RFEX: Simple Random Forest Model and Sample Explainer for non-Machine Learning experts

Machine Learning (ML) is becoming an increasingly critical technology in many areas. However, its complexity and its frequent non-transparency create significant challenges, especially in the biomedical and health areas. One of the critical components in addressing the above challenges is the explainability or transparency of ML systems, which refers to the model (related to the whole data) and sample explainability (related to specific samples). Our research focuses on both model and sample explainability of Random Forest (RF) classifiers. Our RF explainer, RFEX, is designed from the ground up with non-ML experts in mind, and with simplicity and familiarity, e.g. providing a one-page tabular output and measures familiar to most users. In this paper we present significant improvement in RFEX Model explainer compared to the version published previously, a new RFEX Sample explainer that provides explanation of how the RF classifies a particular data sample and is designed to directly relate to RFEX Model explainer, and a RFEX Model and Sample explainer case study from our collaboration with the J. Craig Venter Institute (JCVI). We show that our approach offers a simple yet powerful means of explaining RF classification at the model and sample levels, and in some cases even points to areas of new investigation. RFEX is easy to implement using available RF tools and its tabular format offers easy-to-understand representations for non-experts, enabling them to better leverage the RF technology.

Epigenetics Theoretical Limits of Synthetic Genomes: The Cases of Artificials Caulobacter (C. eth-2.0), Mycoplasma Mycoides (JCVI-Syn 1.0, JCVI-Syn 3.0 and JCVI_3A), E-coli and YEAST chr XII

In (Venetz et al., 2019), authors rebuilt the essential genome of Caulobacter crescentus through the process of chemical synthesis rewriting and studied the genetic information content at the level of its essential genes. Then, they reduced the native Caulobacter crescentus native Caulobacter NA1000 genome sequence real genome ( 4042929 bp ) to the 785,701-bp reduced synthetic genome. Here we demonstrate the existence of a palindromic-like mirror structure that exists in real genomes and disappears totally in the synthetic genome. This biomathematic meta-organization is based on characteristic proportions of Fibonacci numbers between DNA single strand nucleotides proportions TC / AG on the one hand and TG / AC on the other hand. In both cases, we suggest that this meta-structure enhances the three-dimensional cohesion of the two DNA strands of the genome. We then generalize this study to the different synthetic genomes and synthetic cells published by the Craig Venter Institute on Mycoplasma Mycoides JCVI-syn1.0 (in 2010), JCVI-syn3.0 (in 2016) and JCVI-syn3A (in 2019). Finally, in the discussion section, we extend this study to synthetic genomes of E-Coli and Yeast chromosome XII.

VIGOR extended to annotate genomes for additional 12 different viruses

A gene prediction program, VIGOR (Viral Genome ORF Reader), was developed at J. Craig Venter Institute in 2010 and has been successfully performing gene calling in coronavirus, influenza, rhinovirus and rotavirus for projects at the Genome Sequencing Center for Infectious Diseases. VIGOR uses sequence similarity search against custom protein databases to identify protein coding regions, start and stop codons and other gene features. Ribonucleicacid editing and other features are accurately identified based on sequence similarity and signature residues. VIGOR produces four output files: a gene prediction file, a complementary DNA file, an alignment file, and a gene feature table file. The gene feature table can be used to create GenBank submission. VIGOR takes a single input: viral genomic sequences in FASTA format. VIGOR has been extended to predict genes for 12 viruses: measles virus, mumps virus, rubella virus, respiratory syncytial virus, alphavirus and Venezuelan equine encephalitis virus, norovirus, metapneumovirus, yellow fever virus, Japanese encephalitis virus, parainfluenza virus and Sendai virus. VIGOR accurately detects the complex gene features like ribonucleicacid editing, stop codon leakage and ribosomal shunting. Precisely identifying the mat_peptide cleavage for some viruses is a built-in feature of VIGOR. The gene predictions for these viruses have been evaluated by testing from 27 to 240 genomes from GenBank.

以儒家視角探討生命的本質——以人工合成生命為例

LANGUAGE NOTE | Document text in Chinese; abstract also in English.面對科學技術給我們帶來的越來越多的倫理學難題的時候，我們不妨從孔子的教導中尋找答案。美國科學家克雷格．文特爾目前宣佈，他們利用了一段人工合成的DNA 創造了人類有史以來的第一個人造生命，並取名其為“辛西婭”。這也使得人們開始重新思考生命的定義，生命的本質等本源問題。本文將從儒家的哲學視角分析辛西婭的生物學地位，並從儒家的“天命觀”的角度分析合成生物技術。希望能對新技術得出儒家獨到的見解。On May 20, 2010, the Craig Venter Institute, a U.S. private research institution, announced that they had successfully synthesized bacterial deoxyribonucleic acid (DNA) and implanted it in another bacterium. After several attempts, the implanted artificial DNA regained life and began to reproduce in a lab dish. This “artificial life” was named “Synthia” (meaning “man-made children”). The result of this research has attracted broad attention. Even U.S. President Barack Obama expressed concern, and has asked the White House Council on Bioethics to provide a detailed report on synthetic biology within six months, to determine the appropriate ethical boundaries and minimize the potential harm. Indeed, this latest research in synthetic biology requires careful philosophical, ethical and cultural considerations on the essence of life.This essay attempts to analyze the biological status of Synthia and explores the essence of life from the perspective of Confucian philosophy. In particular, it attempts to draw on the Confucian idea of Heaven (tian) or God (shangdi) to disclose unique Confucian insights into new technology in general and artificial life in particular. Indeed, as advanced and pioneering science and technology have brought about more and more ethical difficulties and dilemmas, the Chinese people need to draw on the wisdom of Confucius to work out suitable solutions and guide their actions. Researchers at the Craig Venter Institute recently announced that they could take advantage of man-made DNA to create the first artificial human life. How should Confucians reflect on such actions in terms of their view of the essence and meaning of life?This essay assumes that following the Mandate of Heaven (tianming) is central to Confucian teaching on the essence of life. The Mandate of Heaven is reflected in the natural development and transformation of the myriad things in the universe. However, things like Synthia are outside of this natural process of development and transformation, and cannot be taken as being consistent with the Mandate of Heaven. Just as Confucianism cannot support the creation of human cloning, it cannot support artificial human life such as Synthia, because both violate a fundamental understanding of the essence of life in the Confucian faith. Confucian scholars cannot hold a utilitarian view of maximizing human interests, no matter what those interests are taken to be. Instead, Confucianism must insist that human interests be consistent with the Mandate of Heaven to promote the virtuous essence of human life.DOWNLOAD HISTORY | This article has been downloaded 174 times in Digital Commons before migrating into this platform.

Synthetic Cells and Their Regulatory Challenges

On May 20th, Professor Daniel Gibson and his team at the J. Craig Venter Institute announced in a paper published in Science the creation of a “chemical synthesis of a living organism”. The researchers have constructed a bacterium's genetic software and transplanted it into a host cell. The resulting organism looked and behaved like the species ruled by the synthetic DNA. The main difference between this technique and traditional biotechnology is that, for the first time in history, scientists have not only manipulated existing DNA but have created synthetic DNA and introduced it into a host organism that had been rebooted previously.