Protein language models (pLM) are beneficial to build antibody property prediction models. However, current pLMs lacks the ability to understand antibody properties because region and structure information is not effectively embedded. We propose the Region-Empowered Antibody Language Model (REALM), a pLM built by multi-task pretraining strategy of residue prediction and region prediction tasks in antibodies, to incorporate not only co-evolution but also region information of antibodies. We demonstrate that our REALM improves the understanding of antibody properties, including hydrophobicity and thermo-stability.

Monoclonal antibodies (mAbs) offer significant therapeutic benefits; however, their formulation requires careful optimization to prevent instability. Standard practices for determining optimal formulation conditions rely on time-consuming and costly wet lab experiments. We developed a machine learning-based approach to predict the optimal pH value for stabilizing mAbs using only their amino acid sequences by leveraging a protein language model. Due to the absence of directly relevant methods, we established a baseline by comparing various combinations of elements. We also conducted feature engineering to enhance the predictive performance by incorporating structural information and descriptors. Our approach achieved a high Pearson correlation coefficient of 0.88 on the test folds from 10-fold cross-validation, highlighting its potential to complement wet lab experiments and increase the efficiency of mAb formulation.

Accurate Computer-Assisted Diagnosis, relying on large-scale annotated pathological images, can alleviate the risk of overlooking the diagnosis. Unfortunately, in medical imaging, most available datasets are small/fragmented. To tackle this, as a Data Augmentation (DA) method, 3D conditional Generative Adversarial Networks (GANs) can synthesize desired realistic/diverse 3D images as additional training data. However, no 3D conditional GAN-based DA approach exists for general bounding box-based 3D object detection, while it can locate disease areas with physicians' minimum annotation cost, unlike rigorous 3D segmentation. Moreover, since lesions vary in position/size/attenuation, further GAN-based DA performance requires multiple conditions. Therefore, we propose 3D Multi-Conditional GAN (MCGAN) to generate realistic/diverse 32 × 32 × 32 nodules placed naturally on lung Computed Tomography images to boost sensitivity in 3D object detection. Our MCGAN adopts two discriminators for conditioning: the context discriminator learns to classify real vs synthetic nodule/surrounding pairs with noise box-centered surroundings; the nodule discriminator attempts to classify real vs synthetic nodules with size/attenuation conditions. The results show that 3D Convolutional Neural Network-based detection can achieve higher sensitivity under any nodule size/attenuation at fixed False Positive rates and overcome the medical data paucity with the MCGAN-generated realistic nodules-even expert physicians fail to distinguish them from the real ones in Visual Turing Test.

Active shape model (ASM) has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. ASM local appearance model parameter estimation is based on the assumption that residuals between model fit and data have a Gaussian distribution. Moreover, to generate an allowable face shape, ASM truncates coefficients of shape principal components into the bounds determined by eigenvalues. In this paper, an algorithm of modeling local appearances, called AdaBoosted ASM, and a shape parameter optimization method are proposed. In the algorithm of modeling the local appearances, we describe our novel modeling method by using AdaBoosted histogram classifiers, in which the assumption of the Gaussian distribution is not necessary. In the shape parameter optimization, we describe that there is an inadequacy on controlling shape parameters in ASM, and our novel method on how to solve it. Experimental results demonstrate that the AdaBoosted histogram classifiers improve robustness of landmark displacement greatly, and the shape parameter optimization solves the inadequacy problem of ASM on shape constraint effectively.

This paper proposes a new method to extract a facial sketch image from a facial image robustly. The extraction process consists of two processing steps and morphology plays an important role in the whole processing. Firstly, a generalized symmetry operator, rectangle-filter and a geometric template are used to detect the eyes and mouth. Based on the detected facial parts, the locations of other facial parts are detected using their geometrical locations and characteristic shapes. Secondly, the feature points are determined from the edges of each facial part. Line-drawings connecting them give the facial sketch image. Experiments using 300 facial images were performed and the rate of extracting the facial sketch image correctly was 91%. This result shows the effectiveness of the proposed system.

This paper proposes a new method that can be used to extract facial sketch image automatically and to transform facial expression. The extraction of facial features is performed by the following three processing steps: segmentation using color characteristics, detection of feature points of each part of the face, and their approximation using polynomials. They are called feature curves and they constitute a facial sketch image. Expression transformation of the sketch image based on the facial action coding system (FACS) is carried out easily by adjusting the locations of the feature points. The control scheme of the feature point locations is based on the FACS. Experimental results on the extraction of the facial sketch image and their expression transformations are provided.