Daily Papers

Chromosome classification is critical for karyotyping in abnormality diagnosis. To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks. The approach consists of one global-scale network (G-Net) and one local-scale network (L-Net). It follows three stages. The first stage is to learn both global and local features. We extract global features and detect finer local regions via the G-Net. By proposing a varifocal mechanism, we zoom into local parts and extract local features via the L-Net. Residual learning and multi-task learning strategies are utilized to promote high-level feature extraction. The detection of discriminative local parts is fulfilled by a localization subnet of the G-Net, whose training process involves both supervised and weakly-supervised learning. The second stage is to build two multi-layer perceptron classifiers that exploit features of both two scales to boost classification performance. The third stage is to introduce a dispatch strategy of assigning each chromosome to a type within each patient case, by utilizing the domain knowledge of karyotyping. Evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) 99.2 for both type and polarity tasks. It outperformed state-of-the-art methods, demonstrating the effectiveness of our varifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The proposed method has been applied to assist practical karyotype diagnosis.

Chromosome analysis is vital for diagnosing genetic disorders and guiding cancer therapy decisions through the identification of somatic clonal aberrations. However, developing an AI model are hindered by the overwhelming complexity and diversity of chromosomal abnormalities, requiring extensive annotation efforts, while automated methods remain task-specific and lack generalizability due to the scarcity of comprehensive datasets spanning diverse resource conditions. Here, we introduce CHROMA, a foundation model for cytogenomics, designed to overcome these challenges by learning generalizable representations of chromosomal abnormalities. Pre-trained on over 84,000 specimens (~4 million chromosomal images) via self-supervised learning, CHROMA outperforms other methods across all types of abnormalities, even when trained on fewer labelled data and more imbalanced datasets. By facilitating comprehensive mapping of instability and clonal leisons across various aberration types, CHROMA offers a scalable and generalizable solution for reliable and automated clinical analysis, reducing the annotation workload for experts and advancing precision oncology through the early detection of rare genomic abnormalities, enabling broad clinical AI applications and making advanced genomic analysis more accessible.

We present a tool for exploring the design space of shaders using an interactive evolutionary algorithm integrated with the Unity editor, a well-known commercial tool for video game development. Our framework leverages the underlying graph-based representation of recent shader editors and interactive evolution to allow designers to explore several visual options starting from an existing shader. Our framework encodes the graph representation of a current shader as a chromosome used to seed the evolution of a shader population. It applies graph-based recombination and mutation with a set of heuristics to create feasible shaders. The framework is an extension of the Unity editor; thus, designers with little knowledge of evolutionary computation (and shader programming) can interact with the underlying evolutionary engine using the same visual interface used for working on game scenes.

Convolutional Neural Networks (CNN) have gained great success in many artificial intelligence tasks. However, finding a good set of hyperparameters for a CNN remains a challenging task. It usually takes an expert with deep knowledge, and trials and errors. Genetic algorithms have been used in hyperparameter optimizations. However, traditional genetic algorithms with fixed-length chromosomes may not be a good fit for optimizing deep learning hyperparameters, because deep learning models have variable number of hyperparameters depending on the model depth. As the depth increases, the number of hyperparameters grows exponentially, and searching becomes exponentially harder. It is important to have an efficient algorithm that can find a good model in reasonable time. In this article, we propose to use a variable length genetic algorithm (GA) to systematically and automatically tune the hyperparameters of a CNN to improve its performance. Experimental results show that our algorithm can find good CNN hyperparameters efficiently. It is clear from our experiments that if more time is spent on optimizing the hyperparameters, better results could be achieved. Theoretically, if we had unlimited time and CPU power, we could find the optimized hyperparameters and achieve the best results in the future.

Polyploidization is an important evolutionary process which affects organisms ranging from plants to fish and fungi. The signal left behind by it is in the form of a species' ploidy level (number of complete chromosome sets found in a cell) which is inherently non-treelike. Currently available tools for reconstructing the evolutionary past of a polyploid dataset generally start with a multi-labelled tree obtained for a dataset of interest and then derive a (phylogenetic) network from that tree in some way that reflects that past by interpreting the networks's vertices of indegree at least two as polyploidization events. Since obtaining such a tree can be computationally expensive it is paramount to have alternative approaches available that allow one to shed light into the reticulate evolutionary past of a polyploid dataset. SPRINT aims to reconstruct the evolutionary past of a polyploid dataset in terms of a binary network which realises the dataset's ploidy profile (vector of ploidy levels of the dataset's taxa) and requires the fewest number of polyploidization events. It does this by representing the ploidy level of a species x in terms of the number of directed paths from the root of the network to the leaf of the network labelled by x. SPRINT is distributed on GitHub: https://github.com/lmaher1/SPRINT.

Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To measure this undesirable capability -- CoT controllability -- we introduce the CoT-Control evaluation suite, which includes tasks that require models to solve problems while adhering to CoT instructions, e.g., reasoning about a genetics question without using the word 'chromosome'. We show that reasoning models possess significantly lower CoT controllability than output controllability; for instance, Claude Sonnet 4.5 can control its CoT only 2.7% of the time but 61.9% when controlling its final output. We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty. CoT controllability failures extend even to situations in which models are given incentives (as opposed to direct requests) to evade CoT monitors, although models exhibit slightly higher controllability when they are told they are being monitored. Similarly, eliciting controllability by adversarially optimizing prompts does not meaningfully increase controllability. Our results leave us cautiously optimistic that CoT controllability is currently unlikely to be a failure mode of CoT monitorability. However, the mechanism behind low controllability is not well understood. Given its importance for maintaining CoT monitorability, we recommend that frontier labs track CoT controllability in future models.

DNA sequence alignment involves assigning short DNA reads to the most probable locations on an extensive reference genome. This process is crucial for various genomic analyses, including variant calling, transcriptomics, and epigenomics. Conventional methods, refined over decades, tackle this challenge in 2 steps: genome indexing followed by efficient search to locate likely positions for given reads. Building on the success of Large Language Models in encoding text into embeddings, where the distance metric captures semantic similarity, recent efforts have explored whether the same Transformer architecture can produce embeddings for DNA sequences. Such models have shown early promise in classifying short DNA sequences, such as detecting coding/non-coding regions, and enhancer, promoter sequences. However, performance at sequence classification tasks does not translate to sequence alignment, where it is necessary to search across the genome to align each read, a significantly longer-range task. We bridge this gap by framing the Sequence Alignment task for Transformer models as an "Embed-Search-Align" task. In this framework, a novel Reference-Free DNA Embedding model generates embeddings of reads and reference fragments, which are projected into a shared vector space where the read-fragment distance is used as a surrogate for alignment. Technical contributions include: (1) Contrastive loss for self-supervised training of DNA sequence representations, facilitating rich reference-free, sequence-level embeddings, and (2) a DNA vector store to enable search across fragments on a global scale. DNA-ESA is 99% accurate when aligning 250-length reads onto a human genome (3gb), rivaling conventional methods such as Bowtie and BWA-Mem. DNA-ESA exceeds the performance of 6 Transformer model baselines such as Nucleotide Transformer, Hyena-DNA, and shows task transfer across chromosomes and species.