Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Cytoscape is a free software package for visualizing, modeling and analyzing molecular and genetic interaction networks. This protocol explains how to use Cytoscape to analyze the results of mRNA expression profiling, and other functional genomics and proteomics experiments, in the context of an interaction network obtained for genes of interest. Five major steps are described: (i) obtaining a gene or protein network, (ii) displaying the network using layout algorithms, (iii) integrating with gene expression and other functional attributes, (iv) identifying putative complexes and functional modules and (v) identifying enriched Gene Ontology annotations in the network. These steps provide a broad sample of the types of analyses performed by Cytoscape.

/pdf/integration-of-biological-networks-and-gene-expression-data-40nso072qr.pdf

Integration of biological networks and gene expression data using Cytoscape

A genome-scale genetic interaction map was constructed by examining 5.4 million gene-gene pairs for synthetic genetic interactions, generating quantitative genetic interaction profiles for ~75% of all genes in the budding yeast, Saccharomyces cerevisiae. A network based on genetic interaction profiles reveals a functional map of the cell in which genes of similar biological processes cluster together in coherent subsets, and highly correlated profiles delineate specific pathways to define gene function. The global network identifies functional cross-connections between all bioprocesses, mapping a cellular wiring diagram of pleiotropy. Genetic interaction degree correlated with a number of different gene attributes, which may be informative about genetic network hubs in other organisms. We also demonstrate that extensive and unbiased mapping of the genetic landscape provides a key for interpretation of chemical-genetic interactions and drug target identification.

/pdf/the-genetic-landscape-of-a-cell-58hv8ycydi.pdf

The genetic landscape of a cell.

Consider data consisting of pairwise measurements, such as presence or absence of links between pairs of objects. These data arise, for instance, in the analysis of protein interactions and gene regulatory networks, collections of author-recipient email, and social networks. Analyzing pairwise measurements with probabilistic models requires special assumptions, since the usual independence or exchangeability assumptions no longer hold. Here we introduce a class of variance allocation models for pairwise measurements: mixed membership stochastic blockmodels. These models combine global parameters that instantiate dense patches of connectivity (blockmodel) with local parameters that instantiate node-specific variability in the connections (mixed membership). We develop a general variational inference algorithm for fast approximate posterior inference. We demonstrate the advantages of mixed membership stochastic blockmodels with applications to social networks and protein interaction networks.

/pdf/mixed-membership-stochastic-blockmodels-2a6y107lg8.pdf

Mixed Membership Stochastic Blockmodels

Targeting the interfaces between proteins has huge therapeutic potential, but discovering small-molecule drugs that disrupt protein-protein interactions is an enormous challenge. Several recent success stories, however, indicate that protein-protein interfaces might be more tractable than has been thought. These studies discovered small molecules that bind with drug-like potencies to 'hotspots' on the contact surfaces involved in protein-protein interactions. Remarkably, these small molecules bind deeper within the contact surface of the target protein, and bind with much higher efficiencies, than do the contact atoms of the natural protein partner. Some of these small molecules are now making their way through clinical trials, so this high-hanging fruit might not be far out of reach.

Reaching for high-hanging fruit in drug discovery at protein–protein interfaces

Identification of protein-protein interactions often provides insight into protein function, and many cellular processes are performed by stable protein complexes. We used tandem affinity purification to process 4,562 different tagged proteins of the yeast Saccharomyces cerevisiae. Each preparation was analysed by both matrix-assisted laser desorption/ionization-time of flight mass spectrometry and liquid chromatography tandem mass spectrometry to increase coverage and accuracy. Machine learning was used to integrate the mass spectrometry scores and assign probabilities to the protein-protein interactions. Among 4,087 different proteins identified with high confidence by mass spectrometry from 2,357 successful purifications, our core data set (median precision of 0.69) comprises 7,123 protein-protein interactions involving 2,708 proteins. A Markov clustering algorithm organized these interactions into 547 protein complexes averaging 4.9 subunits per complex, about half of them absent from the MIPS database, as well as 429 additional interactions between pairs of complexes. The data (all of which are available online) will help future studies on individual proteins as well as functional genomics and systems biology.

/pdf/global-landscape-of-protein-complexes-in-the-yeast-1r7clxf9lu.pdf

Global landscape of protein complexes in the yeast Saccharomyces cerevisiae

A key problem of interest to biologists and medical researchers is the selection of a subset of queries or treatments that provide maximum utility for a population of targets. For example, when studying how gene deletion mutants respond to each of thousands of drugs, it is desirable to identify a small subset of genes that nearly uniquely define a drug 'footprint' that provides maximum predictability about the organism's response to the drugs. As another example, when designing a cocktail of HIV genome sequences to be used as a vaccine, it is desirable to identify a small number of sequences that provide maximum immunological protection to a specified population of recipients. We refer to this task as 'treatment portfolio design' and formalize it as a facility location problem. Finding a treatment portfolio is NP-hard in the size of portfolio and number of targets, but a variety of greedy algorithms can be applied. We introduce a new algorithm for treatment portfolio design based on similar insights that made the recently-published affinity propagation algorithm work quite well for clustering tasks. We demonstrate this method using the two problems described above: selecting a subset of yeast genes that act as a drug-response footprint, and selecting a subset of vaccine sequences that provide maximum epitope coverage for an HIV genome population.

http://www.cs.columbia.edu/~delbert/docs/Dueck,Frey,Jojic,Jojic%20--%20Constructing%20Treatment%20Portfolios%20Using%20Affinity%20Propagation%20(RECOMB2008).pdf

Constructing treatment portfolios using affinity propagation

Anosmia (loss of sense of smell) is one symptom of COVID-19 which can linger long after acute infection has passed, with major impact on quality of life. Given the number of people impacted by COVID-19-related anosmia, there is an urgent need to identify effective therapeutics in a faster fashion than using traditional drug discovery and development methods. We used our knowledge graph, the Phenograph, to navigate from phenotypes to genes to drug targets, to rapidly find druggable targets associated with anosmia. This process shortlisted six targets: NRP1, SCN9A, EGR1, VEGFB, PRKCE, and FGFR1. Neuropilin-1 (NRP1) is under active study for its involvement in SARS-CoV-2 infection. Importantly, there is no direct link between anosmia and NRP1 in our knowledge graph; the relationship was inferred through the graph structure. Based on this external validation, we derived hypotheses for the involvement of the remaining five targets in COVID-19-related anosmia, and the mechanism of action desired in a drug candidate to correct the hypothesized dysregulation.

Gabe Musso

Papers

Global landscape of protein complexes in the yeast Saccharomyces cerevisiae

Constructing treatment portfolios using affinity propagation

Phenotype-driven identification of drug targets for post-COVID-19 anosmia