Quantifying the Hardness of Bioactivity Prediction Tasks for Transfer Learning.

Today, machine learning methods are widely employed in drug discovery. However, the chronic lack of data continues to hamper their further development, validation, and application. Several modern strategies aim to mitigate the challenges associated with data scarcity by learning from data on related tasks. These knowledge-sharing approaches encompass transfer learning, multitask learning, and meta-learning. A key question remaining to be answered for these approaches is about the extent to which their performance can benefit from the relatedness of available source (training) tasks; in other words, how difficult ("hard") a test task is to a model, given the available source tasks. This study introduces a new method for quantifying and predicting the hardness of a bioactivity prediction task based on its relation to the available training tasks. The approach involves the generation of protein and chemical representations and the calculation of distances between the bioactivity prediction task and the available training tasks. In the example of meta-learning on the FS-Mol data set, we demonstrate that the proposed task hardness metric is inversely correlated with performance (Pearson's correlation coefficient r = -0.72). The metric will be useful in estimating the task-specific gain in performance that can be achieved through meta-learning.

Enhanced Waddington landscape model with cell-cell communication can explain molecular mechanisms of self-organization.

MOTIVATION: The molecular mechanisms of self-organization that orchestrate embryonic cells to create astonishing patterns have been among major questions of developmental biology. It is recently shown that embryonic stem cells (ESCs), when cultured in particular micropatterns, can self-organize and mimic the early steps of pre-implantation embryogenesis. A systems-biology model to address this observation from a dynamical systems perspective is essential and can enhance understanding of the phenomenon. RESULTS: Here, we propose a multicellular mathematical model for pattern formation during in vitro gastrulation of human ESCs. This model enhances the basic principles of Waddington epigenetic landscape with cell-cell communication, in order to enable pattern and tissue formation. We have shown the sufficiency of a simple mechanism by using a minimal number of parameters in the model, in order to address a variety of experimental observations such as the formation of three germ layers and trophectoderm, responses to altered culture conditions and micropattern diameters and unexpected spotted forms of the germ layers under certain conditions. Moreover, we have tested different boundary conditions as well as various shapes, observing that the pattern is initiated from the boundary and gradually spreads towards the center. This model provides a basis for in-silico modeling of self-organization. AVAILABILITY AND IMPLEMENTATION: https://github.com/HFooladi/Self_Organization. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.