open-source models to generate content that violates societal norms. Addressing this, we introduce Ethical-Lens, a framework designed to facilitate the value-aligned usage of text-to-image tools without necessitating internal model revision. Ethical-Lens ensures value alignment in text-to-image models across toxicity and bias dimensions by refining user commands and rectifying model outputs. Systematic evaluation metrics, combining GPT4-V, HEIM, and FairFace scores, assess alignment capability. Our experiments reveal that Ethical-Lens enhances alignment capabilities to levels comparable with or superior to commercial models such as DALL $·$ E 3, while preserving the quality of generated images. This study indicates the potential of Ethical-Lens to promote the sustainable development of open-source text-to-image tools and their beneficial integration into society.

Immunotherapies, including checkpoint blockade and chimeric antigen receptor T cell (CAR-T) therapy, have revolutionized cancer treatment; however, many patients remain unresponsive to these treatments or relapse following treatment. CRISPR screenings have been used to identify novel single gene targets that can enhance immunotherapy effectiveness, but the identification of combinational targets remains a challenge. Here, we introduce a computational approach that uses sgRNA set enrichment analysis to identify cancer-intrinsic paralog pairs for enhancing immunotherapy using genome-wide screens. We have further developed an ensemble learning model that uses an XGBoost classifier and incorporates features to predict paralog gene pairs that influence immunotherapy efficacy. We experimentally validated the functional significance of these predicted paralog pairs using CRISPR double knockout (DKO). These data and analyses collectively provide a sensitive approach to identifying previously undetected paralog gene pairs that can significantly affect cancer immunotherapy response, even when individual genes within the pair have limited effect.

Gene fusions are common cancer drivers and therapeutic targets, but clinical-grade open-source bioinformatic tools are lacking. Here, we introduce a fusion detection method named SplitFusion, which is fast by leveraging Burrows-Wheeler Aligner-maximal exact match (BWA-MEM) split alignments, can detect cryptic splice-site fusions (e.g., EML4::ALK v3b and ARv7), call fusions involving highly repetitive gene partners (e.g., CIC::DUX4), and infer frame-ness and exon-boundary alignments for functional prediction and minimizing false positives. Using 1,848 datasets of various sizes, SplitFusion demonstrated superior sensitivity and specificity compared to three other tools. In 1,076 formalin-fixed paraffin-embedded lung cancer samples, SplitFusion identified novel fusions and revealed that EML4::ALK variant 3 was associated with multiple fusion variants coexisting in the same tumor. Additionally, SplitFusion can call targeted splicing variants. Using data from 515 The Cancer Genome Atlas (TCGA) samples, SplitFusion showed the highest sensitivity and uncovered two cases of SLC34A2::ROS1 that were missed in previous studies. These capabilities make SplitFusion highly suitable for clinical applications and the study of fusion-defined tumor heterogeneity.

Spectral analysis using wavelets is widely used for identifying biomarkers in EEG signals. Recently, Riemannian geometry has provided an effective mathematical framework for predicting biomedical outcomes from multichannel electroencephalography (EEG) recordings while showing concord with neuroscientific domain knowledge. However, these methods rely on handcrafted rules and sequential optimization. In contrast, deep learning (DL) offers end-to-end trainable models achieving state-of-the-art performance on various prediction tasks but lacks interpretability and interoperability with established neuroscience concepts. We introduce Gabor Riemann EEGNet (GREEN), a lightweight neural network that integrates wavelet transforms and Riemannian geometry for processing raw EEG data. Benchmarking on six prediction tasks across four datasets with over 5,000 participants, GREEN outperformed non-deep state-of-the-art models and performed favorably against large DL models while using orders-of-magnitude fewer parameters. Computational experiments showed that GREEN facilitates learning sparse representations without compromising performance. By integrating domain knowledge, GREEN combines a desirable complexity-performance trade-off with interpretable representations.